{"meta":{"query_hash":"b05057a49128","filters":{"topic":"Machine Learning in Bioinformatics"},"cohort_total":1034,"direct_labels_cover":1,"predictions_cover":1034,"exported":1034,"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/b05057a49128","api":"https://metacan.xera.ac/api/v1/cohort?topic=Machine+Learning+in+Bioinformatics"},"results":[{"id":"W1039050370","doi":"","title":"Identification Of Protein Targets Involved In Adult Cns Neuron Apoptosis Via Quantitative Itraq Analysis Of The Injured Retina","year":2011,"lang":"en","type":"article","venue":"Investigative Ophthalmology & Visual Science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Retina; Identification (biology); Apoptosis; Neuron; Biology; Neuroscience; Cell biology; Biochemistry; Botany","score_opus":0.026380818200873433,"score_gpt":0.3141332052676105,"score_spread":0.28775238706673706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1039050370","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9989384,0.000018422163,0.00009658624,0.00006887551,0.00007105797,0.00037743163,0.000016286465,0.000004681864,0.0004082684],"genre_scores_gemma":[0.9969783,0.0000023056525,0.002866453,0.000053282747,0.000005483887,0.00003548176,0.000017059518,0.000008127715,0.000033535023],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99802047,0.00037515163,0.00063972943,0.0003939625,0.00031224446,0.00025841998],"domain_scores_gemma":[0.9982126,0.000035623914,0.0008020521,0.00041833613,0.00045904328,0.00007237866],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0009708601,0.00016290968,0.00028162255,0.00030507156,0.00010641906,0.0000084279745,0.00071590027,0.00012827212,0.000016910171],"category_scores_gemma":[0.0022753533,0.0001285545,0.000109205095,0.0021739386,0.00337675,0.000027471373,0.0002729876,0.00018665851,0.0000022081806],"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":[0.000046603836,0.000094143994,0.12990405,0.000021227483,0.00005818678,5.3373515e-7,0.0019444621,0.00009693665,0.8674651,0.00033520866,0.0000021327915,0.000031465253],"study_design_scores_gemma":[0.00009062613,0.00037870492,0.3511389,0.00001581395,0.000042210788,0.00000144418,0.00024247663,0.00352373,0.6440542,0.00042796382,7.445314e-7,0.00008320066],"about_ca_topic_score_codex":0.0003303089,"about_ca_topic_score_gemma":0.000046079884,"teacher_disagreement_score":0.22341086,"about_ca_system_score_codex":0.000026344,"about_ca_system_score_gemma":0.00018260234,"threshold_uncertainty_score":0.99933547},"labels":[],"label_agreement":null},{"id":"W1452159285","doi":"10.1128/9781555815806.ch22","title":"Methods for the Computational Prediction of Periplasmic Proteins","year":2014,"lang":"en","type":"book-chapter","venue":"ASM Press eBooks","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Periplasmic space; Identification (biology); Computer science; Pipeline (software); Computational biology; Set (abstract data type); Process (computing); Artificial intelligence; Data mining; Machine learning; Biology; Gene; Genetics","score_opus":0.025045580001451878,"score_gpt":0.3055467829049877,"score_spread":0.28050120290353586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1452159285","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002363452,0.0002707143,0.6143417,0.000026661528,0.00021891209,0.0009785164,0.0001640934,0.000018257575,0.3839575],"genre_scores_gemma":[0.0047092005,0.000048934908,0.22158475,0.00022943487,0.0006695582,0.0002866765,0.0008494393,0.00011684721,0.7715052],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.999199,0.000039520914,0.00033279756,0.00018698168,0.00012653941,0.00011519012],"domain_scores_gemma":[0.998972,0.000117709766,0.00035755924,0.00037222984,0.0001515633,0.000028954606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036853392,0.00019161907,0.00019327832,0.000026905349,0.000084393854,0.000017065964,0.00025487714,0.0002967904,0.000009251898],"category_scores_gemma":[0.00008820578,0.00014644933,0.00016026308,0.0000017091229,0.00014252654,8.882257e-7,0.00012336072,0.00018143235,0.0000013484156],"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":[0.000521794,0.000033303502,0.00001669475,0.0018884338,0.0019741638,4.3707777e-7,0.0008159618,0.016483026,0.02384623,0.58219075,0.024139727,0.34808946],"study_design_scores_gemma":[0.0003118077,0.0002720119,0.000013822101,0.000050540384,0.00010052796,0.000008568832,0.000002114394,0.023642266,0.0076041333,0.0024181707,0.96543515,0.0001408718],"about_ca_topic_score_codex":0.00000832652,"about_ca_topic_score_gemma":0.000001769506,"teacher_disagreement_score":0.94129544,"about_ca_system_score_codex":0.000007726716,"about_ca_system_score_gemma":0.000059658712,"threshold_uncertainty_score":0.597203},"labels":[],"label_agreement":null},{"id":"W1496257230","doi":"10.1186/s12859-015-0586-0","title":"ProtDCal: A program to compute general-purpose-numerical descriptors for sequences and 3D-structures of proteins","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Universidad de San Buenaventura","keywords":"Computer science; Data mining; Sequence (biology); Java; Feature (linguistics); Sequence alignment; Software; Key (lock); Protein function prediction; Artificial intelligence; Theoretical computer science; Machine learning; Programming language; Protein function; Peptide sequence","score_opus":0.03172182749760137,"score_gpt":0.30741463866839125,"score_spread":0.27569281117078986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1496257230","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":[0.16943671,0.00014304365,0.8243211,0.00016135996,0.00024132933,0.0046158824,0.00008232175,0.00009896783,0.00089930603],"genre_scores_gemma":[0.029417202,0.000006242099,0.96957284,0.00028541902,0.0001232041,0.00027265956,0.00014005922,0.000024063926,0.00015829729],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986406,0.000035761477,0.00058851414,0.0001657095,0.00024877168,0.0003206695],"domain_scores_gemma":[0.9988888,0.00001777544,0.00027359414,0.00032562722,0.00023965599,0.0002545796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034499087,0.0002323421,0.00027706687,0.00008531394,0.00006992371,0.00007063879,0.0002792291,0.00017393404,0.0000018387392],"category_scores_gemma":[0.0004456703,0.00018763689,0.000077046614,0.00015252456,0.0001370003,0.00001889954,0.00021756036,0.000099530895,0.0000037774548],"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":[0.0036085253,0.0013335656,0.088494256,0.0152456025,0.0010037799,0.0000049832165,0.022546798,0.08221702,0.03315035,0.014833658,0.092747405,0.6448141],"study_design_scores_gemma":[0.0020043382,0.00556362,0.0013504815,0.00008645164,0.000063714375,0.00009327011,0.000580967,0.77491564,0.021971466,0.0004769226,0.19212452,0.0007686365],"about_ca_topic_score_codex":0.00001940417,"about_ca_topic_score_gemma":0.000009259032,"teacher_disagreement_score":0.6926986,"about_ca_system_score_codex":0.000018885694,"about_ca_system_score_gemma":0.00020629642,"threshold_uncertainty_score":0.76516104},"labels":[],"label_agreement":null},{"id":"W1502751310","doi":"10.1007/11766247_10","title":"Bayesian Learning for Feed-Forward Neural Network with Application to Proteomic Data: The Glycosylation Sites Detection of the Epidermal Growth Factor-Like Proteins Associated with Cancer as a Case Study","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial neural network; Artificial intelligence; Machine learning; Bayesian probability; Probabilistic neural network; Dynamic Bayesian network; Pruning; Time delay neural network; Data mining; Biology","score_opus":0.010090816942031452,"score_gpt":0.25425527956138533,"score_spread":0.24416446261935387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1502751310","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22902818,0.00002481065,0.7678178,0.00012810204,0.000074490985,0.0028764794,0.000015227476,0.00001545069,0.000019488501],"genre_scores_gemma":[0.9927962,0.0000011014223,0.00644609,0.00017142392,0.00026084235,0.0001637273,0.00007403365,0.00003180826,0.00005476473],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983962,0.00007633233,0.00030595338,0.0005653993,0.00037371396,0.0002823635],"domain_scores_gemma":[0.99839014,0.00010075534,0.00054315984,0.00066861184,0.00025807347,0.000039238825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005194837,0.00028109594,0.00022432646,0.00007336601,0.00042875906,0.00009579274,0.0007055937,0.00015562322,8.4543336e-7],"category_scores_gemma":[0.00016552453,0.00016159897,0.00004173584,0.0002858007,0.00018269698,0.000023551207,0.0003784394,0.0004335386,2.3600685e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012276003,0.000028328403,0.02127751,0.000045357276,0.000054712804,0.0000037545087,0.00043852138,0.95293313,0.0029297762,0.00000637601,0.0000064493097,0.022153337],"study_design_scores_gemma":[0.00065945054,0.002049007,0.010228732,0.000186208,0.00008902395,0.00015507557,0.000004925183,0.98051673,0.005253926,0.00017097025,0.00021216327,0.00047376723],"about_ca_topic_score_codex":0.00058690936,"about_ca_topic_score_gemma":0.007796594,"teacher_disagreement_score":0.763768,"about_ca_system_score_codex":0.00008485839,"about_ca_system_score_gemma":0.00020950468,"threshold_uncertainty_score":0.6589815},"labels":[],"label_agreement":null},{"id":"W1517005208","doi":"10.1186/1743-422x-3-24","title":"Predicting the subcellular localization of viral proteins within a mammalian host cell","year":2006,"lang":"en","type":"article","venue":"Virology Journal","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sanofi (Canada); McGill University","funders":"","keywords":"Subcellular localization; Biology; Protein subcellular localization prediction; Proteome; Host (biology); Cell biology; Computational biology; Cell; Human proteome project; Nuclear localization sequence; Proteomics; Virology; Bioinformatics; Cytoplasm; Genetics; Gene","score_opus":0.0030096431846707377,"score_gpt":0.19798370232191084,"score_spread":0.1949740591372401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1517005208","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94038033,0.00025789926,0.05735315,0.00023143641,0.00015559224,0.00013853778,0.000004398839,0.0000071236213,0.0014715263],"genre_scores_gemma":[0.9971233,0.000015341355,0.0018665473,0.00019889676,0.00036780647,0.0000040936493,0.000025261963,0.00001538218,0.00038337734],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989963,0.00015813725,0.00040596348,0.00010319552,0.00014085358,0.00019555808],"domain_scores_gemma":[0.99925673,0.000010645689,0.00042621582,0.00019717129,0.000073835035,0.000035398578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054632046,0.00011132247,0.000109802364,0.000045561206,0.00019584059,0.00002358765,0.00022976486,0.00016301568,0.000024677733],"category_scores_gemma":[0.00007363303,0.00007869577,0.00007113581,0.00006277434,0.00015004317,0.000005479588,0.00007031227,0.00030574028,0.000005351388],"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":[0.00014156346,0.000096858086,0.17772575,0.000049543218,0.000038138296,0.000010502014,0.0003556725,0.034482095,0.78535205,0.00030224587,0.0013137546,0.00013180956],"study_design_scores_gemma":[0.002804197,0.0027471278,0.04447647,0.000045882687,0.00014521295,0.001467966,0.00043655382,0.09417064,0.8243096,0.0010055847,0.027871879,0.0005188706],"about_ca_topic_score_codex":0.000042082633,"about_ca_topic_score_gemma":0.00003176523,"teacher_disagreement_score":0.13324927,"about_ca_system_score_codex":0.00000919651,"about_ca_system_score_gemma":0.00006020343,"threshold_uncertainty_score":0.32091203},"labels":[],"label_agreement":null},{"id":"W1564499834","doi":"10.1186/1471-2407-5-107","title":"Phosphorylation states of cell cycle and DNA repair proteins can be altered by the nsSNPs","year":2005,"lang":"en","type":"article","venue":"BMC Cancer","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital","funders":"Canadian Institutes of Health Research","keywords":"Phosphorylation; Single-nucleotide polymorphism; Biology; Genetics; Protein phosphorylation; DNA repair; Computational biology; DNA; Bioinformatics; Gene; Protein kinase A; Genotype","score_opus":0.006267555861026166,"score_gpt":0.24418059137835119,"score_spread":0.237913035517325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1564499834","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.996661,0.0012275679,0.00047313314,0.00045099962,0.00003497137,0.00022475442,0.00007640575,0.000012414896,0.00083876465],"genre_scores_gemma":[0.99474525,0.00024862128,0.0030063032,0.00045512727,0.00010864063,0.000038018527,0.00008522583,0.000012047806,0.0013007409],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99952805,0.000026856796,0.0001471959,0.00010887763,0.00008168093,0.00010731719],"domain_scores_gemma":[0.9996293,0.000009405832,0.00010861848,0.000190579,0.0000339938,0.000028068014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010780752,0.00007673581,0.000067845096,0.000008749699,0.000048484653,0.000009438004,0.00007571413,0.000051035462,0.000033919438],"category_scores_gemma":[0.000022715445,0.00005733631,0.000032695967,0.000031677602,0.000057277044,0.000002938622,0.000047155234,0.00005579317,8.2649325e-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":[0.00019020421,0.00009690757,0.03783689,0.0003125004,0.000076063756,1.2591151e-7,0.00202971,0.0080733085,0.8735749,0.00004730221,0.06854834,0.009213746],"study_design_scores_gemma":[0.0004835492,0.000120444194,0.0044505447,0.000013084003,0.000018192062,0.0000017561296,0.00013024457,0.013212537,0.82552904,0.000015022258,0.15588836,0.00013725185],"about_ca_topic_score_codex":0.00038722117,"about_ca_topic_score_gemma":0.0011516679,"teacher_disagreement_score":0.08734002,"about_ca_system_score_codex":0.000013956952,"about_ca_system_score_gemma":0.00004654564,"threshold_uncertainty_score":0.23381068},"labels":[],"label_agreement":null},{"id":"W1568933256","doi":"","title":"Fuzzy string kernel representations in speech processing","year":2003,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"String kernel; Kernel (algebra); Pattern recognition (psychology); String (physics); Computer science; Feature vector; Kernel method; Speech recognition; Artificial intelligence; Cluster analysis; Feature (linguistics); Subsequence; Support vector machine; Mathematics; Radial basis function kernel; Discrete mathematics","score_opus":0.008899040661434038,"score_gpt":0.25789136006413427,"score_spread":0.24899231940270022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1568933256","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89603776,0.00026785414,0.0067560053,0.00014235682,0.000213154,0.00022900876,0.000030895473,0.000018763365,0.096304186],"genre_scores_gemma":[0.98733,0.000023472452,0.010979567,0.0003493869,0.00006690247,0.000005539968,0.00006353409,0.00001927491,0.0011622995],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992333,0.000029170174,0.00018928775,0.00015864178,0.00008319702,0.0003064141],"domain_scores_gemma":[0.9994609,0.000008556761,0.000051378414,0.00023413684,0.00005827162,0.00018677615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015818498,0.00010089209,0.000078421996,0.000115249895,0.00008713843,0.000043725086,0.0001259131,0.00011728744,0.000022555401],"category_scores_gemma":[0.00058020576,0.00011639746,0.000023233286,0.00017047834,0.000037706417,0.000004627515,0.000017589566,0.00015793403,0.000016430926],"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":[0.00003335686,0.00015477026,0.44831437,0.0005270234,0.00011355332,0.00032459278,0.0021150478,0.13594548,0.31537884,0.010881694,0.03803061,0.04818065],"study_design_scores_gemma":[0.006541506,0.00064708554,0.52985436,0.00049322733,0.00024142044,0.0011240604,0.010130997,0.081457876,0.046480574,0.006962353,0.3110321,0.0050344747],"about_ca_topic_score_codex":0.0024919163,"about_ca_topic_score_gemma":0.0111471955,"teacher_disagreement_score":0.2730015,"about_ca_system_score_codex":0.00007220319,"about_ca_system_score_gemma":0.00053640635,"threshold_uncertainty_score":0.6220397},"labels":[],"label_agreement":null},{"id":"W1571001643","doi":"10.1007/11424918_17","title":"Fast Protein Superfamily Classification Using Principal Component Null Space Analysis","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Windsor","funders":"","keywords":"Computer science; Principal component analysis; Artificial intelligence; Curse of dimensionality; Classifier (UML); Artificial neural network; Machine learning; Pattern recognition (psychology); Support vector machine; Data mining","score_opus":0.017151535646473075,"score_gpt":0.26300295531413836,"score_spread":0.2458514196676653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1571001643","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":[0.04310849,0.00017300111,0.95363855,0.00018998038,0.00018516903,0.0003997642,0.0000119924935,0.000026614382,0.0022664545],"genre_scores_gemma":[0.6937714,0.000023846223,0.3043906,0.00034683346,0.00058255385,0.000006496915,0.00014350776,0.00003774806,0.00069699995],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99778765,0.000036011763,0.00045589797,0.0007803018,0.0005426943,0.00039745687],"domain_scores_gemma":[0.9984723,0.000026796315,0.00031972496,0.00089704,0.0001741083,0.00011003256],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00049493974,0.00038840805,0.00036846384,0.00048763904,0.00016742609,0.00014599554,0.0008159721,0.00038415584,0.000026721726],"category_scores_gemma":[0.00006955085,0.00036760795,0.00017055133,0.00035004504,0.00043603723,0.000013879591,0.00049666385,0.0005103731,0.000015296559],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004015373,0.00006265678,0.0020459588,0.00009375644,0.00019428426,0.000009097038,0.00040272402,0.78622717,0.1201002,0.0012240055,0.0000116447145,0.08958835],"study_design_scores_gemma":[0.00021485124,0.00014275403,0.0015201259,0.00011095307,0.00009030869,0.000021734362,6.688008e-7,0.9817289,0.009773835,0.00027710389,0.00551341,0.0006053334],"about_ca_topic_score_codex":0.00002685301,"about_ca_topic_score_gemma":0.000106839514,"teacher_disagreement_score":0.6506629,"about_ca_system_score_codex":0.00017378076,"about_ca_system_score_gemma":0.00027033754,"threshold_uncertainty_score":0.9998776},"labels":[],"label_agreement":null},{"id":"W1595684610","doi":"10.1186/1471-2105-5-61","title":"An approach to large scale identification of non-obvious structural similarities between proteins","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; University of British Columbia","funders":"Genome Prairie; Genome British Columbia; Michael Smith Health Research BC","keywords":"Threading (protein sequence); Computational biology; Biology; Genome; Sequence alignment; Genetics; Structural similarity; Peptide sequence; Protein structure; Sequence (biology); Protein sequencing; Gene; DNA microarray; Virulence; Gene expression","score_opus":0.009320389599279316,"score_gpt":0.26985422941676046,"score_spread":0.2605338398174811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1595684610","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49086368,0.000009833522,0.5072505,0.000013455954,0.000051511113,0.000480317,0.00014183194,0.000026321351,0.001162592],"genre_scores_gemma":[0.6823338,0.0000029283376,0.31660748,0.00010270633,0.00010678237,0.000023708026,0.0007451851,0.000019465579,0.000057941714],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834615,0.000028029835,0.0008024014,0.00017379357,0.00031013033,0.00033952217],"domain_scores_gemma":[0.99861807,0.0000074791033,0.00035373867,0.00071056234,0.00015807511,0.00015208739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041647948,0.00022257035,0.00024577716,0.00012248885,0.00014325752,0.00007563033,0.00048595158,0.00021900871,0.000003470753],"category_scores_gemma":[0.000107986045,0.00020722314,0.00009369758,0.00019173876,0.00008659189,0.000041396917,0.00015614196,0.00015055496,0.0000214816],"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":[0.00051971176,0.0013633531,0.367834,0.009591426,0.0005337357,0.0000012119306,0.060659654,0.35909823,0.18061416,0.0047745164,0.0019026969,0.013107305],"study_design_scores_gemma":[0.0043757963,0.0019113693,0.28015056,0.00015346752,0.00016367053,0.000050308605,0.0093738055,0.39115056,0.30807555,0.0006319966,0.0021846404,0.0017782485],"about_ca_topic_score_codex":0.000019332234,"about_ca_topic_score_gemma":0.000021660073,"teacher_disagreement_score":0.19147013,"about_ca_system_score_codex":0.0000306086,"about_ca_system_score_gemma":0.00012884293,"threshold_uncertainty_score":0.84503144},"labels":[],"label_agreement":null},{"id":"W1598700272","doi":"10.1137/1.9781611972795.12","title":"Learning Random-Walk Kernels for Protein Remote Homology Identification and Motif Discovery","year":2009,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Ontario Genomics Institute; Genome Canada","keywords":"Random walk; Kernel (algebra); Random forest; Computer science; Artificial intelligence; Homology (biology); Smith–Waterman algorithm; Machine learning; Mathematics; Pattern recognition (psychology); Computational biology; Sequence alignment; Combinatorics; Biology; Statistics; Genetics; Peptide sequence; Gene","score_opus":0.005541963861312761,"score_gpt":0.2530038942527729,"score_spread":0.24746193039146017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1598700272","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7071799,0.00012010863,0.28920522,0.0006723568,0.000049435457,0.00056221045,0.0000034066559,0.000031630603,0.0021757197],"genre_scores_gemma":[0.9731075,0.000043592856,0.010485563,0.00025628388,0.000101860045,0.00001189272,0.00013021303,0.000012238971,0.015850848],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99922115,0.00005468601,0.00024638226,0.00022350944,0.000069403926,0.0001848588],"domain_scores_gemma":[0.999548,0.00001617079,0.00012588399,0.00020488763,0.00005367627,0.00005134576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034559285,0.00012048988,0.00013017275,0.000037259986,0.000112484086,0.00007292847,0.00010424992,0.00013004991,0.000008147294],"category_scores_gemma":[0.0006068626,0.00010677746,0.000056656536,0.00003912776,0.000046616122,0.000011394674,0.00004146571,0.00010479184,0.0000049612945],"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":[0.00034317293,0.000030232437,0.0006592963,0.00007078735,0.000037862384,8.163248e-7,0.00013051846,0.0005749068,0.93365186,0.001467639,0.00064641464,0.062386468],"study_design_scores_gemma":[0.010400688,0.00419522,0.023983238,0.00009047959,0.00011345798,0.00018163527,0.00035033267,0.09784118,0.78242755,0.009087813,0.069991186,0.0013372191],"about_ca_topic_score_codex":0.000009491197,"about_ca_topic_score_gemma":0.0000045927595,"teacher_disagreement_score":0.27871966,"about_ca_system_score_codex":0.00000663867,"about_ca_system_score_gemma":0.000026976373,"threshold_uncertainty_score":0.43542585},"labels":[],"label_agreement":null},{"id":"W1601201751","doi":"10.1007/11510888_33","title":"Prediction of Secondary Protein Structure Content from Primary Sequence Alone – A Feature Selection Based Approach","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"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":"Feature selection; Computer science; Representation (politics); Artificial intelligence; Set (abstract data type); Pattern recognition (psychology); Feature (linguistics); Protein function prediction; Selection (genetic algorithm); Sequence (biology); Protein secondary structure; Function (biology); Data mining; Machine learning; Protein function; Biology","score_opus":0.015563524884517468,"score_gpt":0.2160696792375443,"score_spread":0.20050615435302682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1601201751","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":[0.012691704,0.00040623435,0.9834636,0.00014626284,0.0002867316,0.00076339906,0.00035600777,0.00004007898,0.00184599],"genre_scores_gemma":[0.45055953,0.000016651746,0.54552346,0.00096270005,0.0008264689,0.000014420255,0.0014886939,0.000049509283,0.0005585557],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979292,0.00004080034,0.00041819605,0.00076641655,0.0005447901,0.00030056597],"domain_scores_gemma":[0.99862194,0.000031898235,0.00043600876,0.00058911793,0.00023930539,0.00008175698],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027779708,0.00040668304,0.0003917378,0.00023005024,0.0001036275,0.00006383024,0.0006413812,0.0006870988,0.000034082794],"category_scores_gemma":[0.000076483695,0.00036606504,0.0001081334,0.00016617491,0.00044721915,0.000022298027,0.0002547196,0.0009492933,0.0000013007693],"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":[0.00017131671,0.00006628522,0.00077230803,0.00041738217,0.00007856189,0.000004674757,0.00025321616,0.12773569,0.6681151,0.00010774761,0.00017312149,0.2021046],"study_design_scores_gemma":[0.0019810956,0.0013052967,0.0031588178,0.000893404,0.00007661898,0.00013204152,0.0000011080266,0.6636983,0.3147973,0.0024068633,0.010235195,0.0013139122],"about_ca_topic_score_codex":0.000029977491,"about_ca_topic_score_gemma":0.000050927392,"teacher_disagreement_score":0.53596264,"about_ca_system_score_codex":0.00015652619,"about_ca_system_score_gemma":0.0006386416,"threshold_uncertainty_score":0.9998791},"labels":[],"label_agreement":null},{"id":"W164082874","doi":"","title":"The proteome analyst suite of automated function prediction tools","year":2005,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Proteome; Gene ontology; Computer science; Function (biology); Suite; Ontology; Sequence (biology); Computational biology; Subcellular localization; Data mining; Bioinformatics; Gene; Biology; Biochemistry; Genetics","score_opus":0.05568293676456858,"score_gpt":0.3325883504638718,"score_spread":0.2769054136993032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W164082874","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.637756,0.00017967944,0.27765414,0.0065073296,0.001138919,0.0020362802,0.00047919757,0.00042871115,0.073819794],"genre_scores_gemma":[0.9983211,0.00002884479,0.00077474007,0.00014410714,0.00020691901,0.000028672268,0.00016719919,0.000006857563,0.0003215403],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988096,0.00006407488,0.0004180316,0.00016357475,0.00040621628,0.00013851366],"domain_scores_gemma":[0.9989202,0.000063202424,0.00020179978,0.00017564613,0.0006033518,0.000035793586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054181385,0.000103848266,0.00008231565,0.000062325256,0.00016929112,0.00007172797,0.00020438302,0.00010114859,0.00007076116],"category_scores_gemma":[0.00081413315,0.00008089697,0.000054365435,0.00016238181,0.00011926361,0.000015498075,0.000037388592,0.00013475298,0.0000839894],"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":[0.00074511935,0.00024279972,0.0006309911,0.000032323165,0.00014148981,2.637826e-7,0.00020346598,0.07880952,0.39199173,0.2837529,0.0024373785,0.24101204],"study_design_scores_gemma":[0.00005692688,0.0005742612,0.0053259404,0.0000276074,0.000015348302,0.0000039137853,0.0001452515,0.66245586,0.3132683,0.00495676,0.0129886875,0.00018115272],"about_ca_topic_score_codex":0.0000049908435,"about_ca_topic_score_gemma":0.000053546642,"teacher_disagreement_score":0.58364636,"about_ca_system_score_codex":0.00003024165,"about_ca_system_score_gemma":0.00014525995,"threshold_uncertainty_score":0.32988825},"labels":[],"label_agreement":null},{"id":"W1727171016","doi":"10.1186/1472-6807-5-16","title":"Computational identification of residues that modulate voltage sensitivity of voltage-gated potassium channels","year":2005,"lang":"en","type":"article","venue":"BMC Structural Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Potassium channel; Feature selection; Classifier (UML); Computational biology; Biological system; Transmembrane protein; Protein methods; k-nearest neighbors algorithm; Computer science; Artificial intelligence; Peptide sequence; Biology; Pattern recognition (psychology); Biochemistry; Biophysics; Gene","score_opus":0.012579751906968773,"score_gpt":0.2735442722984457,"score_spread":0.26096452039147694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1727171016","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9568062,0.00008890221,0.042419985,0.000060307,0.00019246775,0.00015510037,0.0001721623,0.000016176222,0.00008873568],"genre_scores_gemma":[0.9943908,0.000009149745,0.004041948,0.000053130843,0.0001387467,0.0000016656955,0.0011963346,0.000011521666,0.00015670124],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988772,0.00012887134,0.00046446908,0.00023145812,0.00010816528,0.00018979066],"domain_scores_gemma":[0.9989665,0.00006458342,0.00047861657,0.0002682473,0.00018235239,0.000039691527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003422314,0.00015891434,0.00023671065,0.00007689749,0.00004980375,0.000008602333,0.00015002182,0.00020698829,0.000025365167],"category_scores_gemma":[0.0002342616,0.00013892101,0.0000915965,0.000082543775,0.00022795885,0.000009761236,0.00011485425,0.000097916556,0.000005886089],"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":[0.0000926323,0.000011585538,0.059661426,0.000068931105,0.000049796312,2.5564222e-7,0.00009790274,0.03221252,0.90463936,0.0005196706,0.0001280418,0.002517856],"study_design_scores_gemma":[0.0005507669,0.00016084113,0.20335862,0.000011283297,0.000023082077,0.00003583456,0.000039126728,0.08887379,0.7051775,0.0008653237,0.0006756714,0.0002281632],"about_ca_topic_score_codex":0.000055194465,"about_ca_topic_score_gemma":0.000044517783,"teacher_disagreement_score":0.19946189,"about_ca_system_score_codex":0.0000127240655,"about_ca_system_score_gemma":0.0000440475,"threshold_uncertainty_score":0.5665034},"labels":[],"label_agreement":null},{"id":"W1736236789","doi":"10.1002/pmic.201500043","title":"The path of no return—Truncated protein N‐termini and current ignorance of their genesis","year":2015,"lang":"en","type":"article","venue":"PROTEOMICS","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of General Medical Sciences; National Institute of Mental Health","keywords":"Annotation; Proteome; Biology; Computational biology; Human proteome project; Protein function; RNA splicing; Alternative splicing; Cleavage (geology); Proteomics; Genetics; Bioinformatics; Gene; Messenger RNA; RNA","score_opus":0.011652014765242451,"score_gpt":0.24589062857763527,"score_spread":0.23423861381239283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1736236789","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9964345,0.0012754492,0.0012725041,0.00006010444,0.00009426982,0.00052946224,0.000024958325,0.0000061395626,0.00030260748],"genre_scores_gemma":[0.99068284,0.0002553692,0.008786161,0.000015962178,0.000084331434,0.00004816086,0.000025552874,0.000014794297,0.0000868247],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99931055,0.000057668018,0.0002784907,0.0001154519,0.00010896977,0.00012888774],"domain_scores_gemma":[0.99911785,0.000009994205,0.0002777688,0.00032286887,0.00022069956,0.000050807612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040512774,0.0001093838,0.00013293729,0.000014979446,0.000040587995,0.0000119559345,0.00020358087,0.0000746434,8.2842155e-7],"category_scores_gemma":[0.0003391215,0.00007212022,0.0000377587,0.00005205559,0.00014276919,0.0000033941426,0.00014421136,0.00009152947,0.0000014692796],"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":[0.00048021486,0.00008913198,0.016224205,0.00047292977,0.00006876335,3.351015e-7,0.0007960794,0.000052421612,0.9586713,0.0002767505,0.0009949692,0.021872954],"study_design_scores_gemma":[0.00085976813,0.0006544889,0.0021062081,0.00010033833,0.000013952385,0.0000088500465,0.00014014797,0.0062863217,0.9632134,0.00051759323,0.025870558,0.00022840797],"about_ca_topic_score_codex":0.000012534438,"about_ca_topic_score_gemma":0.0000029678176,"teacher_disagreement_score":0.024875589,"about_ca_system_score_codex":0.0000064317946,"about_ca_system_score_gemma":0.00009670347,"threshold_uncertainty_score":0.29409772},"labels":[],"label_agreement":null},{"id":"W1768968559","doi":"10.3233/ifs-151550","title":"Classifying sequences by the optimized dissimilarity space embedding approach: A case study on the solubility analysis of the E. coli proteome","year":2015,"lang":"en","type":"article","venue":"Journal of Intelligent & Fuzzy Systems","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Classifier (UML); Embedding; Proteome; Pattern recognition (psychology); Generality; Protein sequencing; Sequence (biology); Representation (politics)","score_opus":0.0629302058908194,"score_gpt":0.32824646113807643,"score_spread":0.26531625524725705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1768968559","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9844012,0.0004486571,0.012151563,0.0005984126,0.0004291306,0.0010945367,0.00001914401,0.0000046443292,0.00085268123],"genre_scores_gemma":[0.9991734,0.000016260667,0.00037931363,0.0000640556,0.00015185455,0.0000276353,0.000003614542,0.000011917983,0.00017197363],"study_design_codex":"simulation_or_modeling","study_design_gemma":"qualitative","domain_scores_codex":[0.9967342,0.0012245338,0.00096494047,0.00017568667,0.00068882457,0.00021182305],"domain_scores_gemma":[0.9971253,0.00018758154,0.001453615,0.0006949077,0.00043278837,0.00010578567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005101328,0.00020806125,0.00046509315,0.000083944615,0.00024180392,0.00012996182,0.00077169406,0.000111220914,0.0000033227946],"category_scores_gemma":[0.0011103486,0.0000884281,0.0003824114,0.00047155775,0.00018671955,0.000011476107,0.00019418233,0.00051604275,6.606149e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011125801,0.0019702062,0.111422285,0.00033838226,0.010227014,0.0000921904,0.029857295,0.8167357,0.01198396,0.00036235072,0.015564344,0.00033373476],"study_design_scores_gemma":[0.002222512,0.00425362,0.0027643542,0.00040938213,0.004172893,0.0030764418,0.48053634,0.4717251,0.023532176,0.000064938475,0.0063135037,0.00092872395],"about_ca_topic_score_codex":0.00033513148,"about_ca_topic_score_gemma":0.00003035288,"teacher_disagreement_score":0.45067906,"about_ca_system_score_codex":0.00009028506,"about_ca_system_score_gemma":0.00016322694,"threshold_uncertainty_score":0.36059934},"labels":[],"label_agreement":null},{"id":"W1813034246","doi":"10.1186/1471-2105-6-23","title":"Recent Hits Acquired by BLAST (ReHAB): A tool to identify new hits in sequence similarity searches","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency","keywords":"Computer science; Similarity (geometry); Sequence (biology); Alignment-free sequence analysis; Information retrieval; Table (database); Interface (matter); Graphics; Data mining; Genome; Sequence alignment; Sequence database; Software; Multiple sequence alignment; Database; Artificial intelligence; Biology; Genetics; Programming language; Computer graphics (images)","score_opus":0.03302620209898142,"score_gpt":0.3249614275038759,"score_spread":0.29193522540489447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1813034246","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":[0.8891033,0.0007666224,0.09644914,0.0032756906,0.00041482516,0.0019558426,0.0003186614,0.00019043489,0.0075255153],"genre_scores_gemma":[0.15388179,0.0014147212,0.82767403,0.008914566,0.0007414058,0.00010317493,0.0015867,0.00013256421,0.005551069],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975022,0.00007061706,0.0009541582,0.00028801567,0.0004884247,0.0006965856],"domain_scores_gemma":[0.9985104,0.000048168506,0.00024779292,0.0007273889,0.00013623972,0.00033001046],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006569004,0.00036658865,0.0003096301,0.00016753378,0.00010783132,0.00015543867,0.00067606266,0.0003367862,0.00011387005],"category_scores_gemma":[0.0009523128,0.00036375047,0.00010545111,0.00042324016,0.00008713239,0.00006431182,0.00049177924,0.00026591282,0.00039632173],"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":[0.0005890997,0.0004646507,0.020313494,0.00093641825,0.00013722712,0.000005585586,0.0066448166,0.025137728,0.073809706,0.00024266829,0.44502982,0.4266888],"study_design_scores_gemma":[0.0021474978,0.0004452093,0.009274026,0.00016421328,0.000027866145,0.000052731375,0.0004967448,0.15986526,0.034978516,0.00005526327,0.7913448,0.0011478651],"about_ca_topic_score_codex":0.000032823904,"about_ca_topic_score_gemma":0.00029990566,"teacher_disagreement_score":0.7352215,"about_ca_system_score_codex":0.0001423687,"about_ca_system_score_gemma":0.00040872247,"threshold_uncertainty_score":0.99988145},"labels":[],"label_agreement":null},{"id":"W1844089452","doi":"10.1007/978-3-642-41062-8_32","title":"PFMFind: A System for Discovery of Peptide Homology and Function","year":2013,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Ottawa","funders":"National Institutes of Health","keywords":"Python (programming language); Computer science; Plug-in; Homology (biology); Nearest neighbor search; Computational biology; Information retrieval; Data mining; Artificial intelligence; Programming language; Biology; Amino acid; Genetics","score_opus":0.00486217806822931,"score_gpt":0.2246060796678768,"score_spread":0.2197439015996475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1844089452","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4265673,0.000039843206,0.57307494,0.00004720979,0.0001355475,0.00011525841,9.888669e-7,0.000003859608,0.0000150337955],"genre_scores_gemma":[0.9105352,0.000002370155,0.089200504,0.00016084537,0.000075221076,0.000012808401,0.0000059581566,0.0000038614194,0.0000032324886],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994047,0.000017654032,0.00014737288,0.00019590033,0.000077553195,0.00015677602],"domain_scores_gemma":[0.99959934,0.000051262625,0.0000715572,0.00019303593,0.000060516628,0.000024272267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021024451,0.00007502823,0.00009957666,0.00006657658,0.00004868348,0.000048014743,0.00017285593,0.000064042964,6.9198245e-7],"category_scores_gemma":[0.000106089065,0.00006100272,0.00002232872,0.00011693053,0.00021021525,0.000014763772,0.00013954868,0.000057303012,9.1221847e-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":[0.000087778506,0.00006192962,0.036184713,0.00058462645,0.000028988246,0.0000017582274,0.0007702818,0.04997209,0.6150695,0.00074194936,0.00012237036,0.29637396],"study_design_scores_gemma":[0.0012256424,0.0020493441,0.059466884,0.00013651571,0.00001760337,0.00013801575,0.000015499581,0.65876466,0.27411005,0.003066455,0.0005452134,0.00046411925],"about_ca_topic_score_codex":0.000035871723,"about_ca_topic_score_gemma":0.000019922278,"teacher_disagreement_score":0.60879254,"about_ca_system_score_codex":0.000011128509,"about_ca_system_score_gemma":0.000043120817,"threshold_uncertainty_score":0.24876188},"labels":[],"label_agreement":null},{"id":"W1849431564","doi":"","title":"Algorithms for the Hard Pre-Image Problem of String Kernels and the General Problem of String Prediction","year":2015,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université Laval; Institute for Research in Immunology and Cancer","funders":"","keywords":"String (physics); Kernel (algebra); String kernel; Heuristic; Computer science; Computational complexity theory; Function (biology); String metric; Task (project management); Upper and lower bounds; Image (mathematics); Algorithm; Edit distance; String searching algorithm; Artificial intelligence; Mathematics; Kernel method; Discrete mathematics; Radial basis function kernel; Support vector machine; Pattern matching","score_opus":0.03432492016534133,"score_gpt":0.312296814030021,"score_spread":0.2779718938646797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1849431564","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6601422,0.0005577947,0.31357342,0.0033727435,0.0004230306,0.0019844573,0.0002499469,0.00006486139,0.019631559],"genre_scores_gemma":[0.9773134,0.00011911789,0.020972494,0.000045369423,0.00016867399,0.00005154649,0.00013570584,0.000014852312,0.0011788481],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988926,0.00010430738,0.00038408823,0.00018340423,0.00029743343,0.00013816987],"domain_scores_gemma":[0.99894226,0.000100969875,0.0003911855,0.00016090393,0.00036506332,0.000039615774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000941585,0.00014088892,0.00016024582,0.000051709718,0.000090633446,0.000058609934,0.00033701374,0.00007134229,0.00001388511],"category_scores_gemma":[0.0003372309,0.00009013448,0.00007251252,0.000047228445,0.00016304433,0.00001715357,0.00018047249,0.00028291694,7.972075e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0049890648,0.00026920234,0.10166664,0.00060056936,0.001598424,0.000001808789,0.0076163164,0.30177197,0.15466024,0.28680587,0.000853445,0.13916646],"study_design_scores_gemma":[0.0035547626,0.0007849873,0.0044236183,0.00013470124,0.00005812391,0.000020215597,0.00044016913,0.9640597,0.013234589,0.0016322815,0.01147042,0.00018640065],"about_ca_topic_score_codex":0.0001513086,"about_ca_topic_score_gemma":0.000012413147,"teacher_disagreement_score":0.6622878,"about_ca_system_score_codex":0.000013110256,"about_ca_system_score_gemma":0.00007081931,"threshold_uncertainty_score":0.36755776},"labels":[],"label_agreement":null},{"id":"W1910628858","doi":"10.1109/cibcb.2015.7300327","title":"Protein secondary structure prediction using an evolutionary computation method and clustering","year":2015,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Cluster analysis; Artificial intelligence; Classifier (UML); Support vector machine; Artificial neural network; Computer science; Pattern recognition (psychology); Genetic programming; Protein sequencing; Machine learning; Data mining; Peptide sequence; Biology","score_opus":0.01831856601806122,"score_gpt":0.29910401399949577,"score_spread":0.28078544798143457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1910628858","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4925417,0.000043007974,0.50659907,0.000018329776,0.000050497332,0.00011256625,0.000012094268,0.000018431936,0.0006043048],"genre_scores_gemma":[0.6219618,6.696923e-7,0.3775877,0.00006352176,0.000100464335,0.0000016216457,0.00020199857,0.000008098485,0.000074159194],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946654,0.00007466605,0.00014539002,0.00013716865,0.000086687025,0.00008953689],"domain_scores_gemma":[0.9996931,0.0000026810576,0.00006259667,0.000099899094,0.000067116714,0.000074637006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001781272,0.00008139347,0.000060970822,0.000030646803,0.00006106034,0.000024706076,0.000042754713,0.00010075397,0.000009112999],"category_scores_gemma":[0.00004245036,0.00007575655,0.000011646713,0.000034115015,0.000023238208,0.0000143905645,0.00008032239,0.00008770057,5.157103e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014593973,0.000044468616,0.0068203537,0.00015055436,0.00006134222,0.0000015313731,0.0007197113,0.26952487,0.6902056,0.00014954925,0.0008607671,0.03131532],"study_design_scores_gemma":[0.000446322,0.0002718351,0.003068718,0.000008729654,0.000008905873,0.00012927437,0.00017355589,0.98555845,0.008190846,0.0004039287,0.0016185286,0.00012092467],"about_ca_topic_score_codex":0.000028791785,"about_ca_topic_score_gemma":0.000011752921,"teacher_disagreement_score":0.7160335,"about_ca_system_score_codex":0.000016863985,"about_ca_system_score_gemma":0.000060915514,"threshold_uncertainty_score":0.30892625},"labels":[],"label_agreement":null},{"id":"W1913418366","doi":"10.1109/cibcb.2015.7300293","title":"Classification via correlation-based feature grouping","year":2015,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Windsor","funders":"","keywords":"Feature selection; Feature (linguistics); Pattern recognition (psychology); Support vector machine; Artificial intelligence; Computer science; Correlation; k-nearest neighbors algorithm; Feature vector; Filter (signal processing); Set (abstract data type); Data mining; Mathematics","score_opus":0.016054482174551077,"score_gpt":0.26349351253577674,"score_spread":0.24743903036122566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1913418366","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07849751,0.00009671313,0.85856885,0.0014640208,0.00032470602,0.00019223799,0.0000028274083,0.00007458011,0.06077857],"genre_scores_gemma":[0.97401714,0.0000015073236,0.02219494,0.0007680555,0.00012021405,0.0000063844686,0.00039193593,0.000010890502,0.0024889016],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995402,0.000028439152,0.000106364685,0.00011304699,0.00011077322,0.00010114798],"domain_scores_gemma":[0.9995371,0.000008173924,0.00006823653,0.00022631449,0.000090832145,0.00006933062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016473478,0.00007744219,0.000052416664,0.000026144831,0.00003976888,0.000020172709,0.00009585986,0.00012514516,0.00001796096],"category_scores_gemma":[0.00015085515,0.000068461275,0.000030136765,0.000062965766,0.000023427736,0.0000030050608,0.000024599904,0.00008788104,0.00006759827],"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":[0.0003657265,0.00036654738,0.391158,0.00013539873,0.0001267125,0.0000032028552,0.0005961193,0.06548996,0.18201497,0.0069630356,0.32517323,0.027607096],"study_design_scores_gemma":[0.00094768364,0.00032025602,0.019177346,0.000009977473,0.00001511739,0.0000130869175,0.00014753683,0.80061424,0.008575616,0.00012235918,0.16974951,0.00030729244],"about_ca_topic_score_codex":0.000007632139,"about_ca_topic_score_gemma":0.000008658369,"teacher_disagreement_score":0.8955197,"about_ca_system_score_codex":0.000014983053,"about_ca_system_score_gemma":0.0000570173,"threshold_uncertainty_score":0.27917698},"labels":[],"label_agreement":null},{"id":"W1964430425","doi":"10.1186/1471-2105-11-563","title":"TESTLoc: protein subcellular localization prediction from EST data","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Canadian Institutes of Health Research; Université de Montréal; Canadian Institute for Advanced Research","keywords":"Subcellular localization; Computational biology; Support vector machine; Sequence (biology); Function (biology); Protein sequencing; Protein function prediction; Computer science; Biology; DNA microarray; Data mining; Protein function; Artificial intelligence; Peptide sequence; Biochemistry; Genetics; Cytoplasm; Gene","score_opus":0.015299169738053143,"score_gpt":0.24581988314883316,"score_spread":0.23052071341078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964430425","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":[0.23107268,0.000056241774,0.7623827,0.00005085274,0.0005357827,0.00063552125,0.0005649252,0.00013285827,0.0045684557],"genre_scores_gemma":[0.3231368,0.00003802394,0.64813054,0.0004360374,0.0010199542,0.000040398936,0.026452558,0.00007574418,0.000669933],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853456,0.00003300946,0.0006016603,0.0002448688,0.00030664634,0.00027928004],"domain_scores_gemma":[0.99779165,0.000022308495,0.00029039657,0.0016551176,0.000113358146,0.00012719638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041610084,0.0002350712,0.00015807596,0.00006518798,0.00015937493,0.00011910578,0.0007629734,0.00035095535,0.00008131517],"category_scores_gemma":[0.0007097251,0.00021887197,0.000050812265,0.00014593016,0.000109551016,0.00005300674,0.00049050705,0.00033351957,0.00018725435],"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":[0.00048742295,0.0008652185,0.3742195,0.0020682127,0.0004741468,0.0000071700647,0.0028281482,0.025745831,0.46187118,0.0030447587,0.070809916,0.057578504],"study_design_scores_gemma":[0.0005223416,0.00011480308,0.0021901447,0.000026974387,0.00003052443,0.000013599447,0.00009682843,0.87417674,0.013020213,0.00006128592,0.10947182,0.000274714],"about_ca_topic_score_codex":0.00006228462,"about_ca_topic_score_gemma":0.0002500662,"teacher_disagreement_score":0.84843093,"about_ca_system_score_codex":0.000013059256,"about_ca_system_score_gemma":0.00015498207,"threshold_uncertainty_score":0.89253396},"labels":[],"label_agreement":null},{"id":"W1965012204","doi":"10.1155/2013/870372","title":"Predicting<i>β</i>-Turns in Protein Using Kernel Logistic Regression","year":2013,"lang":"en","type":"article","venue":"BioMed Research International","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"University of Saskatchewan","funders":"Central South University; Ministry of Education of the People's Republic of China; National Natural Science Foundation of China","keywords":"Support vector machine; Artificial intelligence; Kernel (algebra); Computer science; Logistic regression; Machine learning; Algorithm; Pattern recognition (psychology); Probabilistic logic; Regression; Mathematics; Statistics; Combinatorics","score_opus":0.07403111163272218,"score_gpt":0.4091610444742174,"score_spread":0.3351299328414952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965012204","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99201715,0.00008219344,0.0008041649,0.00082388066,0.00034977053,0.0004958294,0.00001490081,0.000016529404,0.0053955843],"genre_scores_gemma":[0.991147,0.000022466047,0.0055124667,0.000052446925,0.00045343567,0.0000834623,0.00015034003,0.000017848495,0.0025605706],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983485,0.00016417656,0.0002835264,0.00024846336,0.0005943717,0.00036097114],"domain_scores_gemma":[0.99921215,0.000033621163,0.00008384405,0.0002515369,0.00032020328,0.000098625715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008132052,0.000112119356,0.00008640368,0.00030762955,0.000069426555,0.000094983465,0.0004674613,0.00014930594,0.00024885498],"category_scores_gemma":[0.0013711306,0.00009239541,0.000040090148,0.00021217907,0.00017993766,0.000014948987,0.00039529582,0.0003497293,0.00009209258],"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":[0.0000903744,0.00015813956,0.067615,0.0000752378,0.000044800858,0.000010758932,0.00016998283,0.00028081515,0.922623,0.00035545416,0.0061120284,0.0024644362],"study_design_scores_gemma":[0.004815777,0.0011540977,0.1494931,0.0010383845,0.000009433677,0.0001720852,0.0010242754,0.51609176,0.14443494,0.0043470827,0.17623182,0.0011872095],"about_ca_topic_score_codex":0.00046097822,"about_ca_topic_score_gemma":0.000036963404,"teacher_disagreement_score":0.77818805,"about_ca_system_score_codex":0.000095787436,"about_ca_system_score_gemma":0.0001130557,"threshold_uncertainty_score":0.37677753},"labels":[],"label_agreement":null},{"id":"W1968753483","doi":"10.1016/j.bpj.2012.11.773","title":"Exceptionally Conserved Asparagines in the Pore-Lining Helices of Calcium and Sodium Channels Stabilize the Open State through Interdomain H-Bonds","year":2013,"lang":"en","type":"article","venue":"Biophysical Journal","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"McMaster University","funders":"","keywords":"Asparagine; Chemistry; Biophysics; Sodium channel; Residue (chemistry); Sodium; Amino acid; Stereochemistry; Biochemistry; Biology","score_opus":0.026042364842471803,"score_gpt":0.3063432431182269,"score_spread":0.2803008782757551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968753483","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99464643,0.00006952,0.001198878,0.0031634078,0.000085782325,0.0002539656,0.000007648995,0.0000027025276,0.0005716646],"genre_scores_gemma":[0.9975407,0.000053180815,0.001090526,0.00092823355,0.00023294703,0.000020223504,0.0000160948,0.00001023469,0.00010784998],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988813,0.00022253883,0.00037166002,0.00013093169,0.00019051059,0.00020305018],"domain_scores_gemma":[0.99928445,0.00009963278,0.0002487935,0.00021222897,0.00010979581,0.000045122833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005570573,0.00013761721,0.00017665877,0.000020777483,0.000120932425,0.00022266776,0.0006341906,0.00005688447,0.000032100183],"category_scores_gemma":[0.00011173658,0.000073529234,0.000059314294,0.0000855133,0.00025607846,0.000031479878,0.00033028665,0.00028875566,0.000004695122],"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":[0.0002564041,0.00026888438,0.0064080893,0.00007711992,0.00014853929,0.000008825447,0.00601549,0.0003614916,0.9784705,0.0016055205,0.0040081143,0.0023710353],"study_design_scores_gemma":[0.01581765,0.0092769805,0.36820266,0.00094009854,0.00027613566,0.0025877708,0.028238289,0.044198487,0.42730603,0.042836644,0.057182062,0.0031371948],"about_ca_topic_score_codex":0.00013356861,"about_ca_topic_score_gemma":0.00001641059,"teacher_disagreement_score":0.55116445,"about_ca_system_score_codex":0.000006939509,"about_ca_system_score_gemma":0.000055683107,"threshold_uncertainty_score":0.29984352},"labels":[],"label_agreement":null},{"id":"W1971269462","doi":"10.1142/s0219720006001722","title":"THE USE OF FUNCTIONAL DOMAINS TO IMPROVE TRANSMEMBRANE PROTEIN TOPOLOGY PREDICTION","year":2006,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Caprion (Canada); University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; University of Calgary","keywords":"Transmembrane protein; Topology (electrical circuits); Transmembrane domain; Membrane protein; Computational biology; Computer science; Biology; Mathematics; Gene; Genetics; Membrane","score_opus":0.008049881864178819,"score_gpt":0.22718057682381404,"score_spread":0.21913069495963522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971269462","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65071845,0.00013202764,0.34745637,0.00090917066,0.0002742412,0.00022014863,0.00008662074,0.0000043229284,0.00019866359],"genre_scores_gemma":[0.9407985,0.000048913495,0.058218148,0.00033769588,0.00027128553,0.0000065110967,0.0001605875,0.000008727017,0.0001495815],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988325,0.000051062678,0.00076567987,0.00006642843,0.00014127785,0.00014299837],"domain_scores_gemma":[0.998928,0.00011058253,0.0004919851,0.000097205084,0.00031834233,0.000053865537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034211416,0.00010710593,0.00016310671,0.000092657916,0.00012098009,0.000030074147,0.00011324417,0.00011368441,0.000004336053],"category_scores_gemma":[0.00012918295,0.00007173943,0.0000809306,0.00007683248,0.00017145257,0.000017677032,0.00005038372,0.00012498254,0.0000013860484],"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":[0.00243713,0.00035125302,0.011822238,0.00032926394,0.0007194647,0.000003229441,0.0005691905,0.495281,0.32411942,0.07425997,0.013830891,0.07627694],"study_design_scores_gemma":[0.0071701123,0.012858356,0.06499058,0.00013286789,0.00020079169,0.0013841013,0.00051942415,0.33740914,0.021191224,0.024024127,0.52921826,0.000900996],"about_ca_topic_score_codex":0.000008329919,"about_ca_topic_score_gemma":0.000007440208,"teacher_disagreement_score":0.51538736,"about_ca_system_score_codex":0.00001091272,"about_ca_system_score_gemma":0.000095084164,"threshold_uncertainty_score":0.2925449},"labels":[],"label_agreement":null},{"id":"W1972434016","doi":"10.1093/nar/gkn255","title":"PROTEUS2: a web server for comprehensive protein structure prediction and structure-based annotation","year":2008,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":116,"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; National Institute for Nanotechnology","funders":"Alberta Prion Research Institute; Natural Sciences and Engineering Research Council of Canada; Genome Alberta","keywords":"Protein secondary structure; Web server; Threading (protein sequence); Biology; Computational biology; Annotation; Protein structure prediction; Protein structure database; Homology modeling; Computer science; Hidden Markov model; Pipeline (software); Sequence alignment; Protein tertiary structure; Protein structure; Artificial intelligence; Bioinformatics; Peptide sequence; Sequence database; Genetics; The Internet","score_opus":0.032409509715875834,"score_gpt":0.3212105942469039,"score_spread":0.28880108453102804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972434016","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99630916,0.00007542801,0.0011259224,0.00030799216,0.000041948024,0.0017087453,0.00024360586,0.00003737229,0.00014985385],"genre_scores_gemma":[0.98848987,0.000012389028,0.010254224,0.0001240479,0.00019389708,0.00009976657,0.00050082325,0.00003289989,0.00029209576],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99855775,0.00015409142,0.0002135704,0.00031505944,0.00041530424,0.0003442396],"domain_scores_gemma":[0.9989747,0.000030067104,0.000073183626,0.00033389087,0.0004898955,0.000098280616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002159561,0.00015541316,0.00013408359,0.00011881227,0.00039420303,0.000045551646,0.00018371399,0.00025904982,0.00003440699],"category_scores_gemma":[0.00031841206,0.00013920975,0.00004272178,0.00017279337,0.00025705376,0.000012686525,0.00010942625,0.000360342,0.000003137556],"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":[0.0004398959,0.000027348631,0.007150369,0.00033593242,0.000038051287,0.0000020953703,0.00024640674,0.00047126433,0.984063,0.000111326735,0.004900603,0.0022136602],"study_design_scores_gemma":[0.0070211296,0.004707423,0.08448517,0.0001447364,0.000026699878,0.00015148388,0.00036583608,0.17077747,0.5770261,0.0010269149,0.15348314,0.0007838445],"about_ca_topic_score_codex":0.000013990574,"about_ca_topic_score_gemma":0.00001931104,"teacher_disagreement_score":0.4070369,"about_ca_system_score_codex":0.000031574244,"about_ca_system_score_gemma":0.00019619628,"threshold_uncertainty_score":0.56768084},"labels":[],"label_agreement":null},{"id":"W1973262365","doi":"10.1016/j.jmb.2005.05.037","title":"Armadillo: Domain Boundary Prediction by Amino Acid Composition","year":2005,"lang":"en","type":"article","venue":"Journal of Molecular Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":60,"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; Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital","funders":"","keywords":"Linker; Armadillo; Computational biology; Protein domain; Domain (mathematical analysis); Amino acid; Peptide sequence; Sequence (biology); Biological system; Computer science; Biology; Genetics; Mathematics; Cell biology","score_opus":0.0028390612382496938,"score_gpt":0.24746956885520854,"score_spread":0.24463050761695884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973262365","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8630968,0.0024698053,0.13143215,0.0011369298,0.00030699233,0.00009736006,0.000043755957,0.000010947378,0.0014053002],"genre_scores_gemma":[0.973782,0.00019527476,0.02371919,0.001417107,0.00045969686,0.000002680077,0.00033870566,0.00002067282,0.000064661675],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987867,0.00017468513,0.00052665983,0.00014224766,0.00014293204,0.00022680833],"domain_scores_gemma":[0.99910754,0.000008876497,0.0004320033,0.0002054972,0.00014035522,0.000105743886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040885236,0.00016057704,0.00020414742,0.00009155841,0.00007678151,0.000024779221,0.00024468673,0.0002462008,0.00003272763],"category_scores_gemma":[0.00006194597,0.00014259428,0.0001571697,0.00006518043,0.00012576881,0.000010442133,0.000070944836,0.00028095877,0.00001418159],"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":[0.000111601046,0.00007068008,0.0018642511,0.000009056108,0.00010303067,0.000005631355,0.00004094394,0.0002193289,0.9843567,0.0001363546,0.0084055895,0.0046768473],"study_design_scores_gemma":[0.0013467796,0.0014955519,0.0006294141,0.000019602456,0.00004484298,0.0009138084,0.000030053458,0.00026024852,0.57032377,0.00030019853,0.42442566,0.0002100861],"about_ca_topic_score_codex":0.0000013580922,"about_ca_topic_score_gemma":0.000001001609,"teacher_disagreement_score":0.41602007,"about_ca_system_score_codex":0.000040749568,"about_ca_system_score_gemma":0.00006798414,"threshold_uncertainty_score":0.5814825},"labels":[],"label_agreement":null},{"id":"W1974529710","doi":"10.1109/iembs.2010.5627300","title":"Fast orthogonal search for genetic feature selection","year":2010,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Queen's University","funders":"","keywords":"Computer science; Feature selection; Multivariate statistics; Artificial intelligence; Selection (genetic algorithm); Pattern recognition (psychology); Data mining; Feature (linguistics); Regression; Scale (ratio); Machine learning; Mathematics; Statistics","score_opus":0.004912763823578838,"score_gpt":0.2627368011366409,"score_spread":0.257824037313062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974529710","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9319882,0.00001544813,0.060291976,0.00031768295,0.00020272317,0.00023540569,0.000011234475,0.000027823568,0.0069095003],"genre_scores_gemma":[0.83201873,0.0000069898015,0.15715836,0.00037866985,0.0005821302,0.0000258093,0.00018667853,0.000022629129,0.009619983],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994587,0.0000124872095,0.00009514614,0.00015260778,0.00009035548,0.00019073863],"domain_scores_gemma":[0.9996369,0.000009437344,0.000028768278,0.00016210809,0.00010411683,0.00005865299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012560455,0.00009241402,0.00006029112,0.000028308414,0.000092300674,0.000028945786,0.00012004742,0.000177816,0.00009904589],"category_scores_gemma":[0.0000545411,0.00007962992,0.00005812553,0.000052950552,0.00003281098,0.0000017979999,0.000045466433,0.00020354919,0.000018372502],"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":[0.00005468896,0.000028593704,0.032467157,0.00003804722,0.000029803574,1.9007447e-7,0.000033842745,0.00046608874,0.93766856,0.0010832809,0.013691031,0.014438733],"study_design_scores_gemma":[0.0009688429,0.0006798612,0.05299077,0.0000042154,0.000022074855,0.0001522484,0.000053420215,0.0323812,0.5137715,0.000073092364,0.3984725,0.00043030907],"about_ca_topic_score_codex":0.0000042051743,"about_ca_topic_score_gemma":0.00008262561,"teacher_disagreement_score":0.42389706,"about_ca_system_score_codex":0.0000031042034,"about_ca_system_score_gemma":0.000056265053,"threshold_uncertainty_score":0.3247214},"labels":[],"label_agreement":null},{"id":"W1979548025","doi":"10.1142/s0219720011005355","title":"IMPROVED SEQUENCE-BASED PREDICTION OF STRAND RESIDUES","year":2010,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Artificial intelligence; Computational biology; Classifier (UML); Pattern recognition (psychology); Computer science; Biological system; Biology; Bioinformatics","score_opus":0.009067655613722058,"score_gpt":0.25938986886793786,"score_spread":0.2503222132542158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979548025","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9395926,0.00007017985,0.05931137,0.00019057479,0.0002513566,0.00008304209,0.00010463472,0.000004176909,0.00039204076],"genre_scores_gemma":[0.8978145,0.000032285694,0.10174704,0.00014428659,0.00010382081,7.6119113e-7,0.00014443418,0.0000047750623,0.0000080971395],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907184,0.00002568806,0.00063996797,0.00005468703,0.00010512172,0.00010271059],"domain_scores_gemma":[0.99882084,0.000058069578,0.00063325325,0.00009311004,0.00033035988,0.00006433677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040442616,0.000097229524,0.00017157028,0.00011133984,0.00004778046,0.000016553267,0.00012875731,0.00014759346,0.000010199888],"category_scores_gemma":[0.00016917948,0.00007591445,0.00006997102,0.000055777404,0.00017586742,0.000013477399,0.00003340583,0.0002001828,4.967691e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008259953,0.00025134726,0.08366129,0.0004676772,0.00045415666,0.0000023897762,0.00079728576,0.021921292,0.8176142,0.0076634916,0.0015379097,0.06480295],"study_design_scores_gemma":[0.0048870067,0.0057974155,0.032584984,0.0000897566,0.00010240926,0.0005940683,0.0003215971,0.8992808,0.036382377,0.004827493,0.014707242,0.00042485297],"about_ca_topic_score_codex":0.000002497677,"about_ca_topic_score_gemma":0.0000039033735,"teacher_disagreement_score":0.8773595,"about_ca_system_score_codex":0.000003921706,"about_ca_system_score_gemma":0.00016961372,"threshold_uncertainty_score":0.30957016},"labels":[],"label_agreement":null},{"id":"W1981890639","doi":"10.1186/1471-2105-10-206","title":"Representative transcript sets for evaluating a translational initiation sites predictor","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Calgary Laboratory Services","keywords":"Benchmark (surveying); Set (abstract data type); Population; Computer science; Data mining; Data set; Expression (computer science); Sequence (biology); Test set; Computational biology; Algorithm; Biology; Machine learning; Artificial intelligence; Genetics","score_opus":0.04719615713034547,"score_gpt":0.35682675967505173,"score_spread":0.30963060254470626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981890639","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":[0.16218878,0.00014142477,0.8303544,0.00033596225,0.00015199947,0.0011640817,0.00025188172,0.00008173009,0.0053297444],"genre_scores_gemma":[0.3300297,0.000023067343,0.66544116,0.0009961196,0.00020075699,0.000060086873,0.0029848595,0.000023124207,0.00024109543],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985537,0.000052451305,0.0006305254,0.0001657506,0.0003115002,0.00028607887],"domain_scores_gemma":[0.9990659,0.000083400366,0.00027011926,0.00028476602,0.00021020055,0.000085658365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051803206,0.00020815729,0.00017319927,0.00008321861,0.00016922786,0.00006736937,0.0001975981,0.00017560871,0.000027495758],"category_scores_gemma":[0.0005636493,0.0001984985,0.0001549994,0.0001196978,0.00004966557,0.000042290147,0.000018247672,0.000117875396,0.00001338999],"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":[0.0067451517,0.0016419482,0.06665986,0.0055317744,0.0012304389,0.0000034572436,0.08106658,0.2104223,0.26436046,0.02363402,0.12931845,0.20938556],"study_design_scores_gemma":[0.0022893846,0.0011879742,0.0096813245,0.00003656966,0.00007765533,0.000018666131,0.0005656611,0.97079265,0.008292267,0.0013185353,0.0053497422,0.00038956746],"about_ca_topic_score_codex":9.3165227e-7,"about_ca_topic_score_gemma":0.000006813334,"teacher_disagreement_score":0.7603704,"about_ca_system_score_codex":0.000015483984,"about_ca_system_score_gemma":0.00014193566,"threshold_uncertainty_score":0.8094534},"labels":[],"label_agreement":null},{"id":"W1982075805","doi":"10.1109/cibcb.2005.1594924","title":"Pathway Analyst Automated Metabolic Pathway Prediction","year":2005,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"University of Alberta","funders":"","keywords":"Leverage (statistics); Metabolic pathway; Hidden Markov model; Computer science; Support vector machine; Similarity (geometry); Computational biology; Identification (biology); Artificial intelligence; Machine learning; Biology; Gene; Genetics; Ecology","score_opus":0.005055874996643707,"score_gpt":0.2352774308702761,"score_spread":0.2302215558736324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982075805","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8988413,0.00057962333,0.012320286,0.00039587158,0.000262111,0.00028165683,0.00007100355,0.0007577681,0.08649035],"genre_scores_gemma":[0.98395634,0.000054945485,0.010248448,0.00049641036,0.00040619628,0.0000130495955,0.00039195563,0.000020593363,0.0044120536],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990924,0.00004750037,0.00028844137,0.00019690034,0.00015288648,0.0002218466],"domain_scores_gemma":[0.9993833,0.0000060921734,0.00009236404,0.00036540767,0.000068332236,0.00008455366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002116038,0.00014914622,0.00013075973,0.00006205493,0.000079993435,0.000032893673,0.0001613296,0.0001173512,0.00017036869],"category_scores_gemma":[0.000093648014,0.00012517603,0.00008841731,0.00012572011,0.00003365121,0.00000723491,0.00008034776,0.000100812984,0.0001619932],"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":[0.00007740264,0.0002898914,0.025230825,0.000056575394,0.00043118093,0.0000033849815,0.00033543704,0.016156523,0.8212398,0.0034844282,0.038792174,0.093902364],"study_design_scores_gemma":[0.000453512,0.00013500382,0.009977645,0.000004447444,0.000020605374,0.000025362497,0.000038698254,0.124812365,0.19437908,0.0000069292637,0.6699371,0.00020925552],"about_ca_topic_score_codex":0.000011500431,"about_ca_topic_score_gemma":0.000032936674,"teacher_disagreement_score":0.63114494,"about_ca_system_score_codex":0.000010058587,"about_ca_system_score_gemma":0.00005948549,"threshold_uncertainty_score":0.51045305},"labels":[],"label_agreement":null},{"id":"W1982152162","doi":"10.1021/jf034744i","title":"Pattern Similarity Analysis of Amino Acid Sequences for Peptide Emulsification","year":2004,"lang":"en","type":"article","venue":"Journal of Agricultural and Food Chemistry","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Toronto Metropolitan University; University of British Columbia; Dalhousie University","funders":"Morinaga Milk Industry","keywords":"Peptide; Amino acid; Chemistry; Homology (biology); Residue (chemistry); Proline; Polar; Structural similarity; Biological system; Chromatography; Biochemistry; Biology; Physics","score_opus":0.008901864171211707,"score_gpt":0.23491195770018378,"score_spread":0.22601009352897206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982152162","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9974697,0.00033081125,0.0017226363,0.00024697185,0.000021989801,0.000040516174,0.000037446927,0.0000020655743,0.00012786532],"genre_scores_gemma":[0.9978524,0.00010730561,0.0017200602,0.00003528393,0.00012658574,0.0000015700415,0.000110893285,0.000002658019,0.00004325964],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99936473,0.0000068213585,0.00033728997,0.0000845629,0.00011572325,0.0000908475],"domain_scores_gemma":[0.9991693,0.000009227216,0.0004592768,0.00008131634,0.00022487927,0.000055981855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010661153,0.000094925075,0.00019110148,0.000020931926,0.000039956863,0.000017227516,0.00012549009,0.00009885077,0.000004172048],"category_scores_gemma":[0.00007410965,0.00005994173,0.00018069964,0.00010169418,0.000044812947,0.000009087306,0.000026729533,0.00009253305,8.2405315e-8],"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":[0.00001879313,0.000039439357,0.005272054,0.00011197705,0.0005496827,1.8274064e-7,0.00014644727,0.0014289266,0.9917042,0.000004313903,0.000114760776,0.0006092265],"study_design_scores_gemma":[0.0005020809,0.0003973038,0.10933026,0.000028062232,0.0004292239,0.00006028821,0.00049564696,0.000054619446,0.888253,0.000038071757,0.00028683685,0.00012463654],"about_ca_topic_score_codex":0.000003384168,"about_ca_topic_score_gemma":0.000006926178,"teacher_disagreement_score":0.104058206,"about_ca_system_score_codex":0.000013823901,"about_ca_system_score_gemma":0.000022838392,"threshold_uncertainty_score":0.24443528},"labels":[],"label_agreement":null},{"id":"W1984674282","doi":"10.1109/tnb.2012.2208473","title":"Enhancing Membrane Protein Subcellular Localization Prediction by Parallel Fusion of Multi-View Features","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on NanoBioscience","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"University of Illinois at Urbana-Champaign; Nanjing University of Science and Technology; Concordia University","keywords":"Redundancy (engineering); Subcellular localization; Protein subcellular localization prediction; Computer science; Feature vector; Artificial intelligence; Membrane protein; Benchmark (surveying); Feature (linguistics); Molecular biophysics; Pattern recognition (psychology); Support vector machine; Algorithm; Membrane; Biology; Biochemistry","score_opus":0.00763423259583247,"score_gpt":0.2376660334986215,"score_spread":0.23003180090278905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984674282","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14538577,0.0002987909,0.85349876,0.00003250324,0.00030337568,0.00033478456,0.000036820635,0.000027944343,0.00008126527],"genre_scores_gemma":[0.99181557,0.00018397106,0.0068507846,0.000091218426,0.000030932053,0.000031630698,0.000037312082,0.00001437092,0.00094421266],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989144,0.00007533293,0.00029227568,0.00020901662,0.00024840762,0.0002605457],"domain_scores_gemma":[0.9994123,0.000009995847,0.00014043448,0.00027686814,0.0000684965,0.00009193436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035144007,0.00015156284,0.0001241587,0.00007227754,0.00020056363,0.000016047485,0.00017834624,0.00015520731,0.000029231947],"category_scores_gemma":[0.000028726834,0.00013682463,0.00007054418,0.000248678,0.000121343386,0.000029358338,0.0000038498965,0.00012943921,0.000009492531],"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":[0.000029119848,0.00018318451,0.00009920184,0.00007928025,0.0000075412177,6.894121e-8,0.00016214917,0.006092559,0.9918295,0.0000079134525,0.00009594912,0.0014135195],"study_design_scores_gemma":[0.00031779797,0.00020802136,0.00012547661,0.00006464212,0.000014959722,0.0000082900815,0.000042359272,0.00620824,0.98999465,8.9490794e-7,0.002878785,0.00013590096],"about_ca_topic_score_codex":0.000039932904,"about_ca_topic_score_gemma":0.000018810706,"teacher_disagreement_score":0.846648,"about_ca_system_score_codex":0.000023748638,"about_ca_system_score_gemma":0.00003963697,"threshold_uncertainty_score":0.55795467},"labels":[],"label_agreement":null},{"id":"W1986913015","doi":"10.1016/j.bbrc.2006.07.141","title":"Classifier ensembles for protein structural class prediction with varying homology","year":2006,"lang":"en","type":"article","venue":"Biochemical and Biophysical Research Communications","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":164,"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":"Pattern recognition (psychology); Classifier (UML); Artificial intelligence; Computer science; Support vector machine; Homology (biology); Protein structure prediction; Computational biology; Mathematics; Algorithm; Protein structure; Biology; Genetics; Amino acid","score_opus":0.03527510867903335,"score_gpt":0.33735145138699923,"score_spread":0.3020763427079659,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986913015","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99148965,0.0003271837,0.0017321261,0.0026165382,0.000014232591,0.00067276857,0.00008907644,0.000032635915,0.0030257937],"genre_scores_gemma":[0.98395103,0.000042074458,0.014324304,0.000041034218,0.00020365333,0.00023156778,0.0007199577,0.000016773141,0.00046957802],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988781,0.00012550679,0.00020087136,0.00025551897,0.00021073216,0.0003292657],"domain_scores_gemma":[0.99878025,0.00011404117,0.000054388987,0.00069014134,0.00027179488,0.00008937984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024895903,0.00012895004,0.00012535202,0.000054142645,0.00041472612,0.000060063358,0.00042196072,0.00016874322,0.0000030470924],"category_scores_gemma":[0.0002138699,0.00009829617,0.000049612685,0.0001649456,0.0007979778,0.000009172209,0.00032315758,0.0003348048,0.0000032606026],"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":[0.00014495192,0.00007766288,0.00035336148,0.000048001628,0.000021325628,1.7530108e-7,0.000013475838,0.000004789148,0.9877272,0.008753992,0.001963578,0.00089147646],"study_design_scores_gemma":[0.0017898742,0.0017781343,0.004623985,0.00009609344,0.000039760238,0.000038225295,0.00008830089,0.026604934,0.87888354,0.0066110985,0.07894578,0.00050027587],"about_ca_topic_score_codex":0.000049563827,"about_ca_topic_score_gemma":0.000014340689,"teacher_disagreement_score":0.10884367,"about_ca_system_score_codex":0.000021279122,"about_ca_system_score_gemma":0.00007050423,"threshold_uncertainty_score":0.40084013},"labels":[],"label_agreement":null},{"id":"W1987231763","doi":"10.2174/092986608786071085","title":"Function Prediction of Hypothetical Proteins Without Sequence Similarity to Proteins of Known Function (SUPPLEMENTARY MATERIALS)","year":2008,"lang":"en","type":"article","venue":"Protein and Peptide Letters","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Similarity (geometry); Sequence (biology); Computational biology; Function (biology); Computer science; Protein sequencing; Protein function; Genome; Domain (mathematical analysis); Bioinformatics; Biology; Genetics; Artificial intelligence; Peptide sequence; Mathematics; Gene; Image (mathematics)","score_opus":0.016821329265679256,"score_gpt":0.23456782123005035,"score_spread":0.2177464919643711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987231763","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97851026,0.000018748846,0.018943746,0.00069374143,0.00007561749,0.0014220623,0.000186092,0.00001779781,0.00013193386],"genre_scores_gemma":[0.98426265,0.00001145623,0.014459641,0.0005681421,0.00018183327,0.00017654973,0.00022316148,0.0000198569,0.000096692216],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998799,0.0000979434,0.000413794,0.00025801387,0.00023231056,0.00019891995],"domain_scores_gemma":[0.99936986,0.000006222122,0.00019265836,0.00028098925,0.00007321274,0.00007706716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027369978,0.0001741267,0.00019968563,0.00007593544,0.000096226686,0.000010358497,0.00010361821,0.000114503324,0.000080564816],"category_scores_gemma":[0.00008859464,0.00016313542,0.00005079108,0.000087720306,0.00017292958,0.000013236249,0.00009644727,0.00012440648,0.0000033729743],"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":[0.0005825408,0.000050533647,0.011700327,0.00022735313,0.000042362364,8.733297e-7,0.000142531,0.00007548487,0.9860257,0.00006098329,0.00050278247,0.000588529],"study_design_scores_gemma":[0.00089521415,0.0020877752,0.02420403,0.00011364769,0.00004308087,0.000041697633,0.00003917224,0.00017369991,0.9637185,0.00007342419,0.008384292,0.00022546883],"about_ca_topic_score_codex":0.00017664222,"about_ca_topic_score_gemma":0.000018359358,"teacher_disagreement_score":0.022307204,"about_ca_system_score_codex":0.000017417027,"about_ca_system_score_gemma":0.00003573686,"threshold_uncertainty_score":0.66524696},"labels":[],"label_agreement":null},{"id":"W1987659734","doi":"10.1145/2506583.2512372","title":"Prediction of Biological Protein-protein Interaction Types Using Short-Linear Motifs","year":2013,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Support vector machine; Computer science; Identification (biology); Protein–protein interaction; Curse of dimensionality; Obligate; Dimensionality reduction; Artificial intelligence; Machine learning; Pattern recognition (psychology); Computational biology; Data mining; Biology; Genetics","score_opus":0.03657548176382995,"score_gpt":0.28314043282151913,"score_spread":0.24656495105768916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987659734","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97497314,0.000018361474,0.022099292,0.00003374165,0.000061409824,0.00039125766,0.0000058258574,0.000024194009,0.0023927465],"genre_scores_gemma":[0.9763867,0.000004069513,0.02292516,0.00002961875,0.00011188639,0.000020685306,0.00007775549,0.000009315947,0.00043476938],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99935603,0.000043132113,0.00025518873,0.00013775214,0.00008421455,0.00012368392],"domain_scores_gemma":[0.999579,0.0000040990867,0.000082980776,0.00019106534,0.00010559468,0.000037259124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000107384745,0.00009995137,0.00009842041,0.000035255023,0.00003585952,0.0000123617765,0.00009445997,0.00014634512,0.0002246418],"category_scores_gemma":[0.00013139057,0.000076366814,0.000051260526,0.000053272324,0.000050006623,0.000009300724,0.00008118346,0.00009951232,0.0000269006],"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":[0.000017988617,0.000032160435,0.004082579,0.000023755762,0.000022138862,9.832311e-8,0.000013635848,0.0006350546,0.9934323,0.00007643436,0.000096991374,0.001566869],"study_design_scores_gemma":[0.0001826881,0.0005372892,0.0036213684,0.000037181013,0.000008710499,0.000012799334,0.00010064007,0.102932714,0.8899033,0.00007074348,0.0024519225,0.00014060845],"about_ca_topic_score_codex":0.00008319144,"about_ca_topic_score_gemma":0.0000026287787,"teacher_disagreement_score":0.103528954,"about_ca_system_score_codex":0.000010657661,"about_ca_system_score_gemma":0.000017949316,"threshold_uncertainty_score":0.3114148},"labels":[],"label_agreement":null},{"id":"W1988280752","doi":"10.1109/bibmw.2012.6470326","title":"Protein secondary structure prediction using support vector machines and a codon encoding scheme","year":2012,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Encoding (memory); Computer science; Artificial intelligence; Curse of dimensionality; Sequence (biology); Synonymous substitution; Support vector machine; Binary number; Codon usage bias; Computation; Algorithm; Pattern recognition (psychology); Computational biology; Gene; Mathematics; Genetics; Biology; Genome; Arithmetic","score_opus":0.008860714384948417,"score_gpt":0.24981423128727026,"score_spread":0.24095351690232183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988280752","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99399817,0.00014950914,0.0021517833,0.000035013734,0.00013592244,0.00019759603,0.000039820094,0.000028925162,0.0032632889],"genre_scores_gemma":[0.97404355,0.0000062336003,0.024779536,0.00013752472,0.0003431006,0.000004140791,0.00015959694,0.00001721657,0.0005091119],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99933434,0.00002906273,0.00018989522,0.00013115046,0.00009446995,0.00022106225],"domain_scores_gemma":[0.99963075,0.000003898296,0.00008564608,0.00016125057,0.00002931257,0.00008915634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016551935,0.00013370253,0.00009524674,0.000034565877,0.000095660056,0.000028507407,0.000065027816,0.00014139162,0.00023596182],"category_scores_gemma":[0.000074951764,0.000113258306,0.000027914346,0.000041821095,0.000040812654,0.000016667378,0.000108186636,0.00014911128,0.0000027685267],"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":[0.000019484069,0.000011206426,0.06842547,0.000081460516,0.000025195572,2.5667399e-7,0.00013013081,0.0000131261095,0.92959696,0.00017612525,0.00031642578,0.0012041581],"study_design_scores_gemma":[0.0018138983,0.0007101588,0.074381955,0.000074677206,0.000076718185,0.0006337736,0.00029354784,0.05021795,0.7957668,0.00008288639,0.07496364,0.0009840133],"about_ca_topic_score_codex":0.000016561899,"about_ca_topic_score_gemma":0.0000068038767,"teacher_disagreement_score":0.13383017,"about_ca_system_score_codex":0.000011380659,"about_ca_system_score_gemma":0.000036473673,"threshold_uncertainty_score":0.46185398},"labels":[],"label_agreement":null},{"id":"W1988978678","doi":"10.1109/tcbb.2014.2315668","title":"Guest Editorial: Pattern Recognition in Bioinformatics","year":2014,"lang":"en","type":"editorial","venue":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Windsor","funders":"","keywords":"Field (mathematics); Computer science; Section (typography); Nice; Data science; Pattern recognition (psychology); Bioinformatics; Artificial intelligence; Biology; Mathematics","score_opus":0.00884936687967608,"score_gpt":0.27438640752971105,"score_spread":0.265537040650035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988978678","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006565998,0.00005488049,0.24067526,0.0001370574,0.7559135,0.0005134783,0.0014775816,0.0000777636,0.0004939145],"genre_scores_gemma":[0.003284013,0.0010312514,0.059805036,0.00081020535,0.91388214,0.00012961123,0.020765746,0.00011084846,0.00018116584],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969528,0.00017690033,0.0014017455,0.00041429393,0.00053779397,0.0005165211],"domain_scores_gemma":[0.99730873,0.0008195842,0.0006773085,0.0005939097,0.0004329799,0.00016748735],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0008383201,0.00065465627,0.00061716797,0.0005141157,0.0002736903,0.000120081226,0.00054212054,0.002235525,0.000020724136],"category_scores_gemma":[0.0006107535,0.0006244297,0.00018936265,0.00023150371,0.00029916668,0.00004051921,0.000048186976,0.0014770132,0.0001828414],"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":[0.00021035667,0.0001902796,0.000098081415,0.00078186457,0.00022579887,0.0000013906629,0.00038730926,0.00894611,0.000024437604,0.0000054493566,0.9157454,0.07338353],"study_design_scores_gemma":[0.0029100636,0.0018074049,0.000053461386,0.00041227837,0.00013480602,0.000034348992,0.00014259764,0.06278172,0.00022233922,0.0011891822,0.92889607,0.00141571],"about_ca_topic_score_codex":0.000038736976,"about_ca_topic_score_gemma":0.000098037846,"teacher_disagreement_score":0.18087022,"about_ca_system_score_codex":0.00007784354,"about_ca_system_score_gemma":0.00031619426,"threshold_uncertainty_score":0.9996207},"labels":[],"label_agreement":null},{"id":"W1989100130","doi":"10.1371/journal.pone.0062204","title":"Bioinformatics Analysis Identify Novel OB Fold Protein Coding Genes in C. elegans","year":2013,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Caenorhabditis elegans; Biology; In silico; Gene; Genetics; Computational biology; Gene prediction; Genome project; Genome; Protein sequencing; Annotation; Genomics; Sequence analysis; Peptide sequence","score_opus":0.02263115134143695,"score_gpt":0.24334325189839853,"score_spread":0.22071210055696158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989100130","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9855225,0.000036235273,0.008861812,0.00015999458,0.000015416637,0.0024475593,0.000014377326,0.000032570995,0.002909538],"genre_scores_gemma":[0.9251768,0.000024261208,0.071696855,0.00018726934,0.00009426457,0.0011440124,0.00021154997,0.000027119944,0.0014378654],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987045,0.000027370997,0.0004969339,0.0001792817,0.00027830477,0.00031362424],"domain_scores_gemma":[0.99914414,0.000012819974,0.00020016798,0.0004444473,0.00011701595,0.00008140367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021860389,0.00017920732,0.00026820617,0.00022162357,0.00006022804,0.00009814695,0.0002843043,0.00016357066,0.00012282982],"category_scores_gemma":[0.00020008157,0.00017184904,0.00010340445,0.000429936,0.000043146643,0.000022788241,0.00016349442,0.00017239204,0.00011828395],"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":[0.000014362545,0.00063704373,0.034380563,0.00034697913,0.0008941813,7.7358476e-7,0.0002417936,0.00046791445,0.9618455,0.00011604819,0.00021449543,0.0008403094],"study_design_scores_gemma":[0.0018135902,0.00037989428,0.02825057,0.0002138105,0.00059504004,0.0000044710996,0.0004333842,0.26294124,0.70249015,0.00007155265,0.0018468079,0.00095950434],"about_ca_topic_score_codex":0.00012119041,"about_ca_topic_score_gemma":0.0000992044,"teacher_disagreement_score":0.26247334,"about_ca_system_score_codex":0.000022932218,"about_ca_system_score_gemma":0.000033773435,"threshold_uncertainty_score":0.70078003},"labels":[],"label_agreement":null},{"id":"W1993795746","doi":"10.1109/coginf.2010.5599728","title":"Towards cognitive analysis of DNA","year":2010,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Human genome; Genome; Computational biology; Gene; DNA sequencing; Resource (disambiguation); Biology; Computer science; Data science; Genetics","score_opus":0.005082501929984134,"score_gpt":0.2714314046716093,"score_spread":0.2663489027416252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993795746","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92211026,0.0000068109766,0.0067524994,0.000036351834,0.000050252573,0.000038925147,0.00001628103,0.000006968554,0.070981674],"genre_scores_gemma":[0.9946809,0.000005019873,0.004155153,0.00016888614,0.0000325023,0.00000203425,0.00016359107,0.0000044930866,0.0007874572],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996085,0.000011062676,0.00013491233,0.0000867296,0.00007719592,0.000081606624],"domain_scores_gemma":[0.9996278,0.000009247888,0.00006450997,0.00017389173,0.00009126224,0.000033240045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011776911,0.000059527632,0.00010467404,0.000071785835,0.00001655683,0.0000058851538,0.00009556115,0.00008270274,0.00037727968],"category_scores_gemma":[0.00021333793,0.000049184284,0.000098168544,0.00017748731,0.00005633978,0.0000010247477,0.000060378923,0.00007757829,0.000008215057],"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":[0.00005022429,0.000083375526,0.07484505,0.000022788712,0.0016541318,5.825322e-7,0.00020987524,0.00009607899,0.9040991,0.0020618767,0.0009323532,0.01594454],"study_design_scores_gemma":[0.00045871784,0.0002317717,0.1599132,0.0000035775008,0.00074878323,0.0000043626083,0.0001943689,0.00855738,0.81509745,0.000042939875,0.014491588,0.0002558521],"about_ca_topic_score_codex":0.000027224994,"about_ca_topic_score_gemma":0.00012637167,"teacher_disagreement_score":0.08900166,"about_ca_system_score_codex":8.008083e-7,"about_ca_system_score_gemma":0.000024745776,"threshold_uncertainty_score":0.41309482},"labels":[],"label_agreement":null},{"id":"W1995283805","doi":"10.1093/nar/gkr1025","title":"TopFIND 2.0--linking protein termini with proteolytic processing and modifications altering protein function","year":2011,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":62,"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":"Michael Smith Health Research BC; Bundesministerium für Bildung und Forschung; Deutscher Akademischer Austauschdienst; Canadian Institutes of Health Research; Cancer Research Society; Alexander von Humboldt-Stiftung","keywords":"Biology; Proteome; Computational biology; Proteomics; Proteases; Protease; Cleavage (geology); Protein domain; UniProt; Biochemistry; Genetics; Gene; Enzyme","score_opus":0.047990521225867395,"score_gpt":0.310058947810122,"score_spread":0.2620684265842546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995283805","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.977584,0.00007500428,0.012853935,0.00009424504,0.00001045188,0.001321433,0.0000021057706,0.000039253773,0.008019566],"genre_scores_gemma":[0.97465557,0.0000039797274,0.023468934,0.000022253294,0.0000952531,0.0003827483,0.000017729233,0.000039457835,0.0013140885],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985208,0.00011596439,0.00022723323,0.0003573823,0.00036375175,0.00041485677],"domain_scores_gemma":[0.99915123,0.000006230745,0.000092386996,0.0004103433,0.00022961521,0.000110180365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075160735,0.00015569013,0.00011621434,0.00013457853,0.00040067983,0.000112369125,0.0002467573,0.00014731684,0.000030101892],"category_scores_gemma":[0.00014801108,0.00012993488,0.000022204016,0.0002219725,0.00026558747,0.000026350031,0.00022688945,0.0004333074,0.00001892553],"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":[0.00042319862,0.00010828703,0.0043005343,0.0005773161,0.0000387424,0.0000059541267,0.0015261929,0.000014373964,0.943268,0.0007892437,0.000036498182,0.048911627],"study_design_scores_gemma":[0.0036422857,0.008649576,0.05051841,0.0019517868,0.00006583167,0.00025427272,0.002719232,0.033457287,0.8726188,0.003819372,0.020498402,0.0018047655],"about_ca_topic_score_codex":0.000028456026,"about_ca_topic_score_gemma":0.0000094061415,"teacher_disagreement_score":0.07064925,"about_ca_system_score_codex":0.00002559905,"about_ca_system_score_gemma":0.00014804526,"threshold_uncertainty_score":0.52985907},"labels":[],"label_agreement":null},{"id":"W1996768014","doi":"10.1186/1472-6807-7-25","title":"Prediction of flexible/rigid regions from protein sequences using k-spaced amino acid pairs","year":2007,"lang":"en","type":"article","venue":"BMC Structural Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":145,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; National Natural Science Foundation of China","keywords":"Curse of dimensionality; Pattern recognition (psychology); Feature (linguistics); Protein methods; Computer science; Representation (politics); Threading (protein sequence); Feature selection; Protein structure prediction; Artificial intelligence; Support vector machine; Protein structure; Pseudo amino acid composition; Sequence (biology); Protein tertiary structure; Algorithm; Peptide sequence; Amino acid; Biology; Biochemistry","score_opus":0.03267685854606961,"score_gpt":0.29330253755001834,"score_spread":0.26062567900394873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996768014","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9714014,0.00025358214,0.02712071,0.000026435044,0.00033417833,0.00026161308,0.00015043745,0.000036809914,0.000414816],"genre_scores_gemma":[0.9603918,0.000006668544,0.038523242,0.000044523666,0.00027412025,0.0000054116094,0.0006162848,0.00001303794,0.00012488142],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988201,0.00009590764,0.00040599453,0.0002785082,0.00009217415,0.00030729017],"domain_scores_gemma":[0.99916416,0.000029195311,0.00030401972,0.0003442493,0.00008742892,0.00007093045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020298017,0.00018705796,0.00020453935,0.000075164746,0.00009486558,0.000009622811,0.00022544512,0.00032312714,0.000055404184],"category_scores_gemma":[0.00018926822,0.0001532798,0.00009399407,0.000117581,0.00027625615,0.00000775661,0.000109536595,0.00014480125,0.0000031933562],"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":[0.00011581703,0.000004526274,0.094198726,0.000021171536,0.000046025438,6.1844463e-7,0.00011460074,0.000100285244,0.90358996,0.00083276833,0.000042856325,0.00093266775],"study_design_scores_gemma":[0.000730915,0.0006704578,0.13403225,0.000039468778,0.000042274954,0.000058508453,0.00037197617,0.0019641048,0.8579974,0.001424826,0.0023373857,0.00033044186],"about_ca_topic_score_codex":0.00035196167,"about_ca_topic_score_gemma":0.00011226473,"teacher_disagreement_score":0.045592546,"about_ca_system_score_codex":0.000025179246,"about_ca_system_score_gemma":0.00007442412,"threshold_uncertainty_score":0.6250569},"labels":[],"label_agreement":null},{"id":"W1997967533","doi":"10.1021/pr900665y","title":"SherLoc2: A High-Accuracy Hybrid Method for Predicting Subcellular Localization of Proteins","year":2009,"lang":"en","type":"article","venue":"Journal of Proteome Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":143,"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":"Computer science; Gene ontology; Subcellular localization; Data mining; Protein sequencing; Sequence (biology); Protein subcellular localization prediction; Feature (linguistics); Computational biology; Artificial intelligence; Gene; Biology; Peptide sequence; Genetics; Gene expression","score_opus":0.028056230538562456,"score_gpt":0.3845717248430646,"score_spread":0.3565154943045022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997967533","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":[0.21493101,0.00029015957,0.78294533,0.0005553341,0.000050174833,0.0010434191,0.000009418767,0.000004751059,0.00017039775],"genre_scores_gemma":[0.77345765,0.00007183758,0.22573526,0.00003764495,0.00043061178,0.000025129813,0.000023475606,0.000019886693,0.00019852676],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979449,0.000320607,0.0006634813,0.00013707024,0.00062038086,0.00031358213],"domain_scores_gemma":[0.99777293,0.00010334412,0.00052652357,0.0002590124,0.0012320403,0.00010612426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004703764,0.00011082587,0.00024051647,0.00022537858,0.000120538054,0.00004095391,0.00036778432,0.00011334202,0.0000151309305],"category_scores_gemma":[0.0040798704,0.000091929156,0.00013012336,0.00022157619,0.00006198382,0.000018780383,0.00007217599,0.00040676235,0.000001221283],"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":[0.00064309145,0.00015566919,0.00071606674,0.0003826229,0.000077524,0.0000068249724,0.00018537744,0.0040009874,0.9743302,0.00020064152,0.0011505969,0.018150406],"study_design_scores_gemma":[0.0013092796,0.0053167176,0.0003854337,0.00019165811,0.00002056098,0.00011486658,0.00009668053,0.043957535,0.9347381,0.0017142614,0.012015542,0.00013934869],"about_ca_topic_score_codex":0.00001629571,"about_ca_topic_score_gemma":0.0000011303541,"teacher_disagreement_score":0.5585266,"about_ca_system_score_codex":0.00004043064,"about_ca_system_score_gemma":0.00027624975,"threshold_uncertainty_score":0.48842806},"labels":[],"label_agreement":null},{"id":"W1999957644","doi":"10.1515/hsz-2012-0269","title":"CLIPPER: an add-on to the Trans-Proteomic Pipeline for the automated analysis of TAILS N-terminomics data","year":2012,"lang":"en","type":"article","venue":"Biological Chemistry","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"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":"European Commission; Canadian Breast Cancer Research Alliance; Canadian Institutes of Health Research; Cancer Research Society; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; FP7 People: Marie-Curie Actions; National Science Foundation","keywords":"Clipper (electronics); Pipeline (software); Computer science; Proteomics; Protease; Computational biology; Annotation; Chemistry; Biology; Biochemistry; Artificial intelligence; Operating system; Engineering","score_opus":0.0536990715586675,"score_gpt":0.3395566865141707,"score_spread":0.2858576149555032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999957644","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99131,0.00015342151,0.006541466,0.00041198687,0.00006448553,0.0003760558,0.00080900395,0.000043821718,0.00028974607],"genre_scores_gemma":[0.99417657,0.000045834386,0.0018767121,0.00061379874,0.00038626176,0.000046093428,0.0027223027,0.000011651917,0.000120795485],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99891865,0.000054939934,0.00034489387,0.00027835747,0.000099605946,0.00030353037],"domain_scores_gemma":[0.99829835,0.00011137189,0.00015098945,0.0012802049,0.00005380611,0.00010529798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076988747,0.00017874343,0.00022924556,0.000016814785,0.00011176491,0.000019853755,0.0011339445,0.00023636805,0.00006882418],"category_scores_gemma":[0.0005603199,0.00009162007,0.00014798567,0.00017025102,0.00011842818,0.0000051599227,0.00023622438,0.00013735874,0.0000045067763],"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":[0.0005050428,0.00027278138,0.011136845,0.000063087915,0.0006517111,2.1441846e-7,0.00019064303,0.0034634508,0.9665384,0.000029220759,0.010132708,0.007015883],"study_design_scores_gemma":[0.0008909591,0.0005284524,0.025763078,0.000016299837,0.00088292285,0.000015064821,0.00038152174,0.2816742,0.53302306,0.000005666758,0.15617698,0.000641811],"about_ca_topic_score_codex":0.0000063034327,"about_ca_topic_score_gemma":0.0000043574314,"teacher_disagreement_score":0.43351537,"about_ca_system_score_codex":0.00001007014,"about_ca_system_score_gemma":0.00002428894,"threshold_uncertainty_score":0.37361583},"labels":[],"label_agreement":null},{"id":"W2002030144","doi":"10.1016/j.physa.2006.03.004","title":"Probabilistic analysis of the frequencies of amino acid pairs within characterized protein sequences","year":2006,"lang":"en","type":"article","venue":"Physica A Statistical Mechanics and its Applications","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"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":"Mitacs","keywords":"Probabilistic logic; Amino acid residue; Amino acid; Proteome; Computational biology; Human proteome project; Statistical model; Computer science; Peptide sequence; Biology; Bioinformatics; Proteomics; Artificial intelligence; Genetics; Gene","score_opus":0.008029741016630742,"score_gpt":0.24030785938684412,"score_spread":0.2322781183702134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002030144","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7065716,0.00009408753,0.29010618,0.00025144295,0.000020804877,0.0011942004,0.0012741896,0.000016046453,0.00047148654],"genre_scores_gemma":[0.9924554,0.000008373833,0.007055382,0.000022731796,0.000022974378,0.00018027613,0.00020365804,0.0000077895675,0.00004340447],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991508,0.00004746752,0.00035589986,0.0001790603,0.00015449751,0.00011225792],"domain_scores_gemma":[0.9991973,0.00004322249,0.00030475456,0.00028705577,0.00013534582,0.000032326512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012822053,0.00010906118,0.00021453711,0.000035108715,0.00007734735,0.000012276878,0.00018194075,0.000051443665,0.000009355213],"category_scores_gemma":[0.00015187607,0.000078528385,0.000067031906,0.00032601156,0.000091012385,0.00000432242,0.000081911014,0.00007406648,7.5309197e-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":[0.000006229224,0.000057828078,0.00003879927,0.00006479874,0.00007310695,2.4487704e-8,0.00003014501,0.00012488257,0.5377456,0.4616247,0.000009457433,0.00022442096],"study_design_scores_gemma":[0.00044438732,0.00039615788,0.008859697,0.000051032963,0.0011318118,0.000002733208,0.00013241998,0.20181131,0.70009536,0.08531708,0.0013151858,0.00044282366],"about_ca_topic_score_codex":0.000034743367,"about_ca_topic_score_gemma":0.000028669883,"teacher_disagreement_score":0.3763076,"about_ca_system_score_codex":0.000006360924,"about_ca_system_score_gemma":0.000047382604,"threshold_uncertainty_score":0.32022944},"labels":[],"label_agreement":null},{"id":"W2003464575","doi":"10.1007/s00726-010-0721-1","title":"iFC2: an integrated web-server for improved prediction of protein structural class, fold type, and secondary structure content","year":2010,"lang":"en","type":"article","venue":"Amino Acids","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Web server; Computer science; In silico; Sequence (biology); Protein structure prediction; Similarity (geometry); Structural similarity; Class (philosophy); Data mining; Protein secondary structure; Artificial intelligence; Computational biology; Protein structure; Biology; The Internet; Image (mathematics); Genetics; Biochemistry; World Wide Web","score_opus":0.008275257855806557,"score_gpt":0.23246977089596216,"score_spread":0.2241945130401556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003464575","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9984162,0.000050241102,0.00022003306,0.000042668325,0.00027147433,0.00047386333,0.00040276023,0.000018817935,0.00010395916],"genre_scores_gemma":[0.9900547,0.000004296709,0.008160963,0.0000880029,0.00012547473,0.00001354841,0.0011958153,0.000019059751,0.0003381039],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993262,0.000023643412,0.00023745226,0.00019146127,0.00006514756,0.00015604151],"domain_scores_gemma":[0.999272,0.000006552601,0.00013837124,0.00029311006,0.00022412442,0.00006583006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010373743,0.00014931515,0.00014449404,0.000032525077,0.000054956676,0.000024166993,0.0001375228,0.0002608359,0.000040259496],"category_scores_gemma":[0.00017028493,0.00012077991,0.000036109308,0.00005484425,0.000101166566,0.000015661186,0.00006155614,0.00024660164,3.1154275e-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":[0.00014216398,0.000008553755,0.0066292584,0.00006667705,0.000039249986,9.290403e-8,0.000052231193,0.0000022021948,0.98465776,0.00024317505,0.00016021075,0.007998421],"study_design_scores_gemma":[0.0026159482,0.0025549773,0.08615383,0.00002304353,0.000057621713,0.0000419957,0.0001855798,0.023604551,0.8424288,0.00022558653,0.041761637,0.0003464387],"about_ca_topic_score_codex":0.000028976305,"about_ca_topic_score_gemma":0.00021448823,"teacher_disagreement_score":0.14222898,"about_ca_system_score_codex":0.000005876927,"about_ca_system_score_gemma":0.00009029973,"threshold_uncertainty_score":0.49252617},"labels":[],"label_agreement":null},{"id":"W2006737877","doi":"10.1109/bibmw.2011.6112350","title":"Regularization of sequence data for machine learning","year":2011,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regularization (linguistics); Computer science; Curse of dimensionality; Artificial intelligence; Machine learning; Artificial neural network; Regularization perspectives on support vector machines; Sequence (biology); Deep neural networks; Inductive bias; Generalization; Mathematics; Multi-task learning; Inverse problem; Tikhonov regularization","score_opus":0.0644424757010098,"score_gpt":0.29631745997733966,"score_spread":0.23187498427632985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006737877","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":[0.045436498,0.00014728893,0.92860126,0.000057410987,0.0000960861,0.00032143324,0.00011163404,0.000037221966,0.025191162],"genre_scores_gemma":[0.7555258,0.000049900755,0.23724608,0.00010614905,0.000049236227,0.000005874843,0.0029991467,0.00001776815,0.0040000197],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995427,0.00001999228,0.00016069347,0.00013283166,0.000054771284,0.00008902592],"domain_scores_gemma":[0.9993465,0.000007959931,0.00010452221,0.00045682612,0.00006243832,0.000021754484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023868133,0.000061468214,0.00006733713,0.000019281732,0.00003349515,0.0000041384337,0.00029243904,0.00006181803,0.00005064107],"category_scores_gemma":[0.00036970957,0.000054135853,0.000021076148,0.000037195176,0.000035320292,0.0000049100645,0.000180538,0.000044925957,0.0000017679413],"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":[0.00036343772,0.00016217848,0.08067634,0.0004639232,0.00020702805,7.515417e-7,0.0006541569,0.0009015005,0.87031746,0.017347503,0.0045733056,0.024332426],"study_design_scores_gemma":[0.0010869324,0.0010982151,0.002316431,0.000027470587,0.00006003091,0.000023150544,0.00011177084,0.36921564,0.47070658,0.00059381936,0.15432599,0.00043398375],"about_ca_topic_score_codex":0.000027982536,"about_ca_topic_score_gemma":0.000009986651,"teacher_disagreement_score":0.7100893,"about_ca_system_score_codex":0.0000018850269,"about_ca_system_score_gemma":0.000022921453,"threshold_uncertainty_score":0.2207596},"labels":[],"label_agreement":null},{"id":"W2009142598","doi":"10.1142/s0218127404009491","title":"COMPLEXITY OF EYE MOVEMENTS IN READING","year":2004,"lang":"en","type":"article","venue":"International Journal of Bifurcation and Chaos","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Deutsche Forschungsgemeinschaft","keywords":"Eye movement; Fixation (population genetics); Computer science; Reading (process); Coding (social sciences); Nonlinear system; Artificial intelligence; Dynamical systems theory; Algorithm; Speech recognition; Theoretical computer science; Mathematics; Statistics; Linguistics","score_opus":0.013459514378307436,"score_gpt":0.30453243031479593,"score_spread":0.2910729159364885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009142598","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9938029,0.000057505596,0.004390678,0.00068784604,0.0001437949,0.000029538314,0.0000036243284,9.2207773e-7,0.000883196],"genre_scores_gemma":[0.99731714,0.00011381718,0.0022295457,0.0001935311,0.00007818651,4.6404998e-7,0.000014382063,0.0000028696368,0.000050087056],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9994864,0.000011824381,0.0002731038,0.000039473874,0.00014791674,0.000041286105],"domain_scores_gemma":[0.99951804,0.0000035895555,0.00025152168,0.000044056724,0.00016077302,0.00002199465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016225388,0.000040168612,0.00006326286,0.00009101925,0.000008807087,0.000008822053,0.00011742498,0.00003078948,0.000009131737],"category_scores_gemma":[0.00007528208,0.000036974903,0.000026612186,0.000028842858,0.000041179705,0.000008042498,0.000032535907,0.00005868942,7.756517e-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":[0.0006087731,0.0006313286,0.37888294,0.00009595104,0.00038287835,0.000015183395,0.0042976732,0.008747876,0.55998105,0.019319823,0.00030637046,0.026730146],"study_design_scores_gemma":[0.008105464,0.0009109673,0.6539263,0.00046311834,0.000016781802,0.000215427,0.0014561695,0.0022352634,0.30713657,0.010859695,0.014313174,0.0003610328],"about_ca_topic_score_codex":0.00001830756,"about_ca_topic_score_gemma":0.00001054823,"teacher_disagreement_score":0.2750434,"about_ca_system_score_codex":0.000019826244,"about_ca_system_score_gemma":0.00003256595,"threshold_uncertainty_score":0.15077928},"labels":[],"label_agreement":null},{"id":"W2011692099","doi":"10.1371/journal.pone.0094507","title":"Prediction and Experimental Characterization of nsSNPs Altering Human PDZ-Binding Motifs","year":2014,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"PDZ domain; Computational biology; Genetics; Biology; Single-nucleotide polymorphism; Phenotype; In silico; Binding site; Plasma protein binding; Protein domain; Gene; Bioinformatics; Genotype; Cell biology","score_opus":0.01885792679175896,"score_gpt":0.22789731813979183,"score_spread":0.20903939134803287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011692099","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9982363,0.000010457389,0.00094943814,0.000012645165,0.000021185848,0.000085459294,0.00000826574,0.000013241381,0.0006630238],"genre_scores_gemma":[0.9981808,0.000010022963,0.0012414979,0.000021407528,0.000110954345,0.000006407253,0.0002778431,0.000010622921,0.00014042213],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99956834,0.00002140683,0.00014706358,0.00009650053,0.00008959429,0.00007711204],"domain_scores_gemma":[0.9997369,0.0000027115009,0.00009175318,0.00011938078,0.000021823196,0.00002740305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009117278,0.000063628904,0.00008393403,0.00002826025,0.000053001473,0.000012212886,0.000047672343,0.000053775104,0.0000121511775],"category_scores_gemma":[0.000031404677,0.00006784254,0.00001373779,0.000021023323,0.000027215265,0.000005891537,0.000062590676,0.000042967793,0.000002028308],"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":[0.000007874978,0.00008922044,0.016545378,0.00006990495,0.000027734357,3.086623e-8,0.00012011143,0.0000065339727,0.98297787,0.000037616563,0.0000026054886,0.0001151365],"study_design_scores_gemma":[0.00023027587,0.00026490158,0.012184965,0.000048138412,0.000013891711,0.000001241605,0.000018710258,0.004944548,0.98213714,0.0000028203883,0.00009146958,0.000061884486],"about_ca_topic_score_codex":0.0000025009736,"about_ca_topic_score_gemma":4.415042e-7,"teacher_disagreement_score":0.004938014,"about_ca_system_score_codex":0.0000056126974,"about_ca_system_score_gemma":0.000002718927,"threshold_uncertainty_score":0.27665386},"labels":[],"label_agreement":null},{"id":"W2012019831","doi":"10.1145/2506583.2506630","title":"Classifying Proteins by Amino Acid Variations of Sequential Patterns","year":2013,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Entropy (arrow of time); Pattern recognition (psychology); Cluster analysis; Artificial intelligence; Computer science; Mutual information; Redundancy (engineering); Mathematics; Biology","score_opus":0.008144220186879816,"score_gpt":0.24065662232941745,"score_spread":0.23251240214253763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012019831","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68413657,0.00003290188,0.30113313,0.00033220559,0.00008931399,0.0004063672,0.000039057108,0.000026731757,0.013803696],"genre_scores_gemma":[0.985443,0.000009418886,0.012128015,0.00019394125,0.00005701873,0.00003667086,0.0002203943,0.000011055723,0.0019005067],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99940264,0.0000289315,0.00021616172,0.00011095324,0.000100652855,0.00014067977],"domain_scores_gemma":[0.99953943,0.0000045244597,0.00010760239,0.0002340717,0.00007037238,0.000043965927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000068809524,0.000088197565,0.0000809329,0.000022650089,0.000041740233,0.000023627083,0.00013990511,0.000099438,0.00051499973],"category_scores_gemma":[0.000057593956,0.000076649005,0.000046418856,0.000037274807,0.00002928328,0.000005834568,0.00009191367,0.00007368995,0.000042501968],"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":[0.0000027798517,0.000037002603,0.011504158,0.000039918254,0.000034465236,7.4961754e-8,0.00005860933,0.000021561802,0.97984016,0.00030562418,0.006315625,0.0018400002],"study_design_scores_gemma":[0.0004890714,0.00026411292,0.01077698,0.000015187729,0.000017601147,0.000007402697,0.00010242092,0.005938172,0.96748805,0.000069991635,0.014579415,0.0002515891],"about_ca_topic_score_codex":0.00017938876,"about_ca_topic_score_gemma":0.000015939437,"teacher_disagreement_score":0.3013064,"about_ca_system_score_codex":0.000006330017,"about_ca_system_score_gemma":0.000026148253,"threshold_uncertainty_score":0.56388855},"labels":[],"label_agreement":null},{"id":"W2012352014","doi":"10.1101/gr.2650004","title":"Predicting Subcellular Localization via Protein Motif Co-Occurrence","year":2004,"lang":"en","type":"article","venue":"Genome Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":114,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Subcellular localization; Biology; Protein subcellular localization prediction; Computational biology; Protein Sorting Signals; Membrane protein; Organelle; Green fluorescent protein; Bioinformatics; Cell biology; Cytoplasm; Biochemistry; Gene; Peptide sequence; Signal peptide; Membrane","score_opus":0.027057064866129427,"score_gpt":0.33707073941940097,"score_spread":0.31001367455327156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012352014","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8382422,0.00041884085,0.15673962,0.00018315624,0.00005143682,0.0007498476,0.000043916294,0.000043223656,0.003527777],"genre_scores_gemma":[0.99672854,0.00005114415,0.0017542461,0.000034262317,0.00018275729,0.000045362543,0.00079659343,0.000019403005,0.00038768008],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983727,0.00014066882,0.0002372032,0.00027936941,0.0004934769,0.0004765954],"domain_scores_gemma":[0.9991591,0.0000110805595,0.000059528385,0.0004250182,0.00022035927,0.00012489624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011682351,0.00011918184,0.000096205295,0.000113357055,0.000275747,0.000061288265,0.00034483115,0.00014869768,0.000048995025],"category_scores_gemma":[0.00036023263,0.00011805064,0.00004199158,0.00026643975,0.00015583668,0.000006755328,0.00020064668,0.00035627425,0.00017801399],"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":[0.00006943875,0.00012288889,0.0136459945,0.00032265304,0.00004303486,0.0000126998875,0.00060991646,0.023030767,0.95879817,0.00029309758,0.00025091384,0.0028004064],"study_design_scores_gemma":[0.0026612466,0.002391763,0.0051459577,0.00017594514,0.00001637067,0.00009947511,0.00048686352,0.028417435,0.7854591,0.0016017023,0.17253034,0.0010137848],"about_ca_topic_score_codex":0.000058198235,"about_ca_topic_score_gemma":0.0000107450805,"teacher_disagreement_score":0.17333907,"about_ca_system_score_codex":0.00006659705,"about_ca_system_score_gemma":0.00017531378,"threshold_uncertainty_score":0.48139653},"labels":[],"label_agreement":null},{"id":"W2017099130","doi":"10.4236/jbise.2014.711090","title":"Predicting Βeta-Turns and Βeta-Turn Types Using a Novel Over-Sampling Approach","year":2014,"lang":"en","type":"article","venue":"Journal of Biomedical Science and Engineering","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Institute of Genetics; University of Tokyo; Kanazawa University; Institute of Medical Science, University of Tokyo; Research Organization of Information and Systems","keywords":"Benchmark (surveying); Computer science; Sampling (signal processing); Turn (biochemistry); Folding (DSP implementation); Sensitivity (control systems); Machine learning; Artificial intelligence; Class (philosophy); Algorithm; Pattern recognition (psychology); Data mining; Chemistry","score_opus":0.011402950282996292,"score_gpt":0.2529843262560686,"score_spread":0.2415813759730723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017099130","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.812206,0.00026293928,0.18719035,0.00005541635,0.00015897024,0.000026767797,0.0000010778014,0.0000051498973,0.00009334056],"genre_scores_gemma":[0.9385587,0.00004863331,0.060944065,0.00006838293,0.00036791447,2.9036642e-7,0.0000011249643,0.0000067982523,0.0000040868044],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990361,0.000007360849,0.00026268023,0.0001225953,0.000357051,0.00021422691],"domain_scores_gemma":[0.9994664,0.00002658171,0.00013797251,0.00008325804,0.00007881859,0.00020696346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013372229,0.0000963722,0.00014434723,0.00012413894,0.00008915576,0.00007606263,0.00016342927,0.00007797088,0.0000017048121],"category_scores_gemma":[0.0009546855,0.000072081486,0.000030078663,0.0001946637,0.00019387742,0.00002677193,0.00012862902,0.00019310026,1.04633294e-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":[0.000013308904,0.000034606743,0.0060303416,0.00016493395,0.00004090112,0.0000010679454,0.00034538357,0.0074139843,0.9782617,0.00015230945,0.000014944832,0.007526508],"study_design_scores_gemma":[0.0005469188,0.00031002832,0.012483237,0.000107572894,0.000038265407,0.000704371,0.00010653098,0.97003776,0.0019427637,0.000015497762,0.013511086,0.00019595212],"about_ca_topic_score_codex":0.0000043559185,"about_ca_topic_score_gemma":2.432314e-7,"teacher_disagreement_score":0.97631896,"about_ca_system_score_codex":0.000015692385,"about_ca_system_score_gemma":0.00006157701,"threshold_uncertainty_score":0.29393977},"labels":[],"label_agreement":null},{"id":"W2018157754","doi":"10.1016/j.bpj.2010.12.1945","title":"TMBB-DB: A Proteomic Database of Transmembrane β-Barrel Predictions","year":2011,"lang":"en","type":"article","venue":"Biophysical Journal","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Research Resources; Natural Sciences and Engineering Research Council of Canada","keywords":"Proteome; Transmembrane protein; Proteomics; Computational biology; Bacterial outer membrane; Signal peptide; Biology; Membrane protein; Bioinformatics; Computer science; Database; Peptide sequence; Membrane; Biochemistry; Escherichia coli","score_opus":0.013658877436985096,"score_gpt":0.24588525901535388,"score_spread":0.23222638157836878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018157754","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96736985,0.000028069688,0.02953988,0.00006941749,0.00018342468,0.00015879824,0.00005627639,0.000014125004,0.002580136],"genre_scores_gemma":[0.9895404,0.00006768325,0.009747458,0.00006250537,0.00037674923,0.0000069795997,0.00003946137,0.000016390257,0.00014240028],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99917984,0.00004934731,0.0003018411,0.00011931273,0.00016580668,0.0001838425],"domain_scores_gemma":[0.9993757,0.00000545208,0.00015941521,0.00024960554,0.00007933396,0.00013046812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014120678,0.00012049023,0.00013747174,0.000044863464,0.00008221264,0.000012002921,0.00024172619,0.00008495646,0.00008925895],"category_scores_gemma":[0.000057019144,0.00009885209,0.00014092585,0.00007690561,0.000118365126,0.000009618142,0.000051944302,0.0002663483,0.00001838624],"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":[0.00014779816,0.0001976259,0.0005474543,0.000044957716,0.0000650176,0.0000038706085,0.00018173283,0.000036150755,0.9973292,0.00019562036,0.0005853658,0.0006652263],"study_design_scores_gemma":[0.0013578732,0.0011330103,0.008649125,0.00007810478,0.000085007094,0.00031909553,0.000069761896,0.0031113466,0.9817369,0.000086748514,0.0030957744,0.00027724684],"about_ca_topic_score_codex":0.000010505437,"about_ca_topic_score_gemma":0.0000011470024,"teacher_disagreement_score":0.022170499,"about_ca_system_score_codex":0.0000071227,"about_ca_system_score_gemma":0.00007273745,"threshold_uncertainty_score":0.40310714},"labels":[],"label_agreement":null},{"id":"W2018366325","doi":"10.1016/j.bpj.2008.12.2336","title":"Biophysical Studies Of The Membrane Interactions Of A Transthyretin Fragment TTR(10-20)","year":2009,"lang":"en","type":"article","venue":"Biophysical Journal","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Transthyretin; Fragment (logic); Chemistry; Biophysics; Computational biology; Biology; Computer science; Endocrinology; Algorithm","score_opus":0.013042559543116346,"score_gpt":0.296519581243503,"score_spread":0.2834770217003867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018366325","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9968753,0.00006517701,0.00051476207,0.0013128546,0.00019177892,0.00009356369,0.000013701108,0.000004933243,0.0009279463],"genre_scores_gemma":[0.99819356,0.00007431042,0.00087457965,0.00015689775,0.00034270773,0.0000015892551,0.000005587706,0.000007688662,0.00034306315],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99897134,0.00008679026,0.00041267826,0.00010981649,0.0002569471,0.00016242336],"domain_scores_gemma":[0.9991941,0.000029327315,0.00030046317,0.00024918703,0.0001653982,0.000061550185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012919621,0.00013941721,0.00024513874,0.000033423137,0.000094752875,0.000011789642,0.00029136668,0.00005859029,0.00003226013],"category_scores_gemma":[0.00011697767,0.00008838098,0.00030631898,0.0001294489,0.00020623078,0.000006960848,0.000059237605,0.0002639642,0.00000527877],"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":[0.000100149984,0.00024133714,0.000058338086,0.000027271768,0.00011339385,8.382663e-7,0.0001997368,0.00024535594,0.99583584,0.000268509,0.0012111436,0.0016981025],"study_design_scores_gemma":[0.0005434544,0.0008409927,0.002578034,0.00009156871,0.00007057239,0.000052074738,0.00017111443,0.0007098275,0.98874223,0.00011982414,0.005944206,0.00013607429],"about_ca_topic_score_codex":0.000001491511,"about_ca_topic_score_gemma":9.677066e-7,"teacher_disagreement_score":0.0070935665,"about_ca_system_score_codex":0.000014399348,"about_ca_system_score_gemma":0.000046203942,"threshold_uncertainty_score":0.36040717},"labels":[],"label_agreement":null},{"id":"W2020070775","doi":"10.1016/j.peptides.2003.10.012","title":"Correlations of amino acids in proteins","year":2003,"lang":"en","type":"article","venue":"Peptides","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Correlation; Amino acid; Linear correlation; Positive correlation; Alpha (finance); Mathematics; Chemistry; Biochemistry; Statistics; Geometry; Medicine; Internal medicine","score_opus":0.00782281322024978,"score_gpt":0.2466638799335145,"score_spread":0.23884106671326472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020070775","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96052045,0.00008107832,0.0029427863,0.000025542378,0.00004463823,0.00012729675,0.0000037712587,0.000005738498,0.03624869],"genre_scores_gemma":[0.9874534,0.000012984826,0.011397797,0.00003396084,0.000015730326,0.000010635832,0.00002155799,0.0000061666233,0.0010477799],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995923,0.000031307885,0.00015683372,0.00007152826,0.000055668374,0.000092386486],"domain_scores_gemma":[0.9997281,0.000008692213,0.00005838164,0.00015876107,0.000026853937,0.000019233743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001257393,0.000055741864,0.00006520262,0.00003383756,0.000018186574,0.000004366589,0.00006466058,0.00005778963,0.000028829238],"category_scores_gemma":[0.00033297835,0.000053366723,0.000027804515,0.000068985784,0.000039708175,0.0000021262854,0.000020657475,0.000062459214,0.000011435761],"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":[0.000020493726,0.0001192613,0.792975,0.00008182468,0.00002413688,0.0000010697113,0.0005064538,0.0026437133,0.19441935,0.0068745515,0.0009768076,0.0013573305],"study_design_scores_gemma":[0.0017535927,0.0007531406,0.35289967,0.00011174078,0.00002393625,0.000031709234,0.00062622357,0.0028744054,0.4938588,0.0012552569,0.14519756,0.00061395555],"about_ca_topic_score_codex":0.000012532961,"about_ca_topic_score_gemma":0.000035943576,"teacher_disagreement_score":0.44007534,"about_ca_system_score_codex":0.0000048007437,"about_ca_system_score_gemma":0.000030196496,"threshold_uncertainty_score":0.21762317},"labels":[],"label_agreement":null},{"id":"W2020302515","doi":"10.1371/journal.pcbi.0030106","title":"A Survey of Genomic Properties for the Detection of Regulatory Polymorphisms","year":2007,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Canada's Michael Smith Genome Sciences Centre","funders":"Natural Sciences and Engineering Research Council of Canada; BC Cancer Foundation; Genome British Columbia; Wellcome Trust; Canadian Institutes of Health Research; Genome Canada; Michael Smith Health Research BC; European Molecular Biology Organization","keywords":"Genetics; Biology; Computational biology; Gene; Regulatory sequence; Single-nucleotide polymorphism; Allele; CpG site; DNA binding site; Locus (genetics); Genomics; Genome; Transcription factor; Promoter; Genotype; Gene expression; DNA methylation","score_opus":0.024337331328526966,"score_gpt":0.25718791611485664,"score_spread":0.23285058478632967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020302515","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86413926,0.00060272234,0.13486075,0.00003236108,0.00007464818,0.00019505469,0.000045881603,0.000004574439,0.000044771332],"genre_scores_gemma":[0.99709,0.000006690364,0.0025752871,0.00006597191,0.000049756076,0.000007589081,0.0001714441,0.000007681203,0.000025620242],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99941474,0.00005368784,0.00028089902,0.00009356629,0.000056426714,0.00010065343],"domain_scores_gemma":[0.999243,0.00019715914,0.00019798537,0.00012126188,0.00022560089,0.000014976736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052111445,0.00006645794,0.00010532605,0.000040460684,0.000046777535,0.000001946147,0.00012625684,0.000084494066,0.0000032667224],"category_scores_gemma":[0.00025686724,0.000047054167,0.000045256398,0.000045296376,0.00017010662,0.0000013761137,0.000047600388,0.000041898227,0.0000012209501],"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":[0.0002598735,0.000035364967,0.014444751,0.000035218207,0.000109932305,2.0465958e-8,0.00006204768,0.0051755686,0.97478163,0.00032051123,0.000021880922,0.0047531775],"study_design_scores_gemma":[0.0005030874,0.0006419703,0.62620884,0.000008361367,0.000024010411,0.0000067310325,0.000029684317,0.03781413,0.33360553,0.00029365503,0.000742324,0.000121658275],"about_ca_topic_score_codex":0.000050525116,"about_ca_topic_score_gemma":0.000042293974,"teacher_disagreement_score":0.6411761,"about_ca_system_score_codex":0.0000072369553,"about_ca_system_score_gemma":0.000054189364,"threshold_uncertainty_score":0.19188133},"labels":[],"label_agreement":null},{"id":"W2020879581","doi":"10.1109/cibcb.2010.5510703","title":"Classifying Cytochrome c Oxidase subunit 1 by translation initiation mechanism using side effect machines","year":2010,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Genomics Institute; Genome Canada","keywords":"Mechanism (biology); Cytochrome c oxidase; Translation (biology); Side effect (computer science); Protein subunit; Computer science; Machine translation; SIGNAL (programming language); Computational biology; Gene; Artificial intelligence; Oxidase test; Biology; Enzyme; Genetics; Mitochondrion; Biochemistry; Messenger RNA; Physics","score_opus":0.01104965006066701,"score_gpt":0.27504412710577136,"score_spread":0.26399447704510437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020879581","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92585456,0.000031594198,0.07042185,0.00007231439,0.00015417667,0.00022759454,0.00001410839,0.000050605773,0.0031731676],"genre_scores_gemma":[0.9811229,0.000007226022,0.01784145,0.00023306946,0.00014567652,0.000009806786,0.00045911435,0.000029415733,0.0001513175],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99911463,0.00008038593,0.00024845093,0.00019637356,0.00015235305,0.0002077846],"domain_scores_gemma":[0.99946475,0.00003868239,0.00011823235,0.0002568369,0.00004889343,0.000072583265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000343919,0.00018485308,0.00013069613,0.00006133036,0.00014285247,0.000057105764,0.0001339424,0.00023885474,0.00010188312],"category_scores_gemma":[0.00014102104,0.00016448327,0.00007172672,0.00008506191,0.00003452987,0.000015818634,0.000042015727,0.0002598066,0.000016905859],"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":[0.000024373925,0.0000146418515,0.0010317826,0.000037284524,0.000016916265,6.5079627e-7,0.000039397066,0.0000884208,0.99486077,0.00015711288,0.000109985085,0.003618693],"study_design_scores_gemma":[0.00092132133,0.0002794735,0.0007835359,0.00001346189,0.00004287562,0.000057924666,0.000018481509,0.1151403,0.87882686,0.00017488108,0.003372912,0.00036797446],"about_ca_topic_score_codex":0.000051086536,"about_ca_topic_score_gemma":0.00006390837,"teacher_disagreement_score":0.11603388,"about_ca_system_score_codex":0.000009207075,"about_ca_system_score_gemma":0.000029348159,"threshold_uncertainty_score":0.6707433},"labels":[],"label_agreement":null},{"id":"W2021901733","doi":"10.1016/s1672-0229(07)60022-9","title":"FragAnchor: A Large-Scale Predictor of Glycosylphosphatidylinositol Anchors in Eukaryote Protein Sequences by Qualitative Scoring","year":2007,"lang":"en","type":"article","venue":"Genomics Proteomics & Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":125,"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; Université du Québec à Montréal","funders":"National Center for Research Resources; National Institutes of Health","keywords":"Eukaryote; UniProt; Proteome; Computational biology; Hidden Markov model; Protein sequencing; Human proteome project; Computer science; Noise (video); Scale (ratio); Biology; Artificial intelligence; Proteomics; Bioinformatics; Machine learning; Pattern recognition (psychology); Genetics; Peptide sequence; Gene; Genome","score_opus":0.00645521733399634,"score_gpt":0.26993909283185125,"score_spread":0.2634838754978549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021901733","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8401929,0.00034596922,0.155951,0.00004884595,0.00015526332,0.0016440899,0.0003497473,0.000035021912,0.0012771504],"genre_scores_gemma":[0.70043653,0.00016150404,0.29818827,0.0002191739,0.00014070919,0.00007888321,0.0004610317,0.000065348264,0.00024855373],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99644005,0.00009051995,0.0018071249,0.00035213996,0.00043768756,0.0008724454],"domain_scores_gemma":[0.9978416,0.000056530724,0.0010266358,0.00065378414,0.00020710984,0.00021435255],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002643641,0.0004554936,0.00052098697,0.00030938204,0.0001431494,0.000065018234,0.0006951342,0.00046353834,0.00001342864],"category_scores_gemma":[0.00035229864,0.00046669392,0.00016174899,0.0004648083,0.00022911558,0.0000618427,0.0003528618,0.00052190304,0.000018151366],"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":[0.0013018947,0.00055638165,0.020004628,0.001864291,0.00028744436,0.000008683857,0.064298846,0.0023996634,0.90056753,0.0018957119,0.0014026924,0.0054122526],"study_design_scores_gemma":[0.0029013108,0.0010023252,0.00084233197,0.00030241697,0.000036762827,0.000025655494,0.012051713,0.03370461,0.9393394,0.00063869485,0.008085943,0.0010688097],"about_ca_topic_score_codex":0.000054184005,"about_ca_topic_score_gemma":0.00015383608,"teacher_disagreement_score":0.14223728,"about_ca_system_score_codex":0.0001713998,"about_ca_system_score_gemma":0.00030102316,"threshold_uncertainty_score":0.99977845},"labels":[],"label_agreement":null},{"id":"W2022134844","doi":"10.2174/092986611796378729","title":"3dswap-pred: Prediction of 3D Domain Swapping from Protein Sequence Using Random Forest Approach","year":2011,"lang":"en","type":"article","venue":"Protein and Peptide Letters","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"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":"Centre Hospitalier Universitaire de Québec; Wellcome Trust","keywords":"Sequence (biology); Random forest; Domain (mathematical analysis); Computer science; Limiting; Protein structure; Computational biology; Protein sequencing; Protein domain; Data mining; Web server; Algorithm; Artificial intelligence; Biology; Peptide sequence; Mathematics; Genetics; Biochemistry","score_opus":0.026269553499686762,"score_gpt":0.22429322713328786,"score_spread":0.1980236736336011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022134844","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88505733,0.00009679754,0.112657875,0.00005658738,0.000030487474,0.0007688282,0.000040246683,0.00002194104,0.0012698867],"genre_scores_gemma":[0.81027037,0.000006297309,0.18911257,0.00021143685,0.00012618133,0.00007175206,0.0001292047,0.00002152207,0.000050673414],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988732,0.00010898889,0.00034586416,0.00028253172,0.00015874392,0.0002307196],"domain_scores_gemma":[0.9993453,0.000008482399,0.000233266,0.0003124813,0.000034815464,0.00006566719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030667082,0.00019013855,0.00019692909,0.00005521908,0.000093791976,0.000023571154,0.00017228577,0.00013791649,0.000019985264],"category_scores_gemma":[0.00007747334,0.00017721223,0.00006211304,0.00006855164,0.00017109164,0.00001716508,0.000113439746,0.000175778,0.0000021630774],"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":[0.00022864247,0.000026231408,0.009415309,0.00015036913,0.00006174282,0.000001774853,0.0006896918,0.00023601082,0.9886363,0.000040259387,0.00005843972,0.00045524046],"study_design_scores_gemma":[0.011010575,0.0010100146,0.021359267,0.001102361,0.00019379733,0.00011756689,0.0008922749,0.070382915,0.88477755,0.0016551398,0.0058092987,0.0016892657],"about_ca_topic_score_codex":0.0004941335,"about_ca_topic_score_gemma":0.000010245129,"teacher_disagreement_score":0.10385877,"about_ca_system_score_codex":0.000014044765,"about_ca_system_score_gemma":0.000026597489,"threshold_uncertainty_score":0.7226505},"labels":[],"label_agreement":null},{"id":"W2025117991","doi":"10.1186/1471-2105-8-420","title":"'Unite and conquer': enhanced prediction of protein subcellular localization by integrating multiple specialized tools","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Canadian Institutes of Health Research; Canadian Institute for Advanced Research","keywords":"Interconnectivity; Computer science; Subcellular localization; Proteome; Function (biology); Computational biology; Protein function prediction; Identification (biology); Protein subcellular localization prediction; Set (abstract data type); Machine learning; Artificial intelligence; Biology; Bioinformatics; Protein function; Genetics","score_opus":0.010598265984508089,"score_gpt":0.2339617152942268,"score_spread":0.22336344930971871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025117991","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25073838,0.00009681594,0.74614555,0.0000047019894,0.00005846736,0.00045808428,0.00006985418,0.000027944012,0.002400221],"genre_scores_gemma":[0.82250315,0.00006979134,0.17517735,0.00011704526,0.00011416685,0.000015016232,0.001673372,0.000028173348,0.00030193088],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985755,0.00004326445,0.0007963973,0.00012412417,0.0002192363,0.00024148071],"domain_scores_gemma":[0.99897325,0.000051489413,0.00044825047,0.0002742526,0.0001672679,0.0000855025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007077097,0.00019043012,0.00020017636,0.00008468645,0.00009746431,0.00004996064,0.00013690878,0.00022735966,0.000012460066],"category_scores_gemma":[0.0008110809,0.00017576027,0.00005326265,0.00015144392,0.00013059599,0.000035022207,0.000095538926,0.0001359994,0.000005174098],"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":[0.0005065678,0.00014588401,0.023208939,0.001726293,0.00010716085,6.6996165e-7,0.0028365,0.0017194301,0.93629056,0.001027282,0.0019165901,0.030514136],"study_design_scores_gemma":[0.0017698007,0.0004500157,0.0008379163,0.00013508505,0.000026628626,0.000011953355,0.0013775975,0.35521477,0.6198743,0.000031276075,0.01996959,0.00030107048],"about_ca_topic_score_codex":0.00001598314,"about_ca_topic_score_gemma":0.000035016972,"teacher_disagreement_score":0.57176477,"about_ca_system_score_codex":0.000021299627,"about_ca_system_score_gemma":0.000050739633,"threshold_uncertainty_score":0.71672964},"labels":[],"label_agreement":null},{"id":"W2026123729","doi":"10.1371/journal.pone.0080565","title":"Generalized Baum-Welch Algorithm Based on the Similarity between Sequences","year":2013,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"University of Waterloo; University of Tehran","keywords":"Algorithm; Similarity (geometry); Hidden Markov model; Artificial intelligence; Pattern recognition (psychology); Amino acid; Matrix (chemical analysis); Mathematics; Markov chain; Computer science; Machine learning; Biology; Chemistry; Genetics; Image (mathematics)","score_opus":0.03239532497029153,"score_gpt":0.24107467499039498,"score_spread":0.20867935002010346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026123729","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9852848,0.000048851358,0.0034935153,0.0043003717,0.000034092234,0.00050607027,0.000056354795,0.000037466398,0.006238481],"genre_scores_gemma":[0.9485751,0.000025866822,0.04632376,0.0034527252,0.0004075622,0.00008781006,0.0003036591,0.000026033107,0.0007975178],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99896914,0.00012248073,0.00020120997,0.00018530543,0.00029054095,0.00023134258],"domain_scores_gemma":[0.99920195,0.00006567683,0.0000924979,0.00047217062,0.00009536768,0.000072305425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025591126,0.0001506351,0.00015542406,0.000025663665,0.000133503,0.000058252786,0.00032187146,0.00013546342,0.00043915267],"category_scores_gemma":[0.00023918223,0.00010272287,0.00006113983,0.000073230025,0.00008335822,0.000004494487,0.000080375816,0.00020665569,0.00013034114],"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":[0.00008517899,0.0022592065,0.15451741,0.00042509218,0.00161885,0.0000057622633,0.00036610165,0.0017073177,0.7545206,0.0007583317,0.06474381,0.018992366],"study_design_scores_gemma":[0.001066889,0.0008420431,0.019370295,0.00010347593,0.00015875408,0.0000014571543,0.0000655591,0.24224836,0.72677803,0.0006103007,0.008066147,0.00068872934],"about_ca_topic_score_codex":0.00006924314,"about_ca_topic_score_gemma":0.0000031012376,"teacher_disagreement_score":0.24054103,"about_ca_system_score_codex":0.00001208708,"about_ca_system_score_gemma":0.000039418104,"threshold_uncertainty_score":0.4808414},"labels":[],"label_agreement":null},{"id":"W2027831935","doi":"10.1002/prot.21548","title":"Biological implications of SNPs in signal peptide domains of human proteins","year":2007,"lang":"en","type":"article","venue":"Proteins Structure Function and Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"Canadian Institutes of Health Research","keywords":"Signal peptide; Biology; Membrane protein; Peptide; Peptide sequence; Cell biology; Genetics; Gene; Biochemistry","score_opus":0.009727851530473456,"score_gpt":0.25462049134457715,"score_spread":0.2448926398141037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027831935","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93200356,0.000052307914,0.06424994,0.00004912478,0.00003937717,0.00072858453,0.000059415423,0.000016323333,0.0028013869],"genre_scores_gemma":[0.96248084,0.00001700935,0.037097532,0.00009267847,0.00005587934,0.000011657914,0.0001980933,0.0000092239225,0.00003705982],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9986995,0.000028671086,0.00075665966,0.0001321549,0.00015451155,0.0002285279],"domain_scores_gemma":[0.999089,0.000018230054,0.00043226941,0.0002683161,0.00011960524,0.00007256921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039391004,0.00017614332,0.00022562967,0.00016939618,0.00008433238,0.000012466978,0.00014827476,0.00025385723,0.000046637357],"category_scores_gemma":[0.00010551911,0.00013878835,0.00006467631,0.00022196955,0.0002018902,0.000015279282,0.000110105335,0.00019902505,9.037678e-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":[0.0002524862,0.00011759189,0.09985909,0.00050533784,0.00006263739,3.2842007e-7,0.0005838051,0.00010231438,0.87414914,0.006433166,0.000117318225,0.017816767],"study_design_scores_gemma":[0.0027936522,0.00397984,0.6707656,0.00013730783,0.000049562863,0.00007084201,0.0012444017,0.0011428592,0.3100173,0.004499838,0.004625056,0.00067377207],"about_ca_topic_score_codex":0.000021674394,"about_ca_topic_score_gemma":0.00011182551,"teacher_disagreement_score":0.57090646,"about_ca_system_score_codex":0.000015051601,"about_ca_system_score_gemma":0.000041844374,"threshold_uncertainty_score":0.56596243},"labels":[],"label_agreement":null},{"id":"W2028837010","doi":"10.1159/000024521","title":"Clustering of Murine Lung Metastases Reflects Fractal Nonuniformity in Regional Lung Blood Flow","year":2000,"lang":"en","type":"article","venue":"Invasion and Metastasis","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Ottawa Regional Cancer Foundation","funders":"","keywords":"Metastasis; Lung; Cluster analysis; Cell; Cancer research; Cancer; Biology; Pathology; Medicine; Internal medicine; Genetics; Mathematics; Statistics","score_opus":0.013222124551430788,"score_gpt":0.2707253779698767,"score_spread":0.25750325341844593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028837010","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9957326,0.0012450212,0.000695097,0.00010007472,0.000038882772,0.00016542764,0.000043548793,0.000012569518,0.0019667728],"genre_scores_gemma":[0.9728626,0.0016418832,0.024616783,0.00030428075,0.000054175394,0.000010412409,0.00018733124,0.000018977777,0.00030353517],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99888915,0.00009280894,0.00037743422,0.00023405481,0.00018305125,0.00022353014],"domain_scores_gemma":[0.99944633,0.000030365141,0.0001147561,0.00027582297,0.000041733747,0.000091009955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003799356,0.00017637336,0.0002486898,0.0001084362,0.000060734492,0.000018024904,0.00013587727,0.00010158376,0.00025506152],"category_scores_gemma":[0.000107651416,0.0001573884,0.00008785019,0.00014500674,0.000070004426,0.000016114465,0.000116879884,0.00015198778,0.0000031037532],"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":[0.0021078656,0.0015596811,0.04929018,0.002509752,0.0012368087,0.0001264393,0.0022644117,0.01688443,0.37699005,0.0002585076,0.0072096023,0.5395623],"study_design_scores_gemma":[0.014174931,0.0021674158,0.03813421,0.00085459236,0.0012588586,0.0013268233,0.00086472527,0.18146355,0.59801984,0.00013655193,0.15916128,0.0024372207],"about_ca_topic_score_codex":0.000075563345,"about_ca_topic_score_gemma":0.00013920906,"teacher_disagreement_score":0.53712505,"about_ca_system_score_codex":0.000008774054,"about_ca_system_score_gemma":0.000041635725,"threshold_uncertainty_score":0.64181125},"labels":[],"label_agreement":null},{"id":"W2030124080","doi":"10.1186/1471-2164-8-191","title":"C-terminal motif prediction in eukaryotic proteomes using comparative genomics and statistical over-representation across protein families","year":2007,"lang":"en","type":"article","venue":"BMC Genomics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Ontario Genomics; Ontario Genomics Institute; Genome Canada","keywords":"Biology; Computational biology; Proteome; Human proteome project; Proteomics; Signal peptide; Tripeptide; Genomics; Genetics; Genome; Peptide sequence; Gene; Amino acid","score_opus":0.027261463793126432,"score_gpt":0.3293585705353219,"score_spread":0.3020971067421955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030124080","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8880788,0.00005291998,0.110922374,0.000004679576,0.00006145777,0.0006594679,0.00007741933,0.000011648088,0.00013122316],"genre_scores_gemma":[0.9380046,0.00001259502,0.061538618,0.000024362775,0.00012361145,0.000015011239,0.00018094991,0.000018996165,0.000081213686],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9988131,0.00006602716,0.0004163222,0.00027317283,0.00012057462,0.00031078976],"domain_scores_gemma":[0.9994895,0.000033947497,0.00015768038,0.00019795328,0.00004644141,0.00007447293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041314372,0.00017420032,0.00018289972,0.00006321935,0.00011079714,0.000059142538,0.00010369648,0.00014337715,0.000008652138],"category_scores_gemma":[0.00009969176,0.00018558589,0.000029324374,0.000075383374,0.00015177797,0.000013329014,0.00014739574,0.00016262864,0.000005561137],"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":[0.0004923153,0.00010498718,0.37914512,0.0002281843,0.000043576765,0.0000098000355,0.0042419503,0.018056931,0.5953113,0.00014652625,0.000047497466,0.0021718522],"study_design_scores_gemma":[0.0019767662,0.0004455734,0.67638594,0.000043920325,0.00002961583,0.00009169067,0.0039182324,0.19920397,0.116406895,0.0002301405,0.0007745078,0.00049277715],"about_ca_topic_score_codex":0.000098940254,"about_ca_topic_score_gemma":0.0003334124,"teacher_disagreement_score":0.47890437,"about_ca_system_score_codex":0.000100278136,"about_ca_system_score_gemma":0.00009564993,"threshold_uncertainty_score":0.75679725},"labels":[],"label_agreement":null},{"id":"W2030696082","doi":"10.1111/j.0022-1112.2005.00850.x","title":"Evidence for co‐dominant allelic expression of a phosphoglucomutase regulatory locus polymorphism in the Atlantic salmon","year":2005,"lang":"en","type":"article","venue":"Journal of Fish Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Queen's University","funders":"","keywords":"Biology; Phosphoglucomutase; Salmo; Allele; Genetics; Rainbow trout; Locus (genetics); Isozyme; Phenotype; Genetic variation; Gene; Fishery; Enzyme; Fish <Actinopterygii>; Biochemistry","score_opus":0.021754266329698964,"score_gpt":0.30986554621664003,"score_spread":0.2881112798869411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030696082","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.994544,0.0019467184,0.0011799257,0.001977637,0.00010224734,0.00017310544,0.000011045231,0.0000014308216,0.00006385703],"genre_scores_gemma":[0.9959283,0.00058044953,0.0022545941,0.00088311516,0.00028447228,0.0000057463135,0.000024449975,0.0000088595225,0.000030047493],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99881685,0.00015797051,0.0006101478,0.00011080702,0.000112036156,0.00019220641],"domain_scores_gemma":[0.9987867,0.00017437011,0.0006334475,0.00026473295,0.0000999295,0.000040832158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010768927,0.00011845104,0.0002594155,0.00008042254,0.000037165126,0.0000075408325,0.0004145347,0.00017966624,0.000015217707],"category_scores_gemma":[0.0006267091,0.00007513618,0.00015318108,0.00005737753,0.000113167785,0.000009936563,0.000050499235,0.00018953436,0.0000012834554],"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":[0.00082718546,0.00011893467,0.01811129,0.000060845334,0.00003194852,0.000005950198,0.00032895023,0.00021370072,0.9587319,0.00007628964,0.0158889,0.0056041097],"study_design_scores_gemma":[0.0034636138,0.003175828,0.02689786,0.0004961027,0.000071863644,0.0007703342,0.0002480265,0.0006866702,0.7870826,0.00016504996,0.17661059,0.00033147915],"about_ca_topic_score_codex":0.000017495193,"about_ca_topic_score_gemma":0.000029109073,"teacher_disagreement_score":0.1716493,"about_ca_system_score_codex":0.000018864737,"about_ca_system_score_gemma":0.000088678345,"threshold_uncertainty_score":0.30639645},"labels":[],"label_agreement":null},{"id":"W2032239134","doi":"10.1109/nafips.2008.4531324","title":"A choquet integral-based multi-class classifier and its applications on the prediction of membrane protein types","year":2008,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Choquet integral; Classifier (UML); Artificial intelligence; Class (philosophy); Fuzzy logic; Integral membrane protein; Machine learning; Type (biology); Computer science; Pattern recognition (psychology); Computational intelligence; Mathematics; Data mining; Membrane protein; Membrane; Biology; Biochemistry","score_opus":0.021465861453564015,"score_gpt":0.24458843410052744,"score_spread":0.22312257264696342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032239134","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9669258,0.00009930236,0.017891036,0.0011937812,0.000028496435,0.0011216234,0.000052661377,0.000038799546,0.012648484],"genre_scores_gemma":[0.99534464,0.00003099451,0.002034726,0.00026010472,0.000031239448,0.00012051831,0.000058517195,0.000008503769,0.0021107302],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99954975,0.0000330931,0.00014488077,0.00010966648,0.00008314497,0.00007944362],"domain_scores_gemma":[0.9996107,0.000020390502,0.000071328606,0.00020696792,0.000062969484,0.000027647813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009117431,0.00008068375,0.000068141744,0.000026563495,0.00007647128,0.00000522002,0.000093714174,0.00008453946,0.00002956511],"category_scores_gemma":[0.00011596197,0.000050819213,0.000029370072,0.0000615764,0.00007657249,0.0000020871162,0.00002729122,0.000099479505,0.000008691461],"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":[0.000108407716,0.00023781808,0.001997116,0.00014255676,0.00007268839,3.8301894e-7,0.00013684288,0.0007827531,0.98787785,0.0054814527,0.0016856217,0.0014765162],"study_design_scores_gemma":[0.0006959778,0.0003500996,0.0024475653,0.000026676245,0.000012678459,0.0000092052705,0.000053580203,0.081965044,0.865568,0.000014881999,0.048732758,0.00012356673],"about_ca_topic_score_codex":0.0000064888695,"about_ca_topic_score_gemma":0.000006591744,"teacher_disagreement_score":0.12230988,"about_ca_system_score_codex":0.000004778221,"about_ca_system_score_gemma":0.00003467076,"threshold_uncertainty_score":0.20723474},"labels":[],"label_agreement":null},{"id":"W2032289031","doi":"10.1002/prca.201200068","title":"Computational approaches to predicting essential proteins: A survey","year":2012,"lang":"en","type":"review","venue":"PROTEOMICS - CLINICAL APPLICATIONS","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computational biology; Genome; Biology; Computer science; Data science; Genetics; Gene","score_opus":0.24132492858844048,"score_gpt":0.4155780257776774,"score_spread":0.1742530971892369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032289031","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":[0.00006352108,0.4952986,0.49286625,0.00009661776,0.0001730193,0.009877187,0.00069281773,0.000084600244,0.0008474082],"genre_scores_gemma":[0.00022721016,0.6260194,0.34532216,0.00022852757,0.0028734559,0.01211468,0.012588067,0.00019410605,0.00043236688],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964305,0.00051358057,0.0016716836,0.0007055287,0.00025959872,0.0004190661],"domain_scores_gemma":[0.99746966,0.0002958714,0.0008780659,0.0008933634,0.00013282029,0.0003302148],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002354059,0.00044747902,0.0009552716,0.00009637359,0.00021043702,0.000086824104,0.0008040761,0.0007564004,0.000017403658],"category_scores_gemma":[0.0007803816,0.00041015985,0.00046772853,0.00033515145,0.00015455969,0.0000067056676,0.00064543536,0.0007911524,0.00036926224],"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":[0.000038343245,0.00067917164,0.0017258781,0.00593512,0.0005554524,2.0487334e-7,0.000037893977,0.0004985718,0.000003913573,0.0016336208,0.00079210673,0.9880997],"study_design_scores_gemma":[0.0001788695,0.00011192328,0.00020864546,0.0003009531,0.00028315422,0.000015669495,0.000002699985,0.0007133089,0.000005664489,0.00012832462,0.99754715,0.00050361594],"about_ca_topic_score_codex":0.0000149439575,"about_ca_topic_score_gemma":0.000016726775,"teacher_disagreement_score":0.99675506,"about_ca_system_score_codex":0.000037594564,"about_ca_system_score_gemma":0.00046703673,"threshold_uncertainty_score":0.999835},"labels":[],"label_agreement":null},{"id":"W2033483180","doi":"10.1109/ijcnn.2006.246752","title":"Neural and Statistical Classification to Families of Bio-sequences","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Generalization; Computer science; Property (philosophy); Entropy (arrow of time); Artificial intelligence; Artificial neural network; Feature (linguistics); Pattern recognition (psychology); Feature vector; String (physics); Machine learning; Mathematics","score_opus":0.027900896080192715,"score_gpt":0.2816318045052348,"score_spread":0.2537309084250421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033483180","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98493,0.00002372047,0.0012849106,0.003671526,0.00029852882,0.0002147638,0.00003393218,0.000020602974,0.009522059],"genre_scores_gemma":[0.99688363,0.000037932983,0.0016318355,0.0005555025,0.00044839614,0.00001842374,0.00005602941,0.000010814532,0.00035741745],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989806,0.000018376557,0.00033532892,0.00021675894,0.00025808878,0.00019085653],"domain_scores_gemma":[0.99940515,0.000026299587,0.00019263256,0.00009727756,0.00023324908,0.0000454151],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019663511,0.00015174391,0.0001301759,0.000052365438,0.00008013644,0.00007825201,0.00027684105,0.00006493688,0.000019764084],"category_scores_gemma":[0.00008742868,0.000110122346,0.000034619745,0.00008798034,0.00020881534,0.00001316674,0.00007768463,0.00014409621,0.000007972083],"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":[0.0007865092,0.00015535773,0.051362168,0.0001068407,0.000113989576,0.0000029513014,0.00041495904,0.023201928,0.57647073,0.25457042,0.07095627,0.021857895],"study_design_scores_gemma":[0.0013117824,0.0022860256,0.28840414,0.00027282798,0.000076545206,0.00016642753,0.00080636353,0.62351453,0.05127065,0.011210156,0.019549698,0.0011308152],"about_ca_topic_score_codex":0.00005651544,"about_ca_topic_score_gemma":0.000019522327,"teacher_disagreement_score":0.60031265,"about_ca_system_score_codex":0.000012001942,"about_ca_system_score_gemma":0.000020132802,"threshold_uncertainty_score":0.4490659},"labels":[],"label_agreement":null},{"id":"W2034088007","doi":"10.1371/journal.pone.0063145","title":"A Consistency-Based Feature Selection Method Allied with Linear SVMs for HIV-1 Protease Cleavage Site Prediction","year":2013,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Calgary","funders":"","keywords":"Feature selection; Support vector machine; Artificial intelligence; Computer science; Machine learning; Data mining; Dimensionality reduction; Pattern recognition (psychology); Curse of dimensionality; Feature (linguistics); Feature vector","score_opus":0.013024061574739905,"score_gpt":0.23442782668926979,"score_spread":0.2214037651145299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034088007","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":[0.56474435,0.00006453018,0.42798093,0.0015827392,0.000036533642,0.003772849,0.00018513537,0.00017374613,0.0014591631],"genre_scores_gemma":[0.17420845,0.0000068590075,0.8195631,0.0007456145,0.00030816882,0.0007226006,0.0013859778,0.00005355405,0.0030056646],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99912184,0.00006501788,0.00017468403,0.00024462317,0.000179375,0.0002144646],"domain_scores_gemma":[0.99925613,0.000025700769,0.00014205016,0.00024842226,0.00024207975,0.00008560194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017979737,0.00016376025,0.00016424437,0.000044618984,0.00011718404,0.00003564631,0.000086948705,0.00019265179,0.000031864372],"category_scores_gemma":[0.00020610924,0.00013764323,0.0000539869,0.000090470145,0.000037553265,0.000009165558,0.000023429257,0.00018265066,0.000034524917],"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":[0.0005604025,0.00064974045,0.018019771,0.00059155456,0.00035045287,5.007981e-7,0.000107905056,0.0013286922,0.9699817,0.000019913668,0.0076549584,0.0007344111],"study_design_scores_gemma":[0.002069408,0.0019225058,0.003454899,0.00012201757,0.00023375315,0.000008753263,0.000032255837,0.26307103,0.72474957,0.000016725386,0.0040036687,0.0003154186],"about_ca_topic_score_codex":0.000014164364,"about_ca_topic_score_gemma":0.000010050003,"teacher_disagreement_score":0.3915822,"about_ca_system_score_codex":0.000018397888,"about_ca_system_score_gemma":0.000084627616,"threshold_uncertainty_score":0.5612928},"labels":[],"label_agreement":null},{"id":"W2035431183","doi":"10.1007/s10549-009-0557-0","title":"Learning to predict relapse in invasive ductal carcinomas based on the subcellular localization of junctional proteins","year":2009,"lang":"en","type":"article","venue":"Breast Cancer Research and Treatment","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Athabasca University; University of Saskatchewan; University of Alberta","funders":"","keywords":"Classifier (UML); Breast cancer; Subcellular localization; Decision tree; Machine learning; PTEN; Artificial intelligence; Biology; Decision tree learning; Bioinformatics; Computer science; Cancer; Cytoplasm; Signal transduction; PI3K/AKT/mTOR pathway","score_opus":0.018101540308751243,"score_gpt":0.2895833958624085,"score_spread":0.2714818555536573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035431183","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99633795,0.00012052626,0.00030633557,0.0020648784,0.000014294802,0.00058380474,0.000027130318,0.000004577292,0.00054051983],"genre_scores_gemma":[0.9992342,0.00008707085,0.00009472755,0.00007838695,0.000059163285,0.0001175007,0.00006502631,0.0000069026814,0.0002570191],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991414,0.00012534212,0.00012566599,0.00017138316,0.00024697106,0.00018926352],"domain_scores_gemma":[0.9996017,0.00003211666,0.000034642228,0.00015672074,0.00010360069,0.000071170194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024245527,0.00009176647,0.00008268422,0.00009209559,0.000107718064,0.000016404874,0.00006837752,0.000049412472,0.000026160717],"category_scores_gemma":[0.00009206852,0.00006114888,0.000025055793,0.00016725755,0.00006512591,0.0000033196143,0.000027755734,0.00011836706,0.0000026371686],"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":[0.0055841305,0.0015091189,0.73979616,0.00012491981,0.00015125866,0.000047953094,0.0015657527,0.14487348,0.07037723,0.00091134885,0.0010359444,0.034022696],"study_design_scores_gemma":[0.0053999047,0.023479814,0.7776491,0.00043533513,0.000030507577,0.0000693127,0.0008526922,0.045648463,0.13930453,0.00021244689,0.0064752544,0.00044264793],"about_ca_topic_score_codex":0.00046430057,"about_ca_topic_score_gemma":0.00024013298,"teacher_disagreement_score":0.099225014,"about_ca_system_score_codex":0.00009567605,"about_ca_system_score_gemma":0.00020300134,"threshold_uncertainty_score":0.24935788},"labels":[],"label_agreement":null},{"id":"W2036790151","doi":"10.1038/nrmicro1494","title":"Methods for predicting bacterial protein subcellular localization","year":2006,"lang":"en","type":"review","venue":"Nature Reviews Microbiology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":170,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Subcellular localization; Protein subcellular localization prediction; Biology; Computational biology; Identification (biology); Bacterial protein; Drug target; Annotation; Genome; Bioinformatics; Genetics; Gene; Biochemistry","score_opus":0.017858020789331866,"score_gpt":0.37716868641574386,"score_spread":0.359310665626412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036790151","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":[0.0000018081984,0.9009341,0.09345689,0.000009233619,0.00083035894,0.00431787,0.00019759698,0.000033333294,0.00021882512],"genre_scores_gemma":[2.7825138e-7,0.87586737,0.097591214,0.00011505455,0.00137701,0.00058353995,0.023488196,0.00010565165,0.00087170064],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957995,0.0014336985,0.001481137,0.00073980127,0.000040408584,0.00050546776],"domain_scores_gemma":[0.9975367,0.00009159352,0.0014073873,0.0007613675,0.00013767272,0.00006524034],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0019056513,0.00073191046,0.0021668763,0.00013422368,0.00013854631,0.00004153265,0.0006203184,0.003343147,0.00002931686],"category_scores_gemma":[0.0010849899,0.00055665383,0.0009923067,0.00020908761,0.000100701815,0.0000042981983,0.0002381985,0.0010303496,0.0000312337],"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":[0.000016846003,0.000032623117,0.0000019310985,0.03164778,0.00014765053,5.278204e-7,0.000005247496,0.0000026152738,0.017298229,0.00006496002,0.014420086,0.9363615],"study_design_scores_gemma":[0.00023183416,0.0001820469,3.2950503e-8,0.0033185158,0.00045511278,0.0001238908,4.89116e-7,0.0000335248,0.0010414605,0.000010491047,0.99407864,0.00052396586],"about_ca_topic_score_codex":0.0000028293698,"about_ca_topic_score_gemma":0.0000064513506,"teacher_disagreement_score":0.97965854,"about_ca_system_score_codex":0.000069628215,"about_ca_system_score_gemma":0.0002118327,"threshold_uncertainty_score":0.9996885},"labels":[],"label_agreement":null},{"id":"W2040630248","doi":"10.1371/journal.pcbi.0010066","title":"Refining Protein Subcellular Localization","year":2005,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":123,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Proteome; Computational biology; Subcellular localization; Protein subcellular localization prediction; Protein–protein interaction; Biology; Protein targeting; Function (biology); Organelle; Proteomics; Computer science; Bioinformatics; Membrane protein; Cell biology; Biochemistry; Gene; Cytoplasm","score_opus":0.009820439929410696,"score_gpt":0.2489673547677503,"score_spread":0.2391469148383396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040630248","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5605589,0.00026572964,0.43289554,0.00093102024,0.00007526208,0.00020064328,0.000023049217,0.00007616141,0.004973693],"genre_scores_gemma":[0.9513955,0.0000033492704,0.04539203,0.0008156717,0.00027994163,0.000019847967,0.0016631505,0.000015793918,0.00041468968],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992263,0.000075259806,0.00024079079,0.00019799807,0.00008993675,0.00016973547],"domain_scores_gemma":[0.9995936,0.000019118292,0.00010279465,0.00013703707,0.00010267804,0.00004474115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012428315,0.00011355776,0.00009939144,0.000051219893,0.000090806905,0.0000141448645,0.00013418171,0.0001342474,0.000063843116],"category_scores_gemma":[0.0001469631,0.00011015232,0.000039294773,0.00007137127,0.00006724418,0.0000043840178,0.000078135745,0.000092872615,0.0001283948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011859024,0.00023437371,0.027101293,0.000076130396,0.00017147597,0.0000017210674,0.00017897574,0.56069684,0.3668637,0.023898382,0.0022748709,0.018383635],"study_design_scores_gemma":[0.0009507938,0.0005340412,0.0012153555,0.000029031016,0.000018391936,0.000030797095,0.00001781939,0.67119,0.03924868,0.001659943,0.28463587,0.00046928597],"about_ca_topic_score_codex":0.000003731347,"about_ca_topic_score_gemma":0.000005700257,"teacher_disagreement_score":0.39083663,"about_ca_system_score_codex":0.000016781707,"about_ca_system_score_gemma":0.000048843212,"threshold_uncertainty_score":0.44918814},"labels":[],"label_agreement":null},{"id":"W2041002927","doi":"10.1371/journal.pone.0034007","title":"Comparing the Similarity of Different Groups of Bacteria to the Human Proteome","year":2012,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Proteome; Biology; Human proteome project; Bacteria; Similarity (geometry); Proteomics; Computational biology; Microbiology; Bioinformatics; Genetics; Artificial intelligence; Gene; Computer science","score_opus":0.042299546635775453,"score_gpt":0.25615246907651934,"score_spread":0.2138529224407439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041002927","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9984073,0.00003522314,0.00017988525,0.00023426101,0.000022517832,0.00032059645,0.0000069029934,0.000004434053,0.0007888474],"genre_scores_gemma":[0.99875337,0.000003897536,0.00089402683,0.000091985574,0.0001269046,0.000021179634,0.000026388569,0.000007957873,0.000074312615],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993933,0.00005949178,0.00019893142,0.00005966719,0.00014697274,0.00014166473],"domain_scores_gemma":[0.9994007,0.000013843124,0.00012282193,0.00038295632,0.000043770156,0.00003594394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024454852,0.00007779743,0.00014075919,0.000012446737,0.00006202574,0.000007070967,0.0002650659,0.000043866217,0.000022386383],"category_scores_gemma":[0.00009442297,0.000043460877,0.00003904837,0.000037053214,0.000053213644,0.0000023229627,0.00022572305,0.00010105231,0.0000037384966],"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":[0.000015266347,0.0003236819,0.17996714,0.00010969757,0.0000900968,1.110655e-8,0.00046475718,0.000010012011,0.81870276,0.00021037836,0.000079769285,0.000026424606],"study_design_scores_gemma":[0.00012696383,0.00013853036,0.36726618,0.000036374717,0.00004049934,4.8489034e-7,0.00004563563,0.00017560813,0.63178897,0.000016974094,0.00029786676,0.00006592163],"about_ca_topic_score_codex":0.000012671649,"about_ca_topic_score_gemma":0.000016434411,"teacher_disagreement_score":0.18729903,"about_ca_system_score_codex":0.0000048618103,"about_ca_system_score_gemma":0.00000495913,"threshold_uncertainty_score":0.17722832},"labels":[],"label_agreement":null},{"id":"W2042327217","doi":"10.1103/physreve.73.015701","title":"Monte Carlo basin paving: An improved global optimization method","year":2006,"lang":"en","type":"article","venue":"Physical Review E","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Waterloo","funders":"","keywords":"Maxima and minima; Structural basin; Monte Carlo method; Global optimization; Energy landscape; Computer science; Energy (signal processing); Mathematical optimization; Algorithm; Geology; Mathematics; Physics; Statistics; Paleontology","score_opus":0.006844258660788012,"score_gpt":0.32404910369412193,"score_spread":0.3172048450333339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042327217","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":[0.17461188,0.023559349,0.76646,0.0023978155,0.0003902585,0.002129354,0.0001453575,0.00025108253,0.030054884],"genre_scores_gemma":[0.7448215,0.0025610982,0.24678522,0.0035631529,0.0012214975,0.00006943381,0.00052344566,0.000053836113,0.00040084642],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915147,0.00012799093,0.00021795358,0.00021243944,0.000114268754,0.00017587202],"domain_scores_gemma":[0.9993813,0.000010190785,0.0001209416,0.00035167747,0.00007155998,0.00006434175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019893641,0.00014708568,0.0002168332,0.000006271579,0.00004466801,0.00002346492,0.0001703122,0.000046212113,0.000011837765],"category_scores_gemma":[0.00015531557,0.00012452276,0.00011962534,0.00010589366,0.00002354625,0.000007932164,0.0000727293,0.0000800973,0.000010267433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002135577,0.0024898998,0.00921794,0.00670482,0.00034452262,0.000010794639,0.00014134235,0.42726588,0.13128018,0.011775394,0.03959129,0.37096438],"study_design_scores_gemma":[0.0005231675,0.0004643638,0.0017664914,0.00025891332,0.00016093117,0.000019713007,0.000007084651,0.89113045,0.0039964668,0.0003879081,0.100717984,0.00056650565],"about_ca_topic_score_codex":0.00010303233,"about_ca_topic_score_gemma":0.000011530488,"teacher_disagreement_score":0.5702096,"about_ca_system_score_codex":0.000017776554,"about_ca_system_score_gemma":0.000029165414,"threshold_uncertainty_score":0.50778913},"labels":[],"label_agreement":null},{"id":"W2042427414","doi":"10.1145/2494444.2494459","title":"Protein structural class prediction using predicted secondary structure and hydropathy profile","year":2013,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Support vector machine; Computer science; Sequence (biology); Artificial intelligence; Class (philosophy); Pattern recognition (psychology); Domain (mathematical analysis); Protein secondary structure; Protein structure prediction; Machine learning; Folding (DSP implementation); Data mining; Protein folding; Protein structure; Mathematics; Biology; Engineering","score_opus":0.0035558133339433475,"score_gpt":0.20908707838725563,"score_spread":0.2055312650533123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042427414","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99579644,0.000055617846,0.0010696233,0.00005728673,0.000094352516,0.0006469689,0.000101800644,0.000050095132,0.0021278264],"genre_scores_gemma":[0.9819959,0.0000024630372,0.016543265,0.00013184192,0.00017848964,0.000018744307,0.00039956692,0.000021006117,0.00070873305],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991651,0.00004480287,0.00022821706,0.0002246962,0.00012642721,0.00021073106],"domain_scores_gemma":[0.999492,0.0000032147727,0.00009901074,0.00023701396,0.00008070157,0.00008805948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000052793934,0.00016806627,0.000111703346,0.000039331546,0.0001151492,0.000064498025,0.000102379854,0.00019993036,0.0005079607],"category_scores_gemma":[0.000054027645,0.0001352059,0.000028599039,0.000058109454,0.00007738909,0.000019558895,0.00013251863,0.00020495248,0.000004611116],"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":[0.000023346776,0.0000047204594,0.012480673,0.00010344798,0.00004237285,5.200095e-7,0.00010151363,0.00020203744,0.98155564,0.00008329881,0.0011412215,0.0042612213],"study_design_scores_gemma":[0.0014862963,0.0007205778,0.08067912,0.000046157318,0.000037830458,0.00024968712,0.00020831765,0.5545543,0.35599446,0.00047616314,0.004956891,0.0005902107],"about_ca_topic_score_codex":0.00004644466,"about_ca_topic_score_gemma":0.000005674807,"teacher_disagreement_score":0.6255612,"about_ca_system_score_codex":0.0000129611835,"about_ca_system_score_gemma":0.00005334378,"threshold_uncertainty_score":0.5561813},"labels":[],"label_agreement":null},{"id":"W2044438398","doi":"10.1109/bibmw.2011.6112372","title":"Synthesizing Aligned Random Pattern Digraphs from protein sequence patterns","year":2011,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sequence (biology); Cluster analysis; Protein family; Sequence logo; Protein sequencing; Computational biology; Computer science; Pattern recognition (psychology); Biology; Sequence alignment; Algorithm; Peptide sequence; Artificial intelligence; Genetics","score_opus":0.021380556974874322,"score_gpt":0.2347407782175735,"score_spread":0.21336022124269918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044438398","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9273453,0.000042195228,0.062397648,0.000049085076,0.000070122675,0.00028937793,0.00003791005,0.00005594777,0.009712418],"genre_scores_gemma":[0.9904844,0.000018386883,0.008337933,0.0004526373,0.000086542816,0.000040916788,0.00012421932,0.00002453323,0.0004303878],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99901414,0.00007556596,0.0002673756,0.00025942276,0.00013453556,0.00024898988],"domain_scores_gemma":[0.99928004,0.000016261245,0.00011677959,0.00046581402,0.000039531787,0.00008159908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016265626,0.00018400924,0.00015257992,0.000033356457,0.000064981636,0.000029601712,0.00030918096,0.000133625,0.0004670276],"category_scores_gemma":[0.00009575409,0.0001533186,0.00009637319,0.000041077892,0.000047973524,0.000006482277,0.00012783198,0.00007569941,0.00006174941],"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":[0.00019274047,0.00009756466,0.13430025,0.000068589296,0.00018585609,0.000016814229,0.0010157962,0.000006833902,0.8409303,0.0001252005,0.00039869867,0.022661401],"study_design_scores_gemma":[0.00128369,0.00023514233,0.013386379,0.000089445566,0.000031974705,0.000012040162,0.00024591485,0.0010874012,0.9796218,0.00022788512,0.0032379152,0.00054039067],"about_ca_topic_score_codex":0.00095256197,"about_ca_topic_score_gemma":0.00014266919,"teacher_disagreement_score":0.13869156,"about_ca_system_score_codex":0.0000062110803,"about_ca_system_score_gemma":0.00002211599,"threshold_uncertainty_score":0.6252151},"labels":[],"label_agreement":null},{"id":"W2044679407","doi":"10.1114/1.1289470","title":"Automatic Classification of Protein Sequences into Structure/Function Groups via Parallel Cascade Identification: A Feasibility Study","year":2000,"lang":"en","type":"article","venue":"Annals of Biomedical Engineering","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Cascade; Artificial intelligence; Weighting; Binary classification; Computer science; Hidden Markov model; Pattern recognition (psychology); Identification (biology); Set (abstract data type); Protein sequencing; Test set; Binary number; Algorithm; Nonlinear system; Machine learning; Peptide sequence; Mathematics; Support vector machine; Biology; Engineering; Genetics","score_opus":0.017097920202237937,"score_gpt":0.29274481310644546,"score_spread":0.2756468929042075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044679407","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9745021,0.0001140276,0.02471075,0.00016355526,0.000057322974,0.0003980574,0.000008411425,0.00002719466,0.000018600054],"genre_scores_gemma":[0.99627984,0.000012216959,0.0034584568,0.00001641396,0.000064119355,0.000024294188,0.00010704138,0.000010951624,0.000026666958],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987121,0.000057428035,0.00058191107,0.00019967202,0.00030281954,0.00014604168],"domain_scores_gemma":[0.99928325,0.000013079242,0.00018767733,0.0003516533,0.00008887792,0.00007545073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046117327,0.00012961222,0.0001851663,0.00007700335,0.00003459498,0.000011053833,0.00020529673,0.00013717113,0.000100254365],"category_scores_gemma":[0.00021620015,0.00011720355,0.00006415612,0.00021575477,0.00010229884,0.0000135346145,0.00003275751,0.000115942305,0.0000035198013],"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":[0.000063613006,0.00028673827,0.001603673,0.00045395497,0.00012191896,6.7211704e-7,0.00045598106,0.0025149432,0.95562226,0.00007472164,0.000050037597,0.03875147],"study_design_scores_gemma":[0.0013168773,0.0023506482,0.4026548,0.00019084713,0.00008654358,0.000016547323,0.00041226135,0.4167199,0.17293307,0.00075380225,0.0019381703,0.0006265316],"about_ca_topic_score_codex":0.00003580289,"about_ca_topic_score_gemma":0.000005432178,"teacher_disagreement_score":0.7826892,"about_ca_system_score_codex":0.0000094081715,"about_ca_system_score_gemma":0.000034955327,"threshold_uncertainty_score":0.4779422},"labels":[],"label_agreement":null},{"id":"W2045510682","doi":"10.1101/gr.147901","title":"Evaluation of Gene-Finding Programs on Mammalian Sequences","year":2001,"lang":"en","type":"article","venue":"Genome Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":272,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pacific Centre for Reproductive Medicine; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biology; Exon; Sequence (biology); Gene prediction; Computational biology; Gene; Sequence analysis; Genetics; Strengths and weaknesses; Function (biology); Genome","score_opus":0.15650775225334623,"score_gpt":0.43162210128254286,"score_spread":0.2751143490291966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045510682","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9685731,0.0003420147,0.0002086265,0.0001310183,0.00003862043,0.00039003536,0.0000036290871,0.000007312134,0.030305644],"genre_scores_gemma":[0.99720466,0.0001095272,0.0015506451,0.000016671665,0.00014974106,0.000043308988,0.00011885423,0.000012932094,0.000793632],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99773633,0.00037713104,0.00019661803,0.00019483764,0.0011602329,0.0003348617],"domain_scores_gemma":[0.9989237,0.000017677266,0.00006500537,0.00035704605,0.00056933175,0.000067233166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053288215,0.00008245864,0.0000849937,0.0001363228,0.00011351148,0.000031654825,0.00028081625,0.00010072678,0.000096112664],"category_scores_gemma":[0.0004049683,0.000073714014,0.00004366875,0.00026814203,0.00012232081,0.0000033404262,0.000084143474,0.00018365399,0.000062922234],"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":[0.00013049359,0.00017672544,0.024276722,0.00009516697,0.00010766397,0.000006192744,0.0006289343,0.004482752,0.7806674,0.00039391528,0.00025966385,0.18877433],"study_design_scores_gemma":[0.0042632082,0.010457722,0.097637095,0.00020943955,0.00014402688,0.00021682476,0.0030402741,0.028811006,0.5914286,0.0026073628,0.2597926,0.0013918807],"about_ca_topic_score_codex":0.000034135912,"about_ca_topic_score_gemma":0.000019522726,"teacher_disagreement_score":0.25953293,"about_ca_system_score_codex":0.000056573004,"about_ca_system_score_gemma":0.00019226488,"threshold_uncertainty_score":0.30059704},"labels":[],"label_agreement":null},{"id":"W2047429137","doi":"10.1089/cmb.2008.0031","title":"Learned Random-Walk Kernels and Empirical-Map Kernels for Protein Sequence Classification","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"String kernel; Kernel (algebra); Support vector machine; Random walk; Computer science; Kernel method; Pairwise comparison; Sequence (biology); Artificial intelligence; Pattern recognition (psychology); Random forest; Similarity (geometry); Protein sequencing; Mathematics; Machine learning; Radial basis function kernel; Biology; Peptide sequence; Combinatorics; Statistics; Genetics","score_opus":0.04333806705082064,"score_gpt":0.36681261528494014,"score_spread":0.3234745482341195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047429137","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6826909,0.00042437483,0.30807826,0.007978795,0.00014600436,0.0003849687,0.000022228842,0.000010023565,0.00026442474],"genre_scores_gemma":[0.9530387,0.000030250143,0.045446515,0.0009504565,0.00027379332,0.000005633322,0.00012515657,0.0000070155584,0.0001225046],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990201,0.000115141374,0.00047458807,0.00013860197,0.00010559744,0.00014597317],"domain_scores_gemma":[0.9988899,0.00009855233,0.0004867671,0.000087313245,0.0003496679,0.000087763474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057612587,0.00011574496,0.00020710318,0.00007747008,0.000070805414,0.000024971043,0.00014806486,0.00014779497,0.000009772348],"category_scores_gemma":[0.0006472078,0.00009434915,0.00009141605,0.000051967276,0.00009687227,0.000010476553,0.000022917648,0.00014410859,0.0000024960045],"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":[0.0025612307,0.000251271,0.0074987942,0.00011683349,0.00027437444,0.0000050910057,0.00034219757,0.022590853,0.8481206,0.010546174,0.0059767463,0.101715796],"study_design_scores_gemma":[0.023677787,0.016713832,0.07243971,0.00024215704,0.00019666979,0.001355905,0.00026288204,0.18445115,0.03481072,0.2841774,0.3801603,0.0015114886],"about_ca_topic_score_codex":5.73835e-7,"about_ca_topic_score_gemma":3.3429222e-7,"teacher_disagreement_score":0.8133099,"about_ca_system_score_codex":0.000016160238,"about_ca_system_score_gemma":0.00015108909,"threshold_uncertainty_score":0.38474467},"labels":[],"label_agreement":null},{"id":"W2048299923","doi":"10.1039/c4mb00410h","title":"Predicting protein–protein interactions between human and hepatitis C virus <i>via</i> an ensemble learning method","year":2014,"lang":"en","type":"article","venue":"Molecular BioSystems","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Hepatitis a virus; Ensemble learning; Hepatitis C virus; Computational biology; Virology; Computer science; Biology; Virus; Artificial intelligence; Chemistry","score_opus":0.007431449447555957,"score_gpt":0.2756071699961699,"score_spread":0.26817572054861394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048299923","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7943755,0.00007253628,0.20271255,0.000047455367,0.0000618352,0.0004627018,0.000009768498,0.00008459792,0.0021731032],"genre_scores_gemma":[0.98617846,0.000004199059,0.012387197,0.00008404457,0.0003417637,0.000079800695,0.00037894046,0.00006741869,0.00047816703],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977599,0.0006879479,0.0004781452,0.0004704778,0.00024254777,0.0003610044],"domain_scores_gemma":[0.99886954,0.00002195455,0.00030910192,0.00050955865,0.000101834215,0.00018801594],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008787833,0.00028986827,0.00029849328,0.00009905104,0.00036318868,0.00013294141,0.00023682375,0.00021948521,0.000008737464],"category_scores_gemma":[0.0002570886,0.0002985815,0.0000944164,0.00011516912,0.000055461638,0.000022472399,0.00020166233,0.0003880532,0.000011858295],"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":[0.000008053669,0.000021429663,0.021042595,0.00011872239,0.00006629221,0.000002452845,0.00012180535,0.00014209856,0.9740998,0.00023761543,0.000014810167,0.0041242866],"study_design_scores_gemma":[0.0005636671,0.0010607857,0.0015288744,0.00016567393,0.00005412735,0.00007147294,0.00006427491,0.01308042,0.9539601,0.0001296884,0.028770076,0.0005507979],"about_ca_topic_score_codex":0.0011390125,"about_ca_topic_score_gemma":0.0002654321,"teacher_disagreement_score":0.19180301,"about_ca_system_score_codex":0.000022032318,"about_ca_system_score_gemma":0.000019614929,"threshold_uncertainty_score":0.99994665},"labels":[],"label_agreement":null},{"id":"W2049151260","doi":"10.1021/ci030006i","title":"BHB:  A Simple Knowledge-Based Scoring Function to Improve the Efficiency of Database Screening","year":2003,"lang":"en","type":"article","venue":"Journal of Chemical Information and Computer Sciences","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Simple (philosophy); Function (biology); Computer science; Information retrieval; Data mining","score_opus":0.011226192337527618,"score_gpt":0.264050326589317,"score_spread":0.25282413425178935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049151260","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53585017,0.00005458785,0.46349755,0.000075879805,0.00010841361,0.00004707688,0.0000012061537,0.0000019858182,0.0003631071],"genre_scores_gemma":[0.9713797,0.0000040523887,0.028036207,0.0005102811,0.00006198869,7.9880715e-7,0.0000032481128,0.0000013680119,0.0000023580858],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999299,0.000025853526,0.00035673444,0.000049035385,0.00017372007,0.00009565665],"domain_scores_gemma":[0.9993926,0.00003541625,0.000275525,0.000087361484,0.00015019302,0.000058869184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007701953,0.00006152558,0.00008502426,0.000069961425,0.00007606988,0.00006534848,0.00018834864,0.00002913734,0.0000033897318],"category_scores_gemma":[0.00017568159,0.00003890611,0.000040189963,0.00017055866,0.00009325718,0.000051329083,0.00006599829,0.00008533917,9.858334e-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":[0.00044971608,0.0002804775,0.009586702,0.000529272,0.00011821159,7.498942e-7,0.0032343871,0.05796894,0.5875191,0.0060199113,0.008723673,0.32556885],"study_design_scores_gemma":[0.0010907763,0.00148524,0.0006410944,0.000110871806,0.000024409002,0.000063361105,0.00028012277,0.29593584,0.6580409,0.00007204072,0.042034432,0.0002209003],"about_ca_topic_score_codex":0.0000011786609,"about_ca_topic_score_gemma":1.9491786e-7,"teacher_disagreement_score":0.4355295,"about_ca_system_score_codex":0.000004247327,"about_ca_system_score_gemma":0.00008164295,"threshold_uncertainty_score":0.15865451},"labels":[],"label_agreement":null},{"id":"W2049856614","doi":"10.1109/bibm.2013.6732608","title":"PPI modules detection method through ABC-IFC algorithm","year":2013,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Saskatchewan","funders":"National Science Foundation","keywords":"Cluster analysis; Computer science; Fuzzy clustering; Data mining; Set (abstract data type); Cluster (spacecraft); Correlation clustering; Fuzzy logic; Fuzzy set; CURE data clustering algorithm; Canopy clustering algorithm; Algorithm; Artificial intelligence","score_opus":0.005924938732207405,"score_gpt":0.26793589919875765,"score_spread":0.26201096046655026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049856614","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":[0.029438589,0.00006872036,0.94120646,0.00017048148,0.00016635508,0.00018342237,0.0000024975527,0.000053800413,0.028709708],"genre_scores_gemma":[0.15009637,0.00005554923,0.84382373,0.00088660605,0.00026239417,0.000041994976,0.000060910235,0.000024685109,0.004747732],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992479,0.00005659535,0.00019674534,0.0001882041,0.00010902454,0.00020155152],"domain_scores_gemma":[0.99946845,0.000014044382,0.000071580835,0.00031650183,0.00008049372,0.00004890839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014212157,0.00013424392,0.00010279295,0.000021831156,0.000084602296,0.00004468485,0.00014692043,0.00015447453,0.00029942187],"category_scores_gemma":[0.00007689316,0.000111243135,0.00006869517,0.00006288333,0.000033960157,0.000010011044,0.000101010766,0.000113979084,0.00026022657],"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":[0.000008047317,0.000044969605,0.0002608953,0.000029716432,0.00008231691,5.1523426e-7,0.00015222523,0.00049649685,0.31106636,0.00034566486,0.008207851,0.67930496],"study_design_scores_gemma":[0.000475416,0.00033484044,0.0023264484,0.0000060839734,0.000018237362,0.00005667643,0.00021496545,0.13066247,0.66231084,0.0014614488,0.20173298,0.0003995617],"about_ca_topic_score_codex":0.00022642619,"about_ca_topic_score_gemma":0.00001814166,"teacher_disagreement_score":0.67890537,"about_ca_system_score_codex":0.000008719942,"about_ca_system_score_gemma":0.000012675479,"threshold_uncertainty_score":0.45363632},"labels":[],"label_agreement":null},{"id":"W2050102340","doi":"10.1016/j.peptides.2009.06.035","title":"Codon number shapes peptide redundancy in the universal proteome composition","year":2009,"lang":"en","type":"article","venue":"Peptides","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Saskatchewan","funders":"","keywords":"Pentapeptide repeat; Proteome; Computational biology; Biology; Chemistry; Peptide; Biochemistry","score_opus":0.006952101625538771,"score_gpt":0.25760274183719684,"score_spread":0.25065064021165806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050102340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96560985,0.00004129238,0.000608549,0.0011272614,0.00003130553,0.00025437062,0.000005144052,0.00002093613,0.032301262],"genre_scores_gemma":[0.9952144,0.00002813904,0.0032480217,0.00080549554,0.0001319621,0.00000765077,0.00009125155,0.0000076186816,0.0004654764],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9993075,0.000078995894,0.00016540864,0.0001385601,0.00012946397,0.00018003448],"domain_scores_gemma":[0.99967176,0.00001432321,0.00007112959,0.00018508916,0.000030809173,0.00002688665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021750476,0.00011330048,0.000087128574,0.000026570939,0.000080784215,0.000042310407,0.00022432077,0.00007706602,0.000029782888],"category_scores_gemma":[0.000045023906,0.00008794859,0.00004988002,0.000091437156,0.000050840565,0.000008688571,0.00003178101,0.00015072587,0.000049944472],"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":[0.00058447616,0.00070657284,0.075023144,0.00017319506,0.000088415916,0.00005896655,0.0061119376,0.004098634,0.8480639,0.009049754,0.03976758,0.016273426],"study_design_scores_gemma":[0.0036806825,0.0022388939,0.6820491,0.0003505456,0.00007840109,0.00044493927,0.0026446842,0.00832591,0.073335916,0.0036852101,0.22151601,0.0016497211],"about_ca_topic_score_codex":0.000026259419,"about_ca_topic_score_gemma":0.000023463374,"teacher_disagreement_score":0.774728,"about_ca_system_score_codex":0.000015328424,"about_ca_system_score_gemma":0.000022212464,"threshold_uncertainty_score":0.35864392},"labels":[],"label_agreement":null},{"id":"W2055457958","doi":"10.1145/2147805.2147880","title":"Protein subcellular localization prediction with associative classification and multi-class SVM","year":2011,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Support vector machine; Artificial intelligence; Computer science; Pattern recognition (psychology); Proteome; Class (philosophy); Associative property; Feature vector; Machine learning; Biology; Mathematics; Bioinformatics","score_opus":0.01884088343757109,"score_gpt":0.22266301591914806,"score_spread":0.20382213248157696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055457958","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4948244,0.000039511375,0.4954097,0.000054352702,0.000030185265,0.00046284246,0.0000088397055,0.000051192394,0.009118979],"genre_scores_gemma":[0.97807777,0.000016352174,0.020049052,0.00007907591,0.000030329236,0.000032582204,0.000191249,0.000014571996,0.0015089957],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994318,0.000049450322,0.00014583212,0.00016526078,0.0000974533,0.00011020408],"domain_scores_gemma":[0.99958646,0.0000028178051,0.00011798044,0.00014973996,0.00010026135,0.000042724696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014743974,0.000099096775,0.00006723243,0.0000273842,0.00007516995,0.000017867193,0.000055465356,0.00012508091,0.00001901316],"category_scores_gemma":[0.00006397129,0.00007909744,0.000014811479,0.000060718703,0.000059566686,0.000009200525,0.000030824096,0.0000711557,0.0000070072424],"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":[0.0004213587,0.0004565255,0.59112835,0.00019990132,0.00028367637,0.0000024827016,0.0036187456,0.00026160688,0.38924044,0.0057363315,0.0013755719,0.0072750216],"study_design_scores_gemma":[0.0021607087,0.0014723737,0.15065478,0.000050628783,0.00006360784,0.00001705506,0.0010502484,0.5985951,0.23653542,0.00008727419,0.008821599,0.00049122184],"about_ca_topic_score_codex":0.00003079958,"about_ca_topic_score_gemma":0.000044552376,"teacher_disagreement_score":0.5983335,"about_ca_system_score_codex":0.000015899292,"about_ca_system_score_gemma":0.000024119137,"threshold_uncertainty_score":0.32255},"labels":[],"label_agreement":null},{"id":"W2058021908","doi":"10.1109/cibcb.2006.330972","title":"Prediction of the Number of Helices for the Twilight Zone Proteins","year":2006,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Protein structure prediction; Computer science; Protein secondary structure; Sequence homology; Homology (biology); Multiple sequence alignment; Decision tree; Sequence alignment; Representation (politics); Sequence (biology); Algorithm; Protein structure; Artificial intelligence; Data mining; Peptide sequence; Biology; Genetics","score_opus":0.00664770665033651,"score_gpt":0.23595576507407728,"score_spread":0.22930805842374077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058021908","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9149924,0.00014109885,0.061623096,0.0006718733,0.00015598298,0.0008555798,0.000070114555,0.00001121754,0.021478632],"genre_scores_gemma":[0.9917046,0.000008542069,0.0037154185,0.00005714242,0.000102331636,0.000028800434,0.000023342618,0.0000057167717,0.004354109],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99960226,0.000015299145,0.00017644392,0.000055838886,0.0000831502,0.00006700447],"domain_scores_gemma":[0.9995408,0.000017691735,0.00012647647,0.00024128113,0.000067708155,0.0000060245848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013045745,0.00005050659,0.000053794018,0.000005090202,0.000044729382,0.0000039552324,0.00015118843,0.000053604002,0.000024630179],"category_scores_gemma":[0.000045652385,0.000024784484,0.000067141555,0.000040749142,0.00006622598,0.0000014737069,0.000051437142,0.00003330069,0.0000010517521],"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":[0.000120562,0.00018085202,0.11482802,0.00033731136,0.00013942916,2.7303022e-8,0.00017500574,0.002078103,0.85180676,0.0074738655,0.02016916,0.0026909127],"study_design_scores_gemma":[0.0003517081,0.000098314864,0.026354278,0.000013294426,0.000027731972,0.0000045781026,0.000059530536,0.004189083,0.87624115,0.00012764634,0.09247998,0.000052701387],"about_ca_topic_score_codex":0.0000894303,"about_ca_topic_score_gemma":0.000049532307,"teacher_disagreement_score":0.088473745,"about_ca_system_score_codex":0.000002074814,"about_ca_system_score_gemma":0.00001833288,"threshold_uncertainty_score":0.10106819},"labels":[],"label_agreement":null},{"id":"W2059926522","doi":"10.1016/j.bbrc.2007.02.040","title":"Prediction of protein crystallization using collocation of amino acid pairs","year":2007,"lang":"en","type":"article","venue":"Biochemical and Biophysical Research Communications","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":118,"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":"In silico; Protein crystallization; Naive Bayes classifier; Computer science; Crystallization; Classifier (UML); Sequence (biology); Protein Data Bank (RCSB PDB); Artificial intelligence; Threading (protein sequence); Protein sequencing; Peptide sequence; Computational biology; Pattern recognition (psychology); Protein structure; Algorithm; Chemistry; Biology; Biochemistry; Support vector machine","score_opus":0.07206198932686944,"score_gpt":0.3613267705409309,"score_spread":0.2892647812140614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059926522","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98611754,0.00028906885,0.0124622835,0.00013452105,0.000008086823,0.00030820962,0.00003487421,0.000008192904,0.00063724304],"genre_scores_gemma":[0.9856464,0.0001356985,0.013872559,0.0000070964493,0.000043335855,0.0000111764475,0.00023286109,0.000008203447,0.000042641004],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99895954,0.00011393715,0.00033137883,0.00013444945,0.00029131086,0.00016935806],"domain_scores_gemma":[0.9986571,0.00007232353,0.00012176842,0.0006026113,0.00046977348,0.000076435885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077925937,0.00007626984,0.00010994467,0.000085163774,0.000116772695,0.000009660816,0.0003260703,0.00013313704,0.0000029114474],"category_scores_gemma":[0.00065159117,0.00007033968,0.00004305224,0.0003527348,0.0006850079,0.000007915434,0.00031797923,0.0001809006,7.472916e-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":[0.000056379362,0.00017745832,0.0006632044,0.00009572658,0.00001572679,3.2065127e-8,0.00005871607,0.000003353205,0.99578816,0.0016712134,0.00006216107,0.0014078994],"study_design_scores_gemma":[0.00019551632,0.00025104612,0.003100189,0.000061109706,0.000008763617,0.0000014181403,0.00012481361,0.005190875,0.98963886,0.00019300151,0.0011727693,0.00006164497],"about_ca_topic_score_codex":0.00004066433,"about_ca_topic_score_gemma":0.0000046720775,"teacher_disagreement_score":0.0061492766,"about_ca_system_score_codex":0.000020946094,"about_ca_system_score_gemma":0.00007054573,"threshold_uncertainty_score":0.28683686},"labels":[],"label_agreement":null},{"id":"W2065433699","doi":"10.1016/j.ijar.2010.05.003","title":"Aggregating multiple classification results using fuzzy integration and stochastic feature selection","year":2010,"lang":"en","type":"article","venue":"International Journal of Approximate Reasoning","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"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; National Research Council Canada","funders":"","keywords":"Curse of dimensionality; Pattern recognition (psychology); Classifier (UML); Artificial intelligence; Feature selection; Computer science; Fuzzy logic; Feature vector; Random subspace method; Machine learning; Data mining; Mathematics","score_opus":0.011142645037555509,"score_gpt":0.2845943143249133,"score_spread":0.27345166928735776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065433699","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91021305,0.000045002515,0.08851548,0.00024523798,0.0005073476,0.00007403048,0.000007756741,0.000009432254,0.00038264386],"genre_scores_gemma":[0.88876677,0.000018317141,0.11053464,0.000038118596,0.00054129906,0.0000012575845,0.000053686043,0.000013467997,0.000032439744],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991026,0.000037026282,0.00036047137,0.0001282476,0.00026003184,0.000111635716],"domain_scores_gemma":[0.99856347,0.000041918272,0.000734583,0.00008533562,0.0005246804,0.000050037408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005531378,0.00011367173,0.00010543255,0.000121572026,0.00008730701,0.00011589696,0.0001717551,0.00013313543,0.000002001657],"category_scores_gemma":[0.0019520266,0.00010090774,0.000052761425,0.000064975735,0.00004430977,0.000037241087,0.00005494645,0.00041340114,5.804384e-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":[0.00037224617,0.000035910012,0.0049037896,0.000011650552,0.00009306791,0.000002380492,0.0003774521,0.0041535166,0.9661765,0.0005901675,0.00014654566,0.023136783],"study_design_scores_gemma":[0.0017081607,0.00020453295,0.008745562,0.00028991848,0.000043412325,0.0019287687,0.00044991012,0.93920356,0.045843184,0.00019309547,0.0011393718,0.00025054952],"about_ca_topic_score_codex":0.000011621155,"about_ca_topic_score_gemma":0.00002092397,"teacher_disagreement_score":0.93505,"about_ca_system_score_codex":0.000031990574,"about_ca_system_score_gemma":0.00006541397,"threshold_uncertainty_score":0.4114898},"labels":[],"label_agreement":null},{"id":"W2065475447","doi":"10.1016/j.cjca.2011.07.208","title":"280 Proteomic profiling of mouse and human cardiac membrane proteins reveals novel cardiac proteins","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Toronto Public Health","funders":"","keywords":"Proteomics; Cell biology; Cell; Membrane protein; Myocyte; Medicine; Biology; Biochemistry; Gene; Membrane","score_opus":0.015047178703112046,"score_gpt":0.22937477544380178,"score_spread":0.21432759674068974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065475447","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9914364,0.0006434768,0.0019886182,0.000050994044,0.00024974506,0.0008482625,0.0001249549,0.0000049447845,0.0046525807],"genre_scores_gemma":[0.98752654,0.00005708851,0.011558116,0.000035908855,0.0005413659,0.000031353728,0.000031642656,0.00003640507,0.00018156375],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99840814,0.00020884418,0.0006489653,0.00020066464,0.00013016128,0.0004032513],"domain_scores_gemma":[0.9983568,0.000010906558,0.000523546,0.00038457327,0.00032980338,0.00039432256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009352276,0.00022053173,0.0006728281,0.00021410327,0.00011642162,0.000015371877,0.00031549306,0.00030371948,0.00000578084],"category_scores_gemma":[0.00033735856,0.00020331866,0.00026806482,0.000085486725,0.0003411959,0.000013760805,0.000057783698,0.00036106887,0.0000016655193],"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":[0.00006136538,0.000005222165,0.091121756,0.00016108641,0.0004781696,0.00000848576,0.00027452683,0.0001684529,0.90635186,0.000697565,0.0003704496,0.00030105666],"study_design_scores_gemma":[0.0013646547,0.0023284627,0.043631747,0.00013500029,0.00027901362,0.00025524915,0.00028682555,0.000014449404,0.9261927,0.00015617293,0.024706649,0.00064904976],"about_ca_topic_score_codex":0.0009095943,"about_ca_topic_score_gemma":0.00013794687,"teacher_disagreement_score":0.047490012,"about_ca_system_score_codex":0.000041821404,"about_ca_system_score_gemma":0.00065662916,"threshold_uncertainty_score":0.82910943},"labels":[],"label_agreement":null},{"id":"W2065795346","doi":"10.1093/nar/gkn619","title":"Protein networks markedly improve prediction of subcellular localization in multiple eukaryotic species","year":2008,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"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":"Korea Advanced Institute of Science and Technology; National Chiao Tung University; National Institute of General Medical Sciences; McGill University","keywords":"Biology; Subcellular localization; Protein subcellular localization prediction; Computational biology; Genetics; Evolutionary biology; Gene","score_opus":0.027051962449133493,"score_gpt":0.27061037833991736,"score_spread":0.24355841589078386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065795346","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97561085,0.00018439784,0.02059654,0.000050984996,0.00006559394,0.0006043176,0.000013033231,0.00001660517,0.0028576916],"genre_scores_gemma":[0.9962271,0.00018560831,0.0012209537,0.00001827548,0.00014799215,0.000032876946,0.00016956746,0.00002620348,0.0019714364],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983441,0.0002433994,0.00036464978,0.00024052952,0.00044183026,0.00036546442],"domain_scores_gemma":[0.99918544,0.0000338401,0.00008074248,0.00040085343,0.00023132212,0.00006781825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091677153,0.000118488846,0.00014695572,0.00016454728,0.00014042894,0.000015251161,0.00026276684,0.00023040191,0.0000566925],"category_scores_gemma":[0.00069103343,0.000115606315,0.00005095622,0.00037258846,0.00032046356,0.000011185981,0.00020542777,0.00038308563,0.000012911573],"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":[0.00041035988,0.00020840083,0.53602314,0.0002292832,0.0000351451,0.000013854398,0.00045093495,0.014676515,0.44302458,0.00018467572,0.0030625137,0.0016805948],"study_design_scores_gemma":[0.001636107,0.0011340086,0.15791745,0.000098730365,0.0000052468263,0.00001930408,0.00026084087,0.71046627,0.11341443,0.00005260619,0.014752144,0.00024286676],"about_ca_topic_score_codex":0.00007297443,"about_ca_topic_score_gemma":0.000026963775,"teacher_disagreement_score":0.69578975,"about_ca_system_score_codex":0.000051006125,"about_ca_system_score_gemma":0.00008931385,"threshold_uncertainty_score":0.47142887},"labels":[],"label_agreement":null},{"id":"W2068235693","doi":"10.1007/s00453-007-0062-y","title":"Rapid Homology Search with Neighbor Seeds","year":2007,"lang":"en","type":"article","venue":"Algorithmica","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Western University; Université de Montréal","funders":"","keywords":"Extension (predicate logic); Computer science; Theory of computation; Sensitivity (control systems); Flexibility (engineering); Speedup; Data mining; Theoretical computer science; Mathematics; Algorithm; Parallel computing; Statistics; Programming language; Engineering","score_opus":0.006735526569220527,"score_gpt":0.24887424455147955,"score_spread":0.24213871798225903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068235693","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8016676,0.00041349858,0.15136765,0.0006005662,0.00023992438,0.0003234673,0.000016213711,0.000078101184,0.045292985],"genre_scores_gemma":[0.9490366,0.00005559478,0.047831763,0.0007549099,0.00044333423,0.000006134883,0.00015328587,0.000037454203,0.001680944],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99897945,0.000037183116,0.00019318696,0.00021840775,0.00016605716,0.00040571994],"domain_scores_gemma":[0.9993365,0.00002830879,0.000057085294,0.00037526301,0.00009000155,0.00011287174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042818385,0.00014965175,0.00012515081,0.000067994624,0.0000868893,0.000018531695,0.00023243057,0.0001609665,0.00007573036],"category_scores_gemma":[0.00004012848,0.00012305868,0.000045442146,0.00013699828,0.00014218467,0.0000034484049,0.00011267216,0.00020947099,0.00006933332],"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":[0.0010773509,0.0003746683,0.025200576,0.00012538875,0.00061427295,0.0001804081,0.0010698143,0.00033952828,0.12533265,0.002811386,0.01155386,0.8313201],"study_design_scores_gemma":[0.0025060496,0.003279891,0.031480316,0.000024623145,0.00005651111,0.0009265078,0.0004418969,0.0043024835,0.35364875,0.000075101416,0.6023157,0.0009421537],"about_ca_topic_score_codex":0.000022247186,"about_ca_topic_score_gemma":0.000014296426,"teacher_disagreement_score":0.83037794,"about_ca_system_score_codex":0.000013149022,"about_ca_system_score_gemma":0.0000648314,"threshold_uncertainty_score":0.5018187},"labels":[],"label_agreement":null},{"id":"W2068590600","doi":"10.1145/2506583.2506664","title":"Co-occurrence Clusters of Aligned Pattern Clusters","year":2013,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Closeness; Protein family; Cluster analysis; Computational biology; Triosephosphate isomerase; Set (abstract data type); Sequence (biology); Computer science; Biology; Bioinformatics; Data mining; Genetics; Artificial intelligence; Mathematics","score_opus":0.006602362976867471,"score_gpt":0.25335274303296473,"score_spread":0.24675038005609726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068590600","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9225886,0.000036088342,0.048522763,0.00045501522,0.00018991332,0.0003797838,0.000046477522,0.000031164007,0.027750222],"genre_scores_gemma":[0.9955605,0.000015931393,0.0023137014,0.001026068,0.0000355862,0.000012110742,0.00026627115,0.000008521169,0.0007612692],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99926054,0.00003470073,0.00025679925,0.00014166825,0.00012414722,0.00018212345],"domain_scores_gemma":[0.9994083,0.000013794276,0.00012102672,0.0003223,0.00006777636,0.00006678352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010426852,0.00011728686,0.00011510567,0.000033171753,0.000029148416,0.000018650891,0.00022878898,0.000093301496,0.00032697222],"category_scores_gemma":[0.000054016098,0.00009898905,0.000062097446,0.00004204828,0.00007891115,0.000005086493,0.00007662327,0.000046992107,0.00011418498],"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":[0.00007346679,0.00022732877,0.14200667,0.0005720314,0.00027449435,0.0000018524026,0.001144128,0.0017542756,0.38349473,0.00009094312,0.38526118,0.08509891],"study_design_scores_gemma":[0.0045263637,0.0023517255,0.03453595,0.0001348657,0.000084813204,0.00008328359,0.0020338525,0.08277392,0.75000757,0.00009940314,0.121306114,0.0020621254],"about_ca_topic_score_codex":0.00008469707,"about_ca_topic_score_gemma":0.00000968238,"teacher_disagreement_score":0.36651286,"about_ca_system_score_codex":0.00000519468,"about_ca_system_score_gemma":0.00002330438,"threshold_uncertainty_score":0.4036656},"labels":[],"label_agreement":null},{"id":"W2069116068","doi":"10.1145/507515.507523","title":"KDD Cup 2001 report","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":110,"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 Imperial Bank of Commerce (Canada)","funders":"National Science Foundation","keywords":"Computer science; Artificial intelligence","score_opus":0.036488664020318924,"score_gpt":0.2723488489952492,"score_spread":0.23586018497493028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069116068","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7355424,0.0005940037,0.07506728,0.08697352,0.0016001891,0.0010883351,0.000041328065,0.0003766677,0.09871628],"genre_scores_gemma":[0.8407871,0.00028310943,0.07345465,0.030205922,0.0025736927,0.00024618025,0.0014647548,0.00013035248,0.050854214],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99880004,0.000052260035,0.0003749913,0.00028072676,0.00018537603,0.0003065941],"domain_scores_gemma":[0.99839246,0.00002402311,0.00014123751,0.001262724,0.00008701246,0.00009253453],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016167008,0.00018139447,0.00012631327,0.00006850316,0.00016187633,0.00006956306,0.00037789042,0.00014248744,0.00084254483],"category_scores_gemma":[0.00073968334,0.00017424223,0.000090639194,0.00014947445,0.000066991735,0.000023387242,0.00020325785,0.00017802163,0.0009980784],"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":[0.000005581297,0.00005974116,0.0043858495,0.00000917409,0.00003892383,0.0000332745,0.00023332766,0.0003191782,0.035700895,0.000060126982,0.95732206,0.0018318591],"study_design_scores_gemma":[0.00034279499,0.000097095464,0.0007456791,0.000007566597,0.000020352216,0.00022152599,0.00006188864,0.0016102843,0.011487916,0.000107467116,0.98497504,0.00032240042],"about_ca_topic_score_codex":0.000009239325,"about_ca_topic_score_gemma":0.000013544336,"teacher_disagreement_score":0.10524473,"about_ca_system_score_codex":0.000014520348,"about_ca_system_score_gemma":0.000017796963,"threshold_uncertainty_score":0.99977976},"labels":[],"label_agreement":null},{"id":"W2074156599","doi":"10.1142/9789812776136_0058","title":"EPILOC: A (WORKING) TEXT-BASED SYSTEM FOR PREDICTING PROTEIN SUBCELLULAR LOCATION","year":2007,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":74,"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":"Computer science; Artificial intelligence","score_opus":0.00840131759235885,"score_gpt":0.2408423958874599,"score_spread":0.23244107829510105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074156599","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23941137,0.00008565042,0.753072,0.000092002265,0.00011144688,0.00075828197,0.0000028018865,0.000085155785,0.0063812924],"genre_scores_gemma":[0.9616334,3.747686e-7,0.036843855,0.00012437024,0.00026832655,0.000053765445,0.00017833627,0.00002499726,0.00087261683],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99905,0.000024356665,0.0003203788,0.00019838952,0.00013236972,0.00027450034],"domain_scores_gemma":[0.99933046,0.000027732627,0.0001563867,0.00028989933,0.00012914799,0.000066385626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087112933,0.0001344718,0.000103315404,0.000049698912,0.00011577681,0.000029598063,0.00014921388,0.00016205871,0.0000052776127],"category_scores_gemma":[0.00022719594,0.00012203471,0.000064434644,0.00010308264,0.000028909355,0.000002325762,0.000035441346,0.000084533545,0.000010139511],"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":[0.0006727964,0.00014572438,0.026675265,0.0019177945,0.00014901241,0.0000044388157,0.00015967125,0.0068663177,0.9403035,0.0053827018,0.0015024003,0.016220385],"study_design_scores_gemma":[0.0011481314,0.00050180935,0.0006366537,0.00015029166,0.000030988936,0.000012375259,0.00026447442,0.10007783,0.8513375,0.000013292087,0.045504227,0.00032244605],"about_ca_topic_score_codex":0.000019003877,"about_ca_topic_score_gemma":0.000025629184,"teacher_disagreement_score":0.722222,"about_ca_system_score_codex":0.00003290542,"about_ca_system_score_gemma":0.00006166938,"threshold_uncertainty_score":0.4976431},"labels":[],"label_agreement":null},{"id":"W2076460489","doi":"10.1186/1471-2105-10-414","title":"Modular prediction of protein structural classes from sequences of twilight-zone identity with predicting sequences","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":96,"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; Benchmark (surveying); Artificial intelligence; Support vector machine; Modular design; Similarity (geometry); Feature selection; Feature (linguistics); Pattern recognition (psychology); Class (philosophy); Sequence (biology); Contrast (vision); Data mining; Machine learning; Biology; Image (mathematics)","score_opus":0.01020080503328411,"score_gpt":0.24509219230986357,"score_spread":0.23489138727657946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076460489","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9133903,0.00019522218,0.08507766,0.00002325013,0.000066739645,0.00035809082,0.00019072679,0.000035362697,0.00066265016],"genre_scores_gemma":[0.80102205,0.000023608547,0.19853556,0.000029027326,0.00007373931,0.000005596295,0.00026921634,0.000008730897,0.000032473537],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982685,0.000049988237,0.0008198606,0.00015668826,0.00047536715,0.00022963212],"domain_scores_gemma":[0.99845505,0.000022830945,0.00080628664,0.00042990793,0.00021613693,0.00006977116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026419133,0.00022409607,0.00029418227,0.00008533739,0.000085494205,0.000045738103,0.00038162945,0.00018736244,0.000016100877],"category_scores_gemma":[0.000168725,0.00017295529,0.00008682906,0.00019235836,0.0002107022,0.00011408436,0.000080432925,0.00015757293,0.0000021523144],"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":[0.00050312,0.00013929702,0.24394216,0.0016667115,0.00031400358,0.0000023341172,0.0031564247,0.044262934,0.6989824,0.0015064604,0.00013263163,0.0053915],"study_design_scores_gemma":[0.0014770943,0.0026960147,0.08932839,0.0005441598,0.00014253272,0.00004517549,0.002105898,0.42936525,0.4725552,0.0008788293,0.00033870013,0.0005227565],"about_ca_topic_score_codex":0.00009971873,"about_ca_topic_score_gemma":0.000071660375,"teacher_disagreement_score":0.38510233,"about_ca_system_score_codex":0.000019330751,"about_ca_system_score_gemma":0.00016822964,"threshold_uncertainty_score":0.7052912},"labels":[],"label_agreement":null},{"id":"W2076666663","doi":"10.1186/1742-4690-5-110","title":"HIV-1 coreceptor usage prediction without multiple alignments: an application of string kernels","year":2008,"lang":"en","type":"article","venue":"Retrovirology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Centre hospitalier de l'Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Support vector machine; Computer science; String kernel; Human immunodeficiency virus (HIV); Classifier (UML); CXCR4; Artificial intelligence; Kernel (algebra); String (physics); Computational biology; Machine learning; Bioinformatics; Kernel method; Biology; Radial basis function kernel; Virology; Chemokine; Mathematics; Genetics; Combinatorics; Receptor","score_opus":0.009683524912007248,"score_gpt":0.24471393130649868,"score_spread":0.23503040639449144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076666663","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93165815,0.000035912177,0.06747454,0.00001834475,0.000080169695,0.00018538385,0.000044723733,0.000026592272,0.00047617158],"genre_scores_gemma":[0.9947369,0.000064128406,0.0041158963,0.000098839955,0.00015000497,0.000021725422,0.00056444417,0.000018142522,0.0002298939],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991129,0.00007516948,0.0002876567,0.0002227434,0.0001214071,0.00018013937],"domain_scores_gemma":[0.9992964,0.000013849111,0.00020672625,0.0003732292,0.000048118825,0.00006162266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015281975,0.000117657786,0.00015507832,0.000048122194,0.00007044247,0.0000032549997,0.00017318528,0.00020204627,0.000019667308],"category_scores_gemma":[0.00011126376,0.00011853887,0.000044361102,0.000055467317,0.00013333315,0.000008666417,0.00007198902,0.00010989032,0.000018623934],"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":[0.00008190516,0.000054271062,0.62727845,0.0000145616605,0.000023693947,3.4091232e-7,0.000101723206,0.0009740302,0.37033132,0.000039116443,0.00021828018,0.0008822873],"study_design_scores_gemma":[0.0033754972,0.0033706117,0.5515557,0.000014311906,0.0000651949,0.00019661247,0.00013733612,0.09669944,0.29240286,0.000049702634,0.05160529,0.0005274583],"about_ca_topic_score_codex":0.000028007049,"about_ca_topic_score_gemma":0.000006394939,"teacher_disagreement_score":0.09572541,"about_ca_system_score_codex":0.000017896713,"about_ca_system_score_gemma":0.000026492138,"threshold_uncertainty_score":0.48338747},"labels":[],"label_agreement":null},{"id":"W2076871417","doi":"10.1016/j.biosystems.2013.03.022","title":"Sequence classification with side effect machines evolved via ring optimization","year":2013,"lang":"en","type":"article","venue":"Biosystems","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Guelph","funders":"","keywords":"Classifier (UML); Computer science; Artificial intelligence; Machine learning; Support vector machine; Evolutionary algorithm","score_opus":0.008665865590123832,"score_gpt":0.23719178889368753,"score_spread":0.2285259233035637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076871417","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88724893,0.00013769501,0.10571942,0.0001336394,0.00020906777,0.0008403235,0.0000058332384,0.0000924511,0.005612634],"genre_scores_gemma":[0.98970217,0.000009438591,0.009404849,0.000055768927,0.00015914539,0.000081120415,0.0002115,0.00002485322,0.00035115366],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991529,0.00008768358,0.0002239836,0.00021261579,0.00014547736,0.00017733937],"domain_scores_gemma":[0.9992882,0.000016211254,0.00017557533,0.00035399353,0.00010344999,0.00006254707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018905576,0.00016164994,0.0001303281,0.000041769796,0.00008704606,0.00007124302,0.00015866083,0.000120389144,0.000020900039],"category_scores_gemma":[0.000074925454,0.000119452925,0.000035886846,0.00009754028,0.000036312565,0.000013952874,0.000040037965,0.00007870525,0.00007215179],"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":[0.000052182753,0.000025454496,0.05880297,0.0003210312,0.00007445554,0.0000011413154,0.000079874575,0.026365967,0.907485,0.000049824255,0.0005874929,0.0061546247],"study_design_scores_gemma":[0.0006731745,0.000575512,0.010366388,0.00010134798,0.000026008147,0.00007507256,0.000043861914,0.940899,0.044399474,0.0000037636055,0.002450818,0.00038555218],"about_ca_topic_score_codex":0.00014683147,"about_ca_topic_score_gemma":0.000015508569,"teacher_disagreement_score":0.9145331,"about_ca_system_score_codex":0.000023893017,"about_ca_system_score_gemma":0.000022487875,"threshold_uncertainty_score":0.48711488},"labels":[],"label_agreement":null},{"id":"W2078685372","doi":"10.1142/9789812702456_0035","title":"DISCOVERING SEQUENCE-STRUCTURE MOTIFS FROM PROTEIN SEGMENTS AND TWO APPLICATIONS","year":2004,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Sequence (biology); Protein secondary structure; Cluster (spacecraft); Protein structure prediction; Structural alignment; Local structure; Protein tertiary structure; Support vector machine; Protein structure; Artificial intelligence; Dynamic programming; Data structure; Data mining; Pattern recognition (psychology); Sequence alignment; Algorithm; Peptide sequence; Biology; Physics; Genetics","score_opus":0.005945630023237146,"score_gpt":0.25484949113161154,"score_spread":0.2489038611083744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078685372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9360245,0.000050798328,0.062099945,0.00010472495,0.000016421236,0.00027080489,0.000052986634,0.000018568226,0.0013612515],"genre_scores_gemma":[0.9525788,0.000008527004,0.04659439,0.00016077154,0.00008532582,0.00002694473,0.00024374292,0.000009898254,0.00029164247],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99953437,0.0000078248495,0.00011301504,0.00016257596,0.00007017555,0.000112063964],"domain_scores_gemma":[0.9996677,0.0000019715596,0.000045230547,0.0002211951,0.000015388137,0.000048481215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00002539362,0.00009545387,0.00006149135,0.000012955374,0.000065684006,0.00003422958,0.00010184202,0.000059032645,0.000025397529],"category_scores_gemma":[0.000014899014,0.000081264356,0.000018062878,0.00003446263,0.000040858024,0.0000049296245,0.00010445557,0.000076313365,0.0000075692956],"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":[0.0000069462253,0.000012791901,0.0035472321,0.000018419749,0.000027080672,4.8610406e-7,0.00011562829,0.0027023864,0.9897489,0.0009224215,0.00002014338,0.0028775965],"study_design_scores_gemma":[0.0017458694,0.0001429912,0.004661247,0.000041860025,0.00002411178,0.000025757252,0.00021676111,0.0016811244,0.9690833,0.0063783466,0.015494323,0.0005042769],"about_ca_topic_score_codex":0.00015950593,"about_ca_topic_score_gemma":0.00009701839,"teacher_disagreement_score":0.020665536,"about_ca_system_score_codex":0.000012308218,"about_ca_system_score_gemma":0.000026006614,"threshold_uncertainty_score":0.33138642},"labels":[],"label_agreement":null},{"id":"W2079209745","doi":"10.1109/iembs.2008.4649416","title":"A two-stage neural network based technique for protein secondary structure prediction","year":2008,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Concordia University","funders":"","keywords":"Artificial neural network; Bin; Computer science; Stage (stratigraphy); Artificial intelligence; Sequence (biology); Protein secondary structure; Protein structure prediction; Multi stage; Pattern recognition (psychology); Machine learning; Algorithm; Protein structure; Engineering","score_opus":0.006535475681913279,"score_gpt":0.23642992325160977,"score_spread":0.2298944475696965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079209745","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50940275,0.00008370713,0.4799205,0.00020538997,0.00020518416,0.0025867424,0.00026913546,0.00014412397,0.00718244],"genre_scores_gemma":[0.8617474,0.0000017090581,0.13411869,0.0006423286,0.00037434697,0.00017651297,0.00067984284,0.000026111791,0.002233084],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992332,0.00003540323,0.00022640848,0.00018725518,0.00008875439,0.00022901523],"domain_scores_gemma":[0.99950176,0.0000069592884,0.00009806468,0.00027869327,0.000060465336,0.000054058284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013039952,0.00014440421,0.00010431681,0.000025755671,0.00015575947,0.0000125119695,0.00013372024,0.00016112569,0.0001165064],"category_scores_gemma":[0.00006254769,0.0001257481,0.000075706426,0.00006312484,0.000052124557,0.0000045951856,0.000047950944,0.00016749055,0.0000012742638],"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":[0.0002614838,0.000032723354,0.0058259717,0.00017145915,0.000040624152,0.000003144682,0.000032023407,0.033573814,0.94219303,0.0003874114,0.016516576,0.000961745],"study_design_scores_gemma":[0.0022230116,0.0012129418,0.0022658699,0.000025333477,0.000017166718,0.000104554136,0.00002104385,0.12519984,0.7229915,0.00015973095,0.14529823,0.0004807717],"about_ca_topic_score_codex":0.000008715445,"about_ca_topic_score_gemma":0.000017867926,"teacher_disagreement_score":0.3523446,"about_ca_system_score_codex":0.000009914397,"about_ca_system_score_gemma":0.000091749505,"threshold_uncertainty_score":0.5127859},"labels":[],"label_agreement":null},{"id":"W2081199076","doi":"10.1016/j.ygcen.2014.03.002","title":"Evolution of receptors for peptides similar to glucagon","year":2014,"lang":"en","type":"review","venue":"General and Comparative Endocrinology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Luonnontieteiden ja Tekniikan Tutkimuksen Toimikunta; Canadian Institutes of Health Research","keywords":"Biology; Subfamily; Gene; Receptor; Phylogenetic tree; Vertebrate; Glucagon receptor; Genetics; Phylogenetics; Glucagon-like peptide-1; Glucagon; Biochemistry; Endocrinology; Hormone","score_opus":0.046136913205323773,"score_gpt":0.35181396676301874,"score_spread":0.305677053557695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081199076","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":[0.005353955,0.98517114,0.007411634,0.00003094284,0.00039002538,0.0008258726,0.00010124219,0.000013936439,0.0007012247],"genre_scores_gemma":[0.0014668402,0.9842074,0.010868955,0.000095911055,0.0006104646,0.00027147666,0.00060160103,0.000027698978,0.0018496497],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99859506,0.00016361885,0.0004895678,0.00034761245,0.000064748,0.00033941088],"domain_scores_gemma":[0.9991907,0.00005372918,0.00030907828,0.00027111714,0.000101204256,0.00007418109],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00010879504,0.0003166058,0.0010777342,0.00008544111,0.000077723766,0.000009141841,0.00022291605,0.0002019385,0.000006621545],"category_scores_gemma":[0.00007778233,0.0002576608,0.00022214378,0.00007980285,0.00011512066,0.0000021086282,0.00021099456,0.00014117525,0.000012469002],"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":[0.00020554864,0.00011320637,0.00019638156,0.012146511,0.00086351606,9.0637474e-7,0.00047711786,0.0006297391,0.0015442859,0.016783938,0.034697175,0.9323417],"study_design_scores_gemma":[0.00020369937,0.00082863535,0.000019662117,0.00022682988,0.00009685494,0.000027743112,0.000039087685,0.00010786161,0.00049324625,0.000045318404,0.99765104,0.00026002387],"about_ca_topic_score_codex":0.00001363211,"about_ca_topic_score_gemma":0.000026153277,"teacher_disagreement_score":0.96295387,"about_ca_system_score_codex":0.00002425742,"about_ca_system_score_gemma":0.000066724264,"threshold_uncertainty_score":0.99998754},"labels":[],"label_agreement":null},{"id":"W2081862209","doi":"10.1371/journal.pone.0046302","title":"Prediction of Protein Phosphorylation Sites by Using the Composition of k-Spaced Amino Acid Pairs","year":2012,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":61,"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":"People's Government of Jilin Province; National Natural Science Foundation of China; Natural Science Foundation of Jilin Province","keywords":"Phosphorylation; Protein phosphorylation; Threonine; Serine; Computational biology; Amino acid; Tyrosine phosphorylation; Biology; Benchmark (surveying); Sensitivity (control systems); Biochemistry; Bioinformatics; Computer science; Protein kinase A; Engineering","score_opus":0.02784102342915666,"score_gpt":0.22906347831187376,"score_spread":0.20122245488271712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081862209","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99531806,0.00031514213,0.0038043053,0.00004004313,0.000010741204,0.00025486777,0.000035563015,0.000007665656,0.00021361605],"genre_scores_gemma":[0.993602,0.000013762326,0.005946089,0.000016180098,0.000054262287,0.000008075183,0.00030524196,0.000008121402,0.00004626618],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994753,0.000048837617,0.00017705004,0.00005462193,0.00015048984,0.00009368581],"domain_scores_gemma":[0.99954027,0.0000066022444,0.00019856749,0.00016029655,0.00007309811,0.000021144664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017409465,0.000062818435,0.000085694795,0.000016266833,0.000040200484,0.0000039866895,0.000060674603,0.000072515504,0.0000120998675],"category_scores_gemma":[0.000056065048,0.00005104478,0.0000277264,0.000050193194,0.00005001304,0.0000078449,0.0000337535,0.00005898954,0.0000011184642],"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":[0.000031781594,0.00022465836,0.027226446,0.000095608884,0.000060974995,5.9464096e-9,0.00018243791,0.000048614107,0.97192186,0.000014688332,0.000078059915,0.00011489029],"study_design_scores_gemma":[0.0001579932,0.00014265024,0.0037252537,0.00004261907,0.00004934283,6.0896735e-7,0.000049992195,0.0075563686,0.98817044,0.0000033975473,0.000056468903,0.000044853874],"about_ca_topic_score_codex":0.000009720837,"about_ca_topic_score_gemma":5.4915506e-7,"teacher_disagreement_score":0.023501193,"about_ca_system_score_codex":0.000009349889,"about_ca_system_score_gemma":0.000008807422,"threshold_uncertainty_score":0.20815456},"labels":[],"label_agreement":null},{"id":"W2085102470","doi":"10.1186/1471-2164-15-50","title":"Prediction of bacterial type IV secreted effectors by C-terminal features","year":2014,"lang":"en","type":"article","venue":"BMC Genomics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Institutes of Health; National Natural Science Foundation of China","keywords":"Effector; Biology; Computational biology; Secretion; DNA microarray; Gene; Genetics; Gene expression; Cell biology; Biochemistry","score_opus":0.006200473368906618,"score_gpt":0.21760591700493143,"score_spread":0.21140544363602481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085102470","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9953283,0.000057818528,0.0031595211,0.0000057582465,0.00041011994,0.000112477166,0.00005369203,0.000012966554,0.0008593633],"genre_scores_gemma":[0.994257,0.000020253154,0.0038826207,0.000042590862,0.00035269756,0.0000030391648,0.001042437,0.000018956413,0.00038044763],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994344,0.00006281871,0.00017967026,0.00012729128,0.00007044895,0.00012537919],"domain_scores_gemma":[0.9995329,0.000016996382,0.00012338429,0.00023850764,0.000044317174,0.000043919274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016100031,0.000106262436,0.00011319621,0.000022379858,0.00003379239,0.000014273994,0.0001349395,0.00015157637,0.000023866234],"category_scores_gemma":[0.00016612625,0.00010127851,0.000048795067,0.000034767498,0.000040807012,0.0000022661816,0.00006546956,0.00007539165,0.000008195343],"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":[0.00018698965,0.000015291711,0.009257592,0.000074413954,0.00002216007,6.926103e-8,0.00007051454,0.00020318528,0.98100084,0.000021109292,0.008251247,0.0008965834],"study_design_scores_gemma":[0.0019053059,0.0020272944,0.03909225,0.00002668862,0.00008258614,0.00004632178,0.000049739003,0.010573872,0.65549415,0.000034358476,0.29024217,0.00042523834],"about_ca_topic_score_codex":0.000009294056,"about_ca_topic_score_gemma":0.000010724928,"teacher_disagreement_score":0.3255067,"about_ca_system_score_codex":0.000011406899,"about_ca_system_score_gemma":0.000040093364,"threshold_uncertainty_score":0.41300178},"labels":[],"label_agreement":null},{"id":"W2087292186","doi":"10.1016/j.jalz.2012.05.2088","title":"P3‐414: Evaluation of a novel caspase‐6 inhibitor as a potential treatment for Alzheimer's disease","year":2012,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"New World Laboratories; McGill University","funders":"","keywords":"Caspase; Caspase 3; Molecular biology; Pharmacology; Cell culture; Apoptosis; Caspase-9; Recombinant DNA; Biology; Chemistry; Biochemistry; Programmed cell death; Genetics","score_opus":0.04054360114923575,"score_gpt":0.3275515882479689,"score_spread":0.2870079870987331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087292186","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.837581,0.14474386,0.011258004,0.0003470969,0.0013561259,0.0029730764,0.00032365546,0.000047999034,0.0013692081],"genre_scores_gemma":[0.9902819,0.000045508117,0.007864781,0.0001472917,0.00052584434,0.00024869925,0.0008347799,0.00003737162,0.000013854106],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99853,0.000073413314,0.0003911825,0.0002436565,0.00038076763,0.0003810144],"domain_scores_gemma":[0.9988281,0.000015184344,0.0002595724,0.00044045437,0.00024626817,0.00021041169],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053043023,0.00024395394,0.00018150188,0.000058770725,0.000107474545,0.000022174885,0.0001544666,0.00011481844,0.00011198331],"category_scores_gemma":[0.00008976169,0.00022483554,0.00020765612,0.00006156212,0.00006382109,0.000019939782,0.00009712322,0.000047477788,0.000023904468],"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":[0.0034483448,0.0075800857,0.025580619,0.0000979159,0.0743799,0.0000037540076,0.0019668827,0.008683593,0.38197073,0.0020145932,0.019195404,0.47507817],"study_design_scores_gemma":[0.014432011,0.0030852023,0.014280274,0.000053564556,0.13357626,0.00004835402,0.00030710892,0.06248435,0.6645622,0.00013687686,0.10548563,0.0015481429],"about_ca_topic_score_codex":0.00006800708,"about_ca_topic_score_gemma":0.000011953777,"teacher_disagreement_score":0.47353002,"about_ca_system_score_codex":0.000009027641,"about_ca_system_score_gemma":0.00018936594,"threshold_uncertainty_score":0.9168528},"labels":[],"label_agreement":null},{"id":"W2089818979","doi":"10.1109/tcbb.2011.142","title":"Clustering 100,000 Protein Structure Decoys in Minutes","year":2011,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Pairwise comparison; Computer science; Cluster (spacecraft); Centroid; Benchmark (surveying); Pruning; Data mining; Hierarchical clustering; Pattern recognition (psychology); Single-linkage clustering; Selection (genetic algorithm); Artificial intelligence; Algorithm; Correlation clustering; CURE data clustering algorithm","score_opus":0.016451781770014207,"score_gpt":0.26122310253236625,"score_spread":0.24477132076235203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089818979","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44038218,0.000043360098,0.55779624,0.000112944275,0.0002106376,0.00035197038,0.00015998248,0.000035770874,0.0009069408],"genre_scores_gemma":[0.810431,0.000021547126,0.18889764,0.00034198747,0.00003293657,0.000017172326,0.00015368756,0.000011211649,0.0000927952],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998974,0.000053592892,0.00045180356,0.00018277216,0.00009199932,0.00024583627],"domain_scores_gemma":[0.99945384,0.000048529364,0.00013427464,0.00022617253,0.000062975254,0.000074201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015055078,0.00021533744,0.00017476761,0.0001848017,0.00014975524,0.000021832064,0.0002201614,0.0002742813,0.00007286448],"category_scores_gemma":[0.000040587314,0.00019151736,0.00005475435,0.00013557983,0.00015820429,0.000021127173,0.000020007892,0.0002676917,0.000013674696],"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":[0.0031476032,0.0016760972,0.03991342,0.0019506786,0.0012723643,0.000027867727,0.017190317,0.30748644,0.050076816,0.0040782173,0.0014544955,0.57172567],"study_design_scores_gemma":[0.0075188563,0.005385405,0.03690185,0.00040329373,0.0001332171,0.00067991856,0.00174342,0.83996695,0.07625045,0.02023981,0.007874131,0.0029027085],"about_ca_topic_score_codex":0.000026259728,"about_ca_topic_score_gemma":0.00011168031,"teacher_disagreement_score":0.568823,"about_ca_system_score_codex":0.000016511693,"about_ca_system_score_gemma":0.000052671272,"threshold_uncertainty_score":0.7809852},"labels":[],"label_agreement":null},{"id":"W2097411884","doi":"10.5376/cmb.2012.02.0001","title":"Computational Prediction of Protein Subcellular Locations in Eukaryotes: an Experience Report","year":2012,"lang":"en","type":"article","venue":"Computational Molecular Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Signal peptide; Endoplasmic reticulum; Proteome; Transmembrane protein; Computational biology; Subcellular localization; Secretory protein; Protein targeting; Secretory pathway; Protein Sorting Signals; Computational model; Computer science; Membrane protein; Biology; Cell biology; Bioinformatics; Biochemistry; Secretion; Peptide sequence; Golgi apparatus; Artificial intelligence; Membrane; Gene; Cytoplasm","score_opus":0.012283655641426451,"score_gpt":0.2999240799302989,"score_spread":0.28764042428887243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097411884","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60644937,0.00016986176,0.39280304,0.000044444627,0.0000706038,0.00018835274,0.000025266861,0.000012163341,0.00023686893],"genre_scores_gemma":[0.9438656,0.0000011123337,0.052580245,0.00011464542,0.00007480443,0.00005307151,0.0032696861,0.000015645712,0.000025166077],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99866295,0.00017059242,0.000518344,0.0002475317,0.00016187063,0.0002387333],"domain_scores_gemma":[0.9992211,0.000024981215,0.00022530717,0.00025597695,0.00018303482,0.000089609755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033903858,0.00014654877,0.0001540925,0.00013004287,0.000053033607,0.000007896431,0.0001816819,0.00016197366,0.000020171748],"category_scores_gemma":[0.00022190438,0.00015717225,0.00005684623,0.00016964247,0.00017891223,0.000013610212,0.0000858198,0.00011570502,0.0000066454327],"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":[0.000067107525,0.0005115247,0.3102756,0.000058729544,0.000064598375,0.0000104876535,0.00073596707,0.41900453,0.2318205,0.03631828,0.000045756144,0.0010869075],"study_design_scores_gemma":[0.0032811717,0.0019735398,0.46816772,0.00012144927,0.00005391611,0.0010820988,0.0006265351,0.39768264,0.054525405,0.06665672,0.004511581,0.0013171968],"about_ca_topic_score_codex":0.000022050068,"about_ca_topic_score_gemma":0.0000023535758,"teacher_disagreement_score":0.3402228,"about_ca_system_score_codex":0.000023904044,"about_ca_system_score_gemma":0.00011680009,"threshold_uncertainty_score":0.6409299},"labels":[],"label_agreement":null},{"id":"W2098561597","doi":"10.1093/nar/gkl228","title":"The Path-A metabolic pathway prediction web server","year":2006,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"University of Alberta","keywords":"Web server; Computer science; Metabolic pathway; Path (computing); Classifier (UML); Organism; Biology; Set (abstract data type); Computational biology; Artificial intelligence; Machine learning; Bioinformatics; The Internet; Genetics; World Wide Web; Gene","score_opus":0.014290558043719507,"score_gpt":0.2930937066084847,"score_spread":0.27880314856476524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098561597","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9584373,0.0010819103,0.0001867384,0.0005311122,0.00018789388,0.0002921137,0.00003175458,0.0000458078,0.03920537],"genre_scores_gemma":[0.9889777,0.00036425606,0.0005151421,0.00007054035,0.0006628499,0.000043532124,0.000119366654,0.000032755535,0.009213897],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99808246,0.00028057778,0.00026252866,0.00023750457,0.0006213577,0.0005155757],"domain_scores_gemma":[0.9989064,0.000058326666,0.000054788707,0.0006535643,0.00025283982,0.00007408462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016301266,0.00012762476,0.0000985298,0.00006297768,0.0005831989,0.00013708993,0.00048298942,0.00014673261,0.00005937785],"category_scores_gemma":[0.0003425607,0.0000894821,0.00008083799,0.00025356538,0.00024505338,0.000008040555,0.00031681385,0.00044830615,0.00019901618],"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":[0.00028677288,0.00025966665,0.09759419,0.00009853194,0.00016157283,0.0000120151135,0.00023803092,0.00053252646,0.61944044,0.023282733,0.20766653,0.05042698],"study_design_scores_gemma":[0.00037902594,0.00020276614,0.031060535,0.00000667371,0.0000046325667,0.000013378874,0.00009827345,0.0038216263,0.017348781,0.00036953107,0.9465763,0.000118502176],"about_ca_topic_score_codex":0.00005815521,"about_ca_topic_score_gemma":0.00005832683,"teacher_disagreement_score":0.7389097,"about_ca_system_score_codex":0.000022362588,"about_ca_system_score_gemma":0.00013602647,"threshold_uncertainty_score":0.44855535},"labels":[],"label_agreement":null},{"id":"W2098676247","doi":"10.1093/nar/gkq1093","title":"PSORTdb--an expanded, auto-updated, user-friendly protein subcellular localization database for Bacteria and Archaea","year":2010,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":89,"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":"Biology; Archaea; Bacteria; Database; Bacterial protein; Computational biology; Genetics; Computer science","score_opus":0.01996824358640841,"score_gpt":0.3300858543855556,"score_spread":0.3101176107991472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098676247","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9565959,0.000048043585,0.041591514,0.00015430484,0.000110829315,0.0009609224,0.00009526952,0.000039035436,0.00040417316],"genre_scores_gemma":[0.95536447,0.000039742907,0.04005128,0.00008523346,0.0003822283,0.00015698644,0.0024737553,0.00006991807,0.0013763603],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.998072,0.00019543187,0.00029071356,0.00041608536,0.00040257105,0.0006231734],"domain_scores_gemma":[0.9984859,0.000027974622,0.00007496774,0.0008195475,0.0002991155,0.00029248255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017787898,0.00019154327,0.00015931575,0.00013572417,0.00034091913,0.00013798266,0.00042816662,0.00029067384,0.00014286189],"category_scores_gemma":[0.00075229426,0.00017932981,0.000044184784,0.00016642307,0.00033773697,0.000041238814,0.0004278876,0.0005317191,0.000025134195],"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":[0.00022613959,0.00009896448,0.005889031,0.00014952484,0.000024365481,0.0000020473085,0.0002301292,0.0000073006354,0.9845562,0.0014807524,0.004313336,0.003022189],"study_design_scores_gemma":[0.0015098865,0.0012834339,0.0016448521,0.00003344375,0.000013972826,0.000047252095,0.00033459507,0.032823615,0.33133888,0.00017579203,0.63033795,0.00045634658],"about_ca_topic_score_codex":0.00005554453,"about_ca_topic_score_gemma":0.000077405675,"teacher_disagreement_score":0.6532173,"about_ca_system_score_codex":0.000015784186,"about_ca_system_score_gemma":0.00012261863,"threshold_uncertainty_score":0.73128575},"labels":[],"label_agreement":null},{"id":"W2098712526","doi":"10.1186/1471-2164-6-162","title":"Assessing the precision of high-throughput computational and laboratory approaches for the genome-wide identification of protein subcellular localization in bacteria","year":2005,"lang":"en","type":"article","venue":"BMC Genomics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Simon Fraser University; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Michael Smith Health Research BC; National Science Foundation","keywords":"Proteome; Proteomics; Computational biology; Genome; Subcellular localization; Identification (biology); Biology; Protein subcellular localization prediction; Genome project; Cell fractionation; Function (biology); Bioinformatics; Genetics; Gene","score_opus":0.01951921613799126,"score_gpt":0.2587226159087557,"score_spread":0.23920339977076446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098712526","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60941213,0.00027090212,0.38987407,0.00006967968,0.000015094726,0.00033867985,0.000012995169,0.0000014594044,0.000004962996],"genre_scores_gemma":[0.96040523,0.000026519945,0.039241854,0.00003080009,0.000049471313,0.00002565634,0.0001960709,0.000010482192,0.000013920792],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929684,0.00007209853,0.00036674968,0.000114178416,0.00007755211,0.00007257343],"domain_scores_gemma":[0.9993334,0.00008046721,0.00029326533,0.00019605688,0.00008636843,0.000010466069],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006575406,0.00007068818,0.00008663564,0.000025635283,0.00006467365,0.000034118875,0.00013248749,0.0000669767,0.000001248022],"category_scores_gemma":[0.00016896537,0.000051037867,0.000023957604,0.00006528359,0.00008603939,0.000012136525,0.000058957616,0.00004362035,3.5499832e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005713588,0.000049820243,0.008311874,0.00019301251,0.000024015528,1.6361561e-8,0.00069972326,0.7260884,0.26048875,0.0006300655,0.000023609213,0.003433594],"study_design_scores_gemma":[0.0006646984,0.000073364536,0.09185516,0.000020473224,0.00002818622,0.0000013325836,0.00051626243,0.7101141,0.19126481,0.00052731275,0.0047929464,0.00014132411],"about_ca_topic_score_codex":0.000006721619,"about_ca_topic_score_gemma":0.000025267387,"teacher_disagreement_score":0.35099307,"about_ca_system_score_codex":0.00001839558,"about_ca_system_score_gemma":0.0000813409,"threshold_uncertainty_score":0.20812638},"labels":[],"label_agreement":null},{"id":"W2102803266","doi":"10.1093/bioinformatics/19.2.234","title":"A naive Bayes model to predict coupling between seventransmembrane domain receptors and G-proteins","year":2003,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"AstraZeneca (Canada)","funders":"","keywords":"G protein-coupled receptor; Computational biology; Protein sequencing; Bayesian probability; Transmembrane domain; Bayes' theorem; Computer science; Coupling (piping); Biology; Artificial intelligence; Bioinformatics; Machine learning; Peptide sequence; Genetics; Receptor; Gene","score_opus":0.009458093025253722,"score_gpt":0.24074601573063606,"score_spread":0.23128792270538234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102803266","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6277033,0.00009885011,0.36576155,0.00014462018,0.00011162338,0.00064679724,0.00006628614,0.000058555597,0.005408431],"genre_scores_gemma":[0.6745535,0.00011361017,0.32398358,0.00049786887,0.00010648291,0.00003606398,0.00019699399,0.000045244462,0.00046662154],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858254,0.000026173277,0.00053699105,0.00018916825,0.00025676537,0.00040836798],"domain_scores_gemma":[0.9991028,0.000025808917,0.00015474945,0.0003810752,0.000073116025,0.00026246638],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000501222,0.00026884553,0.0002453655,0.00009573963,0.00017009402,0.00006984505,0.00021377465,0.00022268853,0.000016889146],"category_scores_gemma":[0.00025709646,0.0002503296,0.00007321784,0.00014668083,0.00007832525,0.000020230744,0.000105887564,0.00018621367,0.000031509902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013028372,0.00077365374,0.18576461,0.008429826,0.0028235377,0.000018411438,0.055137996,0.48412466,0.11602529,0.025880694,0.054735724,0.06498275],"study_design_scores_gemma":[0.0050346334,0.0028327038,0.002140855,0.00044694886,0.00023610737,0.00013531551,0.0035998821,0.6761442,0.086351044,0.0016157134,0.21842583,0.0030368126],"about_ca_topic_score_codex":0.0000039907072,"about_ca_topic_score_gemma":0.000004817766,"teacher_disagreement_score":0.19201949,"about_ca_system_score_codex":0.000024159763,"about_ca_system_score_gemma":0.00010524393,"threshold_uncertainty_score":0.9999949},"labels":[],"label_agreement":null},{"id":"W2103619851","doi":"10.1142/s0219525902000547","title":"GENOMIC ORGANIZATION AND HOPFIELD'S MODEL OF ASSOCIATIVE MEMORY","year":2002,"lang":"en","type":"article","venue":"Advances in Complex Systems","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Context (archaeology); Genome; Set (abstract data type); Computer science; Associative property; Hopfield network; Artificial neural network; Content-addressable memory; Function (biology); Recursion (computer science); Bidirectional associative memory; Biology; Computational biology; Artificial intelligence; Gene; Genetics; Mathematics; Algorithm","score_opus":0.01485990621592854,"score_gpt":0.24749845447719424,"score_spread":0.2326385482612657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103619851","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92306095,0.007410975,0.049531706,0.000057271056,0.0001969135,0.00037271576,0.000034493365,0.000021029899,0.019313928],"genre_scores_gemma":[0.9964925,0.00072961475,0.0023342918,0.0000417605,0.00004253382,0.000003890559,0.00003144728,0.000009658031,0.00031429797],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946606,0.000039838244,0.0002202463,0.00010852552,0.000072306306,0.000093023715],"domain_scores_gemma":[0.99961567,0.000020185613,0.00015747716,0.00013082534,0.000057181245,0.000018688695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000098403,0.000073722564,0.00013082268,0.00003071506,0.000027972254,0.000008596111,0.000090904774,0.000062583094,0.000011266181],"category_scores_gemma":[0.00011591771,0.000072895666,0.000012414215,0.00006790092,0.00003815991,0.000008343204,0.000058218673,0.000052684733,0.0000025201819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003529722,0.00015643527,0.2324094,0.0008929698,0.00010292809,0.0000019748218,0.004150133,0.45528603,0.28595892,0.004480558,0.0025552982,0.0139700305],"study_design_scores_gemma":[0.00059046334,0.000115709736,0.0027117862,0.000030023835,0.000007907245,0.000012316239,0.00039872708,0.9892444,0.002201609,0.00010173809,0.0043793623,0.00020598486],"about_ca_topic_score_codex":0.000008756157,"about_ca_topic_score_gemma":0.000011325282,"teacher_disagreement_score":0.5339583,"about_ca_system_score_codex":0.000013931571,"about_ca_system_score_gemma":0.0000065938534,"threshold_uncertainty_score":0.2972599},"labels":[],"label_agreement":null},{"id":"W2104332903","doi":"10.1016/j.bbrc.2007.03.164","title":"Prediction of protein structural class for the twilight zone sequences","year":2007,"lang":"en","type":"article","venue":"Biochemical and Biophysical Research Communications","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":87,"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":"Representation (politics); Computer science; In silico; Classifier (UML); Artificial intelligence; Protein structure prediction; Pattern recognition (psychology); Protein structure; Biology","score_opus":0.06387065908451027,"score_gpt":0.37706020851183036,"score_spread":0.3131895494273201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104332903","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99047065,0.0011256466,0.0039520357,0.0029500178,0.000023069713,0.000709551,0.000094005474,0.000012761673,0.0006622793],"genre_scores_gemma":[0.9934765,0.00017173581,0.005769725,0.000031114072,0.00012901014,0.000062435225,0.0001466216,0.000006930236,0.00020591683],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99909234,0.00007339704,0.00022762586,0.00014146046,0.00023745549,0.00022772275],"domain_scores_gemma":[0.9985196,0.00035753413,0.000061912164,0.0006967676,0.00028875808,0.000075435484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008430965,0.00007994794,0.00008807754,0.000033822194,0.00030470142,0.000023125163,0.0006099703,0.00010764727,0.0000026642379],"category_scores_gemma":[0.0006488007,0.00005137961,0.000059219423,0.0001813299,0.0011070021,0.0000052025744,0.0003662885,0.0002637893,0.0000013037309],"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":[0.00007748148,0.00004149459,0.00017943613,0.00004066757,0.000024844096,2.9754414e-8,0.00004644725,8.0983284e-7,0.98978263,0.0053313295,0.0005377735,0.003937026],"study_design_scores_gemma":[0.000326072,0.0004471644,0.0037427007,0.000032032203,0.000014561531,0.0000035292821,0.00021912924,0.0069970475,0.94162035,0.00092207734,0.045574713,0.00010062564],"about_ca_topic_score_codex":0.000030154795,"about_ca_topic_score_gemma":0.00001221929,"teacher_disagreement_score":0.048162315,"about_ca_system_score_codex":0.000012260118,"about_ca_system_score_gemma":0.00004968516,"threshold_uncertainty_score":0.40787956},"labels":[],"label_agreement":null},{"id":"W2104873783","doi":"10.1093/bioinformatics/btm475","title":"PFRES: protein fold classification by using evolutionary information and predicted secondary structure","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":122,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Protein tertiary structure; Protein secondary structure; Computer science; Pseudo amino acid composition; Similarity (geometry); Classifier (UML); Pattern recognition (psychology); Protein Data Bank (RCSB PDB); Fold (higher-order function); Protein superfamily; Protein structure prediction; Representation (politics); Feature vector; Structural Classification of Proteins database; Protein structure; Sequence (biology); Structural alignment; Data mining; Algorithm; Artificial intelligence; Sequence alignment; Biology; Peptide sequence; Amino acid; Genetics","score_opus":0.006359821080226958,"score_gpt":0.23383970742686902,"score_spread":0.22747988634664207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104873783","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9147561,0.00023667625,0.07972391,0.000071910064,0.00016151206,0.00072799844,0.00045017037,0.00008083306,0.0037908962],"genre_scores_gemma":[0.90902483,0.000041729636,0.086719796,0.00051792833,0.00013633909,0.00000827685,0.0033725423,0.000023091447,0.00015544954],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985908,0.00002300433,0.0006936755,0.00011064344,0.00027511528,0.00030673883],"domain_scores_gemma":[0.99900067,0.000014203073,0.00038309474,0.00032061312,0.00015251765,0.00012889368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029440536,0.00021520966,0.00013775687,0.00012890613,0.00019547003,0.00008329767,0.00017862114,0.0003191696,0.000025299367],"category_scores_gemma":[0.00019808361,0.00020498339,0.00004076739,0.00015942566,0.00011676046,0.000115627736,0.00013101615,0.00023452385,0.000008141166],"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":[0.0008285359,0.00020210126,0.032331817,0.00331084,0.0004787053,0.0000025794357,0.0054949974,0.00082391256,0.57222074,0.0027627198,0.108060375,0.27348268],"study_design_scores_gemma":[0.0030431466,0.0007773762,0.027494166,0.0001712224,0.000087549444,0.0002722591,0.0030118127,0.49539155,0.048070304,0.00023467267,0.42006275,0.0013831853],"about_ca_topic_score_codex":0.000012874647,"about_ca_topic_score_gemma":0.0000066785124,"teacher_disagreement_score":0.52415043,"about_ca_system_score_codex":0.000051655887,"about_ca_system_score_gemma":0.00013148399,"threshold_uncertainty_score":0.835898},"labels":[],"label_agreement":null},{"id":"W2105688189","doi":"10.1002/047001153x.g409201","title":"Hidden<scp>M</scp>arkov models and neural networks","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Genetics, Genomics, Proteomics and Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Artificial neural network; Artificial intelligence; Reading (process); Hidden Markov model; Strengths and weaknesses; Machine learning; Psychology","score_opus":0.005742921697530106,"score_gpt":0.21341664177945946,"score_spread":0.20767372008192936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105688189","genre_codex":"other","genre_gemma":"methods","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":[0.12437593,0.061103053,0.08433416,0.00026227135,0.0023427557,0.006621655,0.0014785165,0.0002992499,0.71918243],"genre_scores_gemma":[0.0047172294,0.24142906,0.5767049,0.0009706938,0.003713129,0.00010335657,0.0016225703,0.0012750595,0.169464],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99721605,0.000056554658,0.0012476608,0.0005020258,0.0002944752,0.0006832339],"domain_scores_gemma":[0.9973532,0.000048483595,0.0012801149,0.00087885524,0.00011520509,0.00032414516],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003892132,0.0008113906,0.0008080944,0.00029733632,0.000118627795,0.00011745834,0.0005777736,0.0010980042,0.000025964307],"category_scores_gemma":[0.00015549875,0.00081147475,0.0001704843,0.000103174214,0.00047343262,0.000019504549,0.0008853266,0.00054920005,0.000007482168],"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":[0.00017974076,0.00044919923,0.006157328,0.0064956984,0.0020982546,0.0000121907115,0.0063722357,0.038730852,0.0018549914,0.0010712729,0.60237235,0.3342059],"study_design_scores_gemma":[0.0011553369,0.00050488097,0.0001471188,0.00012747754,0.00017725129,0.000068498775,0.00036321516,0.4157553,0.00047832122,0.00014206432,0.58039296,0.00068755844],"about_ca_topic_score_codex":0.00004326233,"about_ca_topic_score_gemma":0.00008991631,"teacher_disagreement_score":0.5497184,"about_ca_system_score_codex":0.000031601263,"about_ca_system_score_gemma":0.00015906122,"threshold_uncertainty_score":0.99943364},"labels":[],"label_agreement":null},{"id":"W2106014491","doi":"10.1155/bsb/2006/35809","title":"Multipattern Consensus Regions in Multiple Aligned Protein Sequences and Their Segmentation","year":2006,"lang":"en","type":"article","venue":"EURASIP Journal on Bioinformatics and Systems Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Sequence (biology); Computational biology; Relevance (law); Consensus sequence; Computer science; Biology; Data mining; Bioinformatics; Genetics; Gene; Artificial intelligence; Peptide sequence","score_opus":0.016112281366365985,"score_gpt":0.25401638777124735,"score_spread":0.23790410640488135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106014491","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9935472,0.0005137852,0.004283294,0.00031723353,0.00019161073,0.00042779237,0.000050854014,0.000012605186,0.0006556393],"genre_scores_gemma":[0.9967714,0.00014782792,0.0024866732,0.00017356777,0.00014718887,0.000017100698,0.00011294826,0.000012693419,0.00013060874],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985537,0.00018892248,0.0007409283,0.00014811466,0.00008687363,0.0002814735],"domain_scores_gemma":[0.9991478,0.00007553925,0.00045702473,0.0001593649,0.00007279563,0.000087502085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006106504,0.00022561126,0.00026114204,0.00016651952,0.00018618388,0.000114272516,0.00011835133,0.00019387173,0.0000018168827],"category_scores_gemma":[0.00013175649,0.00015864708,0.000044383425,0.00007331576,0.00016293024,0.000013025535,0.000059348884,0.00018029849,0.0000043111013],"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":[0.0006380397,0.00026940307,0.35179147,0.0008198263,0.0002696903,0.000043109798,0.0033235599,0.0043218946,0.6097381,0.0064091524,0.0030293397,0.019346394],"study_design_scores_gemma":[0.02297051,0.010636275,0.08702878,0.0020372537,0.00009088474,0.0121495705,0.02258024,0.6572934,0.06027544,0.0031650267,0.11744678,0.0043258346],"about_ca_topic_score_codex":0.00011306418,"about_ca_topic_score_gemma":0.00007823019,"teacher_disagreement_score":0.6529715,"about_ca_system_score_codex":0.000022363904,"about_ca_system_score_gemma":0.00003811672,"threshold_uncertainty_score":0.646944},"labels":[],"label_agreement":null},{"id":"W2110251730","doi":"10.1016/j.artmed.2005.02.006","title":"Highly accurate and consistent method for prediction of helix and strand content from primary protein sequences","year":2005,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Content (measure theory); Artificial intelligence; Pattern recognition (psychology); Mathematics","score_opus":0.06080611292777175,"score_gpt":0.3357783467417824,"score_spread":0.27497223381401065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110251730","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83971786,0.0010923643,0.15640745,0.0018792679,0.00008227805,0.0005826603,0.000069747904,0.000007950956,0.0001604244],"genre_scores_gemma":[0.95311993,0.00028763543,0.045933627,0.00026616713,0.00019391651,0.00003558133,0.00011069891,0.000007636549,0.000044813838],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989775,0.00005905582,0.0005148563,0.00020364505,0.000115187504,0.00012979483],"domain_scores_gemma":[0.9994756,0.000103415805,0.00015356993,0.00012663909,0.000087483335,0.000053294523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005993891,0.0001122014,0.00021439478,0.000051953557,0.000036368194,0.000009688431,0.000075789954,0.00009365724,0.000012149719],"category_scores_gemma":[0.0004178092,0.000089380745,0.00002080472,0.00005311898,0.00024759895,0.000010044833,0.000036534166,0.000088339184,5.2877067e-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":[0.0002977203,0.000039809835,0.0016501776,0.000109589986,0.00003538727,7.062547e-7,0.00081598974,0.00036330565,0.8519606,0.001228687,0.000057636942,0.1434404],"study_design_scores_gemma":[0.0006076482,0.0019644182,0.0057844277,0.0004094565,0.00007355999,0.00001630334,0.0024707257,0.078807406,0.90102255,0.004649147,0.0039438824,0.00025047586],"about_ca_topic_score_codex":0.00026037107,"about_ca_topic_score_gemma":0.00023686964,"teacher_disagreement_score":0.14318992,"about_ca_system_score_codex":0.000011002223,"about_ca_system_score_gemma":0.000030977928,"threshold_uncertainty_score":0.3644841},"labels":[],"label_agreement":null},{"id":"W2111105704","doi":"10.5376/cmb.2014.04.0007","title":"FunSecKB2: a fungal protein subcellular location knowledgebase","year":2014,"lang":"en","type":"article","venue":"Computational Molecular Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computational biology; Biology","score_opus":0.00442848962742088,"score_gpt":0.2555454032499011,"score_spread":0.25111691362248023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111105704","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29783586,0.00024390341,0.69910556,0.00020652245,0.000111280744,0.00022292376,0.000008126481,0.00003463315,0.0022312151],"genre_scores_gemma":[0.9699801,0.0000013118956,0.027446572,0.00067013805,0.00019436578,0.000045676352,0.0013772104,0.000029206893,0.00025539144],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986374,0.00027547672,0.0003175046,0.00036413546,0.00012823424,0.00027726844],"domain_scores_gemma":[0.999106,0.000031754214,0.00014698305,0.00033367146,0.00028015158,0.00010145553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003413369,0.00020922955,0.0001658544,0.00009046942,0.000105287196,0.000025872616,0.00026051147,0.00021388875,0.00003306006],"category_scores_gemma":[0.00044929975,0.00021221045,0.00008977421,0.0001567426,0.00014141064,0.000004031608,0.00013893639,0.00015461494,0.00015213242],"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":[0.00015085831,0.00019690843,0.004585494,0.00014113079,0.0001487634,0.0000072464986,0.00008791754,0.054311443,0.7172076,0.20821546,0.0011046365,0.013842498],"study_design_scores_gemma":[0.0059033926,0.004355034,0.008934918,0.00013975712,0.00011840535,0.00036825179,0.00006318663,0.4439774,0.14306977,0.20600222,0.18437925,0.0026884354],"about_ca_topic_score_codex":0.000005649483,"about_ca_topic_score_gemma":0.000003354469,"teacher_disagreement_score":0.6721443,"about_ca_system_score_codex":0.000017897799,"about_ca_system_score_gemma":0.000109042034,"threshold_uncertainty_score":0.8653691},"labels":[],"label_agreement":null},{"id":"W2111693807","doi":"10.1093/bioinformatics/btq266","title":"DETECT—a Density Estimation Tool for Enzyme ClassificaTion and its application to <i>Plasmodium falciparum</i>","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"SickKids Foundation; Canada Research Chairs; Hospital for Sick Children; University of Toronto","funders":"Ontario Ministry of Research and Innovation; Canadian Institutes of Health Research","keywords":"Annotation; Ranking (information retrieval); Computer science; Computational biology; Probabilistic logic; Plasmodium falciparum; Sequence alignment; Genomics; Data mining; Biology; Machine learning; Artificial intelligence; Genetics; Gene; Peptide sequence; Genome; Malaria","score_opus":0.009605648486673174,"score_gpt":0.2615764797752238,"score_spread":0.25197083128855063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111693807","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54544723,0.000011851917,0.45270783,0.00024943732,0.00015756997,0.0009009774,0.00003795414,0.00004650729,0.00044064072],"genre_scores_gemma":[0.82245445,0.00001209703,0.17621197,0.0005539017,0.00011269434,0.00014734767,0.0003689548,0.000019216028,0.00011933843],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900585,0.000012211973,0.00041831564,0.00017403002,0.00015247718,0.00023708574],"domain_scores_gemma":[0.9990544,0.000036086087,0.00021553918,0.0003922908,0.00018595016,0.00011573428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039602388,0.00017825516,0.0001358307,0.000073766445,0.0001754456,0.00007203775,0.0001915618,0.00023411358,0.0000029963412],"category_scores_gemma":[0.0005878659,0.00017624082,0.000047951107,0.00009999645,0.000033758242,0.000028136406,0.000104380655,0.000142932,0.00006213477],"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":[0.00017409644,0.0000536362,0.0016031961,0.0004963477,0.000043482545,9.11305e-8,0.0006363132,0.0015737159,0.8977702,0.0051492644,0.0054730717,0.08702658],"study_design_scores_gemma":[0.0005214654,0.00022993838,0.004603269,0.000009821512,0.000029481462,0.000025481346,0.000051083316,0.7769703,0.16654465,0.00013806323,0.05052901,0.00034743795],"about_ca_topic_score_codex":0.0000022669806,"about_ca_topic_score_gemma":0.000022859975,"teacher_disagreement_score":0.7753966,"about_ca_system_score_codex":0.000014034719,"about_ca_system_score_gemma":0.000051031195,"threshold_uncertainty_score":0.7186892},"labels":[],"label_agreement":null},{"id":"W2112611875","doi":"10.2316/j.2010.210-1023","title":"ALIGNMENT-BASED EXTENSION TO DDPIN FEATURE EXTRACTION","year":2010,"lang":"en","type":"article","venue":"International Journal of Computational Bioscience","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Grantová Agentura České Republiky","keywords":"Extension (predicate logic); Computer science; Feature extraction; Feature (linguistics); Artificial intelligence; Pattern recognition (psychology); Programming language; Linguistics","score_opus":0.005835325165920761,"score_gpt":0.3079265576214354,"score_spread":0.3020912324555146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112611875","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7512014,0.000013601031,0.24036163,0.0057568424,0.0022036901,0.000065516426,0.000011288818,0.000006224495,0.00037979995],"genre_scores_gemma":[0.8658679,0.0000023352268,0.13176231,0.0018686705,0.00036701115,9.3677806e-7,0.000024954898,0.0000054155234,0.000100452926],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998826,0.000023260993,0.0002592917,0.00012705724,0.0006632084,0.00010114546],"domain_scores_gemma":[0.99870926,0.000041486288,0.00027817054,0.00009670395,0.00077133725,0.000103048646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039389494,0.000085969274,0.00007096101,0.00016833397,0.00005739973,0.00007517092,0.0004585225,0.00006466075,0.000031561423],"category_scores_gemma":[0.00049536995,0.000074867385,0.00007205447,0.000103372986,0.000062352396,0.000021558257,0.00006220764,0.00019428258,0.000016682628],"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":[0.00012714448,0.000082596845,0.002120902,0.000002636233,0.00002025855,0.000009687291,0.000039193976,0.09870267,0.88556784,0.00046662762,0.0056195143,0.007240941],"study_design_scores_gemma":[0.0024236294,0.0014203166,0.16994648,0.00013056521,0.000027288499,0.001938225,0.00010622708,0.08856227,0.4091561,0.0021344598,0.32347468,0.0006797543],"about_ca_topic_score_codex":0.0000019783424,"about_ca_topic_score_gemma":0.0000036014205,"teacher_disagreement_score":0.47641173,"about_ca_system_score_codex":0.000021698235,"about_ca_system_score_gemma":0.00018013378,"threshold_uncertainty_score":0.30530035},"labels":[],"label_agreement":null},{"id":"W2112905569","doi":"10.1093/nar/gkh380","title":"ConPred II: a consensus prediction method for obtaining transmembrane topology models with high reliability","year":2004,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":202,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Aging","funders":"Ministry of Education, Culture, Sports, Science and Technology","keywords":"Topology (electrical circuits); Network topology; Biology; Computer science; Reliability (semiconductor); Process (computing); Algorithm; Data mining; Mathematics; Physics; Computer network; Combinatorics; Power (physics); Operating system","score_opus":0.03156165825524426,"score_gpt":0.349017576479136,"score_spread":0.31745591822389174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112905569","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7536829,0.000072869574,0.24038176,0.0021508452,0.0000776158,0.0009132727,0.00009385879,0.00006065433,0.0025662289],"genre_scores_gemma":[0.79866636,0.00003523341,0.2003247,0.00012501219,0.00013550185,0.00011543595,0.00014849314,0.000036446843,0.00041279808],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979186,0.00028016153,0.00034105676,0.00047331792,0.00039334086,0.0005935032],"domain_scores_gemma":[0.9985613,0.00014541784,0.00006174194,0.0005844526,0.0005076387,0.00013943303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020642432,0.0001826263,0.00024253038,0.00010822712,0.0004544988,0.00002544886,0.00031017294,0.000335302,0.000029110137],"category_scores_gemma":[0.0005676163,0.00015549491,0.00007928536,0.00020342736,0.00042990802,0.000009150912,0.00013745645,0.00047968398,0.0000046782175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0077109006,0.0006384059,0.0016978041,0.0008144985,0.00046489108,0.00001777033,0.0047748922,0.49812397,0.44153368,0.028154247,0.003028321,0.0130406115],"study_design_scores_gemma":[0.026119802,0.02690491,0.0025948968,0.00024798122,0.00017660421,0.0005306987,0.0027663454,0.5006266,0.3286997,0.042975966,0.06680374,0.0015526991],"about_ca_topic_score_codex":0.00023662345,"about_ca_topic_score_gemma":0.000052771433,"teacher_disagreement_score":0.112833954,"about_ca_system_score_codex":0.00007805155,"about_ca_system_score_gemma":0.0003169172,"threshold_uncertainty_score":0.6340898},"labels":[],"label_agreement":null},{"id":"W2113515779","doi":"10.1109/grc.2007.72","title":"Comparison of Machine Learning and Pattern Discovery Algorithms for the Prediction of Human Single Nucleotide Polymorphisms","year":2007,"lang":"en","type":"article","venue":"2007 IEEE International Conference on Granular Computing (GRC 2007)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Probabilistic logic; Machine learning; Algorithm; Single-nucleotide polymorphism; Pattern recognition (psychology); Biology; Genetics","score_opus":0.03891084354732889,"score_gpt":0.33018313861519055,"score_spread":0.2912722950678617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113515779","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5479661,0.00015312558,0.44893375,0.00008506536,0.0008550264,0.0002263355,0.000080453465,0.000015279526,0.0016848479],"genre_scores_gemma":[0.99693054,0.00002877001,0.0020184186,0.00007539993,0.00043144397,0.0000020298048,0.0002089116,0.000020325091,0.00028413907],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865055,0.000044130516,0.0005686692,0.00021986157,0.00031304493,0.00020372555],"domain_scores_gemma":[0.99892557,0.00013184262,0.00048715857,0.00017331021,0.00023863926,0.000043467622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006307536,0.0001715426,0.00021324307,0.00009825068,0.00014749562,0.0000441635,0.00027928397,0.00010344021,0.00002456064],"category_scores_gemma":[0.00011078471,0.00014544338,0.00009865807,0.00005048379,0.00016602148,0.000012059742,0.00008599892,0.00022269959,0.0000015412966],"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":[0.0003530306,0.00050099473,0.34094024,0.00014523508,0.00033352058,0.0000024473122,0.0007791281,0.0044911606,0.5935403,0.0017536656,0.0011147425,0.05604554],"study_design_scores_gemma":[0.0021153288,0.0023723196,0.032024898,0.00032750829,0.00008793915,0.00002764896,0.0005813856,0.71523356,0.2387079,0.00016114164,0.007930737,0.00042960906],"about_ca_topic_score_codex":0.0000773013,"about_ca_topic_score_gemma":0.000019676943,"teacher_disagreement_score":0.7107424,"about_ca_system_score_codex":0.000020781623,"about_ca_system_score_gemma":0.00002076206,"threshold_uncertainty_score":0.5931009},"labels":[],"label_agreement":null},{"id":"W2113944588","doi":"10.1093/bioinformatics/btn433","title":"Accurate sequence-based prediction of catalytic residues","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":85,"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":"Nankai University","keywords":"Support vector machine; Curse of dimensionality; Sequence (biology); Computer science; Classifier (UML); Protein structure prediction; Feature selection; Artificial intelligence; Biological system; Data mining; Pattern recognition (psychology); Protein structure; Chemistry; Biology; Biochemistry","score_opus":0.028211413451712894,"score_gpt":0.26240301861543913,"score_spread":0.23419160516372622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113944588","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9414378,0.00013054498,0.03953401,0.00011874831,0.000280164,0.00042889643,0.0002838111,0.00009670048,0.017689323],"genre_scores_gemma":[0.96783745,0.000103865386,0.03064948,0.00022774948,0.000080606056,0.000008977158,0.00070352136,0.000017023904,0.00037132244],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988642,0.000023092003,0.00055991084,0.000097117234,0.00024534567,0.0002103603],"domain_scores_gemma":[0.9989862,0.000020011092,0.00031939187,0.00046070665,0.00014049395,0.00007320621],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019658572,0.00015824579,0.00016399653,0.000087818706,0.00010616287,0.0000119935585,0.00024013115,0.0001505152,0.000014233796],"category_scores_gemma":[0.00025977654,0.00014218852,0.000085798245,0.00014473707,0.00018817182,0.000017796256,0.000072826384,0.00010845049,0.000036819267],"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":[0.0015773431,0.001232331,0.35383806,0.006312343,0.0011762168,0.00005293434,0.015072884,0.1254538,0.24290124,0.0025393637,0.21642981,0.033413667],"study_design_scores_gemma":[0.0030242193,0.0018482847,0.03851151,0.00020115066,0.000095033865,0.00030105584,0.00055232685,0.5443331,0.34532413,0.000052580865,0.064847514,0.00090905634],"about_ca_topic_score_codex":0.000013265272,"about_ca_topic_score_gemma":0.0000042860047,"teacher_disagreement_score":0.41887933,"about_ca_system_score_codex":0.000018647745,"about_ca_system_score_gemma":0.00020967619,"threshold_uncertainty_score":0.57982796},"labels":[],"label_agreement":null},{"id":"W2113979528","doi":"10.1109/fbit.2007.21","title":"Classification of Cell Membrane Proteins","year":2007,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Pseudo amino acid composition; Jackknife resampling; Transmembrane protein; Membrane protein; In silico; Computer science; Protein sequencing; Feature (linguistics); Representation (politics); Cell membrane; Artificial intelligence; Computational biology; Function (biology); Pattern recognition (psychology); Biological system; Membrane; Peptide sequence; Amino acid; Chemistry; Biochemistry; Biology; Mathematics; Cell biology; Receptor; Gene","score_opus":0.008142779209924384,"score_gpt":0.2540919090952387,"score_spread":0.24594912988531434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113979528","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7860258,0.000019930918,0.053940527,0.00004608543,0.000034065997,0.00013372157,0.0000014865427,0.000010917551,0.15978745],"genre_scores_gemma":[0.974478,0.000007584503,0.022650572,0.00006854437,0.00004182363,0.0000019582735,0.000040388826,0.0000061901465,0.00270496],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995726,0.000009153969,0.0001726515,0.00007347923,0.000077880584,0.000094283576],"domain_scores_gemma":[0.99963367,0.0000057528155,0.000084740204,0.00019934236,0.000047906808,0.000028566878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025262934,0.000051317875,0.000049480364,0.000024851806,0.000016853814,0.000003305314,0.0000905295,0.00007242087,0.000045100514],"category_scores_gemma":[0.00004509491,0.000044113916,0.000029051804,0.000047396505,0.000028768518,0.00000114107,0.000029089993,0.000043100074,0.000014411212],"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":[0.000018029965,0.000028507882,0.0025178718,0.000035305966,0.000004057043,9.702536e-8,0.000027411377,0.000014041833,0.9956052,0.00051159714,0.0002718339,0.00096606254],"study_design_scores_gemma":[0.0001634458,0.00010456485,0.011491801,0.0000022277763,0.000002981444,0.0000019032186,0.000059857088,0.0003992277,0.971717,0.000008560737,0.01598941,0.00005900174],"about_ca_topic_score_codex":0.0000075908292,"about_ca_topic_score_gemma":0.000013651183,"teacher_disagreement_score":0.18845217,"about_ca_system_score_codex":0.000003181897,"about_ca_system_score_gemma":0.000017333898,"threshold_uncertainty_score":0.17989133},"labels":[],"label_agreement":null},{"id":"W2115866389","doi":"10.1109/bibm.2007.12","title":"The Normalized Similarity Metric and Its Applications","year":2007,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","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":"Western University","funders":"","keywords":"Similarity (geometry); Metric (unit); Computer science; Metric space; Mathematics; Domain (mathematical analysis); Formal description; Theoretical computer science; Data mining; Artificial intelligence; Discrete mathematics","score_opus":0.0056636567522204105,"score_gpt":0.2732706083868433,"score_spread":0.2676069516346229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115866389","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33218783,0.005494182,0.3542147,0.001555322,0.00017087537,0.0011780991,0.0000133936965,0.0001041488,0.30508143],"genre_scores_gemma":[0.99140817,0.00036279182,0.0040411786,0.00047032704,0.000082529055,0.000013363141,0.000023695438,0.000006886284,0.0035910746],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995716,0.000012686315,0.00012906895,0.00008184135,0.00006859352,0.00013617851],"domain_scores_gemma":[0.9996325,0.000055656383,0.00004184697,0.00017433133,0.00004804133,0.00004762243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046562817,0.000057886507,0.000040290044,0.000021552565,0.00018174761,0.000023955847,0.00011555373,0.00006031106,0.000009722413],"category_scores_gemma":[0.00017530477,0.000038212576,0.000021023578,0.00010740664,0.000032444317,0.000001541934,0.00009053853,0.000068279405,0.000012018817],"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":[0.00041524527,0.00029041228,0.0728269,0.00025789504,0.00045066993,0.0000033938325,0.00038343322,0.00029926316,0.2976671,0.22425705,0.026290055,0.3768586],"study_design_scores_gemma":[0.00026909309,0.000055119486,0.009604273,8.3064975e-7,0.000009859233,0.000014826156,0.00005908109,0.0014826965,0.04972058,0.0000907448,0.9385768,0.00011605036],"about_ca_topic_score_codex":0.0000041101025,"about_ca_topic_score_gemma":0.000032941356,"teacher_disagreement_score":0.91228676,"about_ca_system_score_codex":0.0000032431647,"about_ca_system_score_gemma":0.000011039025,"threshold_uncertainty_score":0.15582637},"labels":[],"label_agreement":null},{"id":"W2117003089","doi":"10.1093/bioinformatics/bti280","title":"Computational identification of human mitochondrial proteins based on homology to yeast mitochondrially targeted proteins","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Hospital for Sick Children","funders":"Canadian Institutes of Health Research; Hospital for Sick Children","keywords":"Biology; Human genome; Computational biology; Saccharomyces cerevisiae; Homology (biology); Genetics; Human proteins; Gene; Genome; Human mitochondrial genetics; Mitochondrion; UniGene; Expressed sequence tag","score_opus":0.008637087028099883,"score_gpt":0.2773267700318632,"score_spread":0.2686896830037633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117003089","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26480561,0.000013377761,0.73112553,0.0014585401,0.00014408698,0.0020243067,0.00004002636,0.000021479735,0.00036705518],"genre_scores_gemma":[0.8750894,5.1147305e-7,0.12346433,0.0004856781,0.00036392268,0.00040587693,0.00014641417,0.000006905703,0.00003698076],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872226,0.00011740673,0.0004125753,0.00030556764,0.00027934386,0.00016282292],"domain_scores_gemma":[0.9991548,0.000035133035,0.00019978627,0.00047000975,0.00010091841,0.000039375514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000349312,0.00012284247,0.00011072051,0.00016238088,0.00018775075,0.000051996765,0.000842194,0.0000763003,0.0000058330356],"category_scores_gemma":[0.000051421426,0.00009483609,0.00005195672,0.00042344708,0.00019974467,0.000008643574,0.000081692866,0.000097354416,0.000018316543],"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":[0.0000634388,0.00096013525,0.002019543,0.000047435085,0.000016097307,2.9167788e-7,0.0011920746,0.31204507,0.66271394,0.00950203,0.0027660702,0.0086739],"study_design_scores_gemma":[0.0026735796,0.0036650242,0.093410976,0.00009881986,0.000039177547,0.000021084148,0.00032848355,0.53288895,0.29377565,0.0024920502,0.06940371,0.0012025295],"about_ca_topic_score_codex":0.000010464669,"about_ca_topic_score_gemma":0.000026505235,"teacher_disagreement_score":0.61028373,"about_ca_system_score_codex":0.000019187022,"about_ca_system_score_gemma":0.000087157125,"threshold_uncertainty_score":0.38673034},"labels":[],"label_agreement":null},{"id":"W2117486996","doi":"10.1038/nmeth.2340","title":"A large-scale evaluation of computational protein function prediction","year":2013,"lang":"en","type":"article","venue":"Nature Methods","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1095,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"U.S. National Library of Medicine; National Institute of General Medical Sciences; National Human Genome Research Institute; Office of Science; Biotechnology and Biological Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Directorate for Biological Sciences; Ministero dell’Istruzione, dell’Università e della Ricerca; Biological and Environmental Research; National Natural Science Foundation of China; University of Miami; Alexander von Humboldt-Stiftung; U.S. Department of Energy; National Science Foundation","keywords":"Annotation; Computer science; Protein function prediction; Function (biology); Protein function; Set (abstract data type); Scale (ratio); Computational biology; Machine learning; Artificial intelligence; Data mining; Biology; Genetics; Gene","score_opus":0.010419519725964346,"score_gpt":0.3501743383184968,"score_spread":0.3397548185925325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117486996","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38276064,0.00026694933,0.6120525,0.000082346334,0.00022308007,0.0005389331,0.000012913486,0.000017232593,0.0040453766],"genre_scores_gemma":[0.6471722,0.0000011234306,0.3520708,0.00011032118,0.00011257296,0.0000629096,0.00028957846,0.000008509102,0.00017197253],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883777,0.000406484,0.00020643973,0.00013828506,0.00030948923,0.0001015139],"domain_scores_gemma":[0.9991103,0.00001902607,0.00014081826,0.00017938658,0.0005211197,0.000029395977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018247083,0.000082167135,0.00008538494,0.000048961443,0.000045058965,0.000011661184,0.000074372685,0.00030454533,0.0001533519],"category_scores_gemma":[0.00053664425,0.000073236224,0.00005095325,0.000102779566,0.00002260698,0.000008039958,0.000040515086,0.00023485362,0.000007965159],"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":[0.00012778612,0.00021549406,0.0055374904,0.00017614015,0.00018052336,5.1201752e-8,0.0005389171,0.026771015,0.77896893,0.0016106786,0.007993629,0.17787935],"study_design_scores_gemma":[0.0019032178,0.0006136087,0.10613618,0.000042180596,0.00013969881,0.000010608627,0.00023986808,0.7386695,0.102318935,0.015588887,0.034063485,0.00027383387],"about_ca_topic_score_codex":0.0000035174314,"about_ca_topic_score_gemma":0.0000021279027,"teacher_disagreement_score":0.7118985,"about_ca_system_score_codex":0.000018367917,"about_ca_system_score_gemma":0.000057826746,"threshold_uncertainty_score":0.29864866},"labels":[],"label_agreement":null},{"id":"W2118532575","doi":"10.1109/tkde.2005.201","title":"Localization site prediction for membrane proteins by integrating rule and SVM classification","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Support vector machine; Computer science; Subsequence; Artificial intelligence; Machine learning; Precision and recall; Data mining; Curse of dimensionality; Kernel (algebra); Feature vector","score_opus":0.01169135818690139,"score_gpt":0.2569569636183845,"score_spread":0.2452656054314831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118532575","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022597538,0.000286768,0.97621983,0.000053606473,0.00008453918,0.0002492404,0.00037191878,0.00004192688,0.00009462565],"genre_scores_gemma":[0.9805459,0.00030025883,0.017350344,0.00003189204,0.00014324741,0.000064419706,0.0013117471,0.000024408464,0.00022777934],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994695,0.000010316137,0.00016276167,0.00020987837,0.000043393986,0.00010412361],"domain_scores_gemma":[0.99962837,0.000019162006,0.000034048488,0.0002354954,0.000035883597,0.000047018366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014139767,0.0001081956,0.00007328372,0.000049329712,0.00011209891,0.00003475426,0.00007417921,0.00009269423,0.0000030744948],"category_scores_gemma":[0.000023627255,0.000108504915,0.000014789418,0.000054887663,0.000017002028,0.000033080643,0.0000046974365,0.000094156545,0.0000025107845],"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":[0.00008474584,0.00017577823,0.00016204592,0.0005312181,0.00009227239,8.278479e-8,0.00059101224,0.046774387,0.7753748,0.0000896467,0.0027593544,0.17336462],"study_design_scores_gemma":[0.0003374516,0.000095328855,0.000039761337,0.0000336085,0.000023950446,0.000005459881,0.0000247194,0.8649211,0.07259946,8.61469e-7,0.061809994,0.00010829601],"about_ca_topic_score_codex":0.0000036063982,"about_ca_topic_score_gemma":0.00002307442,"teacher_disagreement_score":0.9588695,"about_ca_system_score_codex":0.000012218722,"about_ca_system_score_gemma":0.000012381977,"threshold_uncertainty_score":0.44247022},"labels":[],"label_agreement":null},{"id":"W2118769225","doi":"10.1093/nar/gki027","title":"PSORTdb: a protein subcellular localization database for bacteria","year":2004,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":135,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; Genome Canada; Genome Prairie; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Michael Smith Health Research BC; National Science Foundation","keywords":"Biology; Identification (biology); Annotation; Database; Bacterial genome size; Computational biology; Function (biology); Protein function; Genome; Database search engine; Computer science; Information retrieval; Bioinformatics; Search engine; Data mining; Genetics; Gene","score_opus":0.030658187310625883,"score_gpt":0.3387933180577546,"score_spread":0.3081351307471287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118769225","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81178564,0.00012323199,0.1843332,0.000499592,0.0000741746,0.0012709872,0.00006292157,0.00003972176,0.0018105258],"genre_scores_gemma":[0.9659567,0.000041807507,0.030627137,0.00014199966,0.00029992385,0.0001780666,0.0012312448,0.000056702233,0.0014664483],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99854,0.00009724504,0.00023336496,0.0003020849,0.00036861963,0.00045871016],"domain_scores_gemma":[0.9989548,0.000014188382,0.00005164311,0.00057225395,0.00028524644,0.00012192205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010142126,0.00013064357,0.00011140932,0.00009897183,0.000246226,0.000077305245,0.00036183724,0.0001736683,0.00008241799],"category_scores_gemma":[0.0007278395,0.0001244787,0.00006005556,0.00020295697,0.00015084584,0.000011200122,0.00024425014,0.00023226527,0.00009572183],"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":[0.00023039684,0.000108313005,0.00065716007,0.00024224469,0.000029871626,0.000003867241,0.0001639416,0.0005144023,0.9899961,0.0026091374,0.0034823993,0.001962201],"study_design_scores_gemma":[0.0021987965,0.0011515027,0.00037609218,0.00009554085,0.000009475945,0.000017654313,0.00016473097,0.0070558125,0.5873732,0.0009778986,0.4002203,0.00035897532],"about_ca_topic_score_codex":0.000039929262,"about_ca_topic_score_gemma":0.00001948956,"teacher_disagreement_score":0.40262285,"about_ca_system_score_codex":0.00005198004,"about_ca_system_score_gemma":0.00018102373,"threshold_uncertainty_score":0.5076094},"labels":[],"label_agreement":null},{"id":"W2119894516","doi":"10.1186/1471-2105-8-286","title":"CLUSS: Clustering of protein sequences based on a new similarity measure","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Université de Sherbrooke","keywords":"Cluster analysis; Similarity (geometry); Phylogenetic tree; Biological data; Similarity measure; Computer science; Matching (statistics); Protein sequencing; Measure (data warehouse); Data mining; Protein family; Computational biology; Artificial intelligence; Bioinformatics; Biology; Genetics; Peptide sequence; Mathematics; Gene","score_opus":0.018123837303283746,"score_gpt":0.26742335716123616,"score_spread":0.24929951985795243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119894516","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":[0.026815407,0.000058209716,0.950364,0.000096708005,0.00013604152,0.0005706084,0.00002223953,0.00005153245,0.021885263],"genre_scores_gemma":[0.33865976,0.0000061880123,0.6598012,0.0007280024,0.00017669602,0.000006917991,0.00011893521,0.000029546658,0.00047273506],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983229,0.000036148645,0.00071488245,0.00014017621,0.00043239165,0.00035351026],"domain_scores_gemma":[0.99872065,0.000044454453,0.00040586846,0.00055598683,0.00011686977,0.00015618085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010173133,0.00023766354,0.00022332006,0.00012631419,0.00008456973,0.000034433873,0.00036663958,0.0002616708,0.00002540363],"category_scores_gemma":[0.00059484923,0.00020705047,0.0001323712,0.00018878092,0.00009909893,0.000014858552,0.00012302294,0.00021930276,0.000020397767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0057573793,0.0012165839,0.07344097,0.011888614,0.0005380636,0.000018618226,0.0065598125,0.5918657,0.09511126,0.0032541542,0.017870257,0.1924786],"study_design_scores_gemma":[0.0016140767,0.0010714341,0.0021811158,0.00030287183,0.000029800018,0.000016831018,0.00043808165,0.9236535,0.055108942,0.00006741103,0.014965409,0.0005505423],"about_ca_topic_score_codex":0.000028377424,"about_ca_topic_score_gemma":0.00015451352,"teacher_disagreement_score":0.3317878,"about_ca_system_score_codex":0.0000297473,"about_ca_system_score_gemma":0.00030421015,"threshold_uncertainty_score":0.84432733},"labels":[],"label_agreement":null},{"id":"W212014443","doi":"10.5220/0002286801270133","title":"FINDING PROTEIN FAMILY SIMILARITIES IN REAL TIME THROUGH MULTIPLE 3D AND 2D REPRESENTATIONS, INDEXING AND EXHAUSTIVE SEARCHING","year":2009,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Search engine indexing; Computer science; Information retrieval; Theoretical computer science","score_opus":0.016299811243236022,"score_gpt":0.30085485055544126,"score_spread":0.2845550393122052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W212014443","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98078483,0.00010067344,0.0024241004,0.00015980487,0.0000078314015,0.00027499069,0.00000468182,0.000021656511,0.016221425],"genre_scores_gemma":[0.9661896,0.00011018647,0.03258918,0.00020190355,0.000038429804,0.0000087813705,0.000050615392,0.000008772434,0.000802539],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9992649,0.000048278518,0.00019330741,0.00020572635,0.000097565506,0.00019021753],"domain_scores_gemma":[0.99971586,0.000033659344,0.00005404614,0.00013522041,0.000024165003,0.00003702103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022370895,0.00011315636,0.00011175731,0.00005226096,0.00011045127,0.00006127535,0.0000648219,0.000097798256,0.0000054976954],"category_scores_gemma":[0.00020302797,0.00010844519,0.000015347543,0.00006210014,0.000063339525,0.000019861309,0.00010935073,0.00016259449,0.0000015436804],"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":[0.00018683868,0.00009520347,0.16399135,0.00013769195,0.000050328905,0.000015791054,0.0060939314,0.001518177,0.8115467,0.0012722503,0.0005460731,0.014545687],"study_design_scores_gemma":[0.005700973,0.0013390827,0.7411016,0.000427274,0.00003662074,0.000088342545,0.007520362,0.114957176,0.12068747,0.0032965709,0.0033724708,0.001472007],"about_ca_topic_score_codex":0.00019484761,"about_ca_topic_score_gemma":0.000027250853,"teacher_disagreement_score":0.6908592,"about_ca_system_score_codex":0.000010408726,"about_ca_system_score_gemma":0.000023377854,"threshold_uncertainty_score":0.44222665},"labels":[],"label_agreement":null},{"id":"W2121547673","doi":"10.1002/prot.22882","title":"Improved identification of outer membrane beta barrel proteins using primary sequence, predicted secondary structure, and evolutionary information","year":2010,"lang":"en","type":"article","venue":"Proteins Structure Function and Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"In silico; Computational biology; Support vector machine; Protein secondary structure; Benchmark (surveying); Genome; Sequence (biology); Computer science; Membrane protein; Folding (DSP implementation); Classifier (UML); Bacterial outer membrane; Biology; Artificial intelligence; Membrane; Gene; Genetics; Engineering; Biochemistry","score_opus":0.004756539766474144,"score_gpt":0.21043778768937854,"score_spread":0.2056812479229044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121547673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9621263,0.000066360124,0.034563363,0.000068444104,0.0004977595,0.001398942,0.0009399408,0.000056100806,0.000282765],"genre_scores_gemma":[0.91586447,0.000030446348,0.081373096,0.0002518433,0.0001543294,0.000018480241,0.00224655,0.000019293815,0.00004148467],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983245,0.000036961035,0.0009093606,0.00019065311,0.00029190967,0.00024658392],"domain_scores_gemma":[0.99838877,0.000010853644,0.00075453863,0.00041160663,0.00030973414,0.00012450128],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002061147,0.00029886735,0.00025129775,0.0002147278,0.00024370829,0.00011496165,0.00016297422,0.00043822796,0.00005082058],"category_scores_gemma":[0.00015075848,0.00025604363,0.000055984132,0.00018791591,0.00026388507,0.00022920748,0.00018248879,0.0005027835,9.0326785e-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":[0.00020505449,0.00001749709,0.003460821,0.0013627645,0.0000963718,1.3484564e-7,0.00041577904,0.00012642368,0.9783007,0.0003168941,0.00009527848,0.015602294],"study_design_scores_gemma":[0.005422131,0.0015246969,0.12904114,0.00016125575,0.0003753056,0.0007994483,0.0006189355,0.3637152,0.47940442,0.0013593618,0.015890237,0.0016878918],"about_ca_topic_score_codex":0.000023214032,"about_ca_topic_score_gemma":0.00001801438,"teacher_disagreement_score":0.49889627,"about_ca_system_score_codex":0.000021795182,"about_ca_system_score_gemma":0.00019340227,"threshold_uncertainty_score":0.99998915},"labels":[],"label_agreement":null},{"id":"W2125916810","doi":"10.1109/lascas.2013.6518997","title":"An application of the empirical mode decomposition to brain magnetic resonance images classification","year":2013,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Hilbert–Huang transform; Support vector machine; Pattern recognition (psychology); Artificial intelligence; Magnetic resonance imaging; Wavelet transform; Computer science; Entropy (arrow of time); Wavelet; Discrete wavelet transform; Contextual image classification; Image (mathematics); Computer vision; Physics; Medicine; Radiology","score_opus":0.013446525103679401,"score_gpt":0.3477719760260998,"score_spread":0.33432545092242044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125916810","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88419634,0.000043640015,0.10877995,0.003674656,0.000024455992,0.00043987788,0.0000064236187,0.000015953006,0.0028186713],"genre_scores_gemma":[0.9811277,0.0000039869615,0.016958889,0.0013362753,0.000038704547,0.00006384537,0.000056444456,0.000007984294,0.0004061879],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9994409,0.000056572706,0.00017509716,0.00013885814,0.00009717611,0.000091392474],"domain_scores_gemma":[0.9993475,0.000009711543,0.000063187435,0.0004498045,0.00008727803,0.000042508836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000087520595,0.00006751087,0.000053578722,0.00001867324,0.000045342687,0.000018088944,0.00022133038,0.00006735286,0.00002486054],"category_scores_gemma":[0.000055143144,0.000048912167,0.000028451537,0.00008534491,0.00003917463,0.0000062569216,0.0000508049,0.00004961503,0.00003319601],"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":[0.000009404084,0.000038601953,0.015558347,0.000008224162,0.0000015080795,4.6278443e-9,0.0000754603,0.00042359118,0.9434863,0.0002567592,0.008158328,0.031983525],"study_design_scores_gemma":[0.00018321298,0.0002990991,0.65695995,0.000006532953,0.0000055521064,0.000004029157,0.000077214354,0.1265199,0.19758895,0.00024897663,0.0179634,0.00014314748],"about_ca_topic_score_codex":0.000063601736,"about_ca_topic_score_gemma":0.00001994583,"teacher_disagreement_score":0.7458973,"about_ca_system_score_codex":0.0000084332,"about_ca_system_score_gemma":0.000016049113,"threshold_uncertainty_score":0.19945803},"labels":[],"label_agreement":null},{"id":"W2130614771","doi":"10.1093/bioinformatics/btt265","title":"DAPPLE: a pipeline for the homology-based prediction of phosphorylation sites","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Phosphorylation; Pipeline (software); Computer science; Computational biology; Homology (biology); Model organism; Organism; Software; Sequence homology; Biology; World Wide Web; Bioinformatics; Programming language; Cell biology; Biochemistry; Genetics; Peptide sequence; Gene","score_opus":0.011620847573372952,"score_gpt":0.23903340122398387,"score_spread":0.22741255365061092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130614771","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11846112,0.0003175187,0.8759515,0.0006624527,0.00029621457,0.0018150671,0.00024669225,0.000056790126,0.002192622],"genre_scores_gemma":[0.89807355,0.000053198786,0.098822944,0.00073340134,0.00017914087,0.0001957065,0.001414569,0.000023885743,0.00050357624],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991331,0.00001473669,0.00046763875,0.00007634201,0.0001344176,0.00017374152],"domain_scores_gemma":[0.99898714,0.00008748436,0.00029584783,0.00037105833,0.0002210991,0.000037399703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027969113,0.00012737131,0.000119758195,0.000043490225,0.00010649514,0.000027181906,0.00021031835,0.00013998969,0.000046959525],"category_scores_gemma":[0.00032733026,0.00008915481,0.000090783615,0.0000919463,0.000104712875,0.000013422577,0.00005251233,0.00007750009,0.00002356796],"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":[0.000538529,0.0004958388,0.046162102,0.0022425347,0.00053774193,2.3983245e-7,0.002841758,0.05156481,0.15093404,0.0028327857,0.54226565,0.19958395],"study_design_scores_gemma":[0.0007135457,0.0002740587,0.0035273524,0.000013188175,0.000037513917,0.0000042125034,0.00021584854,0.9334764,0.02559215,0.00006406936,0.03596637,0.00011530241],"about_ca_topic_score_codex":0.000013032259,"about_ca_topic_score_gemma":0.0000041867256,"teacher_disagreement_score":0.8819116,"about_ca_system_score_codex":0.000009431477,"about_ca_system_score_gemma":0.000060803406,"threshold_uncertainty_score":0.3635628},"labels":[],"label_agreement":null},{"id":"W2132028676","doi":"10.1093/bioinformatics/btp567","title":"Adaptive multi-agent architecture for functional sequence motifs recognition","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Calgary Laboratory Services","keywords":"Computer science; Artificial intelligence; Machine learning; Robustness (evolution); Classifier (UML); Solver; Distributed computing; Biology","score_opus":0.041040487647807274,"score_gpt":0.2765442407598718,"score_spread":0.2355037531120645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132028676","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":[0.027757699,0.000063086554,0.9680744,0.00030501722,0.00027459904,0.0006652597,0.00021013884,0.000070163005,0.0025796567],"genre_scores_gemma":[0.27206898,0.000053546668,0.7207454,0.00314572,0.00043540858,0.00005854847,0.002698007,0.000029796243,0.00076459616],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989692,0.000020402033,0.00039356053,0.00014838472,0.00017875258,0.00028971757],"domain_scores_gemma":[0.99922776,0.00002248963,0.00021041272,0.00027529817,0.00016583891,0.00009819402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021246093,0.00020752459,0.00014018331,0.00007173783,0.00014749248,0.000044268596,0.00016847013,0.00017999836,0.00001624404],"category_scores_gemma":[0.00024066449,0.00018721016,0.00012765698,0.00008620014,0.000054181142,0.000016078422,0.000043656197,0.0001510782,0.000060594095],"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":[0.0011833723,0.00056999736,0.00075789617,0.0005631225,0.0003500814,0.0000035679138,0.0030315877,0.034520593,0.054605834,0.0012517,0.048472855,0.8546894],"study_design_scores_gemma":[0.0055108303,0.0045225876,0.0072725946,0.00017379929,0.00014800773,0.00026891156,0.0011139965,0.7910222,0.039077815,0.0019079858,0.1471514,0.00182991],"about_ca_topic_score_codex":0.0000017586553,"about_ca_topic_score_gemma":0.0000048776687,"teacher_disagreement_score":0.8528595,"about_ca_system_score_codex":0.000031260362,"about_ca_system_score_gemma":0.00007725321,"threshold_uncertainty_score":0.7634209},"labels":[],"label_agreement":null},{"id":"W2132581719","doi":"10.1002/jcc.21053","title":"Prediction of integral membrane protein type by collocated hydrophobic amino acid pairs","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Chemistry","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":89,"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":"Feature selection; Computer science; Classifier (UML); Benchmark (surveying); Transmembrane protein; Feature (linguistics); Transmembrane domain; Integral membrane protein; Sequence (biology); Artificial intelligence; Pattern recognition (psychology); Membrane protein; Algorithm; Biological system; Chemistry; Amino acid; Membrane; Biology; Biochemistry","score_opus":0.008975504715840538,"score_gpt":0.21985608942988472,"score_spread":0.21088058471404417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132581719","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9968599,0.00019407031,0.001986767,0.00007021263,0.00006487477,0.00006174788,0.000026860193,0.0000062954027,0.00072928745],"genre_scores_gemma":[0.9951514,0.000027154487,0.003857606,0.000037142476,0.0001480019,0.0000013577773,0.000248581,0.000012208684,0.0005165319],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989747,0.000027139355,0.0005012428,0.000084972,0.00031094355,0.00010101961],"domain_scores_gemma":[0.99884236,0.000013956731,0.0005065539,0.00009723552,0.0004713525,0.00006857127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015767443,0.00011346095,0.0001710121,0.000029241797,0.000047258472,0.00000601422,0.00016769626,0.00012380008,0.0000491139],"category_scores_gemma":[0.00015252898,0.0001038679,0.00009057983,0.00011676451,0.000103771716,0.000008612924,0.000032579996,0.00020748297,0.0000020227626],"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":[0.00018000562,0.000086658256,0.0014335228,0.00008930023,0.000084142586,0.000004535644,0.000050083712,0.016286861,0.9761193,0.0000013013822,0.005577314,0.000086970205],"study_design_scores_gemma":[0.0008042724,0.00035209273,0.0011565586,0.000051023206,0.00001736655,0.0005302533,0.000034969777,0.0030993505,0.9905336,0.000073402254,0.0032488562,0.00009828162],"about_ca_topic_score_codex":0.000001743363,"about_ca_topic_score_gemma":7.318623e-8,"teacher_disagreement_score":0.014414269,"about_ca_system_score_codex":0.000026556343,"about_ca_system_score_gemma":0.00023636007,"threshold_uncertainty_score":0.42356098},"labels":[],"label_agreement":null},{"id":"W2136711891","doi":"10.1109/cibcb.2010.5510426","title":"Nearest neighbor training of side effect machines for sequence classification","year":2010,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","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":"University of Guelph","funders":"","keywords":"Computer science; Leverage (statistics); Artificial intelligence; Rand index; Support vector machine; Feature (linguistics); k-nearest neighbors algorithm; Machine learning; Pattern recognition (psychology); Algorithm; Cluster analysis","score_opus":0.023441638748774283,"score_gpt":0.31393979000673583,"score_spread":0.2904981512579615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136711891","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9695211,0.000012284743,0.017544715,0.00017615847,0.0001827429,0.00028016322,0.000020359048,0.00002158253,0.012240914],"genre_scores_gemma":[0.97196186,0.0000027207982,0.027193524,0.000103979815,0.00013104557,0.00002699437,0.00016334624,0.000013536963,0.00040300543],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99945104,0.000021538754,0.00019338215,0.00013207489,0.000070140166,0.00013179347],"domain_scores_gemma":[0.99945915,0.0000589613,0.0001148007,0.00026060297,0.000066730514,0.0000397746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028823077,0.00009715856,0.00010822159,0.000025539874,0.00004744988,0.000014397334,0.00015650211,0.00011658281,0.00002214238],"category_scores_gemma":[0.0006237308,0.00007787296,0.00006565699,0.00004152356,0.000067584304,0.0000036729768,0.00003135971,0.00010398865,0.0000037361722],"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":[0.000037243975,0.000008425355,0.005819222,0.000059488055,0.000012823855,5.4836953e-8,0.000059915266,0.000040080737,0.9696713,0.001972411,0.00020706773,0.022111928],"study_design_scores_gemma":[0.0012426907,0.0010913414,0.025155645,0.00002091594,0.00004036712,0.000031523636,0.00008723692,0.118412554,0.81797135,0.00033068313,0.035230797,0.00038492095],"about_ca_topic_score_codex":0.000015842295,"about_ca_topic_score_gemma":0.000054440978,"teacher_disagreement_score":0.15170002,"about_ca_system_score_codex":0.0000023659825,"about_ca_system_score_gemma":0.00004110994,"threshold_uncertainty_score":0.3175567},"labels":[],"label_agreement":null},{"id":"W2143497908","doi":"10.1007/978-3-319-06483-3_1","title":"A Novel Particle Swarm-Based Approach for 3D Motif Matching and Protein Structure Classification","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Particle swarm optimization; Motif (music); Computer science; Pattern recognition (psychology); Artificial intelligence; Pattern matching; Algorithm","score_opus":0.01429931309546476,"score_gpt":0.24404978799078272,"score_spread":0.22975047489531797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143497908","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":[0.008208598,0.000049340062,0.9906106,0.00013710628,0.00009446488,0.0006021344,0.000018858198,0.00001896699,0.0002599067],"genre_scores_gemma":[0.4320498,0.0000010150825,0.5672037,0.00037001586,0.00017451982,0.0000132494215,0.00007781811,0.000020169415,0.000089729925],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864495,0.000013671248,0.00025640073,0.00057127204,0.00022672741,0.00028700917],"domain_scores_gemma":[0.9991099,0.000043598036,0.00020597258,0.00046801704,0.00009859795,0.00007386722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040254573,0.00025558035,0.00020071332,0.00008690619,0.00013947675,0.00012600217,0.0003978636,0.00029102762,0.0000020468422],"category_scores_gemma":[0.00010767687,0.00022391246,0.000046202054,0.00006175959,0.00028705015,0.0000070135134,0.00017356053,0.00028384512,6.0583875e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008647694,0.000046211142,0.00025740924,0.0007441098,0.000029947527,6.804771e-7,0.00041997415,0.33735895,0.34955233,0.0044462224,0.000020843936,0.30703682],"study_design_scores_gemma":[0.00039661818,0.00018685729,0.00009237071,0.000074249874,0.000009376024,0.0000117599375,2.8483421e-7,0.9750815,0.01936516,0.002968744,0.0015028096,0.00031027524],"about_ca_topic_score_codex":0.000005000901,"about_ca_topic_score_gemma":0.000013826448,"teacher_disagreement_score":0.63772255,"about_ca_system_score_codex":0.000033116645,"about_ca_system_score_gemma":0.00013570103,"threshold_uncertainty_score":0.9130885},"labels":[],"label_agreement":null},{"id":"W2143507938","doi":"10.1145/956750.956800","title":"Frequent-subsequence-based prediction of outer membrane proteins","year":2003,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Bacterial outer membrane; Subsequence; Support vector machine; Computational biology; Classifier (UML); Bacteria; Membrane protein; Computer science; Artificial intelligence; Biology; Bioinformatics; Machine learning; Biochemistry; Membrane; Mathematics; Gene; Genetics","score_opus":0.01055053056386303,"score_gpt":0.22808657895268855,"score_spread":0.2175360483888255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143507938","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8171511,0.00007872345,0.10291007,0.00016034699,0.00020270095,0.00053288235,0.00004070929,0.000050303566,0.07887315],"genre_scores_gemma":[0.96946603,0.000008325266,0.029045478,0.0002446443,0.000033462416,0.000018462219,0.00009551673,0.000011570086,0.0010765361],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99933225,0.000050571183,0.00022719782,0.00012761255,0.00012728914,0.00013507898],"domain_scores_gemma":[0.999497,0.0000053101435,0.00009317716,0.00029097454,0.00007032444,0.00004323408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018885966,0.00009668761,0.0000896571,0.000033637054,0.000029539482,0.000008461321,0.00010003397,0.00010909448,0.00018327154],"category_scores_gemma":[0.00015565887,0.0000818679,0.000058979545,0.00006010253,0.000057593876,0.0000031156799,0.000014938509,0.000069638394,0.00001188627],"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":[0.000027512438,0.00007618079,0.014222803,0.0000862284,0.000036624955,0.0000010151425,0.00003646425,0.0013174694,0.98088527,0.0021507263,0.0006379659,0.00052173954],"study_design_scores_gemma":[0.00051163044,0.00027480614,0.00095963385,0.000012561238,0.000009519371,0.000008973685,0.000018122404,0.0013615969,0.97523445,0.000042717027,0.021467505,0.00009848314],"about_ca_topic_score_codex":0.000013241676,"about_ca_topic_score_gemma":0.000007089957,"teacher_disagreement_score":0.15231489,"about_ca_system_score_codex":0.000008280776,"about_ca_system_score_gemma":0.00007449434,"threshold_uncertainty_score":0.33384758},"labels":[],"label_agreement":null},{"id":"W2143633031","doi":"10.1109/icmla.2006.27","title":"Impact of the Predicted Protein Structural Content on Prediction of Structural Classes for the Twilight Zone Proteins","year":2006,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sequence (biology); Representation (politics); Protein structure prediction; Protein sequencing; Protein secondary structure; Computer science; Artificial intelligence; In silico; Class (philosophy); Pattern recognition (psychology); Protein structure; Alpha (finance); Mathematics; Peptide sequence; Biology; Statistics; Biochemistry","score_opus":0.01096550922401967,"score_gpt":0.2534153032325261,"score_spread":0.24244979400850641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143633031","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9943863,0.00004822463,0.002835311,0.00013945968,0.000094420124,0.0017687387,0.0003249666,0.000013663171,0.00038890724],"genre_scores_gemma":[0.9975802,0.0000013193248,0.0012130796,0.000019616873,0.00013397312,0.000065890934,0.00013871789,0.000013119478,0.00083412393],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99906707,0.00004972696,0.00037600767,0.00013314548,0.00020542309,0.00016860389],"domain_scores_gemma":[0.9990337,0.000027780785,0.00031447408,0.00041307427,0.00018988115,0.000021112373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011231993,0.00015350454,0.00014270046,0.00002311684,0.0001025645,0.000013190033,0.00026709016,0.00011140166,0.000024214385],"category_scores_gemma":[0.0001630056,0.000068908696,0.0002082263,0.000079081336,0.00015407929,0.000005335078,0.00007039411,0.000110796966,1.8242352e-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":[0.0005279848,0.000040661118,0.06556579,0.000114336835,0.00020943135,5.2587463e-8,0.00006645661,0.005605737,0.92450804,0.001167795,0.001300194,0.0008935049],"study_design_scores_gemma":[0.0008702325,0.0013215097,0.5366418,0.000030217729,0.000032826378,0.0000061378955,0.000038598504,0.01752209,0.44297397,0.000089922425,0.00038743712,0.00008528865],"about_ca_topic_score_codex":0.00027661168,"about_ca_topic_score_gemma":0.00007321468,"teacher_disagreement_score":0.4815341,"about_ca_system_score_codex":0.000021707394,"about_ca_system_score_gemma":0.00007760269,"threshold_uncertainty_score":0.2810015},"labels":[],"label_agreement":null},{"id":"W2143801201","doi":"10.1093/bioinformatics/btn463","title":"Improving subcellular localization prediction using text classification and the gene ontology","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Gene ontology; Computer science; Hierarchy; Mechanism (biology); Protein function prediction; Ontology; Function (biology); Artificial intelligence; Data mining; Sequence (biology); Protein sequencing; Information retrieval; Natural language processing; Computational biology; Machine learning; Gene; Protein function; Biology; Peptide sequence; Genetics; Gene expression","score_opus":0.015766448245103544,"score_gpt":0.22927907549808127,"score_spread":0.21351262725297773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143801201","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40834475,0.00030311185,0.58964294,0.00009061704,0.00017216132,0.00033781017,0.000010782267,0.000035763755,0.0010621059],"genre_scores_gemma":[0.96609634,0.0003938427,0.032461878,0.00041788947,0.00016858953,0.000012218487,0.00028883672,0.000018986117,0.00014140499],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990371,0.00006193342,0.00044230086,0.0001147339,0.00015793268,0.00018602004],"domain_scores_gemma":[0.9992217,0.000021464248,0.00028506425,0.00032591764,0.00009459635,0.000051302304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035353593,0.00014250122,0.00013421338,0.000053723466,0.00036219475,0.000034267377,0.00013702697,0.00017440296,0.000004565366],"category_scores_gemma":[0.00022436386,0.000106062966,0.0000469305,0.0000998403,0.00031662572,0.00002212711,0.0000998583,0.00011643777,0.000008673292],"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":[0.0025376985,0.00048182163,0.3202045,0.0026078175,0.0009923095,0.000017529781,0.032975454,0.08160797,0.430546,0.01989461,0.013243782,0.09489053],"study_design_scores_gemma":[0.0010291048,0.00007759335,0.0025348058,0.000007467267,0.00003193764,0.00027382324,0.00024430195,0.98707515,0.0038304338,0.00002212465,0.004739525,0.00013372685],"about_ca_topic_score_codex":0.000034257904,"about_ca_topic_score_gemma":0.000006019415,"teacher_disagreement_score":0.9054672,"about_ca_system_score_codex":0.000025099796,"about_ca_system_score_gemma":0.000068434056,"threshold_uncertainty_score":0.43251222},"labels":[],"label_agreement":null},{"id":"W2144499799","doi":"10.1007/978-3-642-24797-2","title":"Supervised Sequence Labelling with Recurrent Neural Networks","year":2012,"lang":"en","type":"book","venue":"Studies in computational intelligence","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3084,"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":"Labelling; Computer science; Sequence (biology); Artificial intelligence; Artificial neural network; Recurrent neural network; Machine learning; Pattern recognition (psychology); Biology; Genetics","score_opus":0.06960736389883783,"score_gpt":0.35404997795921056,"score_spread":0.28444261406037274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144499799","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":[0.008856617,0.092653364,0.7923367,0.0006433577,0.005795483,0.0028161937,0.00020502249,0.00020741021,0.09648586],"genre_scores_gemma":[0.76758355,0.012160378,0.11135897,0.002308425,0.0044293627,0.00027055637,0.0058304416,0.00035519185,0.095703095],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836916,0.00006761252,0.0005096454,0.00037793862,0.00031442582,0.00036120985],"domain_scores_gemma":[0.9988939,0.00019633073,0.00025535605,0.0002622518,0.00032647955,0.00006569348],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030695257,0.0003761573,0.00034316443,0.00008976984,0.00010877159,0.0000243889,0.00035614782,0.00021231994,0.000019869314],"category_scores_gemma":[0.000119522294,0.0003290859,0.00007436542,0.000112430396,0.00040369848,0.0000082021525,0.00029691457,0.00056597247,0.000018953866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059940623,0.00002890887,0.00088719424,0.00021779873,0.00018247239,0.000009625002,0.00048377007,0.9813522,0.0000030864858,0.0017283169,0.0025768126,0.0124698775],"study_design_scores_gemma":[0.00029237036,0.0007317593,0.00015183036,0.001031972,0.00009017677,0.00013477511,0.00035964214,0.9630393,0.000056769946,0.0034967295,0.029301396,0.0013132925],"about_ca_topic_score_codex":0.0000030789854,"about_ca_topic_score_gemma":0.000027976645,"teacher_disagreement_score":0.75872695,"about_ca_system_score_codex":0.00012359419,"about_ca_system_score_gemma":0.00015308472,"threshold_uncertainty_score":0.99991614},"labels":[],"label_agreement":null},{"id":"W2145023212","doi":"10.1093/bioinformatics/btr657","title":"Prediction and analysis of nucleotide-binding residues using sequence and sequence-derived structural descriptors","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":137,"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":"Killam Trusts","keywords":"Sequence (biology); Computational biology; Sequence alignment; Peptide sequence; Sequence analysis; Nucleotide; Multiple sequence alignment; Protein sequencing; Binding site; Sequence logo; Sequence motif; Consensus sequence; Conserved sequence; Biology; Biochemistry; Gene","score_opus":0.05324823264434206,"score_gpt":0.2742169801333416,"score_spread":0.22096874748899956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145023212","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9951564,0.000065370514,0.0038995817,0.0000040375653,0.000068000954,0.00012467563,0.00010655221,0.000020376241,0.00055498554],"genre_scores_gemma":[0.90818727,0.00010924884,0.09148451,0.000035469155,0.000017338847,0.0000014359931,0.00013748025,0.000010261431,0.000016979408],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903136,0.000029656658,0.00047586122,0.00012724273,0.00014559571,0.00019029343],"domain_scores_gemma":[0.9992514,0.000011941692,0.00032664166,0.00024309166,0.00008375175,0.0000831293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021302488,0.00016317883,0.00022687568,0.00020388722,0.00012038138,0.000034204444,0.0001214308,0.00013137118,0.000014111852],"category_scores_gemma":[0.00012372782,0.0001471214,0.000057821417,0.00024022136,0.00023692475,0.00004445947,0.00014227416,0.00009225012,6.7198397e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010380045,0.0000166267,0.5978204,0.00047109104,0.0010786871,0.0000019930364,0.0114404205,0.00074318924,0.3825969,0.00045104307,0.000060939004,0.0052148863],"study_design_scores_gemma":[0.0006273041,0.00047076706,0.14926386,0.00009826153,0.0010318557,0.00008415028,0.0029735654,0.75660604,0.08804028,0.0000994066,0.00016391497,0.0005406129],"about_ca_topic_score_codex":0.000073199895,"about_ca_topic_score_gemma":0.00001735336,"teacher_disagreement_score":0.75586283,"about_ca_system_score_codex":0.000017842445,"about_ca_system_score_gemma":0.0000381757,"threshold_uncertainty_score":0.5999437},"labels":[],"label_agreement":null},{"id":"W2145270588","doi":"10.1186/1477-5956-11-s1-s5","title":"Predicting beta-turns in proteins using support vector machines with fractional polynomials","year":2013,"lang":"en","type":"article","venue":"Proteome Science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China; Central South University; Ministry of Education of the People's Republic of China; City University of Hong Kong","keywords":"Support vector machine; Computer science; Stability (learning theory); Artificial intelligence; Protein secondary structure; Folding (DSP implementation); Machine learning; Logistic regression; Position (finance); Pattern recognition (psychology); Algorithm; Data mining; Mathematics; Chemistry","score_opus":0.010042241274763584,"score_gpt":0.2643495973709819,"score_spread":0.2543073560962183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145270588","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9946145,0.000016822805,0.0024885903,0.0002725633,0.00007671856,0.00087525614,0.000005731344,0.00001969713,0.0016301617],"genre_scores_gemma":[0.9650072,0.0000016783014,0.034392975,0.00011768323,0.000137961,0.000113938935,0.000010437976,0.000012979657,0.00020518825],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99867874,0.000031068677,0.00025001148,0.00031201632,0.00035901472,0.0003691228],"domain_scores_gemma":[0.9993278,0.000009046067,0.00016998684,0.00026470385,0.00012730513,0.000101156475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000561363,0.00014374689,0.00012179633,0.00012612533,0.0001648092,0.00011773841,0.000340563,0.000067308996,0.00012407599],"category_scores_gemma":[0.00026645602,0.00011111204,0.000025860956,0.0003506446,0.00029376225,0.00005857913,0.00016356028,0.00018906184,0.000025023868],"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":[0.000020433858,0.000033625452,0.25825018,0.000040954565,0.000006899823,0.0000012331673,0.00018107357,0.0013064019,0.7397268,0.000026271904,0.000022985461,0.00038317151],"study_design_scores_gemma":[0.001098666,0.0010057776,0.48214656,0.000111879024,0.0000146927605,0.00024454042,0.00016150555,0.07100833,0.44146428,0.00009753357,0.0018971877,0.0007490635],"about_ca_topic_score_codex":0.00032522497,"about_ca_topic_score_gemma":0.00004901196,"teacher_disagreement_score":0.2982625,"about_ca_system_score_codex":0.000043881737,"about_ca_system_score_gemma":0.0003423722,"threshold_uncertainty_score":0.45310172},"labels":[],"label_agreement":null},{"id":"W2147335610","doi":"10.1093/nar/gki120","title":"PA-GOSUB: a searchable database of model organism protein sequences with their predicted Gene Ontology molecular function and subcellular localization","year":2004,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gene ontology; Biology; Proteome; Annotation; Function (biology); Subcellular localization; Computational biology; Model organism; Gene; Gene Annotation; Ontology; Database; Organism; Genome; Bioinformatics; Genetics; Computer science; Gene expression","score_opus":0.020756307281521506,"score_gpt":0.28105181049911615,"score_spread":0.26029550321759465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147335610","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7092549,0.00021723445,0.2895895,0.00015407438,0.0000080102545,0.00044198261,0.000032100095,0.000018582088,0.00028361237],"genre_scores_gemma":[0.9854753,0.00010525561,0.013750004,0.000055669985,0.000029684687,0.00004094609,0.00037491205,0.000036023954,0.00013219871],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983162,0.00018993033,0.00024454255,0.00035535585,0.00049579586,0.00039816988],"domain_scores_gemma":[0.99886984,0.000012235551,0.000083091036,0.00049609505,0.0004136608,0.0001250919],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076154066,0.00016249371,0.00017045587,0.00014447558,0.00017211089,0.00003395459,0.0002599872,0.00020585489,0.000021701871],"category_scores_gemma":[0.00018667043,0.00013071897,0.000026477423,0.00032357528,0.00051236013,0.000020771982,0.0002657131,0.00033072906,0.0000035630176],"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":[0.00031633268,0.00008081163,0.0018578055,0.00021577215,0.000058027505,0.000008375213,0.00028804265,0.017047899,0.9782842,0.0015108732,0.00002854689,0.00030331503],"study_design_scores_gemma":[0.0014476314,0.0020059294,0.00038390825,0.000093352835,0.000017227558,0.000048933995,0.0003214749,0.11434036,0.8787162,0.0020007654,0.0004085135,0.00021573139],"about_ca_topic_score_codex":0.00015177602,"about_ca_topic_score_gemma":0.000042467538,"teacher_disagreement_score":0.27622038,"about_ca_system_score_codex":0.000042818538,"about_ca_system_score_gemma":0.0003600575,"threshold_uncertainty_score":0.5330565},"labels":[],"label_agreement":null},{"id":"W2148271643","doi":"10.1093/bioinformatics/btv060","title":"Computational identification of MoRFs in protein sequences","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":99,"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 Institutes of Health Research; Genome Canada","keywords":"Computer science; Support vector machine; Identification (biology); Sequence (biology); Artificial intelligence; Computational biology; Data mining; Set (abstract data type); Machine learning; Pattern recognition (psychology); Biology; Genetics","score_opus":0.01588503249904103,"score_gpt":0.2752276049529452,"score_spread":0.25934257245390413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148271643","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9578253,0.000062799416,0.036344036,0.00010643901,0.000088507004,0.0003332973,0.000022784561,0.00001603884,0.0052008135],"genre_scores_gemma":[0.95022297,0.000004140103,0.049266312,0.00005918998,0.000026629696,0.00001176775,0.00019791756,0.000006428236,0.0002046421],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900097,0.000026134747,0.00056895573,0.00006508335,0.00022157599,0.00011729626],"domain_scores_gemma":[0.9993374,0.0000073281303,0.00028070883,0.00018704498,0.00013693799,0.00005058802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047371292,0.000086075,0.000102460355,0.00008365383,0.000017514529,0.00001888121,0.00017364358,0.000081860475,0.0000035840626],"category_scores_gemma":[0.00028722314,0.00008087633,0.000029568493,0.00013623542,0.000071963725,0.000016019965,0.000063615706,0.000065665285,0.000025745147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046790115,0.0006981196,0.110889606,0.0021892628,0.00021408286,0.0000059345393,0.016168721,0.696732,0.10190542,0.021209206,0.013201686,0.036318082],"study_design_scores_gemma":[0.0020566715,0.00059296156,0.011318178,0.00010790432,0.000014983853,0.000039489845,0.0023824815,0.8965242,0.07379486,0.002792018,0.009825882,0.00055036985],"about_ca_topic_score_codex":0.0000128807105,"about_ca_topic_score_gemma":0.000006545612,"teacher_disagreement_score":0.19979222,"about_ca_system_score_codex":0.000018742083,"about_ca_system_score_gemma":0.00013958136,"threshold_uncertainty_score":0.3298041},"labels":[],"label_agreement":null},{"id":"W2150408357","doi":"10.1093/nar/gkh485","title":"Proteome Analyst: custom predictions with explanations in a web-based tool for high-throughput proteome annotations","year":2004,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":100,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Proteome; Gene ontology; Classifier (UML); Naive Bayes classifier; Computer science; Biology; Human proteome project; Bayes' theorem; Function (biology); Machine learning; Protein function; Artificial intelligence; Protein function prediction; Computational biology; Bioinformatics; Gene; Proteomics; Bayesian probability; Genetics; Support vector machine; Gene expression","score_opus":0.020655106452283425,"score_gpt":0.32707769482861837,"score_spread":0.30642258837633496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150408357","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9082172,0.000023978631,0.083990395,0.0028984626,0.000039222385,0.0030035442,0.00021626691,0.00006641921,0.0015445419],"genre_scores_gemma":[0.941668,0.000010113125,0.05512609,0.00009123999,0.00012628539,0.0019175282,0.000555519,0.00004082147,0.0004644324],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99809945,0.00012516447,0.00034735218,0.00037811336,0.00052628154,0.0005236629],"domain_scores_gemma":[0.998722,0.000057726746,0.000083731735,0.00054175564,0.00049526436,0.00009951926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008465347,0.00017083311,0.00016931677,0.00043404158,0.00039148974,0.000091577494,0.00034127856,0.00019234042,0.000040733543],"category_scores_gemma":[0.0006293913,0.00015120917,0.00006170379,0.00087321363,0.00023337477,0.000025507145,0.00008721816,0.00044039506,0.000032254342],"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":[0.0027281477,0.0027460984,0.070652805,0.0012037244,0.0006200858,0.000042849206,0.0031794405,0.4010558,0.48645523,0.015998391,0.011822416,0.0034950057],"study_design_scores_gemma":[0.06670774,0.024637448,0.24414031,0.0014000562,0.00027872281,0.00020021119,0.004136654,0.19273646,0.26461574,0.0089010205,0.1877462,0.0044994135],"about_ca_topic_score_codex":0.000099423894,"about_ca_topic_score_gemma":0.0005369356,"teacher_disagreement_score":0.22183947,"about_ca_system_score_codex":0.00014453691,"about_ca_system_score_gemma":0.00077224296,"threshold_uncertainty_score":0.6166131},"labels":[],"label_agreement":null},{"id":"W2150429539","doi":"10.1007/11691730_5","title":"Frequent Subsequence-Based Protein Localization","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Subsequence; Computer science; Support vector machine; Boosting (machine learning); Extracellular; Artificial intelligence; Computational biology; Biochemistry; Biology; Mathematics","score_opus":0.007828164709343928,"score_gpt":0.22877188275417537,"score_spread":0.22094371804483146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150429539","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":[0.0008144914,0.00018843407,0.9931766,0.00015607502,0.00025908314,0.00040375805,0.00000878916,0.00003232185,0.004960469],"genre_scores_gemma":[0.7317557,0.000016878183,0.26187783,0.0027989498,0.0010250694,0.000030163123,0.0005634455,0.000096796226,0.0018352102],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982317,0.000022495113,0.00036226283,0.000590546,0.00045759734,0.00033538716],"domain_scores_gemma":[0.99886435,0.0000213226,0.00023626524,0.00064674736,0.00016264328,0.00006866452],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003603285,0.0003266261,0.00021318995,0.00022038445,0.00012205194,0.00011311722,0.00067916815,0.00037677345,0.000022667378],"category_scores_gemma":[0.00009497926,0.00030318485,0.00007956082,0.00014355266,0.00050761446,0.000007971291,0.00020547095,0.0003577175,0.000016556207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019043537,0.000029651912,0.0005733887,0.0001408006,0.00001005611,0.000019140258,0.00004305025,0.925106,0.0117790885,0.0010354596,0.00016262638,0.06108171],"study_design_scores_gemma":[0.0006326899,0.0006339639,0.0001612913,0.000624668,0.00001663363,0.000035585494,8.915704e-8,0.81540006,0.13795125,0.013951744,0.0293164,0.0012755945],"about_ca_topic_score_codex":0.000029233099,"about_ca_topic_score_gemma":0.000082477156,"teacher_disagreement_score":0.73129874,"about_ca_system_score_codex":0.00011149188,"about_ca_system_score_gemma":0.00043763182,"threshold_uncertainty_score":0.999942},"labels":[],"label_agreement":null},{"id":"W2151031196","doi":"10.1093/bioinformatics/btr525","title":"Computational prediction of eukaryotic phosphorylation sites","year":2011,"lang":"en","type":"review","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":157,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Phosphorylation; Kinase; Computational biology; Protein phosphorylation; Mechanism (biology); Resource (disambiguation); Sequence (biology); Posttranslational modification; Biology; Computer science; Bioinformatics; Protein kinase A; Biochemistry; Enzyme","score_opus":0.029212896477216817,"score_gpt":0.2834585629456036,"score_spread":0.2542456664683868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151031196","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":[0.000041138603,0.9768348,0.015081429,0.0000014280088,0.00026451668,0.00064599724,0.00039729188,0.000042987063,0.0066904183],"genre_scores_gemma":[0.000052313615,0.95579386,0.037013333,0.000025094929,0.00012291361,0.000021544107,0.006670414,0.00004264278,0.00025786142],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99813175,0.000053698408,0.0012332366,0.00015010835,0.00022580501,0.00020539729],"domain_scores_gemma":[0.9981927,0.00003936236,0.0011018394,0.00044092338,0.00015290054,0.00007222326],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028268408,0.00034927807,0.0006695687,0.0001754697,0.00006393092,0.00002304487,0.00032376134,0.00046547098,0.000054587003],"category_scores_gemma":[0.000163801,0.00030292865,0.00033137994,0.00018715732,0.000101716665,0.000014054833,0.00016544192,0.00022149114,0.00010682927],"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":[0.000019411424,0.00011128058,0.0003456848,0.037501603,0.000514118,4.909408e-7,0.0005159305,0.0007836873,0.0000026345215,0.00088218565,0.008827915,0.95049506],"study_design_scores_gemma":[0.00021344585,0.0002709664,0.000081107704,0.0015849037,0.0003643629,0.000053684922,0.000029799698,0.012200681,0.000016801992,0.000050428607,0.98480344,0.0003304081],"about_ca_topic_score_codex":0.0000024522938,"about_ca_topic_score_gemma":6.4333517e-7,"teacher_disagreement_score":0.9759755,"about_ca_system_score_codex":0.000029636965,"about_ca_system_score_gemma":0.00024951214,"threshold_uncertainty_score":0.9999423},"labels":[],"label_agreement":null},{"id":"W2151790371","doi":"10.1093/bioinformatics/btg447","title":"Predicting subcellular localization of proteins using machine-learned classifiers","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":334,"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":"Subcellular localization; Computer science; Artificial intelligence; Protein subcellular localization prediction; Machine learning; Computational biology; Pattern recognition (psychology); Chemistry; Biology; Biochemistry; Cytoplasm; Gene","score_opus":0.016360328509057477,"score_gpt":0.2565539395148381,"score_spread":0.24019361100578066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151790371","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43751603,0.000117545365,0.55925953,0.00004396578,0.00014039996,0.00041456826,0.000025081523,0.00004635561,0.0024365042],"genre_scores_gemma":[0.87510884,0.000051026804,0.124206215,0.0001646685,0.00008801662,0.000006408234,0.00026997484,0.000033526787,0.00007132959],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986153,0.000029800796,0.0006653707,0.00012634824,0.00028835697,0.00027480998],"domain_scores_gemma":[0.9989064,0.0000077181685,0.0004562255,0.00041076064,0.00012781496,0.00009113401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003133821,0.0001994204,0.00019471179,0.000103594815,0.00013169978,0.00003310751,0.00024020746,0.00021596892,0.000011209612],"category_scores_gemma":[0.00028526332,0.00018866111,0.00010003563,0.00020580238,0.00012030164,0.000023195444,0.00014186083,0.00015534481,0.000011223259],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032321858,0.00038783104,0.11869975,0.0029588009,0.00041502208,0.0000064811643,0.0060111927,0.65702313,0.20492089,0.0034793327,0.00029238296,0.0054819775],"study_design_scores_gemma":[0.0014565459,0.0004485492,0.00025551833,0.00014401674,0.000053350894,0.000050914554,0.0006580178,0.79996437,0.19169345,0.00013213114,0.0047519784,0.00039113572],"about_ca_topic_score_codex":0.00007791262,"about_ca_topic_score_gemma":0.000019871815,"teacher_disagreement_score":0.4375928,"about_ca_system_score_codex":0.000048440448,"about_ca_system_score_gemma":0.00016831791,"threshold_uncertainty_score":0.76933765},"labels":[],"label_agreement":null},{"id":"W2152193127","doi":"10.1109/cibcb.2012.6217244","title":"Sequence learning: analysis and solutions for sparse data in high dimensional spaces","year":2012,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regularization (linguistics); Early stopping; Computer science; Artificial intelligence; Curse of dimensionality; Machine learning; Sequence (biology); Artificial neural network; Theoretical computer science; Algorithm; Pattern recognition (psychology)","score_opus":0.04022862066872505,"score_gpt":0.31012108508172426,"score_spread":0.2698924644129992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152193127","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96517795,0.00028710772,0.033454746,0.00037810332,0.000051461677,0.0001215702,0.00004778953,0.000012788021,0.0004684986],"genre_scores_gemma":[0.97179174,0.000037321166,0.026010342,0.0001126388,0.000062608815,0.0000068693776,0.0011950987,0.0000059972926,0.0007774021],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993481,0.000034143508,0.00013832394,0.00015768784,0.00006981018,0.0002519103],"domain_scores_gemma":[0.9995163,0.00003332813,0.000054652504,0.00030812895,0.000025339046,0.00006227027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004981267,0.000079752004,0.00010265299,0.00007051902,0.00008346426,0.000019225548,0.00013371494,0.000070017726,0.000028692828],"category_scores_gemma":[0.00029753198,0.00006930909,0.000026200887,0.00013029495,0.000051724306,0.000012080466,0.00033353159,0.00007643582,0.0000039495317],"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":[0.000045994824,0.000095717376,0.95458186,0.000039309583,0.0003156375,3.7733466e-7,0.00013812978,0.007954389,0.029177306,0.003031427,0.002285614,0.0023342278],"study_design_scores_gemma":[0.0015425129,0.0003600431,0.3775197,0.000017522365,0.0005972992,0.000032537617,0.00037098528,0.5029694,0.005953238,0.00016308912,0.109628536,0.00084517343],"about_ca_topic_score_codex":0.00013539472,"about_ca_topic_score_gemma":0.00022197253,"teacher_disagreement_score":0.5770622,"about_ca_system_score_codex":0.0000055388155,"about_ca_system_score_gemma":0.000020451229,"threshold_uncertainty_score":0.28263426},"labels":[],"label_agreement":null},{"id":"W2152856869","doi":"10.1186/1477-5956-9-s1-s4","title":"ATPsite: sequence-based prediction of ATP-binding residues","year":2011,"lang":"en","type":"article","venue":"Proteome Science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":81,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts","keywords":"Support vector machine; Dihedral angle; Classifier (UML); Annotation; Computer science; Machine learning; Artificial intelligence; Matthews correlation coefficient; Sequence (biology); Sequence alignment; Computational biology; Data mining; Bioinformatics; Peptide sequence; Biology; Chemistry; Biochemistry; Gene","score_opus":0.038240755086942566,"score_gpt":0.2718583389464778,"score_spread":0.23361758385953524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152856869","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9871611,0.000019667781,0.005588845,0.000032954533,0.00009477264,0.00023836516,0.000016522445,0.000024858615,0.006822933],"genre_scores_gemma":[0.96254444,0.0000047766835,0.037133045,0.00004572608,0.00003162445,0.00001695943,0.000012904448,0.0000064514215,0.00020406333],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99910337,0.000021138954,0.00019604606,0.0002067704,0.00026562097,0.00020705626],"domain_scores_gemma":[0.9993392,0.0000043556006,0.00014654492,0.0003183339,0.0001301408,0.00006137739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064355065,0.000082641774,0.00007377737,0.000098274504,0.00012610502,0.000016561671,0.00038162014,0.00005809019,0.000031775526],"category_scores_gemma":[0.00032455203,0.0000728015,0.000031079042,0.00030501588,0.00048832106,0.000015859378,0.000106625805,0.00007682901,0.0000128541105],"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":[0.000022448296,0.000016951264,0.02517197,0.000030228648,0.0000028105965,3.8534733e-7,0.00030159455,0.00006214066,0.97350925,0.00011164784,0.000031302567,0.0007392925],"study_design_scores_gemma":[0.00014572055,0.00031399346,0.017939234,0.000029063669,0.000003886024,0.000005043104,0.000035117286,0.0025161086,0.97809714,0.000046519457,0.00078441476,0.00008378549],"about_ca_topic_score_codex":0.00002520271,"about_ca_topic_score_gemma":0.0000020878356,"teacher_disagreement_score":0.0315442,"about_ca_system_score_codex":0.000017608114,"about_ca_system_score_gemma":0.0001875859,"threshold_uncertainty_score":0.29687592},"labels":[],"label_agreement":null},{"id":"W2154202919","doi":"10.1093/bioinformatics/bti057","title":"PSORTb v.2.0: Expanded prediction of bacterial protein subcellular localization and insights gained from comparative proteome analysis","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":723,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Simon Fraser University; Michael Smith Health Research BC","keywords":"Proteome; Computer science; n-gram; Subsequence; Support vector machine; Computational biology; MIT License; Subcellular localization; Biology; Artificial intelligence; Software; Bioinformatics; Genetics; Mathematics; Programming language; Language model","score_opus":0.011121309572131761,"score_gpt":0.23112521259350607,"score_spread":0.22000390302137432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154202919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8251913,0.000059904374,0.17363714,0.000016030457,0.000048915124,0.0005405703,0.00010133965,0.000024481631,0.00038029114],"genre_scores_gemma":[0.9697294,0.00002605553,0.027267003,0.00003309084,0.0000804228,0.000028344662,0.0027909817,0.000010640787,0.00003404932],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987788,0.000043288415,0.00064279774,0.00014902459,0.00022889483,0.00015720002],"domain_scores_gemma":[0.999035,0.000008216559,0.00041219033,0.00032656203,0.00013668802,0.000081312464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013189764,0.0001952533,0.00030729958,0.00015377488,0.00008893712,0.000042868956,0.00013161915,0.0001929874,0.000020511043],"category_scores_gemma":[0.00007239404,0.00017262559,0.00008702922,0.00029815853,0.00012018184,0.00003165229,0.00009198807,0.000090450114,0.0000056225226],"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":[0.0009958898,0.00048005377,0.012944383,0.000900951,0.002956508,0.0000030027736,0.03426037,0.055822358,0.88881236,0.0011789986,0.00046824614,0.0011768983],"study_design_scores_gemma":[0.0045197555,0.0012884049,0.008666976,0.00014256575,0.0006003722,0.000007425035,0.0018988013,0.25254852,0.72466385,0.0006717031,0.004361083,0.0006305194],"about_ca_topic_score_codex":0.000048811286,"about_ca_topic_score_gemma":0.000034997443,"teacher_disagreement_score":0.19672617,"about_ca_system_score_codex":0.000025329247,"about_ca_system_score_gemma":0.000073480616,"threshold_uncertainty_score":0.7039467},"labels":[],"label_agreement":null},{"id":"W2156730759","doi":"10.1016/j.compbiolchem.2006.06.003","title":"A comment on “Prediction of protein structural classes by a new measure of information discrepancy”","year":2006,"lang":"en","type":"letter","venue":"Computational Biology and Chemistry","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Measure (data warehouse); Computer science; Folding (DSP implementation); Protein structure prediction; Homology (biology); Protein folding; Class (philosophy); Computational biology; Protein structure; Artificial intelligence; Data mining; Biology; Genetics; Biochemistry; Amino acid; Engineering","score_opus":0.004579167231730309,"score_gpt":0.22660544648438322,"score_spread":0.22202627925265292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156730759","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6209858,0.0030313854,0.0447376,0.30634537,0.00058522815,0.0020309836,0.01197743,0.0001242046,0.010182],"genre_scores_gemma":[0.70990574,0.000045397832,0.012431166,0.1059564,0.0016240476,0.00006234608,0.16867092,0.0000557109,0.0012482929],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99906635,0.000040728217,0.00044767073,0.00016440883,0.00015239831,0.00012844759],"domain_scores_gemma":[0.9991599,0.000035115543,0.0004925675,0.00016142848,0.00012266618,0.000028351025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007199505,0.00020457673,0.00023256449,0.000031480216,0.00004301543,0.000009245331,0.0001407037,0.0006876638,0.000019560666],"category_scores_gemma":[0.00006345285,0.00018460938,0.00007238016,0.00004007775,0.00016542134,0.0000061490005,0.00006524283,0.00039612138,9.61665e-7],"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":[0.000089033914,0.000021869688,0.0018316606,0.0007698257,0.00016443725,3.9297473e-7,0.00003437349,0.0005225176,0.023566775,0.00014672441,0.9716109,0.0012415024],"study_design_scores_gemma":[0.0017339811,0.0006654845,0.0014018352,0.00029578278,0.000082383594,0.00003235233,0.00002751274,0.0024528801,0.0786923,0.0040543424,0.9100458,0.0005153378],"about_ca_topic_score_codex":0.000022298595,"about_ca_topic_score_gemma":2.6847604e-7,"teacher_disagreement_score":0.20038898,"about_ca_system_score_codex":0.000014501539,"about_ca_system_score_gemma":0.00011170997,"threshold_uncertainty_score":0.7528152},"labels":[],"label_agreement":null},{"id":"W2156934870","doi":"10.1007/s00726-008-0080-3","title":"Secondary structure-based assignment of the protein structural classes","year":2008,"lang":"en","type":"article","venue":"Amino Acids","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":62,"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":"Nankai University; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Protein secondary structure; Sequence (biology); Protein tertiary structure; Set (abstract data type); Structural alignment; Class (philosophy); Structural Classification of Proteins database; Computer science; Structural bioinformatics; Protein structure; Computational biology; Mathematics; Artificial intelligence; Sequence alignment; Peptide sequence; Biology; Biochemistry","score_opus":0.006177676116394938,"score_gpt":0.22117693114734233,"score_spread":0.21499925503094738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156934870","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99725145,0.00006994075,0.0005406613,0.00009984218,0.00011320525,0.00021740275,0.00003634839,0.000009539541,0.0016615879],"genre_scores_gemma":[0.99589103,0.0000018902014,0.0031372244,0.0002636513,0.00007233093,0.000007067043,0.000060640174,0.000012679828,0.0005535042],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992416,0.000058229565,0.00021232238,0.00013516887,0.00019326349,0.00015940177],"domain_scores_gemma":[0.9993276,0.0000080872305,0.00014991008,0.00043072004,0.000048772185,0.000034929773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000053025142,0.00013136737,0.000112320486,0.000020080606,0.000109723274,0.000007466659,0.0002878217,0.00011172218,0.000094266674],"category_scores_gemma":[0.0000765579,0.000088125016,0.000081441,0.000064936685,0.00019716946,0.000003486502,0.000109751796,0.0001595989,0.0000021423475],"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":[0.000049216986,0.000018103332,0.08090229,0.000085292544,0.000048965205,0.0000016373324,0.00013304378,0.00078965846,0.91450995,0.00019322704,0.0011622001,0.0021064344],"study_design_scores_gemma":[0.00047796796,0.00020158535,0.12803951,0.000012756201,0.000009170419,0.000027742963,0.000022560987,0.00062230177,0.86160696,0.000058332284,0.008776472,0.00014466132],"about_ca_topic_score_codex":0.000010903994,"about_ca_topic_score_gemma":0.000009084854,"teacher_disagreement_score":0.052902993,"about_ca_system_score_codex":0.000013140475,"about_ca_system_score_gemma":0.00014736844,"threshold_uncertainty_score":0.3593634},"labels":[],"label_agreement":null},{"id":"W2157232703","doi":"10.1109/cec.2011.5949766","title":"Improving splice-junctions classification employing a novel encoding schema and decision-tree","year":2011,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Ambiguity; Schema (genetic algorithms); splice; Probabilistic logic; Computer science; Artificial intelligence; Decision tree; Encoding (memory); Theoretical computer science; Machine learning; Gene; Genetics; Biology","score_opus":0.0346083247286867,"score_gpt":0.2660168978966394,"score_spread":0.2314085731679527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157232703","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4895566,0.00006185044,0.48500508,0.000027290995,0.0001148738,0.00011544772,0.0000020777513,0.00004001093,0.025076728],"genre_scores_gemma":[0.7829857,0.000031072395,0.21641876,0.00013262632,0.00006749408,0.000011595818,0.000017459733,0.000014756976,0.00032055995],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993046,0.000007880377,0.00021683324,0.000218018,0.0000905327,0.00016216216],"domain_scores_gemma":[0.9994557,0.000018153689,0.00009986913,0.00029151136,0.00006385368,0.0000709322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019137755,0.00011554595,0.00008032027,0.000057903708,0.00014941361,0.000026144518,0.00011776242,0.00011533548,0.00004244103],"category_scores_gemma":[0.00025563035,0.00010309086,0.00003768493,0.000075062424,0.000046866146,0.000010767942,0.00014798842,0.00010451106,0.000016617789],"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":[0.000049355658,0.00007173919,0.024416612,0.000040447103,0.000037771486,4.936422e-7,0.0003828686,0.00001633949,0.8789512,0.0028038411,0.0006202781,0.092609055],"study_design_scores_gemma":[0.005380329,0.0014731948,0.2408911,0.00022406943,0.0002473341,0.0005510221,0.006023063,0.32994467,0.36519298,0.0013680103,0.045979783,0.0027244508],"about_ca_topic_score_codex":0.000051971627,"about_ca_topic_score_gemma":0.000052828607,"teacher_disagreement_score":0.51375824,"about_ca_system_score_codex":0.00000973733,"about_ca_system_score_gemma":0.000028834764,"threshold_uncertainty_score":0.42039233},"labels":[],"label_agreement":null},{"id":"W2159184793","doi":"10.1186/1471-2105-11-420","title":"An improved classification of G-protein-coupled receptors using sequence-derived features","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":50,"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":"Ministry of Education, India","keywords":"G protein-coupled receptor; Jackknife resampling; Computational biology; Identification (biology); Artificial intelligence; Subfamily; Computer science; Principal component analysis; Feature (linguistics); Sequence (biology); Biology; Pattern recognition (psychology); Machine learning; Bioinformatics; Receptor; Genetics; Mathematics; Estimator; Statistics; Gene","score_opus":0.02074571848625936,"score_gpt":0.29216161463697266,"score_spread":0.2714158961507133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159184793","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9305156,0.000018272147,0.0677783,0.000019631334,0.000327874,0.00043227896,0.000024970486,0.00004819867,0.0008349054],"genre_scores_gemma":[0.59603405,0.000007370454,0.4033758,0.000056089684,0.00011861817,0.000010200438,0.00029466467,0.000023927623,0.00007926278],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862874,0.000041141422,0.0006489131,0.00016967246,0.00022224445,0.00028926833],"domain_scores_gemma":[0.99820244,0.000016041042,0.0006013405,0.00081973337,0.00023074205,0.00012968181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004093919,0.00023953653,0.00021900515,0.000103733975,0.00012586857,0.00006238012,0.0004483107,0.0003828354,0.00003901793],"category_scores_gemma":[0.00037176904,0.00021608567,0.00010587261,0.00016096327,0.00020524982,0.00004117177,0.000094337825,0.00032389112,0.000009789837],"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":[0.00005258039,0.00003893918,0.0019315925,0.00016288346,0.000020478425,6.6176064e-8,0.0003250239,0.00043513352,0.9945389,0.00022850191,0.00005395887,0.0022119114],"study_design_scores_gemma":[0.0005299648,0.00028907097,0.0034170276,0.000023360388,0.000025550378,0.000023928267,0.0005779849,0.80434895,0.18931766,0.000035799156,0.0010781974,0.00033251644],"about_ca_topic_score_codex":0.000043359792,"about_ca_topic_score_gemma":0.00010534717,"teacher_disagreement_score":0.80522126,"about_ca_system_score_codex":0.00001683031,"about_ca_system_score_gemma":0.00022633163,"threshold_uncertainty_score":0.88117176},"labels":[],"label_agreement":null},{"id":"W2159289309","doi":"10.2174/1875036200802010037","title":"Sequence-Only Based Prediction of β -Turn Location and Type Using Collocation of Amino Acid Pairs","year":2008,"lang":"en","type":"article","venue":"The Open Bioinformatics Journal","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Sequence (biology); BETA (programming language); Turn (biochemistry); Type (biology); Computer science; Collocation (remote sensing); Threading (protein sequence); Algorithm; Amino acid; Peptide sequence; Protein sequencing; Protein structure prediction; Artificial intelligence; Pattern recognition (psychology); Mathematics; Protein structure; Machine learning; Chemistry; Biology; Biochemistry","score_opus":0.04552403034645246,"score_gpt":0.29228650108852544,"score_spread":0.24676247074207297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159289309","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94365716,0.00012152256,0.054109346,0.00009410425,0.00014300276,0.00034251806,0.000023362672,0.000004690809,0.0015042751],"genre_scores_gemma":[0.9647004,0.00022024573,0.034808982,0.00010045062,0.000047445017,0.0000012886909,0.000058312336,0.000008871005,0.00005400772],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998951,0.00006775979,0.00058784214,0.000055152577,0.000217484,0.00012077075],"domain_scores_gemma":[0.9985234,0.00001901465,0.0007414688,0.00025237168,0.00041235617,0.000051402323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076062046,0.00010609707,0.0001509494,0.0000679028,0.0002229562,0.000042128366,0.00034499436,0.00009050099,0.000012165036],"category_scores_gemma":[0.00023270537,0.00007664999,0.000034959477,0.00019488468,0.00019907985,0.000049705213,0.00012537003,0.000148664,0.0000014246626],"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":[0.0017816593,0.00045891377,0.15755369,0.0018111061,0.000755964,0.00000493374,0.015960222,0.09379302,0.66654223,0.0010658765,0.0073061395,0.052966215],"study_design_scores_gemma":[0.0020067682,0.0013760261,0.02509,0.00033386832,0.00012225058,0.0019459301,0.0015325315,0.8190864,0.14617305,0.00009074655,0.0019504033,0.00029208328],"about_ca_topic_score_codex":0.000020135347,"about_ca_topic_score_gemma":0.0000035958296,"teacher_disagreement_score":0.72529334,"about_ca_system_score_codex":0.000023512948,"about_ca_system_score_gemma":0.00042268753,"threshold_uncertainty_score":0.31256956},"labels":[],"label_agreement":null},{"id":"W2160072419","doi":"10.1093/nar/gkg602","title":"PSORT-B: improving protein subcellular localization prediction for Gram-negative bacteria","year":2003,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":426,"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":"Biology; Computational biology; Subcellular localization; Source code; Probabilistic logic; Protein subcellular localization prediction; Bacterial genome size; Protein sequencing; Genetics; Peptide sequence; Genome; Artificial intelligence; Computer science; Gene","score_opus":0.022780337798328318,"score_gpt":0.3099796708341906,"score_spread":0.28719933303586226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160072419","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79308593,0.00008512637,0.19985595,0.0001022754,0.00015900878,0.0018444648,0.000046080837,0.000054821405,0.0047663185],"genre_scores_gemma":[0.9806186,0.000018300208,0.01672147,0.000044303284,0.0001778448,0.00022040661,0.0002773621,0.00005000945,0.0018717357],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982698,0.0002822946,0.0002838525,0.00033048686,0.00036854166,0.00046502415],"domain_scores_gemma":[0.99893695,0.000033796863,0.00008432401,0.0004047366,0.00043251054,0.00010770218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014725762,0.00014723293,0.00012218862,0.00010925581,0.0003462298,0.000094001356,0.00022143572,0.0002454267,0.000092589704],"category_scores_gemma":[0.0020658686,0.00014219849,0.000068322755,0.00022776947,0.00015185736,0.000014898149,0.000097617325,0.0002758843,0.000029923041],"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":[0.00019060087,0.00008704946,0.0033254873,0.00026727765,0.000045984394,0.0000011295275,0.0002967731,0.00025277262,0.98501974,0.0020302874,0.0029889059,0.005493986],"study_design_scores_gemma":[0.001857838,0.0019482266,0.0014874949,0.000061704435,0.000017294178,0.000015949014,0.0006095298,0.04772964,0.7550562,0.0013240575,0.1894867,0.00040533242],"about_ca_topic_score_codex":0.000020108197,"about_ca_topic_score_gemma":0.0000081899125,"teacher_disagreement_score":0.22996351,"about_ca_system_score_codex":0.00006256799,"about_ca_system_score_gemma":0.0001443403,"threshold_uncertainty_score":0.5798686},"labels":[],"label_agreement":null},{"id":"W2160115185","doi":"10.1371/journal.pgen.1002741","title":"Stratifying Type 2 Diabetes Cases by BMI Identifies Genetic Risk Variants in LAMA1 and Enrichment for Risk Variants in Lean Compared to Obese Cases","year":2012,"lang":"en","type":"article","venue":"PLoS Genetics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":267,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Cancer Institute; National Institute on Alcohol Abuse and Alcoholism; Medical Research Council; National Center for Research Resources; National Institute of Dental and Craniofacial Research; Novartis Pharma; National Institutes of Health; Fondation de France; National Heart, Lung, and Blood Institute; Vetenskapsrådet; Sanofi; European Commission; National Human Genome Research Institute; Wellcome Trust; Agence Nationale de la Recherche; Les Laboratories Pierre Fabre; Institut National de la Santé et de la Recherche Médicale; School of Medicine, Boston University; National Institute of Diabetes and Digestive and Kidney Diseases; Lunds Universitet; National Institute on Drug Abuse; Eli Lilly and Company","keywords":"Type 2 diabetes; Overweight; Obesity; Body mass index; Diabetes mellitus; Single-nucleotide polymorphism; Internal medicine; Genome-wide association study; Biology; Risk factor; Case-control study; Genetic association; Endocrinology; Medicine; Bioinformatics; Genetics; Genotype; Gene","score_opus":0.02014445139635725,"score_gpt":0.2782651669371498,"score_spread":0.2581207155407926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160115185","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9941131,0.0043763276,0.00028808208,0.000026155676,0.00018914924,0.00068243564,0.00025577468,0.000014660565,0.000054305867],"genre_scores_gemma":[0.9897766,0.0011500892,0.008500854,0.00010805316,0.00014272387,0.0000676441,0.00015834477,0.000042052365,0.000053613352],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99818593,0.00014612073,0.0005378319,0.00034775294,0.00018589507,0.00059649436],"domain_scores_gemma":[0.9989418,0.0001646418,0.0002146752,0.00040463966,0.00008685358,0.00018743504],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004048006,0.00028463834,0.00030538035,0.00012404354,0.00011125873,0.00007727317,0.00021838465,0.00017225742,0.000015673375],"category_scores_gemma":[0.0010748614,0.0002915084,0.00004152349,0.00017967989,0.000058319605,0.000013125744,0.00021094955,0.00018466658,0.000010520758],"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":[0.000084371815,0.00029051575,0.9036389,0.00017438979,0.000092599934,0.000006188204,0.00095507194,0.002166391,0.09052083,0.0000050256326,0.0009413037,0.0011244144],"study_design_scores_gemma":[0.003417428,0.0019568775,0.6933162,0.00024567667,0.00035432956,0.000047653088,0.0017580314,0.06497868,0.22898132,0.00018441198,0.0031466968,0.0016126968],"about_ca_topic_score_codex":0.00010907701,"about_ca_topic_score_gemma":0.00064254,"teacher_disagreement_score":0.21032271,"about_ca_system_score_codex":0.000033698067,"about_ca_system_score_gemma":0.000047015143,"threshold_uncertainty_score":0.9999537},"labels":[],"label_agreement":null},{"id":"W2161594258","doi":"10.1109/icdmw.2008.130","title":"Plant Protein Localization Using Discriminative and Frequent Partition-Based Subsequences","year":2008,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Extracellular; Discriminative model; Partition (number theory); Computer science; Classifier (UML); Protein subcellular localization prediction; Artificial intelligence; Computational biology; Biology; Biochemistry; Mathematics; Gene; Combinatorics","score_opus":0.02463159534744171,"score_gpt":0.25580727296860556,"score_spread":0.23117567762116384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161594258","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87684345,0.000054478092,0.12185296,0.000073869574,0.000020886968,0.00016974239,0.000011485718,0.000014628389,0.0009584793],"genre_scores_gemma":[0.98960966,0.000012657724,0.009817188,0.00021096256,0.000030896193,0.000010993184,0.00017530154,0.000006745055,0.00012558473],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995175,0.000036630012,0.00012985557,0.000119678785,0.0000899226,0.00010641905],"domain_scores_gemma":[0.9997523,0.000005451056,0.000061406325,0.00009845432,0.00004196579,0.000040430095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000070538794,0.000083144405,0.000062347484,0.000024362225,0.00012782941,0.000012774525,0.000046998975,0.00005519515,0.000023605078],"category_scores_gemma":[0.00006030149,0.00006775607,0.000018049459,0.000040441817,0.0001240263,0.0000047763087,0.000022719112,0.00004084004,0.0000020312118],"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":[0.00020812928,0.00028283417,0.19915938,0.00041329538,0.00011882238,0.000038756094,0.0016894259,0.043015815,0.7438982,0.007706854,0.0019140766,0.0015543796],"study_design_scores_gemma":[0.0006229768,0.00039557464,0.0050361813,0.00006103566,0.000017689797,0.000076387376,0.00022995638,0.32809633,0.66169775,0.00023332419,0.0031515015,0.00038132278],"about_ca_topic_score_codex":0.000078808866,"about_ca_topic_score_gemma":0.000032925538,"teacher_disagreement_score":0.28508052,"about_ca_system_score_codex":0.000009541926,"about_ca_system_score_gemma":0.000052476193,"threshold_uncertainty_score":0.27630123},"labels":[],"label_agreement":null},{"id":"W2162792752","doi":"10.1093/bioinformatics/btq249","title":"PSORTb 3.0: improved protein subcellular localization prediction with refined localization subcategories and predictive capabilities for all prokaryotes","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2574,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Simon Fraser University; Michael Smith Health Research BC; Cystic Fibrosis Foundation","keywords":"Proteome; Protein subcellular localization prediction; Archaea; Computer science; Subcellular localization; Precision and recall; Computational biology; Interface (matter); Proteomics; Software; Metagenomics; Biology; Bioinformatics; Data mining; Artificial intelligence; Bacteria; Cytoplasm; Genetics; Gene; Programming language","score_opus":0.004537457218943714,"score_gpt":0.21131141928287536,"score_spread":0.20677396206393164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162792752","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20389883,0.00005149547,0.793013,0.0001379432,0.00016743001,0.002012748,0.0001692798,0.000103973194,0.0004453416],"genre_scores_gemma":[0.94022065,0.000039052196,0.054412335,0.00025347195,0.00023500156,0.00038630088,0.0039393017,0.000059685957,0.0004542051],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987406,0.000025894076,0.00051799323,0.00021743518,0.00020065831,0.00029740835],"domain_scores_gemma":[0.99882627,0.00002327812,0.00031139882,0.00038056474,0.00035394225,0.00010454052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035361285,0.00027151554,0.00019396249,0.0000853086,0.00021817478,0.00011970151,0.00014287488,0.000296555,0.000005827842],"category_scores_gemma":[0.0003992946,0.0002218342,0.000045013177,0.000116596515,0.00026205412,0.00006983665,0.00007385167,0.000177672,0.0000019325232],"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":[0.0108821,0.0014487416,0.18593249,0.02424354,0.0024434004,0.0000047876574,0.040350202,0.044028547,0.5986182,0.037291355,0.020594282,0.034162354],"study_design_scores_gemma":[0.00146458,0.002060263,0.0006911913,0.000047483525,0.000089913134,0.000031479238,0.0008106132,0.8975166,0.06320073,0.00037323957,0.033293076,0.00042081557],"about_ca_topic_score_codex":0.00001718558,"about_ca_topic_score_gemma":0.000073836636,"teacher_disagreement_score":0.8534881,"about_ca_system_score_codex":0.000019894875,"about_ca_system_score_gemma":0.00011452962,"threshold_uncertainty_score":0.9046136},"labels":[],"label_agreement":null},{"id":"W2162797435","doi":"10.1093/bioinformatics/btl233","title":"BNTagger: improved tagging SNP selection using Bayesian networks","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Selection (genetic algorithm); Computer science; SNP; Bayesian probability; Artificial intelligence; Biology; Genetics; Single-nucleotide polymorphism","score_opus":0.006642357560736971,"score_gpt":0.24105347208302355,"score_spread":0.23441111452228658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162797435","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":[0.1078939,0.00013792295,0.8787523,0.000068497895,0.00043418416,0.0003909075,0.000012296893,0.00014092476,0.012169069],"genre_scores_gemma":[0.8054537,0.000034597047,0.191711,0.00069604156,0.0009052273,0.000011149431,0.0004429747,0.000057683803,0.00068758643],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854976,0.000031329713,0.0006166138,0.00015907401,0.00017712863,0.00046609118],"domain_scores_gemma":[0.9991205,0.000012918876,0.0003494141,0.00033321313,0.000098871926,0.00008510421],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028810126,0.0002631205,0.00018804893,0.000100494886,0.00024713806,0.00011979011,0.00021947561,0.00026717407,0.000026717988],"category_scores_gemma":[0.000060914663,0.0002576138,0.00011516621,0.00021816725,0.00006553656,0.000027430344,0.00013086418,0.00021958149,0.000015824799],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033903192,0.00040290807,0.05698962,0.0010034824,0.00042895123,0.0000065859062,0.0007882767,0.6457323,0.19676629,0.0032371248,0.04973551,0.044569924],"study_design_scores_gemma":[0.00042963863,0.00011620223,0.00053653977,0.00002186886,0.000027796117,0.00007114213,0.0000745039,0.96416914,0.0057455325,0.000023937975,0.028437395,0.00034631573],"about_ca_topic_score_codex":0.00008476362,"about_ca_topic_score_gemma":0.000039942595,"teacher_disagreement_score":0.69755983,"about_ca_system_score_codex":0.00005395166,"about_ca_system_score_gemma":0.00008073329,"threshold_uncertainty_score":0.9999876},"labels":[],"label_agreement":null},{"id":"W2163059805","doi":"10.1093/bioinformatics/btv047","title":"KAPPA, a simple algorithm for discovery and clustering of proteins defined by a key amino acid pattern: a case study of the cysteine-rich proteins","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Executable; Computer science; Cluster analysis; Computational biology; Kappa; Data mining; Pairwise comparison; Cysteine; Set (abstract data type); Sequence (biology); Protein superfamily; Protein sequencing; Peptide sequence; Bioinformatics; Theoretical computer science; Artificial intelligence; Biology; Mathematics; Genetics; Biochemistry; Programming language","score_opus":0.014589410809665969,"score_gpt":0.25502361307559557,"score_spread":0.2404342022659296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163059805","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8042692,0.00007843689,0.19308405,0.00002703837,0.000062553685,0.0021051546,0.00024805567,0.000011196401,0.00011431408],"genre_scores_gemma":[0.94893134,0.000005164145,0.050547518,0.000070663824,0.000045021483,0.00017097859,0.00008964364,0.000025096966,0.00011457751],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852914,0.00005409553,0.0007462081,0.00014318667,0.00027554986,0.00025181685],"domain_scores_gemma":[0.99855185,0.000024977515,0.00059252104,0.0005583876,0.0001835604,0.00008871478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039453886,0.00023310415,0.00030380028,0.000053533426,0.00009493789,0.000049158843,0.00027716206,0.00013191694,7.2687493e-7],"category_scores_gemma":[0.00027332798,0.00016699814,0.00007724257,0.00013344544,0.000097102675,0.000033209253,0.00046020898,0.00011335858,5.7491565e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014139822,0.00858556,0.1344132,0.019750183,0.0033780376,0.00010609759,0.181422,0.005351408,0.16155183,0.00012177972,0.023767553,0.46013838],"study_design_scores_gemma":[0.015657293,0.016062291,0.00095953443,0.00029628552,0.00035036984,0.0018531225,0.053616524,0.77848697,0.12370194,0.000053469983,0.007508221,0.0014539686],"about_ca_topic_score_codex":0.00025595044,"about_ca_topic_score_gemma":0.00021566435,"teacher_disagreement_score":0.7731356,"about_ca_system_score_codex":0.00001956105,"about_ca_system_score_gemma":0.00010216637,"threshold_uncertainty_score":0.6809987},"labels":[],"label_agreement":null},{"id":"W2163449716","doi":"10.1002/jcc.20918","title":"Prediction of protein structural class using novel evolutionary collocation‐based sequence representation","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Chemistry","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":172,"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; Benchmark (surveying); Classifier (UML); Artificial intelligence; Pattern recognition (psychology); Representation (politics); Support vector machine; Sequence (biology); Protein methods; Class (philosophy); Pseudo amino acid composition; Data mining; Machine learning; Sequence analysis; Amino acid; Biology","score_opus":0.03889561558284672,"score_gpt":0.2932569067144774,"score_spread":0.2543612911316307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163449716","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94257456,0.00006695339,0.056922805,0.00007067402,0.000059812497,0.00008015293,0.00004336253,0.0000046407126,0.0001770175],"genre_scores_gemma":[0.9177994,0.0000024023293,0.08170687,0.000028397004,0.00019479493,0.0000015341226,0.00020123209,0.000008521509,0.00005685396],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885803,0.000026156671,0.0005354511,0.000095982134,0.00039945618,0.00008491505],"domain_scores_gemma":[0.9983259,0.000025669995,0.0007394713,0.0001112057,0.00074655394,0.000051228883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013040658,0.00009524165,0.00012947184,0.0000455291,0.0000890758,0.000006602374,0.0001382106,0.00009564211,0.0000225482],"category_scores_gemma":[0.00022825094,0.0000961184,0.00009179258,0.00013242102,0.0001216885,0.000020139292,0.000027333175,0.00014067085,3.239716e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006934657,0.0000256234,0.0043349233,0.000047597994,0.000026850284,0.0000010210692,0.000024694466,0.5113055,0.48403263,0.000007397284,0.000088210756,0.000036171947],"study_design_scores_gemma":[0.0019667011,0.00022466505,0.03373256,0.00013363338,0.00003951598,0.0015836728,0.00007727627,0.5301853,0.43061432,0.0007209118,0.0005217151,0.0001997453],"about_ca_topic_score_codex":0.000003638451,"about_ca_topic_score_gemma":9.2634785e-8,"teacher_disagreement_score":0.053418297,"about_ca_system_score_codex":0.0000643354,"about_ca_system_score_gemma":0.00055568985,"threshold_uncertainty_score":0.39195946},"labels":[],"label_agreement":null},{"id":"W2164620224","doi":"10.1093/bioinformatics/btm115","title":"SherLoc: high-accuracy prediction of protein subcellular localization by integrating text and protein sequence data","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":127,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Sequence (biology); Protein sequencing; Artificial intelligence; Computational biology; Protein subcellular localization prediction; Data mining; Pattern recognition (psychology); Peptide sequence; Biology; Genetics; Gene","score_opus":0.015547919242480267,"score_gpt":0.25874349043564987,"score_spread":0.2431955711931696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164620224","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38257584,0.00023908865,0.6151128,0.000044819608,0.000060389924,0.00077998673,0.00026986407,0.000040745395,0.0008764815],"genre_scores_gemma":[0.8742926,0.00006316589,0.12141255,0.00009452315,0.00008244013,0.000013389549,0.0037496327,0.000026960572,0.000264728],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984665,0.00004297691,0.0007794937,0.0001846281,0.00027056353,0.00025586432],"domain_scores_gemma":[0.99857014,0.000025763728,0.00049333984,0.00068632246,0.00013498166,0.000089418434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010705179,0.0001998337,0.00017492117,0.000068753965,0.00012548722,0.000052645682,0.00037838033,0.00021365016,0.000010492874],"category_scores_gemma":[0.0009825751,0.00018046323,0.000025486963,0.00016855,0.00015045887,0.00006826115,0.00030902374,0.0001992147,0.0000043106284],"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":[0.00015093177,0.0001200351,0.0053537823,0.0017474294,0.00010816486,0.00000183296,0.001376343,0.0002810404,0.9125117,0.0011455219,0.0043785847,0.07282461],"study_design_scores_gemma":[0.0011256167,0.0008396425,0.00044120042,0.00037127847,0.00004562359,0.00003975186,0.0012179912,0.49340394,0.43114367,0.00007527509,0.07076634,0.00052966736],"about_ca_topic_score_codex":0.000067496956,"about_ca_topic_score_gemma":0.000015104466,"teacher_disagreement_score":0.4937002,"about_ca_system_score_codex":0.000023107337,"about_ca_system_score_gemma":0.000071843235,"threshold_uncertainty_score":0.73590773},"labels":[],"label_agreement":null},{"id":"W2165883267","doi":"10.1142/9781860947575_0012","title":"PROTEIN FOLD RECOGNITION USING THE GRADIENT BOOST ALGORITHM","year":2006,"lang":"en","type":"article","venue":"Computational Systems Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"University of Alberta; Bioinformatics Solutions (Canada); University of Waterloo","funders":"","keywords":"Computer science; Algorithm; Threading (protein sequence); Artificial intelligence; Machine learning; Support vector machine; Boosting (machine learning); Computation; Fold (higher-order function); Benchmark (surveying); Protein structure prediction; Protein structure","score_opus":0.013398283772462128,"score_gpt":0.23989169728365473,"score_spread":0.2264934135111926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165883267","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":[0.17682278,0.00026701557,0.817528,0.0001171218,0.0004545647,0.0010592298,0.00012986567,0.000062028,0.0035593875],"genre_scores_gemma":[0.69507825,0.000005827637,0.30043522,0.0002992158,0.0009239052,0.000082449784,0.0025804504,0.000046721205,0.0005479645],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985457,0.00006890294,0.0006478209,0.00012560248,0.00035954977,0.00025239607],"domain_scores_gemma":[0.9990796,0.000029422607,0.00036563174,0.00024500568,0.00022933773,0.000051014245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000387476,0.0001941027,0.00014488162,0.00006847843,0.00029791048,0.00015652357,0.00021766711,0.000121653975,0.0000055570113],"category_scores_gemma":[0.00004797152,0.00014790412,0.000087485314,0.00015271424,0.0000866578,0.000020357262,0.0000982519,0.00013385566,0.0000574767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005694518,0.00023209307,0.0013374138,0.00083580415,0.00027036387,0.000005583023,0.0007706754,0.93102527,0.003453703,0.00412306,0.024182089,0.033706978],"study_design_scores_gemma":[0.00036865522,0.00008834415,0.00029735419,0.00006540927,0.000017782644,0.00013757893,0.00022046537,0.9825525,0.00042150688,0.00040274614,0.015189737,0.00023789282],"about_ca_topic_score_codex":0.00009514387,"about_ca_topic_score_gemma":0.000004755007,"teacher_disagreement_score":0.5182555,"about_ca_system_score_codex":0.000049664413,"about_ca_system_score_gemma":0.000088465684,"threshold_uncertainty_score":0.6031355},"labels":[],"label_agreement":null},{"id":"W2169400290","doi":"10.1142/9781860947322_0008","title":"CONSENSUS FOLD RECOGNITION BY PREDICTED MODEL QUALITY","year":2005,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Server; Support vector machine; Protein structure prediction; Artificial intelligence; Machine learning; Annotation; Data mining; Operating system; Protein structure","score_opus":0.01796172315695359,"score_gpt":0.2889861959954219,"score_spread":0.2710244728384683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169400290","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89838743,0.00007410464,0.037126385,0.0010389317,0.00004442701,0.00016386724,0.00017221586,0.00007967493,0.062912956],"genre_scores_gemma":[0.9517374,0.000030261815,0.03841289,0.0018841153,0.00010945414,0.000009419387,0.0010468265,0.000014356008,0.006755254],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993081,0.00004061251,0.00024611625,0.00014673048,0.0001050544,0.00015334977],"domain_scores_gemma":[0.9995597,0.000011307335,0.00007979381,0.0002185058,0.00006852864,0.00006218669],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001944952,0.0000988779,0.00008048539,0.000015362473,0.00004509367,0.00001480703,0.00008837457,0.00013369886,0.00008912615],"category_scores_gemma":[0.00016261025,0.00009160569,0.000044072225,0.00003178086,0.000038389935,0.0000020279526,0.000048525224,0.000087632005,0.000048127342],"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":[0.00018222179,0.00020065282,0.0024871894,0.000058732694,0.00009824712,3.3844222e-7,0.0001706566,0.005919292,0.463436,0.00028715967,0.4874976,0.039661918],"study_design_scores_gemma":[0.0020029729,0.00029548866,0.0007940147,0.000013969137,0.00003494578,0.000025610425,0.00010738224,0.5491709,0.3103219,0.00033800406,0.13620426,0.0006905422],"about_ca_topic_score_codex":0.000017481807,"about_ca_topic_score_gemma":0.00002278409,"teacher_disagreement_score":0.54325163,"about_ca_system_score_codex":0.000009386392,"about_ca_system_score_gemma":0.000030219051,"threshold_uncertainty_score":0.37355715},"labels":[],"label_agreement":null},{"id":"W2171259901","doi":"10.1093/bioinformatics/btu556","title":"Prediction of Indel flanking regions in protein sequences using a variable-order Markov model","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Indel; Flanking maneuver; Markov chain; Variable (mathematics); Markov model; Computer science; Markov chain Monte Carlo; Order (exchange); Genetics; Mathematics; Statistics; Artificial intelligence; Biology; Gene; Bayesian probability; Geography","score_opus":0.018877510514529117,"score_gpt":0.24661550447183547,"score_spread":0.22773799395730634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171259901","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":[0.41579968,0.00002314271,0.57516575,0.000033624994,0.00006615615,0.00034907876,0.00003157659,0.000024298404,0.008506702],"genre_scores_gemma":[0.5500876,0.000012738972,0.44944727,0.00011644319,0.000051838084,0.0000134849915,0.00011335126,0.000015535836,0.00014175363],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987376,0.000046749687,0.00063680834,0.000114173556,0.00021717789,0.0002475276],"domain_scores_gemma":[0.99911255,0.000014396311,0.0003410649,0.0003598732,0.000121295794,0.000050804258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005815929,0.00016217513,0.00018731688,0.00013920583,0.00006746891,0.000025916741,0.00022258032,0.00021359329,0.0000055145306],"category_scores_gemma":[0.00036598914,0.00015228959,0.0000446863,0.00024848618,0.00008183409,0.00002792559,0.00012787057,0.00016642996,0.0000024119431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019275125,0.00022669007,0.024861854,0.002132136,0.00015130074,8.8337936e-7,0.0036209219,0.7375822,0.20948188,0.012051944,0.0010234665,0.008673979],"study_design_scores_gemma":[0.0004378893,0.0001144658,0.00020264121,0.0001404205,0.00001281369,0.0000135701985,0.00013990105,0.9942845,0.0031812855,0.00045267842,0.0008684871,0.00015133894],"about_ca_topic_score_codex":0.000037229114,"about_ca_topic_score_gemma":0.000013005896,"teacher_disagreement_score":0.2567023,"about_ca_system_score_codex":0.000028442077,"about_ca_system_score_gemma":0.0001705862,"threshold_uncertainty_score":0.62101895},"labels":[],"label_agreement":null},{"id":"W2209615792","doi":"10.1371/journal.pone.0053757.g004","title":"BLAST atlas of NAP1 genomes.","year":2015,"lang":"en","type":"paratext","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Atlas (anatomy); Genome; Biology; Computational biology; Genetics; Anatomy","score_opus":0.021210972842159018,"score_gpt":0.2789211389945873,"score_spread":0.2577101661524283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2209615792","genre_codex":"other","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016084815,0.0071097296,0.000005736249,0.000019595816,0.00036565436,0.00031252243,0.46485665,0.000013408214,0.5271559],"genre_scores_gemma":[0.0016922465,0.00010140319,0.0003433871,0.0001338902,0.00082164136,0.000058600803,0.8259849,0.000069757,0.17079416],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988757,0.000039054605,0.00034406586,0.00025677864,0.00023958481,0.00024485524],"domain_scores_gemma":[0.9985487,0.000014227597,0.0004200396,0.0005966815,0.00031201745,0.00010835036],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000056950947,0.00028530005,0.00031577735,0.000064267915,0.000029811785,0.000024984505,0.00051752606,0.0006014939,0.18207456],"category_scores_gemma":[0.00052941666,0.00027318287,0.00015050704,0.00008077797,0.000016139571,0.0000020774519,0.00043804984,0.0003012691,0.025589392],"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":[0.000011934133,0.000013574314,0.0000034821933,0.0006465041,0.00006391912,9.704804e-7,0.000033010085,0.00030095992,0.00048904424,4.3515632e-7,0.9976767,0.00075948465],"study_design_scores_gemma":[0.0002033651,0.00017259175,0.000014422333,0.00053661334,0.000011225051,0.000011524372,0.000010617835,0.0001035162,0.004850758,0.000001100986,0.9937969,0.00028737236],"about_ca_topic_score_codex":0.00000396424,"about_ca_topic_score_gemma":0.0000051043285,"teacher_disagreement_score":0.36112827,"about_ca_system_score_codex":0.000021793774,"about_ca_system_score_gemma":0.00036924842,"threshold_uncertainty_score":0.99997205},"labels":[],"label_agreement":null},{"id":"W2246311611","doi":"10.1371/journal.pone.0141603","title":"Computational Identification of MoRFs in Protein Sequences Using Hierarchical Application of Bayes Rule","year":2015,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":50,"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":"Canadian Institutes of Health Research; Genome British Columbia; Michael Smith Health Research BC","keywords":"Bayes' theorem; Computer science; Identification (biology); Protein sequencing; Computational biology; Sequence (biology); Sequence alignment; Naive Bayes classifier; Artificial intelligence; Data mining; Bioinformatics; Peptide sequence; Biology; Bayesian probability; Genetics","score_opus":0.032894155162335896,"score_gpt":0.2779105196041278,"score_spread":0.24501636444179192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2246311611","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97641265,0.000037725873,0.023134388,0.000060824266,0.0000043216955,0.00020072905,0.000010558179,0.0000037552668,0.00013502521],"genre_scores_gemma":[0.9471138,0.0000016760846,0.052696314,0.000008244178,0.000020687288,0.000013452428,0.00011994219,0.0000045713446,0.000021314418],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993407,0.000040357972,0.00028775845,0.00008627925,0.0001872202,0.000057641373],"domain_scores_gemma":[0.9995294,0.00000785211,0.00018687239,0.00012059785,0.00013220459,0.000023057442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002462697,0.000045324887,0.00009168659,0.000046644214,0.000010287715,0.000004636682,0.0000921618,0.00005302364,0.0000016622953],"category_scores_gemma":[0.000174068,0.00004669187,0.000014730535,0.00008317883,0.000065132816,0.0000052467485,0.000035276593,0.000055389875,0.0000017571767],"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":[0.000026902371,0.00024686527,0.020254137,0.00012396206,0.000021639773,5.9186156e-8,0.00013061556,0.012782516,0.96566427,0.00040145783,0.000002938443,0.00034465062],"study_design_scores_gemma":[0.00028788374,0.00009637478,0.008007556,0.000052250296,0.0000125068655,0.0000010426664,0.00004648612,0.32805997,0.66112196,0.002230236,0.000009646866,0.00007410026],"about_ca_topic_score_codex":0.00004168326,"about_ca_topic_score_gemma":0.000004519423,"teacher_disagreement_score":0.31527746,"about_ca_system_score_codex":0.000011143725,"about_ca_system_score_gemma":0.00006030499,"threshold_uncertainty_score":0.19040391},"labels":[],"label_agreement":null},{"id":"W2269388516","doi":"10.1016/j.jtbi.2016.01.043","title":"Double-layer clustering method to predict protein complexes based on power-law distribution and protein sublocalization","year":2016,"lang":"en","type":"article","venue":"Journal of Theoretical Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Cluster analysis; Power law; Distribution (mathematics); Power (physics); Mathematics; Statistical physics; Law; Computer science; Environmental science; Biological system; Physics; Biology; Statistics; Mathematical analysis; Political science; Thermodynamics","score_opus":0.008355675939569372,"score_gpt":0.2898331275291714,"score_spread":0.281477451589602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2269388516","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2111317,0.000014479207,0.78554136,0.0023019144,0.000060048475,0.00029422753,0.000040447347,0.000007936127,0.0006078586],"genre_scores_gemma":[0.9800533,0.0000017780114,0.019289423,0.0004657528,0.00010272928,0.000011033131,0.000034369164,0.000012944672,0.000028658607],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998764,0.0002995047,0.0004196831,0.0001692409,0.00012712182,0.00022045428],"domain_scores_gemma":[0.99922085,0.00006930877,0.00022010482,0.00018640519,0.00015610586,0.00014721019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094295276,0.00014984192,0.00021693858,0.000052646956,0.00006192761,0.00002301568,0.00018255135,0.00019808968,0.000058438025],"category_scores_gemma":[0.00048584695,0.00008948883,0.000071544084,0.00005766828,0.00028746919,0.0000064810242,0.00011147478,0.00013868931,0.0000046531877],"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":[0.0019371767,0.00005498092,0.000484565,0.000025520145,0.00003198212,0.0000019024691,0.000015399171,0.00022219354,0.77366173,0.2214047,0.00013167383,0.0020281458],"study_design_scores_gemma":[0.0045116874,0.009955129,0.00053674064,0.0003719896,0.00004872244,0.00013637084,0.00001997984,0.008490597,0.9199005,0.013517631,0.042065542,0.00044514585],"about_ca_topic_score_codex":0.0000024562949,"about_ca_topic_score_gemma":0.0000016175932,"teacher_disagreement_score":0.7689216,"about_ca_system_score_codex":0.00002929097,"about_ca_system_score_gemma":0.000035418052,"threshold_uncertainty_score":0.36492485},"labels":[],"label_agreement":null},{"id":"W2270803733","doi":"","title":"Screening Afua To Find Exclusivity In Invasive Disease-Causing Haemophilus Influenzae Strains","year":2013,"lang":"en","type":"article","venue":"Journal of undergraduate research in Alberta","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Biology; Microbiology; Haemophilus influenzae; Serotype; Virulence; Virology; Gene; Pathogen; Primer (cosmetics); genomic DNA; Genetics; Antibiotics","score_opus":0.04873574769736726,"score_gpt":0.3558060305806437,"score_spread":0.3070702828832764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2270803733","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9580016,0.00014415261,0.0008147893,0.039720856,0.0000778318,0.0004470692,0.000004106001,0.0000023466212,0.00078725105],"genre_scores_gemma":[0.99549514,0.00017534185,0.0031840506,0.00038563294,0.00018001194,0.000013177652,0.00001123427,0.000030221367,0.00052519864],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99710774,0.00048713307,0.00073737506,0.0002484036,0.0007351707,0.0006842004],"domain_scores_gemma":[0.9981629,0.00035839525,0.00024297438,0.00038764617,0.00037406656,0.00047401057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016956879,0.00019873315,0.00029534654,0.00069677987,0.00011188451,0.00015481771,0.00047417136,0.00013943392,0.000015421589],"category_scores_gemma":[0.0036808974,0.00018053628,0.000110730936,0.00063094526,0.0001337335,0.000055997378,0.00048554028,0.0009651183,0.000031893396],"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":[0.0016239611,0.0012523928,0.5615558,0.00094362657,0.0004531047,0.00092621957,0.0023372048,0.1210628,0.25407523,0.0035397338,0.020425819,0.031804137],"study_design_scores_gemma":[0.011806028,0.0044391807,0.83629394,0.0050755073,0.000063865875,0.0008183051,0.0016510368,0.030948028,0.015951974,0.07197697,0.018452652,0.0025225354],"about_ca_topic_score_codex":0.0017756143,"about_ca_topic_score_gemma":0.002688349,"teacher_disagreement_score":0.27473813,"about_ca_system_score_codex":0.00013929751,"about_ca_system_score_gemma":0.0005157039,"threshold_uncertainty_score":0.73620564},"labels":[],"label_agreement":null},{"id":"W2281821131","doi":"","title":"Évaluation de traceurs peptidiques radiomarqués pour la détection du cancer du sein et de la prostate par imagerie TEP","year":2012,"lang":"fr","type":"article","venue":"Knowledge UdeS (Institutional Deposit of the University of Sherbrooke)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Gynecology; Medicine","score_opus":0.008934509857439812,"score_gpt":0.24589966328991086,"score_spread":0.23696515343247104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2281821131","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85907984,0.010107834,0.108114555,0.00068680785,0.0003448981,0.0002403496,0.000024034745,0.000018602464,0.021383101],"genre_scores_gemma":[0.96952707,0.004989745,0.022908518,0.00004535021,0.00022376764,0.0000017654388,0.000027471162,0.000015276444,0.0022610526],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99840593,0.00076918834,0.00021993651,0.00015832805,0.0001806578,0.00026596617],"domain_scores_gemma":[0.99925935,0.000082977036,0.00017742456,0.00019739152,0.0001749556,0.00010787236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010712257,0.00019477007,0.00018521621,0.000064271626,0.0003101353,0.000021938176,0.00030474516,0.00029483446,0.00003529681],"category_scores_gemma":[0.00024072941,0.00020006836,0.00020933777,0.00012326585,0.00080494327,0.00006659037,0.00019154172,0.00026170744,0.00000840341],"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":[0.00046344448,0.0009847372,0.28575662,0.0032789868,0.0005001744,0.000010261852,0.025154242,0.088020205,0.5641147,0.005947962,0.008028219,0.017740425],"study_design_scores_gemma":[0.0015696662,0.00015113641,0.42678103,0.0018436196,0.00047340067,0.00039884567,0.00036767474,0.07167692,0.32102397,0.00016020464,0.17514428,0.0004092669],"about_ca_topic_score_codex":0.0013035979,"about_ca_topic_score_gemma":0.0011661338,"teacher_disagreement_score":0.24309076,"about_ca_system_score_codex":0.00064716366,"about_ca_system_score_gemma":0.0006828213,"threshold_uncertainty_score":0.8158551},"labels":[],"label_agreement":null},{"id":"W2295742112","doi":"10.1007/978-3-319-24282-8_13","title":"Detecting Transmembrane Proteins Using Decision Trees","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Decision tree; Artificial intelligence; Domain (mathematical analysis); Machine learning; Support vector machine; Pattern recognition (psychology); Mathematics","score_opus":0.02037081816447624,"score_gpt":0.27768060966106634,"score_spread":0.2573097914965901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2295742112","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":[0.010663676,0.0004920454,0.9861366,0.000038242706,0.00045670004,0.0003301048,0.000005139365,0.00002688301,0.0018505942],"genre_scores_gemma":[0.4175786,0.000027827637,0.5810474,0.00029031924,0.0007225807,0.00000387506,0.000021994472,0.000059889397,0.0002475075],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980593,0.00002073064,0.00038652658,0.0006175565,0.00054510165,0.00037081024],"domain_scores_gemma":[0.9987988,0.000060674745,0.00020976282,0.0006369328,0.00017811608,0.000115720984],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007426832,0.0003494573,0.00028938102,0.00026188503,0.0001531181,0.00011711024,0.0007785085,0.00039872332,0.000015113864],"category_scores_gemma":[0.00027538906,0.00031008184,0.000095034884,0.00015035467,0.00032748617,0.000012764248,0.00037606558,0.0005152993,0.000007882864],"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":[0.000053299314,0.00001644498,0.00011990552,0.00007227669,0.000017359936,0.000016788777,0.00034202076,0.29024643,0.033538677,0.00007852064,0.000011354371,0.6754869],"study_design_scores_gemma":[0.000999066,0.00092880393,0.00008698561,0.0009576104,0.00003565215,0.00034482326,8.872402e-7,0.91133565,0.06019782,0.010935586,0.012747234,0.0014298959],"about_ca_topic_score_codex":0.000016392567,"about_ca_topic_score_gemma":0.00015086899,"teacher_disagreement_score":0.67405707,"about_ca_system_score_codex":0.000093091316,"about_ca_system_score_gemma":0.00038088395,"threshold_uncertainty_score":0.99993515},"labels":[],"label_agreement":null},{"id":"W2314403353","doi":"10.1142/9789814667944_0018","title":"A METHOD FOR CLUSTERING HEMAGGLUTININ INFLUENZA PROTEIN SEQUENCES","year":2015,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Hemagglutinin (influenza); Cluster analysis; Computer science; Computational biology; Artificial intelligence; Virology; Biology; Virus","score_opus":0.039125132620338364,"score_gpt":0.35570314990788937,"score_spread":0.31657801728755103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2314403353","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":[0.09462664,0.00010565902,0.8851871,0.0003179597,0.0000781589,0.000596807,0.000007856223,0.000052572166,0.019027237],"genre_scores_gemma":[0.09111327,0.0000011092195,0.9036978,0.0011568659,0.00018111017,0.00011280565,0.00003802261,0.000020442261,0.0036786012],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99929726,0.000042409738,0.00020466538,0.00016057426,0.000099864636,0.00019525347],"domain_scores_gemma":[0.9995011,0.000012508609,0.00008302416,0.00020932303,0.000101357415,0.000092659735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005916246,0.000110911475,0.00010442883,0.000025752566,0.00004198858,0.00003143357,0.00016871757,0.00009956516,0.0000109423045],"category_scores_gemma":[0.0003875639,0.00009231792,0.00005085714,0.00004705626,0.000027009304,0.0000041870935,0.00012250373,0.00006026894,0.000013582154],"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":[0.00073323085,0.0001140277,0.0043623126,0.0004996927,0.00021431141,0.000003045865,0.0015660278,0.015504879,0.8852243,0.0054006223,0.026294908,0.06008263],"study_design_scores_gemma":[0.0015241951,0.00090702274,0.000054226886,0.00002753703,0.00001556907,0.000043711283,0.0005297988,0.09162881,0.29937938,0.0007560633,0.60471106,0.00042260738],"about_ca_topic_score_codex":0.00003469816,"about_ca_topic_score_gemma":0.000033202607,"teacher_disagreement_score":0.58584493,"about_ca_system_score_codex":0.0000105558565,"about_ca_system_score_gemma":0.00008769755,"threshold_uncertainty_score":0.37646157},"labels":[],"label_agreement":null},{"id":"W2315625626","doi":"10.1016/j.neucom.2015.08.111","title":"<mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" altimg=\"si0002.gif\" overflow=\"scroll\"><mml:msub><mml:mrow><mml:mi>L</mml:mi></mml:mrow><mml:mrow><mml:mn>2</mml:mn><mml:mo>,</mml:mo><mml:mi>p</mml:mi></mml:mrow></mml:msub><mml:mi mathvariant=\"normal\">-norm</mml:mi></mml:math> and sample constraint based feature selection and classification for AD diagnosis","year":2016,"lang":"lv","type":"article","venue":"Neurocomputing","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"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 Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; National Natural Science Foundation of China; Northern California Institute for Research and Education; Alzheimer's Disease Neuroimaging Initiative; GE Healthcare; Pfizer; BioClinica; Biogen; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; F. Hoffmann-La Roche; Merck; Alzheimer's Drug Discovery Foundation; Meso Scale Diagnostics; Takeda Pharmaceutical Company; AbbVie; National Institute on Aging; Fujirebio Europe; Alzheimer's Association","keywords":"Norm (philosophy); Feature selection; Computer science; Artificial intelligence; Adaptability; Feature (linguistics); Algorithm; Pattern recognition (psychology); Flexibility (engineering); Machine learning; Mathematics; Data mining; Statistics","score_opus":0.014129114280536264,"score_gpt":0.23620206529803858,"score_spread":0.22207295101750232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2315625626","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73165977,0.0014280112,0.009979307,0.0019514374,0.0028692891,0.00012421107,0.0007135171,0.00033980783,0.25093466],"genre_scores_gemma":[0.980246,0.0014602019,0.00993057,0.002518532,0.0022078915,0.001059376,0.0016420648,0.0007772276,0.00015814167],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99087447,0.0005971787,0.0019961058,0.0021364805,0.0018284459,0.002567304],"domain_scores_gemma":[0.99157494,0.0024481022,0.002676603,0.0018866068,0.00028212622,0.0011316184],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022488567,0.0010220913,0.00037590152,0.0005498135,0.0022769773,0.0016770405,0.0016755447,0.0030136064,0.14084148],"category_scores_gemma":[0.003507318,0.001924581,0.0014434783,0.0009846529,0.0015151867,0.0006098634,0.0018624313,0.0018100558,0.00047464497],"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":[0.0033306598,0.000620973,0.00028727937,0.0042554545,0.0026727673,0.0007174699,0.0026774576,0.0046992307,0.036953155,0.22285677,0.69243836,0.028490433],"study_design_scores_gemma":[0.0028822618,0.0025414298,0.00038968216,0.0012269514,0.0012464947,0.001756253,0.00090711354,0.08023004,0.89669544,0.00014336105,0.010213605,0.0017673726],"about_ca_topic_score_codex":0.0008222032,"about_ca_topic_score_gemma":0.00089532364,"teacher_disagreement_score":0.8597423,"about_ca_system_score_codex":0.000019050405,"about_ca_system_score_gemma":0.0015199388,"threshold_uncertainty_score":0.9993593},"labels":[],"label_agreement":null},{"id":"W2326199080","doi":"10.1371/journal.pone.0152964","title":"PSIONplus: Accurate Sequence-Based Predictor of Ion Channels and Their Types","year":2016,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Specialized Research Fund for the Doctoral Program of Higher Education of China; National Science Foundation","keywords":"Computer science; Similarity (geometry); Artificial intelligence; Support vector machine; Ion channel; Identification (biology); Machine learning; Limit (mathematics); Sequence (biology); Pattern recognition (psychology); Data mining; Biology; Mathematics; Genetics","score_opus":0.030706941861394926,"score_gpt":0.23841960926286843,"score_spread":0.2077126674014735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2326199080","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99749106,0.00012960273,0.001424708,0.00038564083,0.00003552533,0.000112091664,0.000046115834,0.000013892079,0.00036133433],"genre_scores_gemma":[0.99775046,0.00013301094,0.0015204374,0.00009761874,0.00011802688,0.000007642505,0.0000309961,0.000009667515,0.00033216714],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99954826,0.000027366696,0.00013397161,0.00010668033,0.00008114477,0.00010260606],"domain_scores_gemma":[0.9995877,0.000024654863,0.00009023395,0.00018940744,0.00006766582,0.000040326155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009947387,0.00008152177,0.000106200634,0.000024284847,0.000024026476,0.00000648442,0.00009117211,0.00007709649,0.00003035183],"category_scores_gemma":[0.00019733794,0.000049400896,0.000021461812,0.000030185787,0.00007033924,0.0000038131811,0.000054271284,0.00003547162,0.0000069586804],"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":[0.00004706389,0.00008151209,0.0037606577,0.00009364334,0.000057675927,1.5261418e-7,0.000055665663,0.000013252365,0.9947961,0.000029611336,0.00010620951,0.0009584565],"study_design_scores_gemma":[0.00044556626,0.0003443148,0.0007296642,0.00017855251,0.00001598142,9.4727966e-7,0.000011467615,0.00244929,0.9948926,0.000084180836,0.00075307157,0.00009434642],"about_ca_topic_score_codex":0.000002499684,"about_ca_topic_score_gemma":0.0000012581818,"teacher_disagreement_score":0.0030309935,"about_ca_system_score_codex":0.0000046950545,"about_ca_system_score_gemma":0.00003099038,"threshold_uncertainty_score":0.201451},"labels":[],"label_agreement":null},{"id":"W2328398973","doi":"10.2174/092986612798472910","title":"CRYSpred: Accurate Sequence-Based Protein Crystallization Propensity Prediction Using Sequence-Derived Structural Characteristics","year":2012,"lang":"en","type":"article","venue":"Protein and Peptide Letters","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts","keywords":"Structural genomics; Computer science; Protein structure prediction; Benchmark (surveying); Protein crystallization; Context (archaeology); Test set; Genomics; Protein sequencing; Classifier (UML); Selection (genetic algorithm); In silico; Sequence (biology); Rule of thumb; Artificial intelligence; Data mining; Machine learning; Crystallization; Protein structure; Algorithm; Peptide sequence; Biology; Genetics; Chemistry; Genome","score_opus":0.034956400969628855,"score_gpt":0.26681989933320255,"score_spread":0.2318634983635737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2328398973","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9671357,0.000033085296,0.031221058,0.00034722564,0.000095182804,0.0010101867,0.00006122111,0.00005057609,0.000045733206],"genre_scores_gemma":[0.97874296,0.0000041401568,0.019509863,0.0007824656,0.00035490704,0.000057719135,0.00046347367,0.000030548534,0.000053931162],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99869376,0.0001406342,0.0003275248,0.00025454458,0.0001992746,0.00038423293],"domain_scores_gemma":[0.99924016,0.0000062887275,0.00027408058,0.00026794858,0.00008117547,0.0001303412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027202425,0.0002471297,0.00017458893,0.00005425186,0.00023178961,0.000100603786,0.0001292578,0.00015226318,0.000022701863],"category_scores_gemma":[0.00016395273,0.00022735266,0.000060827173,0.00008525035,0.00015234682,0.000053214015,0.00008730578,0.0002095872,0.0000038070016],"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":[0.00008717452,0.000010574797,0.016567292,0.00015920891,0.000025444733,0.0000015783979,0.00014408086,0.0005244557,0.98192066,0.000020716667,0.00003394164,0.0005048685],"study_design_scores_gemma":[0.001586989,0.00038217858,0.03991114,0.0003578631,0.000092518996,0.000108890265,0.000065354616,0.09252509,0.85948646,0.000038583057,0.004362274,0.0010826368],"about_ca_topic_score_codex":0.000054690325,"about_ca_topic_score_gemma":0.0000037824545,"teacher_disagreement_score":0.122434184,"about_ca_system_score_codex":0.000050055885,"about_ca_system_score_gemma":0.0000608635,"threshold_uncertainty_score":0.9271172},"labels":[],"label_agreement":null},{"id":"W2337408142","doi":"10.1093/bioinformatics/btw211","title":"Partitioning and correlating subgroup characteristics from Aligned Pattern Clusters","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Waterloo","funders":"","keywords":"A priori and a posteriori; Sequence alignment; Multiple sequence alignment; Biology; Class (philosophy); Similarity (geometry); Function (biology); Computational biology; Conserved sequence; Divergence (linguistics); Sequence (biology); In silico; Protein superfamily; Structural Classification of Proteins database; Rank (graph theory); Cluster analysis; Phylogenetic tree; Computer science; Artificial intelligence; Genetics; Protein structure; Peptide sequence; Mathematics; Gene; Combinatorics","score_opus":0.006556936634770645,"score_gpt":0.2177660405102531,"score_spread":0.21120910387548247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2337408142","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8116853,0.000073333766,0.1858615,0.00027873876,0.00030564997,0.00018174858,0.00014264538,0.00005746316,0.0014136093],"genre_scores_gemma":[0.9816289,0.00018904725,0.016615467,0.00076684606,0.00021535007,0.000010412999,0.00034703006,0.000025823743,0.00020113972],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99885917,0.00003240054,0.00051271624,0.00014806983,0.0001665648,0.00028105947],"domain_scores_gemma":[0.9991183,0.000068779314,0.00030547916,0.00033178818,0.000057265635,0.00011833439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020029156,0.00019791757,0.00017329995,0.000043156717,0.00013646537,0.000077885816,0.00015612264,0.00016253309,0.000049904782],"category_scores_gemma":[0.00028215186,0.00014756418,0.000051125902,0.000046205212,0.00010268544,0.000027915223,0.00020360641,0.00006590096,0.000085276704],"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":[0.00009431229,0.000054572596,0.4238164,0.00022420149,0.00020229485,0.000005192598,0.0024698577,0.00003580058,0.030488597,0.0002195528,0.0055284235,0.53686076],"study_design_scores_gemma":[0.011034799,0.0020581775,0.40025157,0.0017555119,0.00038075756,0.00028628428,0.0031354192,0.35106954,0.040839154,0.0005423028,0.18407275,0.0045737503],"about_ca_topic_score_codex":0.000020124658,"about_ca_topic_score_gemma":0.000013756615,"teacher_disagreement_score":0.532287,"about_ca_system_score_codex":0.00001830405,"about_ca_system_score_gemma":0.000027851267,"threshold_uncertainty_score":0.60174924},"labels":[],"label_agreement":null},{"id":"W2344564588","doi":"10.1016/j.patcog.2008.11.012","title":"Digital image processing and pattern recognition techniques for the detection of cancer","year":2008,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Partition (number theory); Data mining; Pattern recognition (psychology); Pattern matching; Behavioral pattern; Universality (dynamical systems); Semantics (computer science); Artificial intelligence; Sequential Pattern Mining; Mathematics","score_opus":0.01657092539814049,"score_gpt":0.26972729980940957,"score_spread":0.2531563744112691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2344564588","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6919781,0.00023831494,0.30680403,0.00008693566,0.000055352433,0.00036590276,0.00018016573,0.000025998792,0.00026520624],"genre_scores_gemma":[0.997654,0.0004430146,0.0010051497,0.00015907003,0.00018724924,0.00015526358,0.00035019525,0.000018222618,0.000027831235],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99947107,0.000016250086,0.00018860964,0.00013928792,0.000076493845,0.00010827738],"domain_scores_gemma":[0.99953556,0.000024131048,0.00017024395,0.000088641114,0.00016077555,0.00002064787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000096865544,0.00009773236,0.000079200465,0.000033858018,0.00012487601,0.000030658524,0.00005213728,0.00008143462,0.00000937101],"category_scores_gemma":[0.00007353486,0.000078477075,0.000043931977,0.000038614155,0.00007632263,0.000021586106,0.00003113945,0.00007232361,0.0000028609388],"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":[0.00002547614,0.000015145352,0.0048741535,0.000120078475,0.000015010584,1.821797e-7,0.000082350314,3.17296e-7,0.05307964,6.184347e-9,0.000039432936,0.9417482],"study_design_scores_gemma":[0.0006644789,0.00047085635,0.015900377,0.0001917279,0.000076186916,0.00009661771,0.000159089,0.0057223486,0.9730717,0.00010906764,0.0032100484,0.00032752653],"about_ca_topic_score_codex":0.000039457052,"about_ca_topic_score_gemma":0.00004383317,"teacher_disagreement_score":0.9414207,"about_ca_system_score_codex":0.0000080407835,"about_ca_system_score_gemma":0.000014645767,"threshold_uncertainty_score":0.32002023},"labels":[],"label_agreement":null},{"id":"W2366093519","doi":"10.1093/nar/gkw409","title":"MoRFchibi SYSTEM: software tools for the identification of MoRFs in protein sequences","year":2016,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":182,"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; Canada's Michael Smith Genome Sciences Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Genome British Columbia; Michael Smith Health Research BC; Genome Canada","keywords":"Biology; Software; Web server; Identification (biology); Computational biology; Computer science; Bioinformatics; The Internet; World Wide Web; Operating system","score_opus":0.042087929336436826,"score_gpt":0.3482737489374061,"score_spread":0.30618581960096924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2366093519","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9624165,0.00018362717,0.03264618,0.0007893026,0.000053630713,0.0016102045,0.000045037996,0.000024382492,0.0022311078],"genre_scores_gemma":[0.9928085,0.000023486851,0.0024968889,0.000007615843,0.00006399901,0.00021549079,0.000010002649,0.000021560632,0.0043524466],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988655,0.00012852167,0.00031072466,0.0001710493,0.00028782175,0.00023636804],"domain_scores_gemma":[0.9990664,0.00016516057,0.00010445071,0.00044819008,0.00018588887,0.000029885265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018180605,0.000070929884,0.00009047284,0.00007956908,0.00008650929,0.00003949026,0.00043304998,0.000100139456,0.000025923295],"category_scores_gemma":[0.002460168,0.000040475217,0.00004261224,0.00014835529,0.00020802776,0.000010380563,0.00012931884,0.00009728594,0.000031829848],"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":[0.00007764922,0.00002254977,0.0038918147,0.00025189196,0.000020585921,4.6023968e-7,0.00009990466,0.00004261039,0.9596665,0.002040985,0.00087072584,0.033014316],"study_design_scores_gemma":[0.0014379581,0.0006703346,0.017686702,0.00043890282,0.000010914968,0.000012096857,0.0013759622,0.0046565905,0.93324405,0.0004937478,0.03968209,0.0002906494],"about_ca_topic_score_codex":0.000030747302,"about_ca_topic_score_gemma":0.0000194557,"teacher_disagreement_score":0.038811363,"about_ca_system_score_codex":0.00003284232,"about_ca_system_score_gemma":0.00007791515,"threshold_uncertainty_score":0.29452285},"labels":[],"label_agreement":null},{"id":"W2366293344","doi":"","title":"Screening the gene sequences of the interaction proteins of P311 from human adult cDNA library by yeast two-hybrid system","year":2005,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"St. Peter's Hospital","funders":"","keywords":"Yeast; cDNA library; Complementary DNA; Two-hybrid screening; Biology; Gene; Genetics; Function (biology); Computational biology","score_opus":0.005861853791732222,"score_gpt":0.23134310387587206,"score_spread":0.22548125008413983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2366293344","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9894581,0.00013488409,0.0036570171,0.00033545768,0.000054289834,0.00022840496,0.00008735931,0.000017852519,0.006026669],"genre_scores_gemma":[0.99290377,0.000008309333,0.0060479506,0.00018497404,0.00015488187,0.000009776492,0.00013885957,0.000012086973,0.0005393888],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992457,0.000094053954,0.00031252328,0.00011279157,0.00013671767,0.00009820543],"domain_scores_gemma":[0.99927473,0.000010290871,0.00029061627,0.0003634414,0.000038480688,0.000022416178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010026195,0.000100187506,0.00010474119,0.000013692218,0.00008226671,0.000019898234,0.0003567032,0.00004859467,0.00005871496],"category_scores_gemma":[0.000025706151,0.0000565395,0.00007813016,0.00004468587,0.00008513022,0.000013071669,0.00016366334,0.00012385087,0.0000030277824],"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":[0.000027313803,0.00002628692,0.0056065363,0.000047108508,0.000060784947,1.338151e-7,0.00014791296,0.0013341741,0.98731846,0.00024058271,0.0024043163,0.0027864228],"study_design_scores_gemma":[0.00020126444,0.00006426158,0.00063810474,0.00007010844,0.000015191036,0.000009086895,0.00039522888,0.006172358,0.98770005,0.000005509901,0.0046524024,0.00007644038],"about_ca_topic_score_codex":0.00037527177,"about_ca_topic_score_gemma":0.000034242552,"teacher_disagreement_score":0.00548728,"about_ca_system_score_codex":0.000006035391,"about_ca_system_score_gemma":0.000022451288,"threshold_uncertainty_score":0.23056138},"labels":[],"label_agreement":null},{"id":"W2371073355","doi":"","title":"Research Progress and Prediction in Rice Proteomics","year":2011,"lang":"en","type":"article","venue":"Seed","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Proteomics; Biology; Computational biology; Genetics","score_opus":0.024768469928694834,"score_gpt":0.3009495143972294,"score_spread":0.27618104446853453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2371073355","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9907406,0.00010007715,0.0001883243,0.00004209298,0.00003260706,0.00024327704,0.0000027494925,0.000009643592,0.008640622],"genre_scores_gemma":[0.99181855,0.00001887979,0.0075998376,0.00002303813,0.000047309877,0.000030420924,0.00002041432,0.000007707901,0.00043381692],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994984,0.000057168727,0.00010251523,0.00011141687,0.00008428226,0.00014619106],"domain_scores_gemma":[0.9997519,0.00000409139,0.000025051935,0.00014038374,0.000046558125,0.00003197109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044843598,0.000048472924,0.000044013785,0.00005407694,0.000037886908,0.000010997084,0.000078024175,0.000087916065,0.000004172841],"category_scores_gemma":[0.00007469569,0.000044676013,0.00000865399,0.00008633083,0.000086835884,0.000003018096,0.0000924689,0.00014974919,0.000008904456],"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":[0.0002599879,0.00011828288,0.89047754,0.0001490541,0.000022122493,0.0000040623954,0.0021192608,0.00001118249,0.10372549,0.0004013854,0.0004050934,0.0023065158],"study_design_scores_gemma":[0.0005021273,0.00041858005,0.9552112,0.000020166024,0.000002686458,0.000019506022,0.00026116896,0.0020390293,0.039525937,0.00019752407,0.0017043038,0.00009775089],"about_ca_topic_score_codex":0.000031942112,"about_ca_topic_score_gemma":0.000015073102,"teacher_disagreement_score":0.06473366,"about_ca_system_score_codex":0.000007143328,"about_ca_system_score_gemma":0.000023641118,"threshold_uncertainty_score":0.1821835},"labels":[],"label_agreement":null},{"id":"W2380863703","doi":"","title":"Analyzing and predicting of the effect of Lactobacillus peptidoglycan on gene expression in immune cells of BALB/c mice immune cells using GO database","year":2008,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"CAE (Canada)","funders":"","keywords":"Immune system; Peptidoglycan; Biology; Gene expression; Gene; Immunological synapse; Antigen presentation; Lymphocyte; Innate immune system; BALB/c; Immunology; Cell biology; Molecular biology; T cell; Microbiology; Biochemistry; T-cell receptor","score_opus":0.006574663956440325,"score_gpt":0.23125852864156252,"score_spread":0.2246838646851222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2380863703","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99812937,0.00036732128,0.00076239643,0.00000429595,0.000065586966,0.0002175437,0.000035337976,0.0000036400725,0.00041450057],"genre_scores_gemma":[0.9945476,0.00013831879,0.005172829,0.000006953126,0.000018690449,0.000001478125,0.00002875797,0.000014107949,0.00007124087],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99880207,0.00016939119,0.0005362847,0.00017059418,0.00015784675,0.00016380154],"domain_scores_gemma":[0.9989251,0.00008613017,0.0004469778,0.0004687535,0.000042692023,0.000030328341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044931672,0.00015881915,0.00029889733,0.00007170504,0.00005632916,0.0000033763736,0.00021683547,0.00010680662,0.000009009126],"category_scores_gemma":[0.00013941427,0.0001105025,0.00009188975,0.00013982553,0.0001395343,0.0000075454554,0.0003146881,0.00015676883,3.2634924e-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":[0.00012228457,0.000029592866,0.046899285,0.00021349118,0.000022831062,7.266982e-7,0.00016814943,0.004232371,0.9481415,7.8909517e-7,0.000011364552,0.00015759341],"study_design_scores_gemma":[0.0007579043,0.0003100822,0.006637093,0.00022282511,0.000023631623,0.000009424171,0.00005979115,0.0072426978,0.98461616,2.362753e-7,0.000021905378,0.00009825418],"about_ca_topic_score_codex":0.00028236807,"about_ca_topic_score_gemma":0.000011513536,"teacher_disagreement_score":0.04026219,"about_ca_system_score_codex":0.0000118556545,"about_ca_system_score_gemma":0.00003204948,"threshold_uncertainty_score":0.45061612},"labels":[],"label_agreement":null},{"id":"W2392922400","doi":"","title":"Attention of SSR Molecular Marker in Experiment","year":2011,"lang":"en","type":"article","venue":"Seed","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Molecular marker; Computational biology; Biology; Genetics; Gene","score_opus":0.008473749739993887,"score_gpt":0.24003848584817816,"score_spread":0.2315647361081843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2392922400","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9805658,0.000103401944,0.0013202017,0.00001223722,0.00005334382,0.000079950594,0.000001119588,0.000004418628,0.017859517],"genre_scores_gemma":[0.9949336,0.000008610566,0.0046639796,0.000056764897,0.000009487476,0.000006067085,0.000025570504,0.000007429504,0.00028851492],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995801,0.000027113074,0.00015290007,0.00008305272,0.00006240635,0.000094434195],"domain_scores_gemma":[0.9997202,0.0000013665344,0.000058183803,0.00017926014,0.00002139201,0.000019584135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000109111745,0.000059130904,0.000064727916,0.0000308535,0.0000071431664,0.0000020297764,0.00008188402,0.000060208484,0.000030354406],"category_scores_gemma":[0.000026554397,0.000057167603,0.00003714358,0.00004016736,0.000024760637,0.0000014926445,0.000053788754,0.000041216404,0.000008391777],"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":[0.000049884482,0.000053118034,0.07725111,0.00001961531,0.000015868236,0.0000015899656,0.00023550123,0.000016211521,0.9218254,0.00023364645,0.000040614563,0.00025744815],"study_design_scores_gemma":[0.00048656692,0.00016779097,0.3813753,0.000016084108,0.0000054666816,0.0000035160756,0.00016374038,0.00043885125,0.6162856,0.00006486141,0.00087808305,0.00011409324],"about_ca_topic_score_codex":0.00003386179,"about_ca_topic_score_gemma":0.0000048119578,"teacher_disagreement_score":0.30553976,"about_ca_system_score_codex":0.000005068182,"about_ca_system_score_gemma":0.0000115158155,"threshold_uncertainty_score":0.23312272},"labels":[],"label_agreement":null},{"id":"W2409506420","doi":"10.1385/1-59259-184-1:231","title":"Exploring Familial Relationships Using Multiple Sequence Alignment","year":2003,"lang":"en","type":"article","venue":"Humana Press eBooks","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Calcium-binding protein; EF hand; Parvalbumin; Structural motif; Sequence motif; Calcium; Peptide sequence; Biology; Computational biology; Genetics; Biochemistry; Chemistry; Gene","score_opus":0.3328944430416387,"score_gpt":0.3166473202114036,"score_spread":0.01624712283023505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2409506420","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93511593,0.00035369795,0.013433489,0.000003543823,0.00028739424,0.00029137701,0.000008829523,0.000047455924,0.050458305],"genre_scores_gemma":[0.9895251,0.00004542467,0.009188846,0.000053308213,0.00009799709,0.000034806482,0.000022008973,0.000022674865,0.0010098735],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991029,0.00012192225,0.00022137683,0.00019528567,0.00014077988,0.00021773222],"domain_scores_gemma":[0.9994361,0.000018894872,0.00009053897,0.00035575932,0.00003628208,0.0000624722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024187793,0.00013457442,0.00009034985,0.00002907717,0.0002245833,0.000033357614,0.00013802527,0.00007422443,0.0000051319707],"category_scores_gemma":[0.00020222439,0.00013990745,0.00005056299,0.000010377218,0.00005787249,0.0000073316805,0.00007567185,0.00015604116,0.000004772157],"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":[0.00021712609,0.00022730394,0.015992552,0.0005556598,0.00054056844,0.000041679265,0.009765173,0.067926146,0.7564462,0.11089673,0.001834517,0.035556376],"study_design_scores_gemma":[0.0017061501,0.00022338195,0.0012851013,0.00009749658,0.0000869565,0.000066381064,0.00058687275,0.026646418,0.42623696,0.00034370506,0.5416613,0.0010592197],"about_ca_topic_score_codex":0.00006968212,"about_ca_topic_score_gemma":0.000021642487,"teacher_disagreement_score":0.5398268,"about_ca_system_score_codex":0.000024266887,"about_ca_system_score_gemma":0.000029366627,"threshold_uncertainty_score":0.57052606},"labels":[],"label_agreement":null},{"id":"W2410608061","doi":"10.1007/978-1-60327-136-3_11","title":"EST Databases and Web Tools for EST Projects","year":2009,"lang":"fr","type":"article","venue":"Methods in molecular biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Perl; Computer science; Database; Annotation; Key (lock); Process (computing); Interface (matter); Population; World Wide Web; Programming language","score_opus":0.03982723840015152,"score_gpt":0.4190411387041132,"score_spread":0.3792139003039617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2410608061","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":[0.022067044,0.02071873,0.947914,0.0024191977,0.0007392165,0.0011101529,0.00028614054,0.0000280003,0.0047175353],"genre_scores_gemma":[0.009234749,0.0017285665,0.98460865,0.0023751364,0.00029817928,0.00007768405,0.0008630311,0.000043273172,0.0007707095],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99663574,0.0011540941,0.0006410474,0.0007277724,0.000078393525,0.00076298154],"domain_scores_gemma":[0.9984161,0.00039334266,0.00024534608,0.0006978338,0.00010341044,0.0001439369],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019418185,0.00044512737,0.0005409505,0.00017145395,0.000097821634,0.00007417337,0.0003617285,0.00062028016,0.000022996472],"category_scores_gemma":[0.0045309723,0.00045796268,0.00015272074,0.00022773659,0.00038512298,0.000018638435,0.0002690236,0.0004072861,0.0000057526236],"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":[0.00011993784,0.00014234547,0.0009951596,0.00020456605,0.0000683339,0.000015465323,0.000120130644,0.000108937995,0.6757599,0.031370625,0.00039556887,0.29069903],"study_design_scores_gemma":[0.00222724,0.0026605797,0.00046306208,0.00014885899,0.00011233184,0.00020208946,0.00018311528,0.012013114,0.20288756,0.0037195683,0.77443165,0.0009508217],"about_ca_topic_score_codex":0.00004256642,"about_ca_topic_score_gemma":0.000051428935,"teacher_disagreement_score":0.7740361,"about_ca_system_score_codex":0.000036262307,"about_ca_system_score_gemma":0.00024081397,"threshold_uncertainty_score":0.9997872},"labels":[],"label_agreement":null},{"id":"W2426127897","doi":"10.1101/002121","title":"FALDO: A semantic standard for describing the location of nucleotide and protein feature annotation","year":2014,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Ontario Institute for Cancer Research","funders":"National Bioscience Database Center; Basic Energy Sciences; Japan Science and Technology Agency; National Institutes of Health; Research Organization of Information and Systems; Swiss Institute of Bioinformatics; Staatssekretariat für Bildung, Forschung und Innovation; U.S. Department of Energy; Australian Government; Office of Science; Scottish Government","keywords":"Annotation; Feature (linguistics); Computer science; Computational biology; Information retrieval; Biology; Artificial intelligence; Linguistics","score_opus":0.01130978491080346,"score_gpt":0.22173757920698595,"score_spread":0.2104277942961825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2426127897","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91098,0.0006736547,0.08626049,0.0003984378,0.0001764864,0.0013713418,0.000093437186,0.00004111761,0.0000050632057],"genre_scores_gemma":[0.9760511,0.00004994121,0.023331981,0.000114313414,0.00021638625,0.00016328211,0.0000034900313,0.00006096893,0.00000856306],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99871343,0.00010644059,0.00034987045,0.00039587734,0.00019720291,0.0002371993],"domain_scores_gemma":[0.9979172,0.000031385174,0.00053239096,0.00072044646,0.00073294603,0.0000656696],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00076369825,0.00028766613,0.00028463136,0.00007169673,0.00014174839,0.00010355193,0.00028970116,0.00037308887,0.0000011273078],"category_scores_gemma":[0.0008614199,0.00024600598,0.00007299493,0.00014088169,0.00012420058,0.000008242419,0.00025435077,0.00031852492,0.0000011839486],"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":[0.00011615716,0.000023141063,0.002310965,0.002052951,0.000118453,4.2129e-7,0.000031945543,0.0008893442,0.9932542,0.00057225564,0.0006115712,0.00001859521],"study_design_scores_gemma":[0.0011180163,0.00046356456,0.022791322,0.0013681955,0.00021467086,6.056953e-8,0.000019793599,0.019371206,0.93936336,0.000012409935,0.014462093,0.0008153064],"about_ca_topic_score_codex":0.0000128569345,"about_ca_topic_score_gemma":0.000004120951,"teacher_disagreement_score":0.065071106,"about_ca_system_score_codex":0.00003475772,"about_ca_system_score_gemma":0.00025041314,"threshold_uncertainty_score":0.9999992},"labels":[],"label_agreement":null},{"id":"W2444034415","doi":"10.1016/j.ymeth.2016.06.011","title":"Corrigendum to “Text as data: Using text-based features for proteins representation and for computational prediction of their characteristics” [Methods 74 (2015) 54–64]","year":2016,"lang":"en","type":"erratum","venue":"Methods","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital; University of Toronto; Queen's University","funders":"U.S. National Library of Medicine; National Institutes of Health","keywords":"Representation (politics); Computer science; Computational biology; Artificial intelligence; Natural language processing; Biology","score_opus":0.08380043872700878,"score_gpt":0.4424589382317048,"score_spread":0.358658499504696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2444034415","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":[0.00040581627,0.00038061675,0.98537904,0.00021133036,0.0065003643,0.0019932692,0.004836271,0.000023996254,0.00026930068],"genre_scores_gemma":[0.00017547864,0.000043041233,0.9696562,0.00025172095,0.001575516,0.00021464785,0.017313665,0.00008458941,0.010685116],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976043,0.0005972583,0.0006503378,0.0006623314,0.00019158577,0.000294191],"domain_scores_gemma":[0.9974377,0.00035605265,0.00079466647,0.0008377873,0.00046335682,0.0001104179],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024159248,0.00036022443,0.00053514936,0.00017830428,0.00017112213,0.00006753047,0.00042899602,0.0006213937,0.000012867744],"category_scores_gemma":[0.0035033321,0.00029964483,0.00014214475,0.00009706564,0.00011148749,0.000016074693,0.00029074957,0.00025310344,7.1043223e-7],"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":[0.0012488795,0.00012972287,0.00024249489,0.0024979229,0.0005468946,6.195819e-7,0.00045462453,0.00082177715,0.2046588,0.00017426854,0.46888608,0.32033792],"study_design_scores_gemma":[0.0009865239,0.0008542891,0.0015291526,0.000280198,0.00019965628,0.000023831202,0.00005560688,0.12813878,0.035441477,0.00062575063,0.83142525,0.0004394628],"about_ca_topic_score_codex":0.000035630594,"about_ca_topic_score_gemma":0.000006368066,"teacher_disagreement_score":0.3625392,"about_ca_system_score_codex":0.000045785164,"about_ca_system_score_gemma":0.00041891806,"threshold_uncertainty_score":0.9999456},"labels":[],"label_agreement":null},{"id":"W2468937966","doi":"10.1109/embsisc.2016.7508598","title":"Predicting novel protein-protein interactions between the HIV-1 virus and homo sapiens","year":2016,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Human immunodeficiency virus (HIV); Protein–protein interaction; Computer science; Virus; Computational biology; Homo sapiens; Biology; Virology; Genetics","score_opus":0.010096062071775975,"score_gpt":0.2510060298348622,"score_spread":0.24090996776308624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2468937966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9338431,0.000026926633,0.05832688,0.0017814655,0.000041550185,0.00034144765,0.00006692541,0.00003502955,0.005536691],"genre_scores_gemma":[0.9882771,0.0000062236295,0.0045390623,0.00012791832,0.00026633765,0.000040701383,0.000024235043,0.000015900387,0.006702563],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993139,0.000031015457,0.00020067736,0.00016971181,0.00009541836,0.00018928525],"domain_scores_gemma":[0.9994553,0.000033791643,0.00009774781,0.0003099217,0.00004451796,0.000058722344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001941707,0.00012053018,0.00008393495,0.000023940696,0.0001627673,0.000037700956,0.00016516162,0.00007208884,0.000059328635],"category_scores_gemma":[0.00028004803,0.00006395496,0.000040117306,0.0000428809,0.00010044682,0.00000823982,0.00021095804,0.00012278205,0.00004574214],"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":[0.000014092487,0.000017618384,0.022694154,0.000014960388,0.000052629715,2.0496283e-7,0.00008320226,0.0000033810657,0.9677991,0.00029023655,0.00057748816,0.008452878],"study_design_scores_gemma":[0.0014970391,0.00044484987,0.037240658,0.00017540819,0.000052122108,0.00006122939,0.00022079046,0.0008771116,0.7114221,0.00020613706,0.24724615,0.0005564248],"about_ca_topic_score_codex":0.000035803576,"about_ca_topic_score_gemma":0.000040085466,"teacher_disagreement_score":0.25637707,"about_ca_system_score_codex":0.000009449512,"about_ca_system_score_gemma":0.000022405526,"threshold_uncertainty_score":0.26080075},"labels":[],"label_agreement":null},{"id":"W2503895389","doi":"10.1007/0-306-46862-x_152","title":"Prediction of protein transmembrane segments using a hydrophobicity scale derived from hydrophobic peptides","year":2005,"lang":"en","type":"book-chapter","venue":"Kluwer Academic Publishers eBooks","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Hospital for Sick Children; University of Toronto","funders":"","keywords":"Transmembrane protein; Scale (ratio); Chemistry; Chromatography; Biochemistry; Geography; Cartography","score_opus":0.019436507278270496,"score_gpt":0.2329295402295871,"score_spread":0.2134930329513166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2503895389","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6836217,0.00090209796,0.0012124769,0.000061507286,0.0004036934,0.0014702976,0.00064943754,0.000114120674,0.31156465],"genre_scores_gemma":[0.7045993,0.00012933258,0.009501492,0.0005868588,0.0019427127,0.00008131893,0.0024984241,0.00040977966,0.28025076],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99684405,0.000073898496,0.0011748644,0.0007568312,0.00065527385,0.0004950585],"domain_scores_gemma":[0.99787456,0.000020199732,0.0009246968,0.0007771764,0.00017229778,0.00023109488],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0003834529,0.0006960342,0.00069019746,0.00024275926,0.00012556127,0.00009055543,0.0008031085,0.0020764,0.00020009832],"category_scores_gemma":[0.000054810676,0.00072558044,0.000369733,0.000033739263,0.0003937604,0.0000500848,0.0002848633,0.0016379952,0.000015140336],"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":[0.00018614187,0.00002254792,0.0001818355,0.00020810316,0.00037745244,0.0000028222394,0.00043241854,0.00027266983,0.99366367,0.00003534639,0.0016437982,0.0029731758],"study_design_scores_gemma":[0.004486602,0.0007287437,0.00025266348,0.0020769243,0.00090180896,0.000091861075,0.000121590936,0.009119458,0.6431599,0.0018826817,0.33470562,0.0024721231],"about_ca_topic_score_codex":0.000115398325,"about_ca_topic_score_gemma":0.00001809473,"teacher_disagreement_score":0.35050374,"about_ca_system_score_codex":0.00014245558,"about_ca_system_score_gemma":0.00031427958,"threshold_uncertainty_score":0.9995195},"labels":[],"label_agreement":null},{"id":"W2512143001","doi":"10.1186/s12859-016-1115-5","title":"Predicting essential proteins based on subcellular localization, orthology and PPI networks","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Subcellular localization; Computational biology; DNA microarray; Protein subcellular localization prediction; Biology; Computer science; Genetics; Gene; Gene expression","score_opus":0.00529630127268006,"score_gpt":0.21752425144842968,"score_spread":0.21222795017574964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512143001","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":[0.050674282,0.0000464123,0.9469353,0.000115054325,0.0001586326,0.00037532326,0.000016000335,0.00006110574,0.001617911],"genre_scores_gemma":[0.9158099,0.00007903006,0.08202196,0.0010235053,0.0003380537,0.000039967534,0.0002623712,0.000048622296,0.00037655563],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869984,0.00006910775,0.0005035982,0.00018628001,0.00020233035,0.00033884463],"domain_scores_gemma":[0.99900866,0.000056666973,0.00026404014,0.0004576122,0.0000963192,0.00011668679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003719677,0.00022859918,0.00017290025,0.000085425665,0.00016734496,0.000049577877,0.00018868153,0.00027831484,0.000029938845],"category_scores_gemma":[0.00036073243,0.00016310145,0.000064177206,0.00010896439,0.00017438491,0.000016680511,0.00013552117,0.000122009566,0.000023935328],"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":[0.00061943906,0.00023439193,0.7254546,0.0010700808,0.00013244881,0.0000071004715,0.0006096036,0.23927735,0.0050081387,0.0020315617,0.005160405,0.020394852],"study_design_scores_gemma":[0.0010987403,0.00042744356,0.0023595188,0.000085471234,0.00002140044,0.00002325041,0.00005289388,0.9863968,0.002826711,0.000018826988,0.006413172,0.00027577812],"about_ca_topic_score_codex":0.0000037313139,"about_ca_topic_score_gemma":0.000019773213,"teacher_disagreement_score":0.86513567,"about_ca_system_score_codex":0.00001677702,"about_ca_system_score_gemma":0.000084625055,"threshold_uncertainty_score":0.6651084},"labels":[],"label_agreement":null},{"id":"W2527794637","doi":"10.1016/j.compmedimag.2016.08.004","title":"WITHDRAWN: Improving classification of protein binders for virtual drug screening by novel swarm-based feature selection techniques","year":2016,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Lakehead University","funders":"","keywords":"Feature selection; Computer science; Selection (genetic algorithm); Feature (linguistics); Artificial intelligence","score_opus":0.005779229238930653,"score_gpt":0.24733961668204324,"score_spread":0.2415603874431126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2527794637","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":[0.08672089,0.000093021255,0.9102337,0.0025319355,0.000053812684,0.000282688,0.000019189287,0.000054809327,0.000009946269],"genre_scores_gemma":[0.84943604,0.000028759567,0.14951187,0.000590203,0.00013772724,0.00004900643,0.0001418186,0.000026850646,0.000077713165],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990756,0.00004355294,0.00023583297,0.00024564436,0.00021446058,0.00018489998],"domain_scores_gemma":[0.9993567,0.00005752429,0.00019667309,0.00014960462,0.00013326877,0.00010625045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048086751,0.00014673677,0.0001547186,0.00008534787,0.000107982676,0.000027592187,0.00015005676,0.00015214014,0.0000010679008],"category_scores_gemma":[0.00030099432,0.00010946437,0.00006371611,0.00010447082,0.0002504524,0.000011368134,0.00006166191,0.00015561596,7.001724e-8],"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":[0.00012023135,0.000041776977,0.0013183919,0.000117726246,0.000022778106,1.4589259e-7,0.000021973701,0.0000022556274,0.85525745,0.00018967585,0.0017759794,0.14113162],"study_design_scores_gemma":[0.003771806,0.00048487118,0.0009569493,0.00069625315,0.000044688382,0.000026903286,0.000056154884,0.4091534,0.55098695,0.000080213125,0.03324415,0.0004976566],"about_ca_topic_score_codex":0.00001022051,"about_ca_topic_score_gemma":0.0000025069498,"teacher_disagreement_score":0.76271516,"about_ca_system_score_codex":0.0000071520462,"about_ca_system_score_gemma":0.00009013427,"threshold_uncertainty_score":0.44638273},"labels":[],"label_agreement":null},{"id":"W2527882627","doi":"10.1182/blood.v116.21.4226.4226","title":"Genomic Evidence for Elements of a Programmed Cell Death Pathway In Plasmodium: Exploiting Programmed Parasite Death for Malaria Control?","year":2010,"lang":"en","type":"article","venue":"Blood","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Biology; Plasmodium falciparum; Plasmodium (life cycle); Genome; Malaria; Phylogenetics; Genetics; Evolutionary biology; Plasmodium yoelii; Parasite hosting; Gene; Immunology","score_opus":0.023354748994066553,"score_gpt":0.2906320862714622,"score_spread":0.26727733727739567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2527882627","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98954797,0.00012526834,0.007613877,0.000051203908,0.00008866711,0.002397272,0.000067946305,0.000020832902,0.000086935266],"genre_scores_gemma":[0.8955918,0.00001095436,0.10301294,0.000065823384,0.00011154346,0.0009535247,0.00016797487,0.0000347911,0.000050634037],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99848336,0.000038888087,0.0005568877,0.0003106645,0.0001269553,0.00048324317],"domain_scores_gemma":[0.99895173,0.00011532706,0.00036432318,0.000346131,0.0001350993,0.000087357126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007283801,0.00020921172,0.0002627939,0.000060531973,0.000064225,0.000038823262,0.0003063308,0.00020352993,0.0000032653259],"category_scores_gemma":[0.0006377817,0.0001998483,0.00014293667,0.00005805356,0.000035969802,0.000009877576,0.000072291485,0.00016428145,0.0000014244958],"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":[0.00034105242,0.00041920794,0.28437403,0.00036029448,0.000068753056,0.0000010689619,0.00011608088,0.000035012476,0.71111125,0.00024242676,0.0000139048425,0.0029169125],"study_design_scores_gemma":[0.018995361,0.0027054232,0.034430787,0.00014392113,0.00019995698,0.000021759897,0.0001087899,0.0100767715,0.9245725,0.00019635004,0.007896732,0.000651608],"about_ca_topic_score_codex":0.00002404431,"about_ca_topic_score_gemma":0.00008049767,"teacher_disagreement_score":0.24994324,"about_ca_system_score_codex":0.000009125949,"about_ca_system_score_gemma":0.0001300413,"threshold_uncertainty_score":0.81495774},"labels":[],"label_agreement":null},{"id":"W2535391591","doi":"10.1016/j.patrec.2016.10.010","title":"Combining multiple approaches for the early diagnosis of Alzheimer's Disease","year":2016,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Biomedical Imaging and Bioengineering; National Institute on Aging; National Institutes of Health; Canadian Institutes of Health Research; Centre National de la Recherche Scientifique; Consiglio Nazionale delle Ricerche; U.S. Department of Defense","keywords":"Support vector machine; Artificial intelligence; Computer science; Pattern recognition (psychology); Curse of dimensionality; Feature (linguistics); Set (abstract data type); Machine learning; Dimensionality reduction; Feature vector","score_opus":0.043127353401932356,"score_gpt":0.248125077360002,"score_spread":0.20499772395806964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2535391591","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86038214,0.000120315104,0.13496867,0.003733885,0.00013450853,0.00040825165,0.00020401068,0.000013891866,0.000034314715],"genre_scores_gemma":[0.99678147,0.00003895807,0.0009775634,0.0015638641,0.0001462087,0.00029865903,0.00016453488,0.000020221478,0.000008550309],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9993468,0.000044822234,0.00020535596,0.00015279367,0.00009503389,0.00015520945],"domain_scores_gemma":[0.9993343,0.0001993898,0.00015383786,0.0002239248,0.000038698523,0.000049854112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015977284,0.00010732425,0.00008710226,0.00002747911,0.000070550115,0.000015071394,0.00013972099,0.000041187774,0.000023774759],"category_scores_gemma":[0.00022373925,0.00006687734,0.0001142158,0.000027111237,0.000089314744,0.0000069873363,0.000051669733,0.000041951433,0.000015671005],"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":[0.00013123782,0.0000651413,0.4827544,0.00006591493,0.0002460941,5.612534e-7,0.00016346571,0.0000706671,0.016007997,0.0000034002935,0.003112786,0.49737832],"study_design_scores_gemma":[0.008281297,0.0007249173,0.6235592,0.00050606567,0.00086008717,0.000009730847,0.00022640932,0.0071639717,0.33229956,0.0001918165,0.024837837,0.0013390896],"about_ca_topic_score_codex":0.000014571489,"about_ca_topic_score_gemma":0.0000042770803,"teacher_disagreement_score":0.49603924,"about_ca_system_score_codex":0.0000042311667,"about_ca_system_score_gemma":0.000008874495,"threshold_uncertainty_score":0.2727179},"labels":[],"label_agreement":null},{"id":"W2557972923","doi":"10.1145/2975167.2985652","title":"Prediction of Cell Type Specific Transcription Factor Binding Site Occupancy","year":2016,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Transcription factor; ENCODE; DNA binding site; Logistic regression; Computer science; Motif (music); Computational biology; Transcription (linguistics); Occupancy; Sequence motif; Artificial intelligence; Biology; DNA; Machine learning; Promoter; Genetics; Gene; Gene expression","score_opus":0.018422715475558515,"score_gpt":0.2308693664184352,"score_spread":0.21244665094287668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2557972923","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9738982,0.000073132986,0.019602844,0.000028651133,0.00022559075,0.00008236707,0.000086199085,0.000019658572,0.0059833713],"genre_scores_gemma":[0.9938626,0.0002713406,0.0024056716,0.00001831211,0.000085644526,0.0000012403575,0.00009490693,0.0000098587725,0.003250388],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99949133,0.000018675635,0.00018212579,0.00011226351,0.00008731233,0.000108315005],"domain_scores_gemma":[0.9996532,0.0000063641214,0.00007315217,0.00018235814,0.000052916832,0.000032009117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006249396,0.00007822397,0.00006939737,0.00003837502,0.000023512148,0.000005901427,0.00007039266,0.00009179851,0.0002608861],"category_scores_gemma":[0.000019677907,0.000052683954,0.00004480333,0.000053756914,0.000026067995,0.000005475156,0.000018387318,0.000036043984,0.000092835886],"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":[0.000035440626,0.000016282998,0.017304106,0.000020778489,0.000006698578,8.155213e-8,0.00004538354,0.0000025736856,0.9789357,0.000022110587,0.0017710231,0.0018398133],"study_design_scores_gemma":[0.0004439258,0.00029658084,0.014868252,0.000017148326,0.0000057863986,0.00000240406,0.000017141267,0.00007498648,0.91676605,0.000004801274,0.06741545,0.00008745733],"about_ca_topic_score_codex":0.0000023188804,"about_ca_topic_score_gemma":0.0000017092655,"teacher_disagreement_score":0.06564443,"about_ca_system_score_codex":0.000008680746,"about_ca_system_score_gemma":0.000014485934,"threshold_uncertainty_score":0.28565198},"labels":[],"label_agreement":null},{"id":"W2559115594","doi":"","title":"Proteome Analyst: An Overview","year":2004,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Gene ontology; Computer science; Upload; Parsing; UniProt; Proteome; Ontology; Classifier (UML); Set (abstract data type); Function (biology); Class (philosophy); Natural language processing; Computational biology; Artificial intelligence; Gene; Bioinformatics; Biology; Programming language; World Wide Web; Genetics","score_opus":0.020555930780393493,"score_gpt":0.31370116521687536,"score_spread":0.2931452344364819,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559115594","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9499525,0.00049780385,0.018783096,0.00045414767,0.000076507,0.00029203508,0.0000049503738,0.00006603661,0.029872952],"genre_scores_gemma":[0.9648738,0.000106408406,0.03207585,0.0012106422,0.00014498485,0.000013432856,0.00013655864,0.000016119773,0.001422195],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99949175,0.000017650622,0.00013461137,0.00013190556,0.00008847403,0.00013559723],"domain_scores_gemma":[0.9995262,9.994673e-7,0.00004215204,0.00033132685,0.000032147735,0.00006716458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011801724,0.00008665235,0.00007310535,0.000023416482,0.000042381667,0.0000221228,0.000149632,0.000072645744,0.00009946549],"category_scores_gemma":[0.000038569633,0.000071242874,0.000045981844,0.00006752295,0.000024068979,0.000003710551,0.0000580519,0.000060811144,0.00006857976],"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":[0.00013501069,0.0006116152,0.016044332,0.00036957618,0.00030701444,0.000017334618,0.00062916987,0.021008097,0.8901386,0.046027843,0.003486636,0.021224746],"study_design_scores_gemma":[0.0037529252,0.0030616722,0.02986655,0.00007131224,0.00007809976,0.00021702105,0.00027883967,0.0028734272,0.5751605,0.0045238705,0.37856886,0.001546905],"about_ca_topic_score_codex":0.00003847388,"about_ca_topic_score_gemma":0.000051826166,"teacher_disagreement_score":0.37508222,"about_ca_system_score_codex":0.000007630479,"about_ca_system_score_gemma":0.000040269584,"threshold_uncertainty_score":0.29052},"labels":[],"label_agreement":null},{"id":"W2567489417","doi":"10.1093/bioinformatics/btw781","title":"AnglerFish: a webserver for defining the geometry of α-helices in membrane proteins","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Biotechnology and Biological Sciences Research Council; Medical Research Council; Medical Research Council Canada; Pfizer","keywords":"Perl; Crystallography; Protein Data Bank (RCSB PDB); Helix (gastropod); Transmembrane protein; Orientation (vector space); Computer science; Membrane protein; Integral membrane protein; Protein structure; Transmembrane domain; Web server; Software; Computational biology; Biology; Membrane; Chemistry; Geometry; Biochemistry; Mathematics; Programming language; World Wide Web; The Internet","score_opus":0.010021768268550921,"score_gpt":0.24895022811555564,"score_spread":0.23892845984700473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2567489417","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9635864,0.00033525444,0.02821404,0.00081548124,0.0002290867,0.001182161,0.00017059514,0.000030430532,0.0054365383],"genre_scores_gemma":[0.9513539,0.00014307191,0.04717514,0.00043998333,0.000089884285,0.00010402982,0.00007735589,0.000028574561,0.00058804126],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99887544,0.000025865782,0.00056248554,0.00009739535,0.00016953697,0.00026929664],"domain_scores_gemma":[0.9990188,0.000104135164,0.00032044857,0.00042170406,0.00009453105,0.000040404007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060203817,0.00014983436,0.00017662004,0.00009040275,0.000058335238,0.000020707132,0.00036571166,0.0001381304,0.000019087322],"category_scores_gemma":[0.0006872924,0.000083549676,0.00009793572,0.0001698039,0.00010693145,0.000019788402,0.00014102922,0.00007263726,0.000015056479],"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":[0.0021375527,0.0009399798,0.2128534,0.0095284935,0.0010471748,0.0000038525427,0.010726991,0.0028793518,0.32116884,0.04123378,0.037361857,0.36011872],"study_design_scores_gemma":[0.009269469,0.0025516239,0.028386045,0.00097435724,0.000111962116,0.00006559503,0.0022790828,0.03363087,0.5848027,0.00053398707,0.33583942,0.0015549004],"about_ca_topic_score_codex":0.000010861159,"about_ca_topic_score_gemma":0.000034483342,"teacher_disagreement_score":0.3585638,"about_ca_system_score_codex":0.000014375659,"about_ca_system_score_gemma":0.000075034215,"threshold_uncertainty_score":0.3407057},"labels":[],"label_agreement":null},{"id":"W2590688707","doi":"10.1002/humu.23193","title":"Predicting phenotype from genotype: Improving accuracy through more robust experimental and computational modeling","year":2017,"lang":"en","type":"article","venue":"Human Mutation","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"National Institute of General Medical Sciences; Defense Advanced Research Projects Agency; National Institutes of Health; Cancer Prevention and Research Institute of Texas; National Science Foundation","keywords":"Biology; Phenotype; Genotype; Genotype-phenotype distinction; Computational biology; Genetics; Bioinformatics; Gene","score_opus":0.026346046560803412,"score_gpt":0.3129055952071076,"score_spread":0.2865595486463042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2590688707","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8998411,0.00017118682,0.0990411,0.000039986928,0.00007154707,0.00010929958,0.000010863647,0.000020267458,0.00069461274],"genre_scores_gemma":[0.97430265,0.0000027004824,0.024691708,0.00009052107,0.00025440074,0.000007207716,0.00060286437,0.000017776614,0.00003017261],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935997,0.000018794079,0.00018445878,0.00019974068,0.00012095662,0.00011610537],"domain_scores_gemma":[0.9994672,0.000012971995,0.0002097841,0.00022171698,0.00005760865,0.000030696818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008094817,0.00010952219,0.0000785242,0.000014939392,0.00065205555,0.00016481393,0.00013594574,0.00007818146,0.000017665174],"category_scores_gemma":[0.00015306241,0.00011615956,0.000024876392,0.000008896181,0.000060651986,0.000038877002,0.00014408804,0.000092512426,0.0000039325896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009502491,0.00007591528,0.020082567,0.000081213104,0.000112372494,0.0000072095213,0.008306472,0.63968897,0.323245,0.0009099185,0.000113223236,0.0072821397],"study_design_scores_gemma":[0.0006660002,0.00008119163,0.012734932,0.000018580175,0.000017886705,0.000007193884,0.00060885435,0.9789302,0.0061283605,0.00059562345,0.00003823338,0.00017294491],"about_ca_topic_score_codex":0.0003297569,"about_ca_topic_score_gemma":0.000019855863,"teacher_disagreement_score":0.33924124,"about_ca_system_score_codex":0.00001480263,"about_ca_system_score_gemma":0.000023227463,"threshold_uncertainty_score":0.50151503},"labels":[],"label_agreement":null},{"id":"W2598976994","doi":"10.1016/j.patrec.2017.03.011","title":"Feature selection by maximizing correlation information for integrated high-dimensional protein data","year":2017,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Machine Learning in Bioinformatics","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":"York University","funders":"Specialized Research Fund for the Doctoral Program of Higher Education of China; Natural Sciences and Engineering Research Council of Canada; Ministry of Industry and Information Technology of the People's Republic of China; National Natural Science Foundation of China","keywords":"Feature selection; Random forest; Computer science; Benchmark (surveying); Feature (linguistics); Pattern recognition (psychology); Correlation; Artificial intelligence; Support vector machine; Feature vector; Coding (social sciences); High dimensional; Data mining; Mathematics; Statistics","score_opus":0.015535182070913827,"score_gpt":0.2529235969522161,"score_spread":0.23738841488130227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2598976994","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5237016,0.000008015911,0.46974975,0.004660183,0.00031968538,0.0006623301,0.0007876513,0.000038895472,0.00007187906],"genre_scores_gemma":[0.888802,0.000005888275,0.026734738,0.0042868336,0.00036187397,0.00013601578,0.0794555,0.000032064934,0.0001851154],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992195,0.000041186617,0.00020369035,0.00021262675,0.0001450994,0.0001779414],"domain_scores_gemma":[0.99896795,0.000012865489,0.00040727106,0.00043090762,0.00013848826,0.000042515163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002573659,0.00015197796,0.00009789811,0.000053085656,0.00038131652,0.00020256951,0.00029641532,0.00015509698,0.000027341543],"category_scores_gemma":[0.00038401937,0.00015057252,0.00003881847,0.000027908136,0.000040320185,0.000121664285,0.00012017456,0.00017969935,0.000050183775],"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":[0.0003454703,0.0000503152,0.00817791,0.00018389573,0.00013988807,5.1310246e-7,0.000071978524,0.00052414427,0.32744613,0.0000035096716,0.29032674,0.3727295],"study_design_scores_gemma":[0.008688975,0.00079366163,0.02367069,0.0005238118,0.00022493547,0.00009582178,0.000103458726,0.45390123,0.21101467,0.00012750285,0.298889,0.0019662466],"about_ca_topic_score_codex":0.0000765203,"about_ca_topic_score_gemma":0.000023505125,"teacher_disagreement_score":0.45337707,"about_ca_system_score_codex":0.00002597084,"about_ca_system_score_gemma":0.00002497759,"threshold_uncertainty_score":0.61401695},"labels":[],"label_agreement":null},{"id":"W2602556590","doi":"10.1371/journal.pone.0174392","title":"ML2Motif—Reliable extraction of discriminative sequence motifs from learning machines","year":2017,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Banting and Best Diabetes Centre, University of Toronto; Bundesministerium für Bildung und Forschung; National Research Foundation of Korea; Deutsche Forschungsgemeinschaft; National Research Foundation","keywords":"Artificial intelligence; Computer science; Support vector machine; Machine learning; Discriminative model; Pattern recognition (psychology); Computation; Data mining; Algorithm","score_opus":0.04477034974656711,"score_gpt":0.29424838557992594,"score_spread":0.24947803583335884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602556590","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98980117,0.00008531959,0.0012499477,0.00016656527,0.000073548756,0.00011456839,0.000028424136,0.000015386355,0.008465071],"genre_scores_gemma":[0.9839199,0.00012522284,0.013297593,0.000025127323,0.00014389999,0.000008379259,0.0002523411,0.000017750008,0.0022097623],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992125,0.00003890233,0.00020730135,0.00019048163,0.00019866395,0.00015212572],"domain_scores_gemma":[0.99892795,0.000023129342,0.00038643405,0.0005038199,0.00011236876,0.000046269208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014295538,0.00012541912,0.00017431866,0.000026647793,0.00022842146,0.00005035094,0.0003157727,0.000107031214,0.000098299315],"category_scores_gemma":[0.00090928416,0.000119352866,0.0000483536,0.00001960864,0.00011974428,0.00001910259,0.00017313192,0.00021966714,0.000020282967],"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":[0.000042948162,0.00023646542,0.0795703,0.00009285529,0.00014842732,0.0000013239827,0.00027576805,0.0003092338,0.9176398,0.00006259709,0.000112061294,0.0015082478],"study_design_scores_gemma":[0.0005011153,0.0003532445,0.051935196,0.00020883125,0.00013151647,0.0000025777613,0.00015614144,0.031230465,0.91387707,0.0003489821,0.00097412313,0.00028073954],"about_ca_topic_score_codex":0.00036164725,"about_ca_topic_score_gemma":0.000035092417,"teacher_disagreement_score":0.03092123,"about_ca_system_score_codex":0.000011707907,"about_ca_system_score_gemma":0.000025343334,"threshold_uncertainty_score":0.48670685},"labels":[],"label_agreement":null},{"id":"W2605595174","doi":"10.1186/s12859-017-1602-3","title":"A machine learning approach for viral genome classification","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Biology; Subtyping; Computational biology; In silico; Genetics; Artificial intelligence; Computer science; Gene","score_opus":0.029051288775398105,"score_gpt":0.28135736090967217,"score_spread":0.2523060721342741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605595174","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":[0.010625185,0.00011206914,0.9508111,0.00006904471,0.00014734638,0.00068823533,0.00007068175,0.00006593917,0.03741042],"genre_scores_gemma":[0.25324067,0.00009091047,0.7404467,0.00021031729,0.00035215993,0.0001052137,0.0024073026,0.00005073725,0.0030959737],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876714,0.000028876588,0.00047964495,0.00018744833,0.00018638969,0.0003504775],"domain_scores_gemma":[0.99822307,0.000018586477,0.0006318124,0.0009070194,0.0001173707,0.00010212579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053152104,0.00023218442,0.00020101233,0.0000641783,0.00077608717,0.00027083457,0.0006797421,0.00022618347,0.000009046016],"category_scores_gemma":[0.0007537461,0.00021221723,0.00015500309,0.000029923216,0.00013743712,0.000034927434,0.0002562544,0.00020717639,0.00003375246],"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":[0.0035537528,0.0017322487,0.38629824,0.015000826,0.0017025708,0.0000031873165,0.009468461,0.22210386,0.1229196,0.054703627,0.017884057,0.16462956],"study_design_scores_gemma":[0.00091839535,0.00024981756,0.0063202344,0.000007725442,0.000027615226,0.000015242051,0.00015719814,0.9137168,0.00049398956,0.000043525124,0.07773948,0.000309975],"about_ca_topic_score_codex":0.000007701352,"about_ca_topic_score_gemma":0.000006323701,"teacher_disagreement_score":0.69161296,"about_ca_system_score_codex":0.000023311268,"about_ca_system_score_gemma":0.00007993015,"threshold_uncertainty_score":0.8653968},"labels":[],"label_agreement":null},{"id":"W2606957126","doi":"10.1371/journal.pcbi.1005499","title":"Exhaustive search of linear information encoding protein-peptide recognition","year":2017,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Toronto","funders":"Weizmann Institute of Science","keywords":"Computational biology; SH3 domain; Saccharomyces cerevisiae; Protein domain; Peptide; Protein sequencing; Biology; Sequence (biology); Genetics; Peptide sequence; Yeast; Gene; Biochemistry; Proto-oncogene tyrosine-protein kinase Src; Signal transduction","score_opus":0.02998149561634161,"score_gpt":0.3030676450318327,"score_spread":0.2730861494154911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606957126","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9678547,0.0000124273365,0.024975851,0.00019496503,0.000068616464,0.00029433306,0.00010454347,0.000015585254,0.0064790025],"genre_scores_gemma":[0.964721,0.0000070313718,0.03328128,0.00009931408,0.00011279723,0.00001766397,0.0017025567,0.000006543449,0.00005177976],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99928254,0.000046721118,0.00029348664,0.00011969125,0.000114636234,0.00014291865],"domain_scores_gemma":[0.9990548,0.000028501958,0.00031718478,0.00020828104,0.00035298654,0.00003824005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020603059,0.00009952023,0.00012240116,0.00007146192,0.00022104799,0.000024875317,0.00023079987,0.00012441726,0.000031883817],"category_scores_gemma":[0.0005190921,0.00009551931,0.000047429305,0.000028297336,0.00016175232,0.000025345505,0.00016332873,0.0001203291,0.00006943511],"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":[0.0011083501,0.0004655481,0.108671516,0.000943892,0.00082527194,0.0000034616194,0.0019368171,0.046489667,0.7531043,0.013468266,0.0011249027,0.07185799],"study_design_scores_gemma":[0.0047579384,0.0035007996,0.08124069,0.00038892997,0.00009309849,0.000071052105,0.00051301235,0.28649625,0.5950761,0.01305283,0.0134381475,0.0013711294],"about_ca_topic_score_codex":0.000021860775,"about_ca_topic_score_gemma":0.0000021206895,"teacher_disagreement_score":0.2400066,"about_ca_system_score_codex":0.000011556893,"about_ca_system_score_gemma":0.00007745424,"threshold_uncertainty_score":0.38951644},"labels":[],"label_agreement":null},{"id":"W2610497813","doi":"10.71781/26408","title":"Molecular protein function prediction using sequence similarity-based and similarity-free approaches","year":2007,"lang":"en","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Deutsche Forschungsgemeinschaft; Canadian Institute for Advanced Research","keywords":"Similarity (geometry); Sequence (biology); Computational biology; Function (biology); Structural similarity; Computer science; Data mining; Artificial intelligence; Biological system; Mathematics; Biology; Genetics","score_opus":0.011947256162412788,"score_gpt":0.20265006444358075,"score_spread":0.19070280828116795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610497813","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97005314,0.0033681726,0.015906643,0.00006546537,0.0003540271,0.0006358652,0.00011372063,0.000079127814,0.009423839],"genre_scores_gemma":[0.9797623,0.000055170927,0.011290009,0.0001728787,0.00021106144,0.000029277107,0.004019899,0.0000614264,0.0043979534],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99820065,0.000103801816,0.0003472535,0.00053654076,0.00048957905,0.0003221718],"domain_scores_gemma":[0.9987183,0.0000150093365,0.00037035433,0.00052123796,0.0001939895,0.00018108015],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00029909256,0.0003889388,0.00024595248,0.000227485,0.0021718498,0.00005811319,0.00029678855,0.0007946853,0.0000052544424],"category_scores_gemma":[0.0001326546,0.00046246633,0.00016279168,0.00016722527,0.00017684167,0.000030712967,0.00014966824,0.00049656635,0.0000018193223],"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":[0.0032910088,0.00026756153,0.011822098,0.0013481478,0.0006370277,0.0004366968,0.0025260667,0.04984301,0.9212176,0.0044940617,0.0003081996,0.0038085273],"study_design_scores_gemma":[0.006690438,0.0017291795,0.035325646,0.0012584314,0.0019474407,0.0012843825,0.012539264,0.23017244,0.6472389,0.0013879866,0.056863952,0.0035618993],"about_ca_topic_score_codex":0.0012109345,"about_ca_topic_score_gemma":0.0007329374,"teacher_disagreement_score":0.27397865,"about_ca_system_score_codex":0.0008271257,"about_ca_system_score_gemma":0.0009024882,"threshold_uncertainty_score":0.9997827},"labels":[],"label_agreement":null},{"id":"W2618911605","doi":"10.4310/sii.2017.v10.n4.a9","title":"Detection of threshold points for gene expressions under multiple biological conditions","year":2017,"lang":"en","type":"article","venue":"Statistics and Its Interface","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Regina","funders":"","keywords":"Mathematics; Statistics; Computational biology; Computer science; Biology; Econometrics; Genetics","score_opus":0.028790288283039256,"score_gpt":0.33156691780229963,"score_spread":0.3027766295192604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2618911605","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6011149,0.00010688081,0.39728257,0.000050364735,0.00012977811,0.00015806417,0.000939158,0.000004860125,0.00021342505],"genre_scores_gemma":[0.98694426,0.00009593776,0.012488095,0.000039055907,0.00003981731,0.000013881061,0.00012752507,0.000008762828,0.00024267685],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99953794,0.000012741923,0.00016300488,0.00013094289,0.000044634635,0.00011074928],"domain_scores_gemma":[0.9994391,0.000042565647,0.00016178815,0.0002157271,0.00009758999,0.000043190597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000086171225,0.00008526679,0.00009899857,0.000016409987,0.00023749836,0.000029089542,0.00013038487,0.00008862484,0.000014649673],"category_scores_gemma":[0.0005901017,0.000071340444,0.0000255916,0.000007103004,0.000102303486,0.0000046953883,0.00013096568,0.00006186793,0.0000022073498],"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":[0.000052671552,0.00002820323,0.0007287163,0.00003366212,0.000032707652,1.563046e-7,0.00004803883,0.00016049843,0.9954011,0.0023535974,0.0006490707,0.0005116177],"study_design_scores_gemma":[0.000929621,0.00067259965,0.0140260225,0.000033048553,0.000023292088,0.000009356083,0.00011533776,0.032237288,0.94550407,0.0024264771,0.0038255288,0.00019737877],"about_ca_topic_score_codex":0.0000049270584,"about_ca_topic_score_gemma":0.00001673758,"teacher_disagreement_score":0.38582933,"about_ca_system_score_codex":0.0000036354359,"about_ca_system_score_gemma":0.0000122081565,"threshold_uncertainty_score":0.29091787},"labels":[],"label_agreement":null},{"id":"W2624061738","doi":"10.71781/25871","title":"Développement d'outils bio-informatique pour l'étude de la transcription cryptique","year":2016,"lang":"fr","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Biology; Molecular biology","score_opus":0.003834416303317783,"score_gpt":0.20067953235810618,"score_spread":0.19684511605478838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2624061738","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89720744,0.007806967,0.024645872,0.0014712742,0.0010035118,0.0006680132,0.00015886175,0.00010294979,0.06693514],"genre_scores_gemma":[0.94386387,0.004446007,0.009471316,0.00036798738,0.00037769912,0.000057511123,0.0015162011,0.000063153646,0.039836265],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9972485,0.0003809613,0.000700544,0.000501554,0.00050877157,0.00065969164],"domain_scores_gemma":[0.99808466,0.000085142994,0.0006186929,0.0004943351,0.00032210982,0.00039504783],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0005589615,0.00064033596,0.0004070497,0.00025230888,0.003345687,0.00010372562,0.0005831839,0.0013424534,0.000098544224],"category_scores_gemma":[0.00015026948,0.0006688053,0.00044315425,0.00015489988,0.00033901157,0.00007208834,0.00012809706,0.00062252866,0.00011259238],"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":[0.0012041978,0.0003034477,0.02744224,0.0008029045,0.00084429054,0.00035118457,0.03818574,0.0025941955,0.8987865,0.016461564,0.0018012577,0.011222503],"study_design_scores_gemma":[0.0037564277,0.00050765503,0.09275929,0.0010921122,0.00060137035,0.0019006049,0.0198445,0.004911038,0.6131296,0.0004830741,0.25918835,0.0018259266],"about_ca_topic_score_codex":0.0030655102,"about_ca_topic_score_gemma":0.0011099915,"teacher_disagreement_score":0.28565684,"about_ca_system_score_codex":0.0036296723,"about_ca_system_score_gemma":0.0028917794,"threshold_uncertainty_score":0.999954},"labels":[],"label_agreement":null},{"id":"W2737578470","doi":"10.1186/s12859-017-1758-x","title":"Exploring general-purpose protein features for distinguishing enzymes and non-enzymes within the twilight zone","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Carleton University","funders":"European Regional Development Fund; Dirección General de Asuntos del Personal Académico, Universidad Nacional Autónoma de México; Fundação para a Ciência e a Tecnologia; Universitat de València","keywords":"Benchmark (surveying); Proteome; Computational biology; Computer science; Protein function prediction; Structural bioinformatics; Protein structure database; Sequence alignment; Similarity (geometry); Structural alignment; Protein methods; Protein sequencing; Annotation; Protein family; Protein function; Function (biology); Structural similarity; Sequence (biology); Protein structure; Multiple sequence alignment; Artificial intelligence; Biology; Bioinformatics; Peptide sequence; Sequence database; Genetics; Gene; Biochemistry","score_opus":0.04100894492899753,"score_gpt":0.2774749193984699,"score_spread":0.23646597446947237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2737578470","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8258196,0.0010070681,0.15998994,0.0009590725,0.0010327848,0.0030986767,0.00012876572,0.00012205041,0.007842014],"genre_scores_gemma":[0.5534595,0.000106328196,0.44065672,0.00044478578,0.0010272925,0.00040982116,0.00019028015,0.00007245178,0.0036328104],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986149,0.000031129297,0.000530568,0.00020952077,0.00023025356,0.00038359882],"domain_scores_gemma":[0.99801135,0.000057817113,0.00065774785,0.0010334738,0.00012583926,0.000113757866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072722766,0.00031384843,0.00025399422,0.00005027936,0.0011999452,0.0006652902,0.0007303707,0.0001618574,0.000002233124],"category_scores_gemma":[0.0016578446,0.00021782162,0.00011641572,0.00004089962,0.00025078835,0.000086997854,0.0005213114,0.00024852814,0.0000061733244],"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":[0.004161162,0.0010009321,0.15303367,0.029459355,0.0029111276,0.000034225028,0.0914553,0.021474821,0.1561883,0.17340736,0.12971,0.23716374],"study_design_scores_gemma":[0.0047624265,0.0012012149,0.03192105,0.0007190706,0.00023642422,0.00018514843,0.0047032456,0.4180893,0.40097055,0.0006073932,0.13426921,0.0023349596],"about_ca_topic_score_codex":0.000035764773,"about_ca_topic_score_gemma":0.00012304551,"teacher_disagreement_score":0.3966145,"about_ca_system_score_codex":0.000014854771,"about_ca_system_score_gemma":0.00008894926,"threshold_uncertainty_score":0.92291296},"labels":[],"label_agreement":null},{"id":"W2747126452","doi":"10.4236/jbise.2017.108030","title":"Combined Use of k-Mer Numerical Features and Position-Specific Categorical Features in Fixed-Length DNA Sequence Classification","year":2017,"lang":"en","type":"article","venue":"Journal of Biomedical Science and Engineering","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Japan Society for the Promotion of Science; Institute of Genetics; University of Tokyo; Institute of Medical Science, University of Tokyo; Research Organization of Information and Systems","keywords":"Categorical variable; Sequence (biology); Position (finance); DNA sequencing; Feature (linguistics); Algorithm; Pattern recognition (psychology); Mathematics; Computer science; DNA; Artificial intelligence; Computational biology; Biology; Genetics; Statistics","score_opus":0.014956366997019441,"score_gpt":0.2671672753798142,"score_spread":0.25221090838279475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2747126452","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9953403,0.00019550518,0.0031960364,0.0010416806,0.0001496077,0.00004034927,0.0000022202148,0.00000243306,0.000031888598],"genre_scores_gemma":[0.9950448,0.00032162876,0.0045078006,0.000036675567,0.00007352153,6.203847e-7,0.0000029194491,0.000003647832,0.000008380222],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9992022,0.000011046422,0.00023588976,0.00010584454,0.00030101664,0.00014400315],"domain_scores_gemma":[0.99942195,0.000028806802,0.0001759735,0.00013845168,0.000096316835,0.00013847476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046885113,0.00007555069,0.0001314557,0.000114495546,0.00010412463,0.00009470941,0.00022146347,0.00008684768,0.000001546394],"category_scores_gemma":[0.00066838815,0.00005690397,0.000022739338,0.00011150359,0.0004153248,0.000049484817,0.000086196516,0.00019567511,1.4846262e-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":[0.00005949624,0.00005146392,0.008635745,0.00004364037,0.000013074385,0.0000136431845,0.00016839991,0.00016387473,0.97510314,0.00068710314,0.0008201098,0.014240333],"study_design_scores_gemma":[0.0005996133,0.00050205435,0.9648429,0.00008875529,0.000009928553,0.0004003344,0.00006939144,0.013665729,0.015050453,0.00003661852,0.004568142,0.00016607498],"about_ca_topic_score_codex":0.000012969856,"about_ca_topic_score_gemma":7.9664943e-7,"teacher_disagreement_score":0.96005267,"about_ca_system_score_codex":0.000022952181,"about_ca_system_score_gemma":0.00006285728,"threshold_uncertainty_score":0.23204766},"labels":[],"label_agreement":null},{"id":"W2748722638","doi":"10.3389/fbioe.2017.00048","title":"Navigating the Functional Landscape of Transcription Factors via Non-Negative Tensor Factorization Analysis of MEDLINE Abstracts","year":2017,"lang":"en","type":"article","venue":"Frontiers in Bioengineering and Biotechnology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"University of British Columbia","funders":"University of Memphis","keywords":"Computational biology; Computer science; Tensor (intrinsic definition); Annotation; Gene; Information retrieval; KEGG; Factorization; Data mining; Transcription factor; Bioinformatics; Biology; Mathematics; Genetics; Artificial intelligence; Gene expression; Algorithm; Transcriptome; Pure mathematics","score_opus":0.006194924937983612,"score_gpt":0.2276831702067423,"score_spread":0.2214882452687587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2748722638","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85241276,0.00011716997,0.1469796,0.00017984718,0.0001869867,0.000073611285,0.00002362075,0.000009272437,0.000017137567],"genre_scores_gemma":[0.99334925,0.00015357567,0.006351295,0.000005258537,0.000020425416,0.000002840601,0.00010242549,0.000007108405,0.000007817835],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99937135,0.000010744522,0.00028004532,0.00013832515,0.000079861056,0.00011968925],"domain_scores_gemma":[0.99939054,0.000013761332,0.00026260706,0.00027321323,0.00004214593,0.000017730883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001519414,0.000112081965,0.0002210097,0.00013087937,0.00007455445,0.000010081863,0.00017501098,0.00026070428,0.0000019165655],"category_scores_gemma":[0.0002075744,0.00008363542,0.00006278035,0.00017143159,0.00018532305,0.000008461328,0.000046196656,0.00022679729,6.2671425e-8],"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":[0.00005488671,0.000036148598,0.4801661,0.000090830064,0.00061281846,4.5897522e-7,0.0004461648,0.03877494,0.47196227,0.000034233104,0.000049810165,0.0077713127],"study_design_scores_gemma":[0.0003709383,0.0001421115,0.5857892,0.000035855723,0.00013579888,0.0000019814943,0.000467107,0.12394397,0.28881305,0.000031826443,0.00012962919,0.00013850885],"about_ca_topic_score_codex":0.00007332594,"about_ca_topic_score_gemma":0.000025139048,"teacher_disagreement_score":0.18314923,"about_ca_system_score_codex":0.0000073931087,"about_ca_system_score_gemma":0.000009145965,"threshold_uncertainty_score":0.34105536},"labels":[],"label_agreement":null},{"id":"W2749642841","doi":"10.1101/181222","title":"Identifying genetic determinants of complex phenotypes from whole genome sequence data","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Proteome; Phenotype; Boosting (machine learning); Genome; Chunking (psychology); Random forest; Whole genome sequencing; Workflow","score_opus":0.05324352506404843,"score_gpt":0.2979008119735182,"score_spread":0.24465728690946975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2749642841","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98171794,0.0020108076,0.008961088,0.00003352076,0.0008792396,0.00047755294,0.0058312677,0.00007026278,0.000018340152],"genre_scores_gemma":[0.94326484,0.00044613337,0.05543444,0.000082505576,0.0005477985,0.000026268377,0.0000716238,0.000111441026,0.000014959506],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9971814,0.00012514595,0.00077398546,0.001071822,0.00037835914,0.0004692875],"domain_scores_gemma":[0.9927786,0.000025225725,0.0012718946,0.0054180287,0.00032655342,0.00017969933],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047941477,0.0005303216,0.0006329182,0.000109404245,0.00021881415,0.00025142185,0.003231894,0.0005800491,0.000038351693],"category_scores_gemma":[0.00053477346,0.0005890494,0.00012381622,0.00007761171,0.0002965272,0.00002474328,0.0041810744,0.0005003789,0.000045917695],"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":[0.000021982727,0.00004429366,0.025773445,0.00045297935,0.00016732057,0.000017937553,0.000011029196,0.00016011094,0.9731145,0.0000042976167,0.00020639063,0.000025713836],"study_design_scores_gemma":[0.00089912466,0.00013307932,0.6551317,0.0007295609,0.00037726568,1.3489044e-7,0.0000056263257,0.015476832,0.2741722,0.000007370705,0.051265217,0.0018019015],"about_ca_topic_score_codex":0.0003274149,"about_ca_topic_score_gemma":0.000027645297,"teacher_disagreement_score":0.6989423,"about_ca_system_score_codex":0.000047757443,"about_ca_system_score_gemma":0.00049155194,"threshold_uncertainty_score":0.9996561},"labels":[],"label_agreement":null},{"id":"W2762498896","doi":"10.1371/journal.pcbi.1005621","title":"Vicus: Exploiting local structures to improve network-based analysis of biological data","year":2017,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"SickKids Foundation; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; California HIV/AIDS Research Program","keywords":"Biological network; Computer science; Network analysis; Computational biology; Data science; Biology; Engineering","score_opus":0.044531456206472975,"score_gpt":0.33262380984572393,"score_spread":0.28809235363925095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2762498896","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6465292,0.000052578358,0.35205343,0.00028861657,0.00012284456,0.00016060336,0.0004722559,0.00001788636,0.00030256776],"genre_scores_gemma":[0.9362063,0.0000032952425,0.057458553,0.00061114784,0.00018993588,0.000008125511,0.0055071786,0.000008946639,0.000006514542],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987722,0.00010299912,0.00036843758,0.0004032145,0.00010991548,0.00024324686],"domain_scores_gemma":[0.99842376,0.00012763393,0.00035690912,0.0008565871,0.00015724047,0.00007788157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028844218,0.0001544091,0.00030934036,0.000095453885,0.00019731911,0.000031113752,0.0009501267,0.00017788423,0.00004253788],"category_scores_gemma":[0.00072805776,0.00012794805,0.0000899997,0.00011204189,0.00025203163,0.0000061001942,0.0007476549,0.00010739513,0.0000066101857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020510251,0.00008811502,0.18730983,0.000031662916,0.0015396118,0.0000016704496,0.00003931456,0.75963706,0.0356404,0.0033512278,0.0006775478,0.011478447],"study_design_scores_gemma":[0.00062412483,0.00066322606,0.13128504,0.00001395745,0.0002612439,0.000002498451,0.00003364226,0.8573475,0.004640246,0.0018018197,0.0029514902,0.00037523537],"about_ca_topic_score_codex":0.000028257842,"about_ca_topic_score_gemma":0.000028899463,"teacher_disagreement_score":0.29459488,"about_ca_system_score_codex":0.000009396987,"about_ca_system_score_gemma":0.00007254443,"threshold_uncertainty_score":0.521757},"labels":[],"label_agreement":null},{"id":"W2766215291","doi":"10.24870/cjb.2017-a217","title":"In silico analysis of SNPs of SYK gene Involved in Oral Cancer","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Biotechnology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cancer; dbSNP; Single-nucleotide polymorphism; Tongue; In silico; Medicine; Genetics; Gene; Computational biology; Bioinformatics; Biology; Genotype; Pathology","score_opus":0.01075440695965736,"score_gpt":0.27847556070167007,"score_spread":0.2677211537420127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766215291","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9974002,0.00076570484,0.00014331986,0.001381662,0.00011169361,0.000046376284,0.000033335367,7.949744e-7,0.00011687214],"genre_scores_gemma":[0.9985811,0.00026907577,0.0009981609,0.000084300715,0.000020569174,0.0000010860531,0.000006974422,0.0000068728004,0.000031870943],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990704,0.000032602322,0.00052263285,0.0000963713,0.000067587185,0.00021042535],"domain_scores_gemma":[0.99869204,0.000007653901,0.0006831606,0.00042939102,0.000094956355,0.000092809896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032956142,0.00009172103,0.00039231236,0.0010372301,0.00003123087,0.000008176831,0.00059220666,0.00037774784,0.00003964182],"category_scores_gemma":[0.0004665062,0.00008931234,0.000107560314,0.00029591244,0.00031862856,0.000008031983,0.0000516983,0.0002704503,3.68057e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004607052,0.000026254496,0.7137135,0.000035982408,0.0004277027,0.000050800474,0.0001709166,0.0024315317,0.2775059,0.0002830908,0.00031360923,0.0049945856],"study_design_scores_gemma":[0.0013205766,0.00047543578,0.32314798,0.00008761096,0.00021886177,0.00003263495,0.0002556981,0.0026414513,0.6629124,0.00016290322,0.008497928,0.0002464785],"about_ca_topic_score_codex":0.02044428,"about_ca_topic_score_gemma":0.38223538,"teacher_disagreement_score":0.39056554,"about_ca_system_score_codex":0.000055410615,"about_ca_system_score_gemma":0.000555298,"threshold_uncertainty_score":0.9860787},"labels":[],"label_agreement":null},{"id":"W2774022032","doi":"10.24870/cjb.2017-a279","title":"Computational Profiling of Deleterious Non-Synonymous SNP’s in HFE","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Biotechnology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computational biology; SNP; Biology; Genetics; Profiling (computer programming); Evolutionary biology; Computer science; Single-nucleotide polymorphism; Gene; Genotype","score_opus":0.008812340627757874,"score_gpt":0.25626148284417266,"score_spread":0.24744914221641479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2774022032","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9936641,0.00018765527,0.0040817186,0.0011782082,0.0001917557,0.00007137808,0.000013235596,0.0000019586264,0.0006100017],"genre_scores_gemma":[0.98683745,0.000025013342,0.012951529,0.00009248753,0.000050872553,8.6025295e-7,0.000008993148,0.000009797235,0.0000229747],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99923676,0.000017183847,0.00038182645,0.000087217464,0.000068481815,0.00020853277],"domain_scores_gemma":[0.9989825,0.0000077642035,0.0005064417,0.00029153068,0.00010446112,0.00010732134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002432912,0.00008942183,0.00019046714,0.00028143657,0.000093962946,0.000022062084,0.0005377175,0.00030302326,0.000009698372],"category_scores_gemma":[0.00044483933,0.000089007226,0.000058773127,0.0000467385,0.00028699462,0.000006700822,0.000050237708,0.00028321816,0.0000025239885],"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":[0.00024118602,0.00012062565,0.41287744,0.0003247268,0.00039617612,0.00077762164,0.00081518886,0.026558101,0.4173649,0.0049634213,0.003334245,0.13222636],"study_design_scores_gemma":[0.004896651,0.0033371777,0.11678235,0.00039079273,0.000061027124,0.003400309,0.000643087,0.015585983,0.8168516,0.0025109362,0.034592047,0.00094799715],"about_ca_topic_score_codex":0.0008407218,"about_ca_topic_score_gemma":0.005223236,"teacher_disagreement_score":0.39948675,"about_ca_system_score_codex":0.000033776912,"about_ca_system_score_gemma":0.000642614,"threshold_uncertainty_score":0.36296093},"labels":[],"label_agreement":null},{"id":"W2779844278","doi":"10.1101/217802","title":"WeSeqMiner: A Weka package for building machine-learning models for sequence data","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Workbench; Computer science; Workflow; Sequence (biology); Artificial intelligence; Data mining; Machine learning; Database; Visualization","score_opus":0.05009955651760598,"score_gpt":0.2929193196621664,"score_spread":0.2428197631445604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2779844278","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":[0.123573765,0.0030278952,0.85852695,0.0005157933,0.0017693903,0.0035632197,0.008549336,0.00039873214,0.00007495119],"genre_scores_gemma":[0.7814358,0.0006006879,0.21539046,0.0002122685,0.0012378882,0.00058228284,0.00013649782,0.0002967931,0.00010735749],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99644053,0.00010982465,0.0007182486,0.0015479834,0.00033058642,0.0008527981],"domain_scores_gemma":[0.9934074,0.00010306016,0.0011207053,0.004490692,0.0006062393,0.0002719003],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016417531,0.0007803032,0.00068912253,0.00015524683,0.0005423507,0.000518689,0.0030346846,0.000930269,0.0000075001117],"category_scores_gemma":[0.0027392993,0.0008390874,0.00027926534,0.00007934999,0.00017415879,0.000054629287,0.0029152422,0.0008770964,0.000007897276],"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":[0.00017852585,0.00008234154,0.002219998,0.002031006,0.00046622028,0.000007731999,0.000014021148,0.005482847,0.9856208,0.0010202785,0.0028423222,0.000033918765],"study_design_scores_gemma":[0.0017323513,0.00033413546,0.00043136382,0.00058520184,0.00035263016,1.7482975e-7,0.0000034522595,0.5614064,0.17779917,0.000027527087,0.2553102,0.0020174307],"about_ca_topic_score_codex":0.000040962743,"about_ca_topic_score_gemma":0.0000062083213,"teacher_disagreement_score":0.80782163,"about_ca_system_score_codex":0.000094633106,"about_ca_system_score_gemma":0.0006720688,"threshold_uncertainty_score":0.999406},"labels":[],"label_agreement":null},{"id":"W2782155089","doi":"10.1038/s41598-017-17842-9","title":"Multi-label Deep Learning for Gene Function Annotation in Cancer Pathways","year":2018,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institutes of Health; U.S. Food and Drug Administration; Hamilton Health Sciences Foundation; National Institute of General Medical Sciences; National Natural Science Foundation of China","keywords":"Annotation; Deep learning; Computer science; Function (biology); Artificial intelligence; Autoencoder; Computational biology; Machine learning; Data science; Biology; Genetics","score_opus":0.022130976697149526,"score_gpt":0.2946325694902569,"score_spread":0.2725015927931074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2782155089","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93019974,0.00018960537,0.06538288,0.000021482483,0.0033807368,0.00030066623,0.0000017716135,0.000024468925,0.0004986169],"genre_scores_gemma":[0.9783206,0.0000084746,0.018670598,0.00005730053,0.00023353586,0.000071413066,0.00037402974,0.000016436894,0.002247635],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989161,0.000028824506,0.00031395978,0.0003793758,0.00014443077,0.00021733603],"domain_scores_gemma":[0.9991879,0.000006110678,0.0002365192,0.00028833046,0.00023816936,0.00004299453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083049893,0.00009536731,0.000081932034,0.000084052,0.00023348558,0.00007914634,0.00006611998,0.00009397402,0.00001753803],"category_scores_gemma":[0.0003587011,0.000092487746,0.000036444042,0.00017228181,0.00010721199,0.000010427312,0.000046820023,0.0000766143,0.0000083868645],"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":[0.00003810837,0.000069205395,0.020217527,0.000032413718,0.00001355096,0.0000026383477,0.00049883703,0.0019114264,0.94587415,0.000011168005,0.0015504087,0.029780548],"study_design_scores_gemma":[0.0013220676,0.0006221623,0.024281124,0.00004878481,0.00003417832,0.00007047022,0.0002727528,0.4053197,0.37848768,0.00055408326,0.18844965,0.00053734763],"about_ca_topic_score_codex":0.000023360257,"about_ca_topic_score_gemma":0.00019235682,"teacher_disagreement_score":0.5673865,"about_ca_system_score_codex":0.000024730816,"about_ca_system_score_gemma":0.00007448542,"threshold_uncertainty_score":0.37715408},"labels":[],"label_agreement":null},{"id":"W2784791781","doi":"10.1101/240515","title":"De novo profile generation based on sequence context specificity with the long short-term memory network","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Institute of Medical Science, University of Tokyo; Japan Society for the Promotion of Science; Ministry of Education, Culture, Sports, Science and Technology; Institute of Genetics; Japan Agency for Medical Research and Development","keywords":"Sequence (biology); Context (archaeology); Computer science; Generator (circuit theory); Scalability; Similarity (geometry); Artificial intelligence; Computational biology; Bioinformatics; Power (physics); Biology; Genetics","score_opus":0.02028968337993811,"score_gpt":0.24496464858728667,"score_spread":0.22467496520734856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784791781","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9712,0.00030513684,0.02604898,0.00036497918,0.00059711316,0.0010569711,0.00013748382,0.00010242376,0.00018689851],"genre_scores_gemma":[0.9909056,0.000052879204,0.0060801283,0.00080712215,0.0018030803,0.00020003978,0.000011350537,0.00010326125,0.000036581612],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99777675,0.00021006889,0.00035796216,0.0007306746,0.00037021568,0.0005543137],"domain_scores_gemma":[0.99667096,0.00003204537,0.00049178215,0.0022886135,0.0003507798,0.00016582615],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00090788957,0.00053544965,0.00035021652,0.000055880915,0.0005075779,0.00043789455,0.0009522594,0.00055327377,0.000032061263],"category_scores_gemma":[0.00019219515,0.00042222446,0.0001263009,0.000091224625,0.00027090125,0.000012261421,0.00035762362,0.0008728076,0.000021024502],"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":[0.00038491303,0.00016285786,0.053407542,0.0004773032,0.00029785588,0.00010536875,0.000024689856,0.052933645,0.8871075,0.00021713659,0.0048180153,0.000063161904],"study_design_scores_gemma":[0.00097175676,0.00064079737,0.09802631,0.00072002184,0.0002115411,4.3639935e-7,0.0000054763154,0.07828489,0.81039643,5.3382274e-7,0.008919503,0.0018222922],"about_ca_topic_score_codex":0.000020211379,"about_ca_topic_score_gemma":0.00003140457,"teacher_disagreement_score":0.07671107,"about_ca_system_score_codex":0.00014323261,"about_ca_system_score_gemma":0.0008003735,"threshold_uncertainty_score":0.999823},"labels":[],"label_agreement":null},{"id":"W2788724289","doi":"10.1073/pnas.1800256115","title":"Classification and interaction in random forests","year":2018,"lang":"en","type":"letter","venue":"Proceedings of the National Academy of Sciences","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":276,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Random forest; Ask price; Computer science; Artificial intelligence; Machine learning; Classifier (UML); Medical diagnosis; Decision tree; Complaint; Data science; Medicine","score_opus":0.03080431165518348,"score_gpt":0.32082783700131307,"score_spread":0.2900235253461296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788724289","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80373627,0.00013215098,0.0000059077965,0.1820803,0.000070176284,0.00038706433,0.000018894943,0.0000056575295,0.013563581],"genre_scores_gemma":[0.97891045,0.00005602084,0.00083740405,0.019336423,0.00054762117,0.000010309256,0.0000041636986,0.0000053597273,0.00029227955],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99900573,0.0000084529,0.00028023197,0.00017149537,0.0004446185,0.00008944882],"domain_scores_gemma":[0.9992513,0.000039740295,0.0005415443,0.000008056916,0.0001509192,0.000008447529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007785753,0.00008523718,0.00011059607,0.0001314951,0.00005609344,0.000019019875,0.00039720425,0.000287132,0.0000032526225],"category_scores_gemma":[0.0006592115,0.00005914123,0.000039638515,0.00016893291,0.00052754564,0.000019077132,0.00012116195,0.00033490153,5.6451574e-7],"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":[0.000118825985,0.000034515946,0.075527705,0.0007593349,0.000050305025,1.0679852e-8,0.00029254422,0.00007744595,0.22045006,0.0016188744,0.70026666,0.00080372195],"study_design_scores_gemma":[0.00170854,0.00043652358,0.42547733,0.0009341645,0.000055322984,0.00008125129,0.0002291197,0.016124062,0.16171414,0.017636845,0.37498927,0.00061344606],"about_ca_topic_score_codex":0.0000030268804,"about_ca_topic_score_gemma":2.584267e-7,"teacher_disagreement_score":0.34994963,"about_ca_system_score_codex":0.000013315553,"about_ca_system_score_gemma":0.000025219464,"threshold_uncertainty_score":0.24117094},"labels":[],"label_agreement":null},{"id":"W2790921906","doi":"10.1093/bioinformatics/bty095","title":"Improved genomic island predictions with IslandPath-DIMOB","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":223,"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":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Computer science; Computational biology; Biology","score_opus":0.004793943520078781,"score_gpt":0.2206221854113326,"score_spread":0.21582824189125382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790921906","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5703038,0.00010150583,0.3327569,0.00019781668,0.0006401781,0.0008310604,0.00021027433,0.00019171619,0.09476673],"genre_scores_gemma":[0.91740257,0.000067977046,0.07737092,0.000889104,0.00092073024,0.000032858177,0.00046901626,0.00005371528,0.0027931272],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989624,0.000017774615,0.00037847983,0.0001456663,0.00015950846,0.00033618626],"domain_scores_gemma":[0.9989816,0.000010189184,0.00020276953,0.0005429663,0.00015112106,0.00011134507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017639846,0.00021662563,0.00015089716,0.000072847426,0.00021745019,0.00007373568,0.00026780958,0.00015846323,0.0000762873],"category_scores_gemma":[0.000070067355,0.00016713336,0.00005769524,0.00012655731,0.00021014981,0.000017210767,0.00014277082,0.00014394437,0.0001494319],"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":[0.004113267,0.0012381069,0.1590388,0.0024420274,0.0033521003,0.000020451118,0.030997539,0.0046077752,0.23189913,0.003474673,0.48256263,0.0762535],"study_design_scores_gemma":[0.0040326705,0.0059386096,0.009427648,0.00009126384,0.0001552652,0.00043712667,0.0011096474,0.437321,0.020789977,0.000055264692,0.5192991,0.0013424163],"about_ca_topic_score_codex":0.000011678708,"about_ca_topic_score_gemma":0.00013639712,"teacher_disagreement_score":0.43271324,"about_ca_system_score_codex":0.000020334282,"about_ca_system_score_gemma":0.00012020609,"threshold_uncertainty_score":0.6815501},"labels":[],"label_agreement":null},{"id":"W2791624206","doi":"10.3390/proteomes6010010","title":"Revealing Subtle Functional Subgroups in Class A Scavenger Receptors by Pattern Discovery and Disentanglement of Aligned Pattern Clusters","year":2018,"lang":"en","type":"article","venue":"Proteomes","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Scavenger receptor; Sequence (biology); Subclass; Vector space; Association (psychology); Function (biology); Computational biology; Position (finance); Biology; Scavenger; Class (philosophy); Genetics; Mathematics; Computer science; Pure mathematics; Artificial intelligence; Antibody","score_opus":0.006725707124624676,"score_gpt":0.2312487918037938,"score_spread":0.22452308467916912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791624206","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9877341,0.00013845382,0.011141646,0.0003271133,0.00013405703,0.0003026114,0.00003613158,0.000006717915,0.00017921416],"genre_scores_gemma":[0.99868083,0.000042474836,0.00037993368,0.0002509938,0.0001256695,0.000037341175,0.00016523474,0.000016113145,0.0003013851],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999137,0.000057730645,0.0002762729,0.0002009768,0.00014645138,0.00018160201],"domain_scores_gemma":[0.9995991,0.00001209164,0.00013620626,0.00017608158,0.00003568277,0.000040865958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022269496,0.00012671873,0.0001326294,0.0000459556,0.000041492,0.000025105977,0.000090391084,0.00007912524,0.00006637047],"category_scores_gemma":[0.000042732783,0.00011363785,0.00003778313,0.000054077787,0.00010918133,0.000011630391,0.0001374469,0.000058181573,0.0000051921334],"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":[0.00015775634,0.00013582692,0.74354315,0.00034588188,0.000100227,0.00000126817,0.0008570686,0.000039597315,0.22916903,0.00001019895,0.007086173,0.018553833],"study_design_scores_gemma":[0.0058251456,0.0025278716,0.177451,0.00056523096,0.00008375113,0.000029952822,0.0017143944,0.008249877,0.7670225,0.00013760997,0.034867015,0.0015256428],"about_ca_topic_score_codex":0.00007423536,"about_ca_topic_score_gemma":0.00007146429,"teacher_disagreement_score":0.56609213,"about_ca_system_score_codex":0.000019682579,"about_ca_system_score_gemma":0.000018321436,"threshold_uncertainty_score":0.4634017},"labels":[],"label_agreement":null},{"id":"W2795167779","doi":"","title":"De novo Peptide Sequencing by Deep Learning","year":2018,"lang":"en","type":"article","venue":"Research in Computational Molecular Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Waterloo","funders":"","keywords":"Computer science; Deep learning; Computational biology; Artificial intelligence; Evolutionary biology; Biology","score_opus":0.027213550428425434,"score_gpt":0.39290999236528534,"score_spread":0.3656964419368599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795167779","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68109435,0.00034817998,0.3109397,0.000514739,0.0000563706,0.0001826995,0.000008159899,0.00002259102,0.0068332194],"genre_scores_gemma":[0.971718,0.000021500331,0.026961409,0.00045032497,0.00016400458,0.00002514606,0.00045980845,0.00002566602,0.0001741237],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99775904,0.00072147977,0.00028067557,0.00035921647,0.00025269183,0.00062687893],"domain_scores_gemma":[0.9991515,0.00014658402,0.000065309134,0.00020245138,0.00031717855,0.000116939205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014915597,0.00014143296,0.0001350704,0.00021096603,0.0001821932,0.000045074,0.00034239964,0.00022124266,0.000044573622],"category_scores_gemma":[0.0008353475,0.00014933893,0.000050922612,0.00031912056,0.00043828005,0.000004912602,0.00028477953,0.000534881,0.000077504854],"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":[0.00012437836,0.000068466215,0.028029704,0.000047692414,0.0000735924,0.00003767583,0.0002948294,0.048717733,0.8992134,0.012484433,0.0010102958,0.009897829],"study_design_scores_gemma":[0.0040786373,0.0061900932,0.0062644947,0.00016926417,0.000017222636,0.0008082099,0.0008206522,0.59004885,0.11643122,0.09001388,0.18349059,0.0016668743],"about_ca_topic_score_codex":0.0000607623,"about_ca_topic_score_gemma":0.000021037795,"teacher_disagreement_score":0.78278214,"about_ca_system_score_codex":0.000129304,"about_ca_system_score_gemma":0.00026448662,"threshold_uncertainty_score":0.60898644},"labels":[],"label_agreement":null},{"id":"W2796148592","doi":"10.1101/293159","title":"TranCEP: Predicting transmembrane transport proteins using composition, evolutionary, and positional information","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Transmembrane protein; Proteome; Computational biology; Membrane protein; Genome; Transport protein; Biology; Transmembrane domain; Amino acid; Membrane transport; Membrane; Membrane transport protein; Biochemistry; Chemistry; Gene","score_opus":0.006308556193433299,"score_gpt":0.2109663616667824,"score_spread":0.2046578054733491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796148592","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9304335,0.0004150824,0.066981174,0.00015274137,0.00032485285,0.0009233298,0.0005815859,0.00013835225,0.000049349444],"genre_scores_gemma":[0.96353257,0.00008856913,0.03532308,0.000259952,0.00060609216,0.000088748624,0.000039556435,0.000060002214,0.0000014066889],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980012,0.000090903435,0.0006890545,0.00048593408,0.00033997316,0.00039293707],"domain_scores_gemma":[0.99824333,0.000011043541,0.00043188356,0.0005639329,0.00056156906,0.00018826348],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003944024,0.00046565238,0.00033749134,0.00017859382,0.00033507138,0.000114956616,0.0002992131,0.0006401074,0.000022259255],"category_scores_gemma":[0.00004765034,0.0005317113,0.0001329733,0.00016559685,0.00024702502,0.000067094545,0.00013544115,0.000522166,0.000008289122],"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":[0.00022042746,0.00012966835,0.020671181,0.0018280746,0.0002989049,0.0000055608507,0.00007921767,0.002934614,0.97336376,0.00025978,0.0002059025,0.0000028867466],"study_design_scores_gemma":[0.0036024621,0.0007700677,0.39448774,0.0019175644,0.0006094323,0.0000030254103,0.000016619015,0.088717796,0.49264953,0.00001539558,0.014098345,0.0031120325],"about_ca_topic_score_codex":0.000029251623,"about_ca_topic_score_gemma":0.0000011815437,"teacher_disagreement_score":0.48071426,"about_ca_system_score_codex":0.000090299356,"about_ca_system_score_gemma":0.00043950428,"threshold_uncertainty_score":0.9997134},"labels":[],"label_agreement":null},{"id":"W2798373489","doi":"10.1186/s12918-018-0573-y","title":"Improved flower pollination algorithm for identifying essential proteins","year":2018,"lang":"en","type":"article","venue":"BMC Systems Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Pollination; Identification (biology); Computational biology; Computer science; Systems biology; Biology; Biological data; Interaction network; Gene; Algorithm; Machine learning; Bioinformatics; Genetics; Pollen; Botany","score_opus":0.015930890438922294,"score_gpt":0.3077845931180571,"score_spread":0.2918537026791348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798373489","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":[0.053143177,0.00021751561,0.94304806,0.000027146107,0.0019197811,0.0010135544,0.00007751663,0.00004394421,0.00050931127],"genre_scores_gemma":[0.9047892,0.0000070495444,0.08836946,0.0000903859,0.0035564343,0.00031787515,0.0008398559,0.000042321004,0.0019873842],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988215,0.000109010565,0.00037577417,0.0003135018,0.000063547355,0.00031664086],"domain_scores_gemma":[0.9991041,0.000023157681,0.00022793224,0.00033469446,0.00025539356,0.000054720836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045890285,0.00016761672,0.00018655395,0.00007031862,0.00016277944,0.00004753005,0.00022461994,0.00031533302,0.00001300722],"category_scores_gemma":[0.00023447891,0.00014931918,0.00009713849,0.0000697297,0.000119645,0.0000058591118,0.000104447114,0.00006959607,0.000029186096],"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":[0.00010960425,0.000060915492,0.0013887305,0.00025285734,0.00012623191,2.6384862e-7,0.00016919931,0.000021715234,0.98567384,0.0012925243,0.0017105957,0.009193511],"study_design_scores_gemma":[0.004029221,0.002968803,0.00069629325,0.000093394505,0.00008817117,0.00012280903,0.0004710883,0.4650041,0.28864235,0.00016399499,0.2366022,0.0011175736],"about_ca_topic_score_codex":0.00007660689,"about_ca_topic_score_gemma":0.00008801717,"teacher_disagreement_score":0.8546786,"about_ca_system_score_codex":0.000019751855,"about_ca_system_score_gemma":0.00007893817,"threshold_uncertainty_score":0.608906},"labels":[],"label_agreement":null},{"id":"W2807292965","doi":"10.1101/342899","title":"A Visualization Tool to Evaluate Pairwise Protein Structure Alignment Algorithms","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Windsor","funders":"","keywords":"Pairwise comparison; Premise; Visualization; Structural alignment; Computer science; Measure (data warehouse); Algorithm; Sample (material); Data mining; Artificial intelligence; Sequence alignment; Chemistry","score_opus":0.00898360103877009,"score_gpt":0.25455628125180946,"score_spread":0.24557268021303938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807292965","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9643943,0.00015949774,0.031763267,0.00015323075,0.0008557641,0.0020837868,0.00038289776,0.00018858259,0.000018674602],"genre_scores_gemma":[0.9474801,0.00003379312,0.0499447,0.0006738167,0.0012731635,0.00035311,0.000013068915,0.0001824051,0.000045837423],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9968441,0.00021934007,0.0006856843,0.0010303941,0.0006219003,0.00059854606],"domain_scores_gemma":[0.99679816,0.0000077849345,0.00050152896,0.0016985794,0.00071209,0.00028186096],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007641194,0.00068249484,0.0004402756,0.00018632635,0.00017504535,0.0002383702,0.00071963813,0.000818809,0.00010276839],"category_scores_gemma":[0.0005864027,0.00070231577,0.00015286652,0.0002924632,0.00009459443,0.0000115405555,0.001163905,0.00043337044,0.000101690195],"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":[0.000068229616,0.000071965565,0.001018319,0.00039034974,0.00018636025,0.0000057892107,0.000021905997,0.0007751829,0.9938611,0.00012062325,0.003465982,0.000014207779],"study_design_scores_gemma":[0.0006846643,0.00046362987,0.006659855,0.00037745707,0.00011167252,4.930366e-8,0.0000025707309,0.0067956564,0.9290346,0.0000051702923,0.054544725,0.0013199782],"about_ca_topic_score_codex":0.000017326623,"about_ca_topic_score_gemma":0.0000024220856,"teacher_disagreement_score":0.06482651,"about_ca_system_score_codex":0.00017820385,"about_ca_system_score_gemma":0.00053044513,"threshold_uncertainty_score":0.9995428},"labels":[],"label_agreement":null},{"id":"W2807539577","doi":"10.1038/s41598-018-27349-6","title":"Author Correction: Multi-label Deep Learning for Gene Function Annotation in Cancer Pathways","year":2018,"lang":"en","type":"erratum","venue":"Scientific Reports","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"U.S. Food and Drug Administration; National Institutes of Health; Hamilton Health Sciences Foundation; People's Government of Jilin Province; Jilin University; National Institute of General Medical Sciences; Chinese Academy of Sciences; National Natural Science Foundation of China","keywords":"Annotation; Computer science; Function (biology); Computational biology; Gene; Artificial intelligence; Information retrieval; Bioinformatics; Biology; Genetics","score_opus":0.025062982029509278,"score_gpt":0.30259545301394797,"score_spread":0.2775324709844387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807539577","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":[0.04005109,0.004059006,0.13514367,0.00012855373,0.80797476,0.0025831515,0.000041133542,0.00020670488,0.009811953],"genre_scores_gemma":[0.016642695,0.00011824159,0.010922979,0.000103658334,0.0043227607,0.0005528087,0.017299246,0.00013898118,0.94989866],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974385,0.00008177867,0.0007502793,0.0009493843,0.00037282036,0.0004072521],"domain_scores_gemma":[0.9976901,0.000012708407,0.0009837443,0.0006477805,0.0005769197,0.000088774534],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014977378,0.0003061838,0.00027480573,0.00025420525,0.00044611603,0.00022662155,0.00015831461,0.0006818506,0.00004777945],"category_scores_gemma":[0.0010123028,0.0003118166,0.00012741947,0.00032715837,0.00015914229,0.000014831662,0.000109993794,0.0005220263,0.000014491615],"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":[0.000049921327,0.000097066826,0.0012510887,0.00018086733,0.000048317906,0.000008266533,0.0003774773,0.0019597956,0.021001875,0.0000017879244,0.95453686,0.020486658],"study_design_scores_gemma":[0.0002994474,0.00023028451,0.00077665976,0.00011023624,0.000048127633,0.00006189596,0.00008388755,0.123059995,0.0041694725,0.00006410725,0.87071335,0.0003825075],"about_ca_topic_score_codex":0.000055118206,"about_ca_topic_score_gemma":0.00053512777,"teacher_disagreement_score":0.94008666,"about_ca_system_score_codex":0.00011066512,"about_ca_system_score_gemma":0.00045665837,"threshold_uncertainty_score":0.9999334},"labels":[],"label_agreement":null},{"id":"W2809728348","doi":"10.4236/jbise.2018.116012","title":"Improving Protein Sequence Classification Performance Using Adjacent and Overlapped Segments on Existing Protein Descriptors","year":2018,"lang":"en","type":"article","venue":"Journal of Biomedical Science and Engineering","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Institute of Genetics; University of Tokyo; Institute of Medical Science, University of Tokyo; Research Organization of Information and Systems","keywords":"Subsequence; Sequence (biology); Computer science; Protein sequencing; Pattern recognition (psychology); Segmentation; Feature selection; Feature (linguistics); Feature vector; Artificial intelligence; Peptide sequence; Mathematics; Biology; Genetics; Gene","score_opus":0.026269294207579705,"score_gpt":0.273701352229618,"score_spread":0.2474320580220383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809728348","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9891187,0.0000336775,0.010556894,0.00004612033,0.00010896288,0.00009135125,5.850762e-7,0.000004748323,0.00003893801],"genre_scores_gemma":[0.97863185,0.000010857673,0.021118572,0.000027441753,0.00019346034,0.0000013872922,6.2337585e-7,0.000005391698,0.000010412438],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990683,0.000009089251,0.00023556392,0.00012296159,0.00036614158,0.00019790693],"domain_scores_gemma":[0.9994678,0.00000439408,0.00016970701,0.00007913675,0.00012733611,0.0001516333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089151936,0.00008530472,0.000083092375,0.00010950045,0.00014778278,0.00005753363,0.00013408196,0.00005462628,0.0000015120128],"category_scores_gemma":[0.000552774,0.00006677995,0.000013069177,0.00018663931,0.00029040728,0.000036689406,0.00007710352,0.0001378657,4.1429877e-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":[0.000014841368,0.0000087819935,0.00045937765,0.000053003816,0.0000035695527,8.019424e-7,0.000063170155,0.000042085707,0.98102224,0.000018616536,0.0000032975322,0.018310186],"study_design_scores_gemma":[0.000511077,0.0016224706,0.008990172,0.0006228869,0.0000106512925,0.00016827357,0.0001359266,0.67879474,0.30682394,0.0000047327717,0.0020777578,0.00023736783],"about_ca_topic_score_codex":0.000004267746,"about_ca_topic_score_gemma":1.6788057e-7,"teacher_disagreement_score":0.67875266,"about_ca_system_score_codex":0.000054695123,"about_ca_system_score_gemma":0.00011404748,"threshold_uncertainty_score":0.27232072},"labels":[],"label_agreement":null},{"id":"W2810921553","doi":"10.4236/jbise.2018.116013","title":"Improved Protein Phosphorylation Site Prediction by a New Combination of Feature Set and Feature Selection","year":2018,"lang":"en","type":"article","venue":"Journal of Biomedical Science and Engineering","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"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":"Japan Society for the Promotion of Science; Institute of Genetics; University of Tokyo; Institute of Medical Science, University of Tokyo; Research Organization of Information and Systems","keywords":"Phosphorylation; Feature selection; Computer science; Random forest; Feature (linguistics); Set (abstract data type); Support vector machine; Artificial intelligence; Selection (genetic algorithm); Posttranslational modification; Data mining; Pattern recognition (psychology); Chemistry; Enzyme; Biochemistry","score_opus":0.0023117228399206612,"score_gpt":0.21117261644729104,"score_spread":0.2088608936073704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810921553","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97209466,0.00018635936,0.027062858,0.00046145965,0.00010686194,0.0000648287,0.0000035387982,0.000004211632,0.000015200986],"genre_scores_gemma":[0.9933404,0.000039935094,0.006344934,0.000023741522,0.00016996494,4.5575774e-7,0.000008601148,0.0000032747532,0.000068714064],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994806,0.0000056960084,0.00013022234,0.000071383656,0.00022143724,0.00009064401],"domain_scores_gemma":[0.99957544,0.0000040149002,0.00012474517,0.000036371686,0.00015586779,0.00010358075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004513346,0.000054763674,0.000069046975,0.00007983847,0.00005194456,0.000024298726,0.00005649421,0.0000929175,0.0000016306121],"category_scores_gemma":[0.0002769937,0.000043106917,0.0000128575275,0.0002275886,0.00012315896,0.000027897182,0.000027437385,0.00011923944,8.086513e-8],"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":[0.000021168196,0.000007582912,0.00047748734,0.00002321332,0.000006149186,7.5107025e-8,0.00011619537,0.000011583936,0.99103236,0.000006148874,0.0021653099,0.0061326977],"study_design_scores_gemma":[0.0014796879,0.003802149,0.025929553,0.00018940498,0.00003198646,0.00021021103,0.00008126141,0.28036875,0.64546394,0.00002829912,0.042218983,0.00019575669],"about_ca_topic_score_codex":0.0000053771396,"about_ca_topic_score_gemma":7.876701e-7,"teacher_disagreement_score":0.34556845,"about_ca_system_score_codex":0.000016743534,"about_ca_system_score_gemma":0.00006897805,"threshold_uncertainty_score":0.1757849},"labels":[],"label_agreement":null},{"id":"W2811144380","doi":"10.3390/molecules23071569","title":"Feature Selection via Swarm Intelligence for Determining Protein Essentiality","year":2018,"lang":"en","type":"article","venue":"Molecules","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Feature selection; Computer science; Classifier (UML); Artificial intelligence; Swarm intelligence; Swarm behaviour; Selection (genetic algorithm); Feature (linguistics); Machine learning; Data mining; Particle swarm optimization","score_opus":0.008728061370248766,"score_gpt":0.2826654296705437,"score_spread":0.2739373683002949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811144380","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33279413,0.00003450653,0.6657455,0.00018547504,0.00010750834,0.00030491906,0.0000056798212,0.00003062004,0.0007916846],"genre_scores_gemma":[0.9286037,0.0000028240188,0.06973593,0.00023821137,0.0003971013,0.000057802034,0.00007645817,0.000022184555,0.0008657826],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992904,0.000036556034,0.00014246555,0.00022319044,0.00009251129,0.00021484583],"domain_scores_gemma":[0.99949586,0.0000074182612,0.00010102242,0.00020388476,0.00014564591,0.000046189612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017206655,0.00013302117,0.000091546324,0.000031467127,0.00014990631,0.000040130086,0.0001652059,0.00014758123,0.000010566687],"category_scores_gemma":[0.00020111946,0.0001276198,0.00006566009,0.000077710996,0.000087522196,0.0000042707607,0.000076116245,0.00009115652,0.000015697315],"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":[0.0001019592,0.00003180317,0.0006522688,0.00008685704,0.00004022063,5.5299273e-7,0.00012020927,0.00013774724,0.9733598,0.0002818887,0.0019596245,0.023227058],"study_design_scores_gemma":[0.00012050384,0.0004712605,0.00027587212,0.000017600923,0.000011793626,0.000015757285,0.000020400046,0.016731428,0.94418794,0.00024662065,0.037722874,0.00017793146],"about_ca_topic_score_codex":0.0000071197837,"about_ca_topic_score_gemma":0.00003524639,"teacher_disagreement_score":0.59600955,"about_ca_system_score_codex":0.000010747855,"about_ca_system_score_gemma":0.000034337772,"threshold_uncertainty_score":0.52041847},"labels":[],"label_agreement":null},{"id":"W2811287490","doi":"10.1038/s41598-018-28698-y","title":"Publisher Correction: IMSindel: An accurate intermediate-size indel detection tool incorporating de novo assembly and gapped global-local alignment with split read analysis","year":2018,"lang":"en","type":"erratum","venue":"Scientific Reports","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Innovation Cluster (Canada)","funders":"","keywords":"Indel; Computational biology; Computer science; INDEL Mutation; Biology; Genetics; Gene","score_opus":0.006279171502251089,"score_gpt":0.2556583194186704,"score_spread":0.2493791479164193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811287490","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72499466,0.00020487311,0.12114725,0.000090286885,0.12055263,0.0012574428,0.000038007598,0.00024211535,0.031472743],"genre_scores_gemma":[0.9187067,0.000018372777,0.0038783178,0.00016643098,0.0012629152,0.00007865012,0.00390409,0.0000776986,0.07190678],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99615616,0.00017871353,0.000970183,0.0013843488,0.0007735204,0.00053710106],"domain_scores_gemma":[0.9959842,0.000016397347,0.0016086492,0.0014788277,0.0006451634,0.00026674458],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002380238,0.00049696147,0.0004953548,0.00023927006,0.00047159704,0.0014109624,0.0003063003,0.000799381,0.000034013032],"category_scores_gemma":[0.00069088937,0.00043092127,0.00016719915,0.0010234127,0.0006012972,0.00007605162,0.00034334153,0.0005264866,0.00000426902],"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":[0.00035068058,0.00030505905,0.035430714,0.00034978235,0.0020351869,0.00034923077,0.0005212433,0.0030172402,0.005731399,0.000009786394,0.92909473,0.02280495],"study_design_scores_gemma":[0.0020475497,0.003788861,0.06524139,0.0008076598,0.0048084115,0.009867977,0.00233641,0.18094657,0.008523311,0.0019256443,0.7141251,0.0055811275],"about_ca_topic_score_codex":0.00019079912,"about_ca_topic_score_gemma":0.0022590775,"teacher_disagreement_score":0.21496965,"about_ca_system_score_codex":0.00024913764,"about_ca_system_score_gemma":0.0008270994,"threshold_uncertainty_score":0.9998143},"labels":[],"label_agreement":null},{"id":"W2811297572","doi":"10.1016/j.compbiolchem.2018.06.007","title":"A novel feature selection method to predict protein structural class","year":2018,"lang":"en","type":"article","venue":"Computational Biology and Chemistry","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"York University","funders":"Science and Technology Major Project of Guangxi; Natural Sciences and Engineering Research Council of Canada; Ministry of Industry and Information Technology of the People's Republic of China; National Natural Science Foundation of China","keywords":"Feature selection; Computer science; Feature (linguistics); Pattern recognition (psychology); Benchmark (surveying); Class (philosophy); Artificial intelligence; Data mining; Feature vector; Projection (relational algebra); Set (abstract data type); Machine learning; Algorithm","score_opus":0.004953738647541233,"score_gpt":0.28958905132522583,"score_spread":0.2846353126776846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811297572","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7726153,0.000046779223,0.22501281,0.000572608,0.000053527077,0.0001454281,0.000044554134,0.000028735758,0.0014802637],"genre_scores_gemma":[0.83353174,6.4025534e-7,0.1642511,0.00049928966,0.0004862835,0.000015719259,0.00042533016,0.000008911463,0.0007809844],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993848,0.000025846784,0.00012527348,0.000251985,0.000057399517,0.00015469971],"domain_scores_gemma":[0.999619,0.000016416689,0.000065235276,0.00009004574,0.00013340054,0.00007591879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000116274954,0.00012702151,0.00009530195,0.00001716662,0.00013789514,0.000016461618,0.00010540126,0.00023455491,0.000035804016],"category_scores_gemma":[0.000097585624,0.000115575385,0.000028628188,0.000073282805,0.00011446899,0.000002964204,0.000101702084,0.00014076557,0.0000059715676],"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":[0.00009379082,0.0000108036675,0.0038081636,0.00003379494,0.000047015557,1.3702288e-7,0.00004196893,0.00081257423,0.9906985,0.00034831936,0.0014832272,0.002621673],"study_design_scores_gemma":[0.0016591822,0.0009939461,0.02680992,0.000047312344,0.000036476555,0.00057634717,0.00006856144,0.09475311,0.78186226,0.0029866784,0.089451894,0.0007542854],"about_ca_topic_score_codex":0.0000028821048,"about_ca_topic_score_gemma":0.0000017590789,"teacher_disagreement_score":0.20883624,"about_ca_system_score_codex":0.000010434188,"about_ca_system_score_gemma":0.000054953034,"threshold_uncertainty_score":0.47130275},"labels":[],"label_agreement":null},{"id":"W2822741556","doi":"10.1007/978-3-032-18842-7_3","title":"Position Weight Matrix and Perceptron","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Randomness; Artificial intelligence; Pattern recognition (psychology); Algorithm; Perceptron; Computer science; Linear discriminant analysis; Multivariate statistics; Mathematics; Artificial neural network; Machine learning; Statistics","score_opus":0.0042471786805515594,"score_gpt":0.23784956385012035,"score_spread":0.2336023851695688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2822741556","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":[0.003001276,0.0006508069,0.0013443859,0.00014043746,0.00013728684,0.00015697847,0.000025372394,0.000028556453,0.9945149],"genre_scores_gemma":[0.003328226,0.0005374024,0.0059678312,0.0002794757,0.0006599156,0.0000021709875,0.00066082546,0.00004545858,0.9885187],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993782,0.000007071708,0.0001759824,0.0002150878,0.00010220862,0.0001214258],"domain_scores_gemma":[0.99950707,0.0000038050293,0.000098689976,0.00027835992,0.000054861088,0.000057196732],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000071657545,0.00020764544,0.00013535541,0.000041887815,0.00005515213,0.000027604927,0.000096962685,0.00041700437,0.0019439844],"category_scores_gemma":[0.000009438498,0.00018230123,0.00006349984,0.000004262026,0.00009944768,0.0000017155751,0.00014213362,0.00014166534,0.0002846509],"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":[0.0003516501,0.000053109583,0.00059208536,0.0008134177,0.000773108,0.000017182983,0.00057019724,0.000010754472,0.06204436,0.18205689,0.7305104,0.022206841],"study_design_scores_gemma":[0.00019049988,0.00036968966,0.000079483485,0.00003574247,0.000045600576,0.00007748968,0.000006980211,0.00014579241,0.00078779605,0.0010650896,0.9968736,0.00032223537],"about_ca_topic_score_codex":0.000002674468,"about_ca_topic_score_gemma":0.000007583874,"teacher_disagreement_score":0.2663632,"about_ca_system_score_codex":0.000010636116,"about_ca_system_score_gemma":0.000022872522,"threshold_uncertainty_score":0.99896836},"labels":[],"label_agreement":null},{"id":"W2849436992","doi":"10.1007/978-3-032-18842-7_8","title":"Hidden Markov Models and Protein Secondary Structure Prediction","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Hidden Markov model; Viterbi algorithm; Forward algorithm; Computer science; Stochastic matrix; Algorithm; Sequence (biology); Pattern recognition (psychology); Artificial intelligence; Markov model; Hidden semi-Markov model; Maximum-entropy Markov model; Markov chain; Variable-order Markov model; Machine learning; Biology; Genetics","score_opus":0.006094340806673071,"score_gpt":0.20868347434296558,"score_spread":0.20258913353629251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2849436992","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":[0.006884841,0.00044367346,0.0022252311,0.000067661575,0.00015030486,0.0005567054,0.00038783016,0.00004933778,0.9892344],"genre_scores_gemma":[0.011464712,0.00013815582,0.018551748,0.0003190502,0.0008084978,0.00000929415,0.0015872588,0.00008377099,0.9670375],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990791,0.00001148435,0.0002870159,0.0003190904,0.00015051849,0.000152807],"domain_scores_gemma":[0.9992583,0.0000031200989,0.00017663806,0.00040104674,0.00008423542,0.000076694065],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008852636,0.00029006883,0.0001843984,0.00005317682,0.000067762005,0.000039454186,0.00014726365,0.00070580613,0.0015472935],"category_scores_gemma":[0.00001603683,0.0002542686,0.00006042357,0.000006908085,0.00012441304,0.0000055772266,0.0002281474,0.00033269075,0.000017088161],"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":[0.0009089466,0.00005476263,0.00024492826,0.0033733747,0.0022759489,0.000024343024,0.0010600948,0.00012293295,0.087524034,0.08351502,0.60291857,0.21797703],"study_design_scores_gemma":[0.0007691438,0.0009009153,0.00007191954,0.00017652754,0.00009614153,0.00014846347,0.000021994936,0.005597313,0.005342142,0.034407064,0.95155597,0.00091239525],"about_ca_topic_score_codex":0.000003653754,"about_ca_topic_score_gemma":0.000020017158,"teacher_disagreement_score":0.34863737,"about_ca_system_score_codex":0.000012349471,"about_ca_system_score_gemma":0.00007611064,"threshold_uncertainty_score":0.99999094},"labels":[],"label_agreement":null},{"id":"W2884259377","doi":"","title":"Régulation de l'expression de gènes testiculaires par les facteurs de transcription GATA","year":2008,"lang":"fr","type":"article","venue":"Corpus Université Laval (Université Laval)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Biology; Transcription (linguistics); Transcription factor; Molecular biology; Cell biology; Gene; Genetics; Philosophy","score_opus":0.00892594684353453,"score_gpt":0.19714956448404347,"score_spread":0.18822361764050893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884259377","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9688044,0.0044815573,0.019911971,0.0019091729,0.00032376422,0.00028462065,0.0001192088,0.00012520056,0.0040400843],"genre_scores_gemma":[0.9693672,0.010343556,0.0072607417,0.00016284711,0.00024956616,0.0000013616655,0.00041658696,0.000062099956,0.012136054],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977011,0.00036533634,0.00028403182,0.00050392974,0.00032673785,0.0008188786],"domain_scores_gemma":[0.99845135,0.000081819504,0.0003089999,0.0005146001,0.00022276342,0.00042049275],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026778496,0.00046504335,0.00033753435,0.0002268188,0.0010926045,0.000047903563,0.00061873876,0.0007541758,0.00007529069],"category_scores_gemma":[0.00014475615,0.00057553354,0.0003109178,0.00032860687,0.00041095802,0.000094123345,0.00025665114,0.00051872554,0.000017810637],"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":[0.00042065018,0.00018582828,0.20056401,0.00023050116,0.00014491269,0.00036860234,0.010957987,0.006818386,0.7617958,0.00079607393,0.0035093662,0.014207829],"study_design_scores_gemma":[0.0029735044,0.0008407636,0.24806319,0.00042734464,0.00058190525,0.001254821,0.0027462225,0.015477593,0.5559689,0.00020705436,0.17027365,0.0011850911],"about_ca_topic_score_codex":0.0065420726,"about_ca_topic_score_gemma":0.0016219931,"teacher_disagreement_score":0.20582698,"about_ca_system_score_codex":0.00076904206,"about_ca_system_score_gemma":0.0006869383,"threshold_uncertainty_score":0.9996696},"labels":[],"label_agreement":null},{"id":"W2887711510","doi":"10.1038/s41598-019-40561-2","title":"Interpretable genotype-to-phenotype classifiers with performance guarantees","year":2019,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":108,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo; Canada Research Chairs; Government of Canada; Compute Canada; Université Laval","keywords":"Interpretability; Machine learning; Computer science; Artificial intelligence; Scalability; Curse of dimensionality; Generalization; Turnkey; Mathematics","score_opus":0.003900188324957552,"score_gpt":0.21397638053678783,"score_spread":0.21007619221183027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887711510","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95466363,0.000047772126,0.0012502215,0.000041317246,0.0021218504,0.0002917131,0.0000010716348,0.000028995857,0.041553427],"genre_scores_gemma":[0.9728314,0.000002729393,0.0036140562,0.00016305754,0.00004848031,0.00001019115,0.00007450837,0.000019801355,0.023235725],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986022,0.000017001414,0.00027721934,0.00049435825,0.00030118666,0.00030800168],"domain_scores_gemma":[0.9986231,0.000004447346,0.00016182449,0.0009774837,0.00013621699,0.000096926036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005487816,0.00014737988,0.00013436464,0.00008374186,0.00013486529,0.00014302906,0.00020457516,0.00007564116,0.00013245964],"category_scores_gemma":[0.000067555535,0.00011452781,0.000043717246,0.00023472696,0.00010596543,0.000013461415,0.00013368933,0.00011185563,0.00023121004],"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":[0.00031410065,0.00010927534,0.2799732,0.0002212721,0.00012521048,0.000028469538,0.0011556133,0.015354223,0.64846957,0.00013249871,0.04728903,0.0068275207],"study_design_scores_gemma":[0.00038564974,0.00082648685,0.016331896,0.0001329842,0.000029103952,0.00037011554,0.00020528417,0.006406235,0.12351164,0.00010254292,0.850999,0.0006990708],"about_ca_topic_score_codex":0.000006799797,"about_ca_topic_score_gemma":0.000010130046,"teacher_disagreement_score":0.80371,"about_ca_system_score_codex":0.000017480877,"about_ca_system_score_gemma":0.00013856369,"threshold_uncertainty_score":0.46703085},"labels":[],"label_agreement":null},{"id":"W2893054076","doi":"10.1016/j.str.2019.01.008","title":"Tertiary Structural Motif Sequence Statistics Enable Facile Prediction and Design of Peptides that Bind Anti-apoptotic Bfl-1 and Mcl-1","year":2019,"lang":"en","type":"article","venue":"Structure","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Office of Research Infrastructure Programs, National Institutes of Health; National Center for Research Resources; Health Effects Institute; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Office of Science; Koch Institute for Integrative Cancer Research, Massachusetts Institute of Technology; Argonne National Laboratory; U.S. Department of Energy; National Institutes of Health; National Science Foundation","keywords":"Motif (music); Sequence motif; Computational biology; Sequence (biology); Chemistry; Structural motif; Stereochemistry; Biology; Biochemistry; Physics; Gene","score_opus":0.00801524920236433,"score_gpt":0.22727912017904364,"score_spread":0.21926387097667932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2893054076","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9941208,0.00020529468,0.0045583514,0.00001505649,0.0001388752,0.00027107185,0.00060605153,0.000012175435,0.000072355644],"genre_scores_gemma":[0.97912174,0.000098896846,0.020195434,0.000050543797,0.000041085732,0.0000015098374,0.00027753023,0.000015592383,0.0001976519],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991887,0.000051771756,0.00019308936,0.0002320558,0.00014362189,0.00019071143],"domain_scores_gemma":[0.9994744,0.00003020163,0.00013752215,0.00024163997,0.00005522107,0.00006101722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008101301,0.00017606604,0.00017276546,0.000042313506,0.00006624989,0.000036299196,0.00010533145,0.00016418335,0.000055743592],"category_scores_gemma":[0.00008018705,0.00014676433,0.000018613291,0.000042048596,0.00013917738,0.00001623722,0.00010207323,0.00015023733,0.0000013604308],"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":[0.000033359775,0.000003358444,0.29828203,0.0004064156,0.000057882946,0.0000011239392,0.0003498646,0.0037367838,0.69500756,0.00011263421,0.00043020514,0.0015788059],"study_design_scores_gemma":[0.0017673523,0.0010052933,0.5181332,0.00013774967,0.000120371944,0.00037072314,0.0005452438,0.061932083,0.41149157,0.0027007577,0.001043167,0.0007524453],"about_ca_topic_score_codex":0.00002350993,"about_ca_topic_score_gemma":0.0000050029103,"teacher_disagreement_score":0.28351596,"about_ca_system_score_codex":0.000008439745,"about_ca_system_score_gemma":0.000045565925,"threshold_uncertainty_score":0.59848756},"labels":[],"label_agreement":null},{"id":"W2895946932","doi":"10.1021/acs.jpcb.8b07680","title":"Prediction of Misfolding-Specific Epitopes in SOD1 Using Collective Coordinates","year":2018,"lang":"en","type":"article","venue":"The Journal of Physical Chemistry B","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia; University of British Columbia","funders":"Alberta Prion Research Institute; Canadian Institutes of Health Research","keywords":"Epitope; SOD1; Protein folding; Computational biology; Computer science; Biology; Cell biology; Immunology; Genetics","score_opus":0.01563227595754153,"score_gpt":0.2605335700930044,"score_spread":0.24490129413546285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895946932","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9977111,0.00013407941,0.0008001166,0.00003923401,0.00004241003,0.000042332285,0.0000068038044,0.0000018882193,0.0012219902],"genre_scores_gemma":[0.9988014,0.000028325,0.0003452033,0.000011849888,0.000711153,3.9749696e-7,0.0000029054602,0.000008605479,0.00009013308],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99934363,0.00004676656,0.00028305623,0.00006212645,0.00014898274,0.00011544619],"domain_scores_gemma":[0.99923545,0.00004571788,0.00033301336,0.00014646669,0.00020554652,0.000033776534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029138708,0.00009126233,0.00016096125,0.00001882284,0.000048955244,0.000007737417,0.00021555398,0.00006113476,0.000014338767],"category_scores_gemma":[0.000137433,0.0000644072,0.00007737394,0.00012820328,0.00019342132,0.000006604925,0.00006162805,0.00018626159,8.306676e-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":[0.00016283456,0.00007016818,0.0011276687,0.000028320423,0.000034863202,4.971891e-7,0.00048713223,0.0010004002,0.99641657,0.0000043421796,0.00045755054,0.00020962722],"study_design_scores_gemma":[0.00041794646,0.000314037,0.0013949232,0.00005958785,0.000023295739,0.00004602813,0.00021840507,0.005863876,0.9904841,0.00015721023,0.0009591754,0.000061373794],"about_ca_topic_score_codex":0.000004371673,"about_ca_topic_score_gemma":4.998506e-7,"teacher_disagreement_score":0.0059324545,"about_ca_system_score_codex":0.000035036708,"about_ca_system_score_gemma":0.00007401428,"threshold_uncertainty_score":0.26264492},"labels":[],"label_agreement":null},{"id":"W2898847664","doi":"10.21203/rs.3.rs-878139/v1","title":"PSL-Recommender: Protein Subcellular Localization Prediction using Recommender System","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Health Network","funders":"Iran National Science Foundation; National Science Foundation","keywords":"Recommender system; Computer science; PSL; Machine learning; Inference; Artificial intelligence; Matrix decomposition; Data mining; Mathematics","score_opus":0.0551759197009809,"score_gpt":0.3660431512395883,"score_spread":0.3108672315386074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898847664","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45355627,0.0041621006,0.5293259,0.00059106306,0.0012925962,0.004545335,0.00032657426,0.00027284614,0.0059273024],"genre_scores_gemma":[0.9851121,0.0003112543,0.0065777935,0.00005233542,0.00075748435,0.00024184445,0.006310926,0.000113618335,0.0005226473],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956921,0.0013260527,0.00064351835,0.0007618597,0.0009166317,0.00065986736],"domain_scores_gemma":[0.99732757,0.00003259625,0.00027091094,0.0012285892,0.00094447786,0.00019585877],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021863834,0.00036509178,0.00035143323,0.0002765953,0.0004138597,0.0003433168,0.0004924974,0.00096312194,0.00008867842],"category_scores_gemma":[0.00051877054,0.0003850939,0.00020898563,0.00031325006,0.00009897871,0.000011428707,0.0017985047,0.0015212721,0.000019404686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001084204,0.0019255657,0.064341865,0.09368469,0.0029259594,0.00029867137,0.0052714944,0.45577434,0.2863666,0.0017759396,0.06327525,0.023275413],"study_design_scores_gemma":[0.0010549417,0.00059958134,0.00037261043,0.004917402,0.00007367608,0.000098727214,0.0046675103,0.88424236,0.055996805,0.000086897235,0.04688606,0.0010034527],"about_ca_topic_score_codex":0.00024878085,"about_ca_topic_score_gemma":0.000032785567,"teacher_disagreement_score":0.53155583,"about_ca_system_score_codex":0.00044970066,"about_ca_system_score_gemma":0.0006071094,"threshold_uncertainty_score":0.9998601},"labels":[],"label_agreement":null},{"id":"W2900916532","doi":"10.1186/s12859-018-2378-9","title":"The predictive performance of short-linear motif features in the prediction of calmodulin-binding proteins","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; University of Windsor","keywords":"Calmodulin; Motif (music); Computational biology; DNA microarray; Calmodulin-binding proteins; Bioinformatics; Biology; Computer science; Genetics; Biochemistry; Gene; Gene expression","score_opus":0.012059938183981482,"score_gpt":0.2541088111200603,"score_spread":0.2420488729360788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900916532","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9797376,0.00006511018,0.014271538,0.000041897547,0.00018271086,0.0007521593,0.00008957607,0.000014392283,0.004845036],"genre_scores_gemma":[0.97751445,0.000106729574,0.021887312,0.00004391103,0.00018112539,0.00003068243,0.000101636004,0.000012796552,0.00012137718],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854445,0.00007148657,0.00069008983,0.00009724058,0.00035092313,0.0002458104],"domain_scores_gemma":[0.9988327,0.00006772926,0.00033082915,0.00054850517,0.0001897238,0.00003051789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085644925,0.00015996551,0.00016094456,0.00006892593,0.00017975937,0.000021049587,0.00051387906,0.0001650869,0.0000029558569],"category_scores_gemma":[0.0003935044,0.00009375156,0.00007971027,0.00023222598,0.00040428748,0.00002168232,0.00013797743,0.00022995312,0.0000048492575],"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":[0.0032645655,0.0008472534,0.7936194,0.005317934,0.0006394318,0.0000013980239,0.04399073,0.043514106,0.048762165,0.0023259008,0.011762393,0.045954723],"study_design_scores_gemma":[0.00065701245,0.0023492847,0.08889022,0.00016816481,0.000042280666,0.00003831708,0.0029231904,0.83505565,0.0654189,0.000020713678,0.0042304588,0.00020582757],"about_ca_topic_score_codex":0.000010417991,"about_ca_topic_score_gemma":0.000046877183,"teacher_disagreement_score":0.7915415,"about_ca_system_score_codex":0.000016255006,"about_ca_system_score_gemma":0.00010331865,"threshold_uncertainty_score":0.38230777},"labels":[],"label_agreement":null},{"id":"W2901314256","doi":"10.1016/j.jtbi.2018.11.011","title":"Predicting protein–protein interactions by fusing various Chou's pseudo components and using wavelet denoising approach","year":2018,"lang":"en","type":"article","venue":"Journal of Theoretical Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"University of Calgary","funders":"National Institute of Food and Agriculture; Project of Shandong Province Higher Educational Science and Technology Program; Natural Science Foundation of Shandong Province; National Natural Science Foundation of China; Kansas NSF EPSCoR; South Dakota State University; National Science Foundation","keywords":"Support vector machine; Computer science; Pattern recognition (psychology); Pseudo amino acid composition; Artificial intelligence; Feature vector; Feature (linguistics); Classifier (UML); Data mining; Machine learning; Biology; Amino acid","score_opus":0.009586050802162849,"score_gpt":0.2744400496105388,"score_spread":0.26485399880837596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901314256","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.877811,0.0001172036,0.12065661,0.00016883992,0.00015755747,0.00015252935,0.000010762107,0.000007993783,0.00091750186],"genre_scores_gemma":[0.9507002,0.0000086056825,0.048525207,0.00015306666,0.0005398282,0.0000017733471,0.000024106568,0.000021283,0.00002589712],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99857706,0.0002587735,0.0005482654,0.0001939551,0.000119555574,0.00030236886],"domain_scores_gemma":[0.9989889,0.000040687122,0.00046038325,0.00018404031,0.00019119531,0.00013474457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000670224,0.00018162518,0.00027064013,0.00008856406,0.00020366743,0.000054501917,0.00022433193,0.00021150759,0.000032846114],"category_scores_gemma":[0.00062592817,0.00014472203,0.000084019666,0.00007582994,0.0007976331,0.000014265893,0.00022016653,0.00043208382,0.0000021183812],"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":[0.00019632901,0.00007183916,0.002092364,0.000026972268,0.000095918476,0.0000017333404,0.000111345544,0.000013668819,0.9912999,0.0045775054,0.00004848877,0.0014638895],"study_design_scores_gemma":[0.005479193,0.007839282,0.0015252546,0.0008446857,0.00042713803,0.008193912,0.0006177841,0.17557861,0.75567436,0.024652764,0.017480014,0.0016870145],"about_ca_topic_score_codex":0.000011123921,"about_ca_topic_score_gemma":5.980787e-7,"teacher_disagreement_score":0.23562561,"about_ca_system_score_codex":0.00003258441,"about_ca_system_score_gemma":0.000045043475,"threshold_uncertainty_score":0.5901593},"labels":[],"label_agreement":null},{"id":"W2910654431","doi":"10.1016/j.gpb.2018.08.004","title":"Integration of A Deep Learning Classifier with A Random Forest Approach for Predicting Malonylation Sites","year":2018,"lang":"en","type":"article","venue":"Genomics Proteomics & Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":107,"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":"National Natural Science Foundation of China; Natural Science Foundation of Shandong Province; Qingdao Postdoctoral Science Foundation","keywords":"Classifier (UML); Computer science; Random forest; Artificial intelligence; Deep learning; Machine learning; Training set; Pattern recognition (psychology); End-to-end principle","score_opus":0.009638930436779197,"score_gpt":0.23279893240496957,"score_spread":0.22316000196819039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910654431","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":[0.36609605,0.000021808957,0.63030034,0.000010461237,0.00005208304,0.0011308391,0.000020897858,0.00002734232,0.002340201],"genre_scores_gemma":[0.46278203,0.000021828333,0.53573674,0.000056795816,0.00026964588,0.000099020814,0.0008915429,0.000037905695,0.000104496685],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837136,0.000043575925,0.0007961334,0.00022107421,0.00020145487,0.00036637302],"domain_scores_gemma":[0.99795854,0.00004369651,0.0008367057,0.00039442355,0.00068324304,0.000083377185],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007470973,0.0002891822,0.0003093744,0.00018145259,0.00026740288,0.00008765745,0.00028559275,0.00027251986,0.000003997207],"category_scores_gemma":[0.00068113516,0.000246543,0.00012027034,0.00020457494,0.00022649477,0.000040289782,0.0001302095,0.00024068821,0.000004759852],"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":[0.00952904,0.00039465813,0.06743961,0.0027969023,0.0009803291,5.217637e-7,0.018951103,0.15440339,0.69002753,0.0035883687,0.0007164055,0.051172145],"study_design_scores_gemma":[0.002317528,0.0015244011,0.00057812175,0.000034696557,0.00006943367,0.00001862754,0.00090589334,0.9402418,0.05132271,0.0000921131,0.0025667723,0.00032788806],"about_ca_topic_score_codex":0.000006034313,"about_ca_topic_score_gemma":0.000041627973,"teacher_disagreement_score":0.7858384,"about_ca_system_score_codex":0.00005300203,"about_ca_system_score_gemma":0.000114876515,"threshold_uncertainty_score":0.9999987},"labels":[],"label_agreement":null},{"id":"W2911322539","doi":"","title":"Proceedings of the 24th international conference on Machine learning","year":2007,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Presentation (obstetrics); Library science; Computer science; Medical education; Medicine","score_opus":0.010062716251899936,"score_gpt":0.2612075380839381,"score_spread":0.2511448218320382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911322539","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6084779,0.000007044356,0.0009107522,0.0003453484,0.0001133757,0.00006652145,0.0000019134811,0.000010721335,0.39006642],"genre_scores_gemma":[0.991299,0.000012726419,0.0015193318,0.00025253795,0.000058871574,8.404139e-7,0.000012095339,0.0000059091544,0.0068386956],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995385,0.000003938362,0.00014298623,0.000082326194,0.00013906682,0.00009318697],"domain_scores_gemma":[0.9996996,0.000005930055,0.00010362036,0.00007057629,0.0000989865,0.000021273623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024231272,0.00006417437,0.000048099653,0.000022380063,0.000037586316,0.000011684172,0.0002304816,0.000052708147,0.000095719464],"category_scores_gemma":[0.00014877175,0.00004159293,0.000038293903,0.00004326701,0.000043895605,0.0000018977752,0.000113542665,0.00013504697,0.000006061849],"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":[0.00018782531,0.00009049832,0.22670399,0.00004220545,0.00007527525,3.141204e-7,0.00032644861,0.00024202764,0.69611394,0.06612185,0.002781719,0.0073138927],"study_design_scores_gemma":[0.000861161,0.0005726148,0.048634812,0.00005471526,0.000012934463,0.000029630419,0.00054508157,0.01570702,0.78845507,0.00023309822,0.14459907,0.00029477393],"about_ca_topic_score_codex":0.000008776418,"about_ca_topic_score_gemma":0.000009510515,"teacher_disagreement_score":0.3832277,"about_ca_system_score_codex":0.0000057176167,"about_ca_system_score_gemma":0.00001186926,"threshold_uncertainty_score":0.16961105},"labels":[],"label_agreement":null},{"id":"W2912093348","doi":"","title":"Proceedings of the 9th IAPR International Conference on Pattern Recognition in Bioinformatics - Volume 8626","year":2014,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Windsor","funders":"","keywords":"Volume (thermodynamics); Computer science; Data science","score_opus":0.011979286231218965,"score_gpt":0.23847127193332007,"score_spread":0.2264919857021011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912093348","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73062646,0.0000014532372,0.005377019,0.0008121804,0.00036123893,0.00019578572,0.000016098016,0.000013602569,0.26259613],"genre_scores_gemma":[0.9950647,0.000011984524,0.0030726884,0.0004851556,0.00005354481,0.0000063975835,0.000053949934,0.0000066470484,0.0012449592],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993978,0.000009747344,0.00025836486,0.00008400182,0.00014787658,0.000102222904],"domain_scores_gemma":[0.9995838,0.0000058121786,0.00016295393,0.00011117247,0.00011547365,0.00002079872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020569161,0.00008538811,0.00007598949,0.000042468044,0.000021850814,0.000024015317,0.00025376197,0.00008089069,0.000095560776],"category_scores_gemma":[0.00017060028,0.00006050512,0.000038905288,0.00005545564,0.000047155198,0.000007588881,0.00010637659,0.00011166911,0.00003113046],"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":[0.00023140908,0.00048967195,0.49947438,0.0006271084,0.00014551362,2.7100967e-7,0.0023534806,0.00047910644,0.083915964,0.0075954534,0.032128032,0.37255964],"study_design_scores_gemma":[0.0030731175,0.0013693635,0.09147734,0.00053141103,0.00003105638,0.000048994294,0.0015098611,0.6553968,0.18808195,0.0015913588,0.055967156,0.00092154695],"about_ca_topic_score_codex":0.000014684897,"about_ca_topic_score_gemma":0.000021220956,"teacher_disagreement_score":0.6549177,"about_ca_system_score_codex":0.0000096438625,"about_ca_system_score_gemma":0.000016047237,"threshold_uncertainty_score":0.24673273},"labels":[],"label_agreement":null},{"id":"W2913430916","doi":"10.2174/1875036201912010030","title":"A Simple Genetic Algorithm for Optimizing Multiple Sequence Alignment on the Spread of the SARS Epidemic","year":2019,"lang":"en","type":"article","venue":"The Open Bioinformatics Journal","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Direktorat Riset dan Pengabdian Masyarakat","keywords":"Phylogenetic tree; Phylogenetic network; Mutation; Multiple sequence alignment; Tree (set theory); Sequence (biology); Algorithm; Computer science; Sequence alignment; Biology; Genetics; Mathematics; Gene; Combinatorics","score_opus":0.027581319727887858,"score_gpt":0.2994065380552482,"score_spread":0.27182521832736034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913430916","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75110257,0.00023147395,0.22246154,0.0048012272,0.001404082,0.007248616,0.0003048014,0.000021393085,0.012424316],"genre_scores_gemma":[0.7010416,0.00035581272,0.29076687,0.0061423313,0.00030683188,0.00009239516,0.00006183298,0.00007100229,0.0011613278],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982669,0.0001551456,0.0007615658,0.000112031776,0.00034351062,0.00036084995],"domain_scores_gemma":[0.99776506,0.00025513337,0.0008858075,0.0008966184,0.00013417678,0.00006320191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018219216,0.00021702974,0.000233905,0.000030277195,0.00045586895,0.00019762082,0.0021962922,0.0001003179,0.00004080846],"category_scores_gemma":[0.00040113687,0.000100886624,0.00021150721,0.000111317124,0.00014925638,0.000025179872,0.0007179835,0.0003709081,0.00002739798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010720243,0.0005047457,0.014391369,0.0007361125,0.0022756692,0.0000044377102,0.013804101,0.37601697,0.15859085,0.0043713055,0.11787542,0.310357],"study_design_scores_gemma":[0.0016819965,0.0007332587,0.0010493399,0.00019215069,0.00007776687,0.00035613062,0.001677103,0.9161945,0.04258357,0.00084436685,0.03424967,0.00036017076],"about_ca_topic_score_codex":0.00002161764,"about_ca_topic_score_gemma":0.000004016507,"teacher_disagreement_score":0.5401775,"about_ca_system_score_codex":0.0000433082,"about_ca_system_score_gemma":0.00015321877,"threshold_uncertainty_score":0.41140372},"labels":[],"label_agreement":null},{"id":"W2919745482","doi":"","title":"Identification of protein components of the rod outer segment plasma membrane by label-free protein correlation profiling","year":2018,"lang":"en","type":"article","venue":"Investigative Ophthalmology & Visual Science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Profiling (computer programming); Identification (biology); Chemistry; Chromatography; Biology; Computer science; Botany","score_opus":0.019792606565380694,"score_gpt":0.299699987317554,"score_spread":0.2799073807521733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2919745482","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9982436,0.000013440359,0.00016436222,0.00016905228,0.00014355013,0.0008345514,0.000028855697,0.0000070297674,0.00039557164],"genre_scores_gemma":[0.9952833,3.4957455e-7,0.0041553373,0.00003306295,0.000033213062,0.000048964375,0.0000324619,0.00000967605,0.00040365226],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99831647,0.00020034038,0.00050048134,0.0003291622,0.00041909024,0.00023446228],"domain_scores_gemma":[0.99836475,0.000016537406,0.00069160276,0.00047287584,0.00038572444,0.000068529334],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0009140365,0.00014806117,0.00015772678,0.00006083914,0.00021290491,0.000017187354,0.00076716486,0.00012372686,0.000011970249],"category_scores_gemma":[0.0011337606,0.00011357623,0.00003767972,0.0003913124,0.0036562143,0.000026995382,0.00044834905,0.00014516896,0.000007800091],"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":[0.000036779697,0.00008359833,0.0075963167,0.000042269196,0.0000141648525,3.2447542e-7,0.00026646326,0.000053050662,0.9916767,0.00013429383,0.00002124653,0.000074791504],"study_design_scores_gemma":[0.00035457025,0.0006031109,0.009498828,0.000060818595,0.0000082621,0.000018222845,0.00005200988,0.009859666,0.9790818,0.00032822427,0.000022285647,0.00011217619],"about_ca_topic_score_codex":0.000042159856,"about_ca_topic_score_gemma":0.0000017760142,"teacher_disagreement_score":0.012594876,"about_ca_system_score_codex":0.000031247986,"about_ca_system_score_gemma":0.00016318352,"threshold_uncertainty_score":0.99905527},"labels":[],"label_agreement":null},{"id":"W2949514040","doi":"10.1186/s12859-018-2284-1","title":"De novo profile generation based on sequence context specificity with the long short-term memory network","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Medical Science, University of Tokyo; Japan Society for the Promotion of Science; Ministry of Education, Culture, Sports, Science and Technology; Institute of Genetics; Japan Agency for Medical Research and Development","keywords":"Context (archaeology); Term (time); Sequence (biology); DNA microarray; Long short term memory; Computational biology; Computer science; Biology; Genetics; Artificial intelligence; Gene; Artificial neural network; Recurrent neural network; Gene expression; Paleontology","score_opus":0.025768379538747735,"score_gpt":0.2655191005374179,"score_spread":0.23975072099867017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949514040","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38664985,0.000034070086,0.5940933,0.00019277626,0.00024186974,0.00072448584,0.00003287358,0.00006317654,0.017967578],"genre_scores_gemma":[0.8848834,0.000007996625,0.10996048,0.002898602,0.0012338668,0.000040531122,0.00038437074,0.00003305066,0.0005576843],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986901,0.000077450684,0.00036593468,0.000165204,0.0002916577,0.00040961694],"domain_scores_gemma":[0.9987957,0.000042519994,0.00020072708,0.0006967269,0.00016977367,0.00009457053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055951346,0.0002465377,0.00015381478,0.000036136404,0.00034190645,0.00014103812,0.00037094418,0.00017061095,0.00007078165],"category_scores_gemma":[0.000093907474,0.0001623491,0.00006765841,0.00015066766,0.00030286668,0.000018404156,0.00008589011,0.00022019983,0.00008294318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036188709,0.00060255907,0.21060085,0.0016369362,0.00049700215,0.000030053061,0.0070971544,0.4590696,0.031462044,0.0031029237,0.17850637,0.10377564],"study_design_scores_gemma":[0.00049249263,0.0010365585,0.003420425,0.000057627596,0.000029361747,0.00005844142,0.00022106312,0.9669034,0.021313831,0.0000034507048,0.0061144424,0.00034893342],"about_ca_topic_score_codex":0.000004831892,"about_ca_topic_score_gemma":0.00021241081,"teacher_disagreement_score":0.5078338,"about_ca_system_score_codex":0.000047973437,"about_ca_system_score_gemma":0.0002369245,"threshold_uncertainty_score":0.6620404},"labels":[],"label_agreement":null},{"id":"W2950259236","doi":"10.48550/arxiv.q-bio/0603011","title":"PFMFind: a system for discovery of peptide homology and function","year":2006,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Ottawa","funders":"","keywords":"Python (programming language); Computer science; Plug-in; Homology (biology); Computational biology; Data mining; Programming language; Theoretical computer science; Artificial intelligence; Information retrieval; Biology; Amino acid; Genetics","score_opus":0.01980607468470608,"score_gpt":0.17652358412903182,"score_spread":0.15671750944432575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950259236","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79611504,0.00008730807,0.20115195,0.000006706057,0.00020943274,0.0002618992,0.00008375031,0.000017808528,0.0020660877],"genre_scores_gemma":[0.99567395,0.000043306805,0.00088261813,0.000017489168,0.00010147688,0.0000020472144,0.00044863665,0.000018207771,0.0028122917],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918646,0.000051561714,0.00019175943,0.00037862652,0.000029997436,0.00016158675],"domain_scores_gemma":[0.99915767,0.000026375106,0.00029433073,0.00040576232,0.00008054384,0.000035300913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013612212,0.00018451975,0.00024601605,0.00008679499,0.000054217664,0.000019173955,0.00019622635,0.00036251885,0.000001135437],"category_scores_gemma":[0.000033896657,0.0002052126,0.00013841692,0.000050814848,0.00012144779,0.000005968311,0.00042873094,0.00016508863,0.0000014126231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004066427,0.00049881294,0.14665285,0.014896455,0.0022036026,0.00013520228,0.00033927365,0.6275047,0.052861594,0.13707925,0.011662456,0.0020993906],"study_design_scores_gemma":[0.023833832,0.010517412,0.14538911,0.0027330464,0.0066476897,0.00038179985,0.0034954746,0.6064121,0.071754195,0.03440759,0.085319616,0.0091081],"about_ca_topic_score_codex":0.00013384051,"about_ca_topic_score_gemma":0.000072946066,"teacher_disagreement_score":0.20026933,"about_ca_system_score_codex":0.000032885586,"about_ca_system_score_gemma":0.000072320625,"threshold_uncertainty_score":0.8368327},"labels":[],"label_agreement":null},{"id":"W2950355818","doi":"10.48550/arxiv.1307.7798","title":"Towards Reliable Automatic Protein Structure Alignment","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Similarity (geometry); Consistency (knowledge bases); Structural alignment; Computer science; Multiple sequence alignment; Sequence (biology); Structural similarity; Pattern recognition (psychology); Sequence alignment; Artificial intelligence; Algorithm; Local structure; Mathematics; Data mining; Biology; Peptide sequence; Image (mathematics); Crystallography","score_opus":0.018875200518797083,"score_gpt":0.1820648219013108,"score_spread":0.1631896213825137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950355818","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97855,0.000057241283,0.013263376,0.00007341493,0.00027101056,0.0007851685,0.000056452245,0.00008919507,0.0068541206],"genre_scores_gemma":[0.98671144,0.000054383312,0.004477238,0.0001327797,0.00013461578,0.0000043150876,0.00035973333,0.000040296352,0.008085184],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985864,0.0000816353,0.00025402664,0.00062008976,0.000105203275,0.00035262754],"domain_scores_gemma":[0.9983057,0.0000051629077,0.00032322726,0.0010958428,0.00012126826,0.00014881672],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001301795,0.00037883123,0.00028729174,0.00008806727,0.000103522565,0.00007073977,0.0007437931,0.000606958,0.00035991482],"category_scores_gemma":[0.00006665685,0.00039392,0.00017043881,0.00011598584,0.00009920495,0.000008433446,0.001341693,0.0005194125,0.00010276661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017159981,0.00033965358,0.0072806086,0.003300432,0.0014209864,0.00013606975,0.0005905018,0.852981,0.056086306,0.028692009,0.045234952,0.0037659002],"study_design_scores_gemma":[0.0023771985,0.00077567855,0.0026914848,0.0006658835,0.00038449356,0.000036382673,0.00034428583,0.8382855,0.054050233,0.031874463,0.065459594,0.0030548032],"about_ca_topic_score_codex":0.00016872455,"about_ca_topic_score_gemma":0.000017517199,"teacher_disagreement_score":0.020224638,"about_ca_system_score_codex":0.00010139346,"about_ca_system_score_gemma":0.00021451947,"threshold_uncertainty_score":0.9998513},"labels":[],"label_agreement":null},{"id":"W2951055794","doi":"10.1101/388348","title":"Interpretable genotype-to-phenotype classifiers with performance guarantees","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo; Compute Canada; Université Laval","keywords":"Interpretability; Machine learning; Artificial intelligence; Computer science; Scalability; Curse of dimensionality; Generalization; Turnkey; Limit (mathematics); Interpretation (philosophy); Mathematics","score_opus":0.006912013707576995,"score_gpt":0.21289609290087802,"score_spread":0.20598407919330103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951055794","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9852409,0.00031924783,0.012218428,0.00010688327,0.0008574967,0.00067329564,0.0000908119,0.00017705164,0.00031590383],"genre_scores_gemma":[0.96969163,0.00014148765,0.028429475,0.0006748328,0.0007049238,0.00011619958,0.0000029068879,0.00016568218,0.000072882736],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99740666,0.000081031714,0.0005025497,0.0009304741,0.0003818941,0.0006973956],"domain_scores_gemma":[0.99693197,0.000014193175,0.00038883355,0.0018092511,0.0005657313,0.00028999668],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047737203,0.0006628749,0.0004800031,0.0001962639,0.00020173035,0.00020016977,0.00096332934,0.0006364968,0.00007372103],"category_scores_gemma":[0.00020655949,0.00061511545,0.00011506087,0.00030090477,0.00022383344,0.000016266218,0.00095078064,0.0007068249,0.00022326397],"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":[0.00082855474,0.00015606436,0.046096,0.0011071995,0.0007036082,0.00001616682,0.000071055685,0.0027989382,0.94052076,0.00011511904,0.00756532,0.000021221535],"study_design_scores_gemma":[0.0014902821,0.0022760273,0.12804602,0.0014599544,0.00033350594,2.5959162e-7,0.000013133346,0.010171062,0.69577205,0.000001351875,0.15698639,0.0034499513],"about_ca_topic_score_codex":0.000020829335,"about_ca_topic_score_gemma":0.000005807159,"teacher_disagreement_score":0.2447487,"about_ca_system_score_codex":0.00010728152,"about_ca_system_score_gemma":0.00058962463,"threshold_uncertainty_score":0.99963003},"labels":[],"label_agreement":null},{"id":"W2952663747","doi":"10.1101/563601","title":"Deep learning in bioinformatics: introduction, application, and perspective in big data era","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Community Based Research Centre; Kootenay Association for Science & Technology","funders":"King Abdullah University of Science and Technology","keywords":"Deep learning; Artificial intelligence; Computer science; Interpretability; Big data; Autoencoder; Machine learning; Field (mathematics); Deep neural networks; Overfitting; Convolutional neural network; Data science; Artificial neural network; Implementation; Data mining","score_opus":0.009148252838469676,"score_gpt":0.23091129961200202,"score_spread":0.22176304677353234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952663747","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91547334,0.00393287,0.07514896,0.0014055988,0.0013862455,0.0021828648,0.00014212527,0.00019990726,0.00012810796],"genre_scores_gemma":[0.9845994,0.000959308,0.013178131,0.0001535545,0.0009024522,0.00009288637,0.000022390113,0.00008113046,0.000010728854],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975425,0.00014168856,0.0006999964,0.00096087845,0.00023279196,0.0004221307],"domain_scores_gemma":[0.9970793,0.000029822962,0.00048262047,0.0019897746,0.00030965518,0.00010879688],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010494727,0.00043838855,0.00043933344,0.0003871402,0.00007800478,0.00014611735,0.0007942638,0.00057884323,0.0000061701107],"category_scores_gemma":[0.0009793225,0.0004950858,0.00004457739,0.0003857591,0.00012572292,0.00003253263,0.0016919193,0.0012641224,0.000034902092],"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":[0.00039593552,0.00065846165,0.5383324,0.004214364,0.0006382611,0.00002218772,0.00092817197,0.08160937,0.36756143,0.0026838672,0.0023334706,0.00062207296],"study_design_scores_gemma":[0.0035908092,0.00035829179,0.40326357,0.0005500902,0.00014754786,5.436021e-7,0.00046002868,0.48478037,0.027437022,0.000020072153,0.07604499,0.0033466604],"about_ca_topic_score_codex":0.00014531794,"about_ca_topic_score_gemma":0.00006099795,"teacher_disagreement_score":0.403171,"about_ca_system_score_codex":0.00017451223,"about_ca_system_score_gemma":0.00038476553,"threshold_uncertainty_score":0.9997501},"labels":[],"label_agreement":null},{"id":"W2953705189","doi":"10.1002/pro.3673","title":"<i>ProtDCal‐Suite</i>: A web server for the numerical codification and functional analysis of proteins","year":2019,"lang":"en","type":"article","venue":"Protein Science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Boehringer Ingelheim Stiftung; Deutsche Forschungsgemeinschaft","keywords":"Suite; Computer science; Computational biology; Web server; World Wide Web; Biology; Bioinformatics; The Internet; Geography","score_opus":0.010324617247455047,"score_gpt":0.2583926146349856,"score_spread":0.24806799738753055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953705189","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95337033,0.00007489044,0.04508109,0.00018450286,0.000025580119,0.0010287585,0.000014186397,0.000003538891,0.00021709676],"genre_scores_gemma":[0.9937365,0.0000039247857,0.0059040426,0.000038783073,0.000012875373,0.00010143991,0.000012248709,0.0000030646804,0.00018710762],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993171,0.00001672205,0.00017432615,0.00016524762,0.00022291638,0.000103652535],"domain_scores_gemma":[0.9993295,0.00002613266,0.00016319605,0.00028844,0.00016715082,0.000025551808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007057023,0.000055632692,0.000098065546,0.00006517693,0.00006901355,0.00001542774,0.00019506992,0.000034536246,0.000017640437],"category_scores_gemma":[0.00030004542,0.00003741747,0.00005365942,0.00051545637,0.0002545076,0.000008177919,0.000087923865,0.00004145882,0.000001348571],"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":[0.0000513221,0.000022440974,0.01658016,0.000058244736,0.00005324425,6.3779555e-9,0.00005877806,0.0011840386,0.9787031,0.0017231366,0.000012495248,0.001553049],"study_design_scores_gemma":[0.00051630713,0.0004987491,0.10717917,0.000018643135,0.0001331709,0.0000021521753,0.00008735422,0.29223812,0.59364766,0.000103288585,0.0054063154,0.0001690409],"about_ca_topic_score_codex":0.000011358916,"about_ca_topic_score_gemma":0.000002963363,"teacher_disagreement_score":0.3850554,"about_ca_system_score_codex":0.0000047418444,"about_ca_system_score_gemma":0.00010386946,"threshold_uncertainty_score":0.15258402},"labels":[],"label_agreement":null},{"id":"W2955141396","doi":"10.6026/97320630015388","title":"Prediction of normalized signal strength on DNA sequencing micro arrays by n-grams within a neural network model","year":2019,"lang":"en","type":"article","venue":"Bioinformation","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Memorial University of Newfoundland","funders":"","keywords":"Oligonucleotide; Pattern recognition (psychology); Artificial neural network; Confusion matrix; Computer science; Algorithm; Artificial intelligence; Data mining; Mathematics; Statistics; DNA; Genetics; Biology","score_opus":0.010514414586564205,"score_gpt":0.21467416543230794,"score_spread":0.20415975084574373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955141396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9727977,0.00002934433,0.021128327,0.000027390075,0.00021541506,0.0003783271,0.00010824133,0.000044675693,0.0052705966],"genre_scores_gemma":[0.9878471,0.000015774094,0.009630105,0.00024783539,0.00009808854,0.0000107723645,0.0018220489,0.0000179901,0.00031029692],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873483,0.000037134,0.00058156333,0.00014545521,0.00025517948,0.0002458557],"domain_scores_gemma":[0.99906456,0.000012819041,0.00047115778,0.0003023326,0.0000880545,0.00006104264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003281449,0.00019081362,0.00017662357,0.000057543028,0.00007351463,0.00003451181,0.00017146031,0.0001927086,0.000024524523],"category_scores_gemma":[0.000035796642,0.00017543463,0.00008721211,0.00011569931,0.00003650817,0.00004440317,0.000056895344,0.00016433449,0.000030696177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002432562,0.00002869083,0.002301481,0.00013867626,0.000045245186,8.589446e-8,0.00062979147,0.6010235,0.38920027,0.00021464343,0.004083021,0.0020913717],"study_design_scores_gemma":[0.00075534865,0.00047559073,0.00018220644,0.000043669013,0.000013865391,0.000007052519,0.00012551206,0.8701496,0.12711498,0.000019648862,0.000951108,0.0001614395],"about_ca_topic_score_codex":0.000011554022,"about_ca_topic_score_gemma":0.0000028078978,"teacher_disagreement_score":0.26912612,"about_ca_system_score_codex":0.00004398264,"about_ca_system_score_gemma":0.00007727696,"threshold_uncertainty_score":0.7154017},"labels":[],"label_agreement":null},{"id":"W2956168392","doi":"10.1016/j.cmpb.2019.07.009","title":"AMC-Net: Asymmetric and multi-scale convolutional neural network for multi-label HPA classification","year":2019,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"York University; University of Ontario Institute of Technology","funders":"Knut och Alice Wallenbergs Stiftelse; National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Human Protein Atlas; Pattern recognition (psychology); Deep learning; Multi-label classification; Artificial neural network; Feature extraction; Binary classification; Machine learning; Robustness (evolution); Support vector machine","score_opus":0.06901865286101067,"score_gpt":0.3827700430446068,"score_spread":0.31375139018359616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2956168392","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":[0.14741994,0.002286205,0.8486784,0.0002484829,0.0005368326,0.0007723593,0.0000073096594,0.00002134489,0.000029133735],"genre_scores_gemma":[0.035089888,0.0001496804,0.96345073,0.00038817344,0.00036164737,0.000044746626,0.00035798523,0.000017395101,0.00013975715],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880517,0.00015038646,0.0003350574,0.00034242249,0.00008780429,0.00027916924],"domain_scores_gemma":[0.9993936,0.00009338692,0.00013443483,0.00020850825,0.00007379833,0.00009630334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010769323,0.00017482889,0.00024698864,0.00010592604,0.0000643349,0.000034715642,0.00012446917,0.00017305804,0.0000021160001],"category_scores_gemma":[0.000053839067,0.00014495186,0.00003466726,0.00025723327,0.00016868062,0.000007357491,0.00013730011,0.00014554395,0.0000010795201],"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":[0.000058111356,0.000105833875,0.10454085,0.000146932,0.000029974808,3.085723e-7,0.000104320454,0.000037004527,0.0055925767,0.00011486703,0.0002502325,0.889019],"study_design_scores_gemma":[0.0029403886,0.00089098123,0.08031377,0.000042471413,0.000016403508,0.000022787093,0.000034921224,0.89383256,0.000098047996,0.000042329902,0.021585545,0.00017977599],"about_ca_topic_score_codex":0.000012758932,"about_ca_topic_score_gemma":0.0000072249704,"teacher_disagreement_score":0.89379555,"about_ca_system_score_codex":0.000010557488,"about_ca_system_score_gemma":0.000017167615,"threshold_uncertainty_score":0.5910965},"labels":[],"label_agreement":null},{"id":"W2962655813","doi":"10.1093/bioinformatics/btz337","title":"Prediction of mRNA subcellular localization using deep recurrent neural networks","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":86,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Montreal Clinical Research Institute; McGill University","funders":"Institut de Valorisation des Données","keywords":"Computational biology; Sequence (biology); Computer science; Identification (biology); RNA; Subcellular localization; Variety (cybernetics); Messenger RNA; Biology; Set (abstract data type); Deep learning; RNA-binding protein; Artificial neural network; Artificial intelligence; Gene; Genetics","score_opus":0.012123227150818776,"score_gpt":0.23152418127151167,"score_spread":0.21940095412069288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962655813","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51645035,0.0002149016,0.4809129,0.000007328431,0.00063824,0.00034949495,0.00001808411,0.000028346945,0.0013803965],"genre_scores_gemma":[0.98630756,0.000084200015,0.012686647,0.00011178786,0.0001271832,0.0000026766832,0.00059834245,0.000021399368,0.000060216043],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988273,0.000033706307,0.0005916753,0.00010685478,0.00021727404,0.00022321114],"domain_scores_gemma":[0.99904644,0.000010160478,0.000372779,0.00038416026,0.00012398504,0.00006249459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023193382,0.00016322471,0.00017118857,0.00007228552,0.000055936303,0.000025757703,0.00018085937,0.00018959594,0.000031709533],"category_scores_gemma":[0.00006412285,0.00015412565,0.00008806523,0.00015406833,0.000049036604,0.000021814409,0.00011650169,0.00012737617,0.000013602436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000079887344,0.000066357294,0.08589184,0.0005727056,0.00007807434,3.6341345e-7,0.00054803945,0.895071,0.006911257,0.000182685,0.0006111136,0.009986633],"study_design_scores_gemma":[0.00039611247,0.00025980294,0.00081845606,0.000034652858,0.000024598272,0.00001551847,0.0001277927,0.99231416,0.0028785588,0.0000050550266,0.0029838143,0.00014147432],"about_ca_topic_score_codex":0.0000056420927,"about_ca_topic_score_gemma":0.0000017752035,"teacher_disagreement_score":0.46985722,"about_ca_system_score_codex":0.000024182618,"about_ca_system_score_gemma":0.000031630563,"threshold_uncertainty_score":0.6285062},"labels":[],"label_agreement":null},{"id":"W2964327378","doi":"","title":"Analysis of semi-supervised learning with the Yarowsky algorithm","year":2007,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"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":"Weighted Majority Algorithm; Computer science; Algorithm; Semi-supervised learning; Supervised learning; Graph; Bootstrapping (finance); Artificial intelligence; Entropy (arrow of time); Machine learning; Unsupervised learning; Wake-sleep algorithm; Mathematics; Theoretical computer science; Generalization error; Artificial neural network","score_opus":0.00397787480399339,"score_gpt":0.23593966833249108,"score_spread":0.2319617935284977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964327378","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61497676,0.00007141908,0.36077613,0.00012760515,0.00001814957,0.00009021689,0.0000029226824,0.000018843431,0.023917984],"genre_scores_gemma":[0.98146504,0.000015012145,0.015312818,0.00027747406,0.000046060657,0.0000019398205,0.00010309322,0.000011263001,0.0027672697],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931884,0.000033535955,0.00018580371,0.00012270514,0.00016501268,0.00017407582],"domain_scores_gemma":[0.9994449,0.000036473568,0.00010687521,0.00028315885,0.00008857516,0.000040028503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052326213,0.000099665536,0.0001379769,0.00008312894,0.00007125317,0.000012164231,0.00017972146,0.000073036244,0.000088857814],"category_scores_gemma":[0.000048433754,0.000058161047,0.00009511369,0.00042437259,0.00007792648,0.0000020227676,0.000067709705,0.0001313018,0.000003736786],"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":[0.00037228808,0.0002169861,0.49779612,0.00009547695,0.007998645,0.000010447489,0.002803414,0.08643746,0.1871784,0.00065137766,0.0031766915,0.2132627],"study_design_scores_gemma":[0.001870147,0.0017885094,0.15427727,0.000022464434,0.0021455057,0.0000382273,0.005613187,0.4688791,0.20111573,0.0000083327795,0.16326895,0.0009725885],"about_ca_topic_score_codex":0.00003866653,"about_ca_topic_score_gemma":0.000099790515,"teacher_disagreement_score":0.38244164,"about_ca_system_score_codex":0.000004563579,"about_ca_system_score_gemma":0.000020031466,"threshold_uncertainty_score":0.23717386},"labels":[],"label_agreement":null},{"id":"W2967615861","doi":"10.18280/ria.330113","title":"Frequent Subtree Mining Algorithm for Ribonucleic Acid Topological Pattern","year":2019,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Natural Science Foundation of Guangxi Province; National Natural Science Foundation of China","keywords":"Computational biology; Computer science; Data mining; Topology (electrical circuits); Biology; Mathematics; Combinatorics","score_opus":0.019947964174483638,"score_gpt":0.2749466384040802,"score_spread":0.25499867422959654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967615861","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3547272,0.00019744397,0.6402167,0.00027644774,0.00046059318,0.00045237705,0.000026557887,0.000036837908,0.0036058202],"genre_scores_gemma":[0.9697423,0.000039040446,0.026043802,0.00045909252,0.00024071297,0.000040163664,0.00014400925,0.000029027722,0.0032618563],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987476,0.000035607212,0.00038056966,0.00036110647,0.00010820747,0.00036694092],"domain_scores_gemma":[0.99914795,0.00004853033,0.00013240962,0.0005027754,0.00008680919,0.00008153645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030735217,0.00018223433,0.00018814857,0.000042115105,0.00009290281,0.000042573236,0.00034243366,0.00017562104,0.00034624583],"category_scores_gemma":[0.00013224414,0.00017005311,0.00014915799,0.0000647662,0.00006949004,0.000006799691,0.00013808503,0.00013070946,0.00031894722],"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":[0.00006574979,0.00025057676,0.016427524,0.00024229038,0.00010790312,0.000007707825,0.000946524,0.010993966,0.19167663,0.0014095037,0.0029065148,0.7749651],"study_design_scores_gemma":[0.00015241242,0.0008978129,0.00020480037,0.000049406564,0.000017269926,0.00004281657,0.0008098829,0.616946,0.32525393,0.00020341882,0.054998916,0.00042332173],"about_ca_topic_score_codex":0.000010669087,"about_ca_topic_score_gemma":0.0000083734385,"teacher_disagreement_score":0.7745418,"about_ca_system_score_codex":0.00001925193,"about_ca_system_score_gemma":0.000026061234,"threshold_uncertainty_score":0.6934565},"labels":[],"label_agreement":null},{"id":"W2968362167","doi":"10.1101/730481","title":"Augmenting protein network embeddings with sequence information","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Representation (politics); Computer science; Abstraction; Protein function prediction; Function (biology); Sequence (biology); Artificial intelligence; Task (project management); Simple (philosophy); Property (philosophy); Protein function; Key (lock); Machine learning; Natural language processing; Theoretical computer science; Computational biology; Biology","score_opus":0.006772824951950272,"score_gpt":0.21239656057523323,"score_spread":0.20562373562328295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2968362167","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9676764,0.0002262366,0.029340528,0.00010282274,0.0005622102,0.001572829,0.00009890271,0.000225077,0.00019500709],"genre_scores_gemma":[0.9471125,0.000043361757,0.051631425,0.00039507073,0.00050179503,0.00018795286,0.000009615785,0.00009183267,0.000026424297],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977356,0.00009000461,0.0005953239,0.0005336405,0.00041271097,0.00063272205],"domain_scores_gemma":[0.9971988,0.00001223466,0.00088624656,0.0012898162,0.00045508635,0.00015782038],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00068620424,0.0005509622,0.00038703324,0.00011362219,0.00017135673,0.00033170264,0.0006278965,0.0006244422,0.000019825246],"category_scores_gemma":[0.00022437354,0.00053696387,0.00010974743,0.00025228277,0.00009955943,0.00004641415,0.0007898482,0.00079369167,0.00011680414],"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":[0.0002686723,0.000089569505,0.036986258,0.003137629,0.0006226672,0.000015358197,0.000052813542,0.06549672,0.8891165,0.000928249,0.0032639185,0.00002162472],"study_design_scores_gemma":[0.003238463,0.0011890059,0.044713832,0.0043995585,0.00038493017,4.6780002e-7,0.00002611577,0.04543743,0.70179325,0.0000052827727,0.1931722,0.0056394655],"about_ca_topic_score_codex":0.00002478811,"about_ca_topic_score_gemma":0.0000016785428,"teacher_disagreement_score":0.18990828,"about_ca_system_score_codex":0.00010418663,"about_ca_system_score_gemma":0.0005764395,"threshold_uncertainty_score":0.9997082},"labels":[],"label_agreement":null},{"id":"W2970637111","doi":"10.32470/ccn.2019.1187-0","title":"An overview of functional alignment in artificial and biological neural networks: Current recommendations and open questions","year":2019,"lang":"en","type":"article","venue":"2019 Conference on Cognitive Computational Neuroscience","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Current (fluid); Computer science; Artificial neural network; Artificial intelligence; Machine learning; Engineering; Electrical engineering","score_opus":0.12237437434873742,"score_gpt":0.3921920490278917,"score_spread":0.26981767467915424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970637111","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97123444,0.0001757909,0.027234342,0.00039442515,0.00025390548,0.00041415254,0.00008224462,0.000005932783,0.0002047732],"genre_scores_gemma":[0.99834234,0.00041117318,0.00045686244,0.0005149598,0.000020127096,0.0000131984925,0.00022489383,0.0000037476484,0.000012712413],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910444,0.00014232578,0.00020991938,0.00030753633,0.00012001038,0.000115796865],"domain_scores_gemma":[0.999537,0.00009202121,0.00011046235,0.0000791028,0.00012307327,0.000058331603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002202002,0.000099930294,0.00011349581,0.00005612016,0.00007147841,0.0000720701,0.00014319352,0.000037923433,0.00002599914],"category_scores_gemma":[0.00013412695,0.000090995454,0.000014052592,0.00010307099,0.00017649026,0.000029099665,0.0001841155,0.000114131704,0.0000027472684],"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":[0.00077644567,0.0016395261,0.2731096,0.00011223569,0.000022553384,0.000002756115,0.0003601648,0.25153983,0.03987633,0.20659178,0.00041751046,0.22555125],"study_design_scores_gemma":[0.00040019647,0.0007777894,0.37912795,0.00009202089,0.0000034326033,0.000008951792,0.000056257428,0.6175635,0.00009637388,0.0015785426,0.00015284934,0.00014213583],"about_ca_topic_score_codex":0.000007588306,"about_ca_topic_score_gemma":0.000007117726,"teacher_disagreement_score":0.3660237,"about_ca_system_score_codex":0.0000053720496,"about_ca_system_score_gemma":0.00006524838,"threshold_uncertainty_score":0.3710687},"labels":[],"label_agreement":null},{"id":"W2970852745","doi":"10.1093/bioinformatics/btz645","title":"DeepCOP: deep learning-based approach to predict gene regulating effects of small molecules","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Deep learning; Computational biology; Computer science; Drug discovery; Artificial intelligence; Genomics; Gene expression; Gene; Gene regulatory network; Machine learning; Biology; Bioinformatics; Genetics; Genome","score_opus":0.00474345889461414,"score_gpt":0.20703925714135216,"score_spread":0.20229579824673802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970852745","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4867091,0.00012878966,0.5006805,0.000020042116,0.00017163607,0.00085527764,0.000008319858,0.000068398025,0.01135795],"genre_scores_gemma":[0.61102796,0.0000118136295,0.38771984,0.00036924696,0.00007508037,0.000030192938,0.0003555435,0.00004685642,0.0003635111],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834424,0.000069568174,0.0006554707,0.00021173392,0.0003176787,0.00040131365],"domain_scores_gemma":[0.9985818,0.00006467416,0.00040687792,0.0006394819,0.00014743237,0.00015970641],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034182513,0.00029268814,0.00032480436,0.00014791556,0.00007673653,0.00004110338,0.00042390372,0.00024329573,0.000008601799],"category_scores_gemma":[0.000546193,0.00027305345,0.00014983315,0.00022848559,0.000059277994,0.000010896588,0.00023529888,0.00021761503,0.000071792245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002286651,0.00026640197,0.028237294,0.00514508,0.00023363883,0.0000011993482,0.0021246127,0.8711361,0.07549017,0.00035054868,0.000614506,0.016171774],"study_design_scores_gemma":[0.0012401287,0.0010442331,0.0031315263,0.00011018724,0.000043563366,0.0000141305045,0.00021278048,0.8764609,0.11228821,0.0000073277497,0.0050021964,0.0004448168],"about_ca_topic_score_codex":0.0000065587774,"about_ca_topic_score_gemma":0.000001823317,"teacher_disagreement_score":0.124318846,"about_ca_system_score_codex":0.000024669444,"about_ca_system_score_gemma":0.00007934212,"threshold_uncertainty_score":0.99997216},"labels":[],"label_agreement":null},{"id":"W2973436233","doi":"10.1007/s11033-019-05076-z","title":"Possible synergistic effect of apoE and LRP1 genotypes on metabolic syndrome development in Serbian patients","year":2019,"lang":"en","type":"article","venue":"Molecular Biology Reports","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 British Columbia","funders":"Ministarstvo Prosvete, Nauke i Tehnološkog Razvoja","keywords":"Genotype; Metabolic syndrome; Apolipoprotein E; Internal medicine; Odds ratio; Disease; Biology; Genetics; Medicine; Bioinformatics; Gene; Obesity","score_opus":0.0018230247450800928,"score_gpt":0.22690469071226707,"score_spread":0.22508166596718698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2973436233","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9971227,0.00040248415,0.00018687389,0.000009001286,0.00020836177,0.00041133215,0.0000031246025,0.000009854837,0.0016462741],"genre_scores_gemma":[0.998547,0.000015196917,0.0009094466,0.00010187542,0.0000071675536,0.000022636508,0.00022185229,0.000021429989,0.00015336034],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99865407,0.00014341294,0.00046382222,0.00037041106,0.00011321855,0.0002550867],"domain_scores_gemma":[0.9991886,0.000022576125,0.00026032934,0.00042228357,0.000045981804,0.000060202325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040149206,0.00021523463,0.0003629278,0.00012612512,0.00002768724,0.000008048961,0.00010734742,0.00022292438,0.000010030553],"category_scores_gemma":[0.00023824432,0.00017989668,0.00005621699,0.00010027129,0.000068203764,0.000002915644,0.00014896962,0.00012913761,0.000010597748],"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":[0.000079401696,0.00007679894,0.80925876,0.00013022478,0.00010644121,0.000054093314,0.000051740615,0.00026087766,0.18760575,0.00014746835,0.000013554504,0.0022148762],"study_design_scores_gemma":[0.001258633,0.0020452,0.42492217,0.00009049652,0.000043261618,0.00021999308,0.0000053306558,0.00009888132,0.56508136,0.00009258289,0.0056618936,0.00048018713],"about_ca_topic_score_codex":0.000020652506,"about_ca_topic_score_gemma":0.000005421418,"teacher_disagreement_score":0.3843366,"about_ca_system_score_codex":0.00001194264,"about_ca_system_score_gemma":0.000052825424,"threshold_uncertainty_score":0.73359734},"labels":[],"label_agreement":null},{"id":"W2975621569","doi":"10.2210/pdb5tvl/pdb","title":"Crystal structure of foldase protein PrsA from Streptococcus pneumoniae str. Canada MDR_19A","year":2016,"lang":"en","type":"paratext","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Foldase; Streptococcus pneumoniae; Bacterial protein; GroEL; Biology; Genetics; Bacteria; Gene","score_opus":0.0032605101786166127,"score_gpt":0.21709118318600895,"score_spread":0.21383067300739234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2975621569","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8666667,0.00131288,0.0016048817,0.00031505647,0.0019211513,0.002483738,0.027093498,0.000033529515,0.0985686],"genre_scores_gemma":[0.80696213,0.000072862014,0.0016786541,0.00022887024,0.0010923829,0.000044924684,0.009022975,0.00012180958,0.18077537],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99776185,0.00009928942,0.0007070915,0.0005328051,0.0004522613,0.00044670855],"domain_scores_gemma":[0.9978605,0.000027211054,0.00070676254,0.0010180624,0.00020907166,0.00017840297],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000056985667,0.00056465506,0.0005516803,0.00005706149,0.000067516856,0.000035421504,0.00067010673,0.00076379784,0.004758567],"category_scores_gemma":[0.00012370732,0.00042096598,0.00015676975,0.00006668693,0.00010539477,0.000004581971,0.00036537938,0.0004307846,0.0000610536],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037555623,0.000018301736,0.0003163791,0.00025296942,0.00025051698,0.0000031252957,0.000018088575,0.00008153038,0.70897377,0.000011156401,0.28919917,0.000837453],"study_design_scores_gemma":[0.00061936,0.00023166103,0.00016826585,0.00022423544,0.000042222917,0.0000032631563,0.000039393562,0.00006383681,0.42972264,0.000025615767,0.5682221,0.00063740363],"about_ca_topic_score_codex":0.11361843,"about_ca_topic_score_gemma":0.22729461,"teacher_disagreement_score":0.2792511,"about_ca_system_score_codex":0.00008358844,"about_ca_system_score_gemma":0.0018181296,"threshold_uncertainty_score":0.9998242},"labels":[],"label_agreement":null},{"id":"W2983914065","doi":"10.7554/elife.40889.026","title":"Decision letter: Insights into the key determinants of membrane protein topology enable the identification of new monotopic folds","year":2018,"lang":"en","type":"peer-review","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Membrane protein; Integral membrane protein; Lipid bilayer; Membrane topology; Peripheral membrane protein; Transmembrane protein; Membrane; Topology (electrical circuits); Computational biology; Structural biology; Bilayer; Biology; Chemistry; Biochemistry; Mathematics","score_opus":0.013225920850683618,"score_gpt":0.2996054694170814,"score_spread":0.28637954856639775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2983914065","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7345252,0.112531714,0.030495388,0.066313244,0.010687704,0.015219384,0.00012127963,0.00009714039,0.030008916],"genre_scores_gemma":[0.22150409,0.022653645,0.011673333,0.009515277,0.0030053728,0.00038116702,0.0013468736,0.00016288347,0.72975737],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99789923,0.0001764314,0.0011048313,0.00029458295,0.00033641476,0.00018848333],"domain_scores_gemma":[0.9970902,0.000061898754,0.0010947374,0.0014129783,0.00030100645,0.000039164886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007395699,0.00026215194,0.00045548225,0.00006034155,0.00010312451,0.00002051999,0.0010775502,0.00040096798,0.00018017531],"category_scores_gemma":[0.0007689184,0.00013845687,0.00018964554,0.00013295304,0.00026157367,0.0000054523885,0.000406426,0.0002292829,0.00002362738],"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":[0.00006601614,0.00005939631,0.000093190305,0.00326314,0.00015520545,8.5080336e-7,0.00084634376,0.00002275072,0.082499616,0.00023010651,0.86508536,0.04767803],"study_design_scores_gemma":[0.00014694367,0.00016429657,0.00003674466,0.00042228829,0.00007001933,0.0000050860053,0.00001319722,0.00021262384,0.24296105,0.00032696006,0.75551444,0.00012638117],"about_ca_topic_score_codex":0.0007335818,"about_ca_topic_score_gemma":0.00092102296,"teacher_disagreement_score":0.69974846,"about_ca_system_score_codex":0.000013890238,"about_ca_system_score_gemma":0.0001983249,"threshold_uncertainty_score":0.5646108},"labels":[],"label_agreement":null},{"id":"W2998018748","doi":"10.1186/s12859-019-3278-3","title":"IILLS: predicting virus-receptor interactions based on similarity and semi-supervised learning","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Similarity (geometry); Computational biology; Artificial intelligence; Computer science; Cross-validation; Virus; Pattern recognition (psychology); Machine learning; Biology; Virology","score_opus":0.008804090554234723,"score_gpt":0.24521196154674885,"score_spread":0.23640787099251412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998018748","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89966476,0.00005409099,0.06258327,0.00016085753,0.0006212471,0.0007479401,0.00008679169,0.00018416544,0.035896856],"genre_scores_gemma":[0.84919703,0.00007033173,0.14566034,0.0018229854,0.00026875772,0.000030453239,0.00093389803,0.00007214793,0.0019440454],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863905,0.00007615012,0.0004961925,0.00020473603,0.00025898774,0.00032490084],"domain_scores_gemma":[0.99895,0.00012627721,0.000258362,0.0004447194,0.00008844717,0.00013218539],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040487124,0.000266674,0.00021513915,0.000117330674,0.00019952709,0.00010983784,0.00021045026,0.000198156,0.0001795789],"category_scores_gemma":[0.0005544544,0.00024737124,0.0001031425,0.00012853423,0.00006371483,0.000033499877,0.00017961292,0.00047541512,0.00022292773],"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":[0.000718553,0.00036962665,0.6636577,0.0024583684,0.00022181464,0.0000011416018,0.0032066896,0.26881662,0.035384506,0.0003060511,0.008844152,0.016014757],"study_design_scores_gemma":[0.0008561931,0.0004513575,0.0023981044,0.000094812334,0.000018516279,0.000008789023,0.0006116431,0.9441281,0.0033743011,0.0000034078516,0.047747627,0.00030713007],"about_ca_topic_score_codex":0.000010808764,"about_ca_topic_score_gemma":0.000018411583,"teacher_disagreement_score":0.6753115,"about_ca_system_score_codex":0.000030278516,"about_ca_system_score_gemma":0.00008918598,"threshold_uncertainty_score":0.99999785},"labels":[],"label_agreement":null},{"id":"W3000015309","doi":"10.1371/journal.pone.0227683","title":"TranCEP: Predicting the substrate class of transmembrane transport proteins using compositional, evolutionary, and positional information","year":2020,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Concordia University","funders":"","keywords":"Transmembrane protein; Proteome; Computational biology; Transmembrane domain; Membrane protein; Transport protein; Membrane transport protein; Biology; Genome; Protein sequencing; Membrane; Substrate specificity; Membrane transport; Amino acid; Peptide sequence; Biochemistry; Biophysics; Gene; Enzyme","score_opus":0.02103729878029415,"score_gpt":0.21290977955207557,"score_spread":0.19187248077178143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000015309","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9901994,0.00012929986,0.00719389,0.0014332836,0.000008231086,0.00035455462,0.0001631196,0.00001507109,0.0005031774],"genre_scores_gemma":[0.98916084,0.00003940717,0.009799414,0.00038948463,0.000087128705,0.000012452461,0.0004989808,0.0000075313606,0.000004785761],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99921846,0.000031767577,0.00029827445,0.000091059876,0.000252229,0.00010821365],"domain_scores_gemma":[0.9996215,0.000012122474,0.00012483174,0.000088289555,0.00010175253,0.00005149786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000942541,0.00009628537,0.00011750326,0.000019317627,0.00011455553,0.000011101489,0.000098115066,0.000073525094,0.000017632152],"category_scores_gemma":[0.000021418033,0.00008313266,0.000042549294,0.00007464589,0.00011018839,0.000026159369,0.000013392247,0.00013148996,0.0000013216169],"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":[0.00029726917,0.00019518156,0.016720047,0.00074297626,0.00023977441,4.9660366e-7,0.0012625917,0.0046919407,0.975311,0.00043468966,0.000026144746,0.000077908975],"study_design_scores_gemma":[0.0026397516,0.0012646783,0.13399754,0.00041138593,0.00041710143,0.000059727514,0.00044240145,0.364687,0.4946847,0.00009441998,0.00076931005,0.00053197175],"about_ca_topic_score_codex":0.000009220408,"about_ca_topic_score_gemma":0.000001881497,"teacher_disagreement_score":0.48062629,"about_ca_system_score_codex":0.000006520765,"about_ca_system_score_gemma":0.000059434806,"threshold_uncertainty_score":0.33900514},"labels":[],"label_agreement":null},{"id":"W3000297642","doi":"10.1016/j.jtbi.2020.110172","title":"Identification of potential therapeutic targets in Neisseria gonorrhoeae by an in-silico approach","year":2020,"lang":"en","type":"article","venue":"Journal of Theoretical Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Deutscher Akademischer Austauschdienst; University Grants Commission","keywords":"Neisseria gonorrhoeae; In silico; Identification (biology); Computational biology; Biology; Microbiology; Ecology; Genetics","score_opus":0.005773743987130411,"score_gpt":0.26106425754155,"score_spread":0.25529051355441956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000297642","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9569008,0.000763802,0.041011535,0.00077186886,0.00011207208,0.00011096127,0.000013292757,0.0000028608802,0.0003128554],"genre_scores_gemma":[0.9982897,0.0000939249,0.0010875873,0.0003538916,0.00009758223,0.0000016087645,0.000062470746,0.000010024792,0.000003200908],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986539,0.00028092097,0.0007094975,0.00014028451,0.0000462562,0.00016914771],"domain_scores_gemma":[0.9993254,0.000021702785,0.0003528283,0.00014688444,0.00006932677,0.00008387052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059572665,0.000108668915,0.00025472557,0.00006547867,0.000012404896,0.000009873895,0.0003375719,0.00020289866,0.000037162987],"category_scores_gemma":[0.000306196,0.00008711377,0.000079396144,0.00010811305,0.00024974305,0.000008326595,0.000060412975,0.00026219856,0.0000019692877],"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":[0.0004605156,0.00016307905,0.006698459,0.000027806509,0.00002848699,6.304909e-7,0.00021818932,0.0007272408,0.976724,0.012900961,0.0000673095,0.0019832717],"study_design_scores_gemma":[0.009228059,0.013517424,0.036237426,0.00006611375,0.00019014701,0.0004184694,0.002137864,0.19209614,0.69052607,0.045245886,0.00894907,0.001387357],"about_ca_topic_score_codex":0.0000017345074,"about_ca_topic_score_gemma":6.8161717e-7,"teacher_disagreement_score":0.28619802,"about_ca_system_score_codex":0.000010602289,"about_ca_system_score_gemma":0.00004081899,"threshold_uncertainty_score":0.35523963},"labels":[],"label_agreement":null},{"id":"W3000887590","doi":"10.1016/j.ygeno.2020.01.017","title":"Using extreme gradient boosting to identify origin of replication in Saccharomyces cerevisiae via hybrid features","year":2020,"lang":"en","type":"article","venue":"Genomics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Artificial Intelligence in Medicine (Canada)","funders":"Taipei Medical University; Nvidia","keywords":"Biology; Computational biology; Replication (statistics); DNA replication; Boosting (machine learning); Benchmark (surveying); Mechanism (biology); DNA sequencing; Computer science; Gene; Artificial intelligence; Genetics; Machine learning","score_opus":0.048074391897773565,"score_gpt":0.32139510699012147,"score_spread":0.2733207150923479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000887590","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9853471,0.00026410737,0.0135368705,0.0003087102,0.00005855004,0.000213119,0.000014212281,0.000009840043,0.00024749953],"genre_scores_gemma":[0.9754417,0.000040462546,0.023785438,0.00048197422,0.00013671801,0.0000039085803,0.00007182146,0.00001790481,0.00002005706],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991421,0.00003107961,0.00032365194,0.0002594588,0.00008350552,0.00016016587],"domain_scores_gemma":[0.99935514,0.000008574861,0.00017489355,0.00034552754,0.000042527474,0.00007331333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020328545,0.00011020557,0.00014356032,0.000045648772,0.0000340454,0.000020453346,0.00021254369,0.00005286279,0.0000065951676],"category_scores_gemma":[0.00022967634,0.00011858116,0.000047814257,0.00010731574,0.000018002249,0.000004632918,0.0001540151,0.0000979196,0.0000071598206],"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":[0.00003789021,0.000011377738,0.010464298,0.00007778945,0.000014677005,0.0000012592594,0.00043195515,0.006727339,0.97673595,0.00004391272,0.00036443002,0.005089152],"study_design_scores_gemma":[0.00082116935,0.0003753898,0.04065541,0.00009498818,0.000047696278,0.00007396486,0.00029545915,0.0451866,0.8579391,0.00013576672,0.053710878,0.0006635462],"about_ca_topic_score_codex":0.000045534085,"about_ca_topic_score_gemma":0.00001097127,"teacher_disagreement_score":0.11879679,"about_ca_system_score_codex":0.00003388618,"about_ca_system_score_gemma":0.000038862257,"threshold_uncertainty_score":0.48355994},"labels":[],"label_agreement":null},{"id":"W3003386370","doi":"10.1101/2020.02.02.919944","title":"Metabolic pathway inference using multi-label classification with rich pathway features","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; Compute Canada; Genome Canada","keywords":"Inference; Computer science; Computational biology; Genome; Artificial intelligence; Population; Machine learning; Metabolic pathway; Biology; Gene; Genetics","score_opus":0.029574166973793635,"score_gpt":0.262496035896684,"score_spread":0.23292186892289038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003386370","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93852663,0.0018863253,0.057248086,0.00019241485,0.00054206623,0.00095054304,0.0003447803,0.00027269198,0.00003646387],"genre_scores_gemma":[0.8848136,0.0002290803,0.11385409,0.00036136745,0.00045695878,0.000106905085,0.00000971192,0.0001561693,0.000012136069],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9970918,0.00021071469,0.00059764157,0.0010878517,0.00044525234,0.0005667114],"domain_scores_gemma":[0.9967424,0.000027734362,0.00080219924,0.0015184209,0.0006001426,0.00030907686],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039660418,0.0007625916,0.0006015114,0.00016361474,0.00021819536,0.00027412229,0.0008172261,0.00085167965,0.0000103799075],"category_scores_gemma":[0.0005875747,0.0007156634,0.00012185597,0.00041524868,0.00017095408,0.000021149453,0.0007654506,0.0011351319,0.000030927982],"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":[0.000059684175,0.00013006327,0.010049849,0.0003275199,0.00023491665,0.00001239262,0.000024817755,0.00039764814,0.98814607,0.000530165,0.00006889761,0.000017980388],"study_design_scores_gemma":[0.0014100685,0.00022866389,0.10463992,0.00032228,0.00021589005,1.9067838e-7,0.000013322732,0.029882247,0.85121894,0.0000013070636,0.0103503335,0.001716841],"about_ca_topic_score_codex":0.00003916847,"about_ca_topic_score_gemma":0.000007428007,"teacher_disagreement_score":0.13692713,"about_ca_system_score_codex":0.0000797242,"about_ca_system_score_gemma":0.0011261854,"threshold_uncertainty_score":0.9995294},"labels":[],"label_agreement":null},{"id":"W3004509766","doi":"10.1109/bibm47256.2019.8983020","title":"Ontology-based transporter substrate annotation for benchmark datasets","year":2019,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Concordia University","funders":"","keywords":"Benchmark (surveying); Computer science; Annotation; Class (philosophy); Ontology; Process (computing); Automation; Artificial intelligence; Gene ontology; Substrate (aquarium); Data mining; Machine learning; Information retrieval; Programming language; Chemistry; Engineering; Biology","score_opus":0.005737852420947691,"score_gpt":0.25377078275191284,"score_spread":0.24803293033096516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004509766","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9493818,0.00003091421,0.042841226,0.00031239077,0.00018120577,0.0005014437,0.00032133007,0.000023611845,0.006406046],"genre_scores_gemma":[0.9678769,0.0000026942835,0.017945083,0.0010975696,0.000045200846,0.000021533002,0.012282871,0.000011942867,0.0007162132],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99941343,0.000014200189,0.00017530168,0.00017170672,0.000063066254,0.00016231569],"domain_scores_gemma":[0.99956244,0.000014412829,0.00006544698,0.00028295477,0.000038165366,0.00003657333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013949674,0.000100308316,0.000089624926,0.000024882875,0.000029745413,0.000013468437,0.000120670455,0.00010948931,0.00018476602],"category_scores_gemma":[0.000019736552,0.000088514375,0.000057016045,0.000029736022,0.000021590775,0.0000041423095,0.000008298057,0.00005002434,0.000036962472],"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":[0.0014890151,0.00034366729,0.26398557,0.00094777276,0.00026910368,0.0000038621456,0.00025683257,0.0105166845,0.60228366,0.004205581,0.10510673,0.0105915535],"study_design_scores_gemma":[0.005757905,0.0019426225,0.090535425,0.0000311359,0.00008010171,0.000015262893,0.000119870885,0.06458143,0.2200582,0.0002479147,0.615667,0.00096310844],"about_ca_topic_score_codex":0.000008381439,"about_ca_topic_score_gemma":0.000057258865,"teacher_disagreement_score":0.5105603,"about_ca_system_score_codex":0.000004096194,"about_ca_system_score_gemma":0.000041403524,"threshold_uncertainty_score":0.36095113},"labels":[],"label_agreement":null},{"id":"W3006920220","doi":"10.1109/icmla.2019.00259","title":"Convolutional Classification of Pathogenicity in H5 Avian Influenza Strains","year":2019,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Pathogenicity; Convolutional neural network; Outbreak; Biology; Influenza A virus subtype H5N1; Pathogenicity island; Computational biology; Genome; Genetics; Artificial intelligence; Virology; Computer science; Gene; Microbiology; Virus","score_opus":0.012518210179213092,"score_gpt":0.27229853210327987,"score_spread":0.25978032192406675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006920220","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9856185,0.000024095238,0.0012198857,0.000036024874,0.000040001793,0.000121163925,0.000011102081,0.000005761931,0.012923473],"genre_scores_gemma":[0.99729234,0.000004896628,0.0019923805,0.00019769932,0.000019461399,0.0000032628213,0.000087394044,0.000005277781,0.0003972705],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99943626,0.000028658305,0.0002305322,0.0001089878,0.0000950476,0.00010053271],"domain_scores_gemma":[0.9996232,0.0000066256644,0.000090176036,0.0002066898,0.000049143375,0.000024173867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016694146,0.00006405736,0.000078733196,0.000037087248,0.00001002929,0.0000042506167,0.00010663615,0.00010060115,0.00011185427],"category_scores_gemma":[0.000054798995,0.000060363338,0.00003687412,0.000059245176,0.00003625232,0.000003146681,0.000042515083,0.000074445714,0.0000314359],"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":[0.00001432993,0.000038501305,0.5515071,0.0000293646,0.000009169659,1.2956959e-7,0.00007806452,0.0004549003,0.4441408,0.0029830704,0.000096213495,0.00064834865],"study_design_scores_gemma":[0.0006843175,0.00014772704,0.96866846,0.000010827155,0.0000034716302,0.000006184384,0.00031237357,0.0099402685,0.014488708,0.00007149563,0.0055270554,0.00013908766],"about_ca_topic_score_codex":0.00003472639,"about_ca_topic_score_gemma":0.00006222035,"teacher_disagreement_score":0.42965207,"about_ca_system_score_codex":0.000010769843,"about_ca_system_score_gemma":0.00006115062,"threshold_uncertainty_score":0.24615456},"labels":[],"label_agreement":null},{"id":"W3012532670","doi":"10.1186/s12859-020-3345-9","title":"Prediction of tumor location in prostate cancer tissue using a machine learning system on gene expression data","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; University of Windsor","keywords":"Laterality; Prostate cancer; Prostate; Gene; Human leukocyte antigen; Computational biology; DNA microarray; Cancer; Gene expression; Biology; Artificial intelligence; Computer science; Genetics; Neuroscience; Antigen","score_opus":0.041854032633337535,"score_gpt":0.2834448822248406,"score_spread":0.24159084959150307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012532670","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77820426,0.00064055476,0.21815516,0.0000862745,0.00027287455,0.0011755979,0.0007173828,0.00011101708,0.00063687196],"genre_scores_gemma":[0.8654811,0.00008133482,0.1322898,0.00013483486,0.00015464587,0.000017431757,0.0017741257,0.000034173947,0.000032576478],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986051,0.00007184102,0.0006810094,0.0001922547,0.00025148838,0.00019831704],"domain_scores_gemma":[0.99886525,0.000016585587,0.00049078173,0.0004580094,0.00008976797,0.000079593905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032034627,0.00018008283,0.00021087761,0.00007951256,0.00006755008,0.000026250998,0.00032951517,0.00009401711,0.000006091477],"category_scores_gemma":[0.00029717217,0.00016317677,0.000025370531,0.00023547998,0.00003770146,0.000035792968,0.00030358374,0.00021219908,0.000008807802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006680471,0.00008924527,0.079197735,0.0057207765,0.00004712653,0.0000031216807,0.002644676,0.6845847,0.2231278,0.000040985047,0.000491725,0.0033840772],"study_design_scores_gemma":[0.0006417696,0.00036721822,0.00054564496,0.00029118574,0.000017609003,0.000012707452,0.0004714555,0.92153305,0.074187644,4.307297e-7,0.0017953283,0.00013594546],"about_ca_topic_score_codex":0.00006580559,"about_ca_topic_score_gemma":0.000020487787,"teacher_disagreement_score":0.23694837,"about_ca_system_score_codex":0.00004392649,"about_ca_system_score_gemma":0.00014385919,"threshold_uncertainty_score":0.6654155},"labels":[],"label_agreement":null},{"id":"W3016163695","doi":"10.1007/978-3-030-44094-7_18","title":"Classification of Autism Genes Using Network Science and Linear Genetic Programming","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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; Memorial University of Newfoundland","funders":"","keywords":"Autism; Computer science; Set (abstract data type); Genetic programming; Autism spectrum disorder; Genetic network; Machine learning; Biological network; Gene regulatory network; Artificial intelligence; Gene; Computational biology; Biology; Genetics; Medicine; Psychiatry","score_opus":0.01780806667127422,"score_gpt":0.2655374994877649,"score_spread":0.24772943281649068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016163695","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":[0.012347986,0.00087989133,0.9855792,0.00015941111,0.00032046484,0.00029210458,0.0000026918085,0.000015965346,0.00040226546],"genre_scores_gemma":[0.3980367,0.00006944704,0.6013154,0.0002040565,0.0003267591,0.0000018060596,0.000008089486,0.000019428797,0.000018362374],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824333,0.0000149072,0.00034911174,0.0005998337,0.0004892101,0.00030359137],"domain_scores_gemma":[0.99892473,0.00002673321,0.00030262105,0.00043168018,0.00021452969,0.00009970721],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055398635,0.00022677999,0.00022466804,0.00016054563,0.00018426558,0.00009477712,0.00065829314,0.00019650179,0.000002115308],"category_scores_gemma":[0.000148081,0.00021535644,0.000037732636,0.00032358416,0.0015050041,0.000012743473,0.00066605094,0.0002665528,0.0000011143284],"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":[0.000016492004,0.000012847197,0.0018795043,0.00020431234,0.000016813045,0.0000056007793,0.00032898673,0.14945504,0.0821964,0.0017384406,0.0000063131984,0.76413924],"study_design_scores_gemma":[0.00012670267,0.00023266667,0.0015447813,0.000170622,0.00001625389,0.000051071554,4.0890913e-7,0.9882294,0.004802434,0.0019144783,0.0025738473,0.0003373563],"about_ca_topic_score_codex":0.000006096291,"about_ca_topic_score_gemma":0.000009413443,"teacher_disagreement_score":0.8387743,"about_ca_system_score_codex":0.000048522033,"about_ca_system_score_gemma":0.00055906497,"threshold_uncertainty_score":0.8781981},"labels":[],"label_agreement":null},{"id":"W3019119825","doi":"10.1371/journal.pone.0232391","title":"Machine learning using intrinsic genomic signatures for rapid classification of novel pathogens: COVID-19 case study","year":2020,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1034,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Computational biology; Genomics; Biology; Novel virus; Virus classification; Decision tree; Virus; Artificial intelligence; Computer science; Genetics; Gene","score_opus":0.10247101244067092,"score_gpt":0.3021214621668543,"score_spread":0.1996504497261834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3019119825","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97535276,0.0003748089,0.02315808,0.00019154097,0.000016821523,0.000766188,0.000074569034,0.000027936654,0.000037269845],"genre_scores_gemma":[0.97559077,0.000030513856,0.023489252,0.00046539062,0.0001508555,0.00002457219,0.0001993678,0.00003090173,0.000018368133],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990098,0.00008072358,0.00034578648,0.0002525281,0.0001536251,0.0001575462],"domain_scores_gemma":[0.9991982,0.000054190117,0.0002853336,0.00022297124,0.00011416816,0.00012513793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028596935,0.0001474307,0.00023128849,0.00005011852,0.00013150086,0.000017921955,0.00015015299,0.00011292388,0.000017457156],"category_scores_gemma":[0.0013310924,0.00014898168,0.00006521791,0.000103688304,0.000040644227,0.000004598138,0.00011884651,0.00019108651,0.0000013589449],"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":[0.00017312745,0.00087768445,0.009383263,0.00035905204,0.00024195238,0.000010865854,0.0011100016,0.0049922457,0.9822176,0.000017859193,0.000020928428,0.0005953898],"study_design_scores_gemma":[0.0061573037,0.0051018232,0.0015444397,0.000044796896,0.0007294671,0.00013266208,0.004115591,0.88798535,0.090813585,0.000008093859,0.0026537369,0.00071313354],"about_ca_topic_score_codex":0.00004330067,"about_ca_topic_score_gemma":0.000014235043,"teacher_disagreement_score":0.89140403,"about_ca_system_score_codex":0.000026958965,"about_ca_system_score_gemma":0.00010298874,"threshold_uncertainty_score":0.6075297},"labels":[],"label_agreement":null},{"id":"W3020323696","doi":"10.1186/s12859-019-3311-6","title":"TooT-T: discrimination of transport proteins from non-transport proteins","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; King Saud University; Saudi Arabian Cultural Bureau; Genome Canada","keywords":"Computational biology; Classifier (UML); Membrane protein; Membrane transport protein; Protein function prediction; Computer science; Function (biology); Protein sequencing; Transport protein; Protein function; Artificial intelligence; Machine learning; Membrane; Bioinformatics; Chemistry; Biology; Peptide sequence; Biochemistry; Genetics; Gene","score_opus":0.014126327398125518,"score_gpt":0.2362567035197294,"score_spread":0.22213037612160388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3020323696","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":[0.31800786,0.000051896244,0.6723864,0.0002702119,0.00013243298,0.0012746176,0.00035701334,0.000063681015,0.0074558696],"genre_scores_gemma":[0.67170084,0.00003936114,0.32540527,0.00048832747,0.00023839848,0.000053832726,0.0018831656,0.000039682745,0.0001511163],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981178,0.0000243749,0.000945591,0.00020982506,0.00040481283,0.00029759848],"domain_scores_gemma":[0.9987331,0.000013934032,0.00045835922,0.00047997132,0.0001359935,0.0001786249],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019374608,0.000296921,0.00033645588,0.00005701087,0.00007805634,0.000017542801,0.0004401636,0.00026390605,0.00006526803],"category_scores_gemma":[0.00013639554,0.00027040442,0.00019657185,0.0001910599,0.0001222129,0.000037669924,0.00007201303,0.00022289918,0.000043569526],"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":[0.0034611726,0.0017233787,0.4227405,0.024563117,0.0014054633,0.000026405978,0.08017759,0.055994544,0.36560264,0.0027713487,0.010253275,0.03128059],"study_design_scores_gemma":[0.005233729,0.0029300656,0.10443992,0.0004957676,0.00038156196,0.000019623825,0.00344313,0.5330232,0.294866,0.00014866289,0.05295897,0.0020593854],"about_ca_topic_score_codex":0.00006774094,"about_ca_topic_score_gemma":0.00009524088,"teacher_disagreement_score":0.47702864,"about_ca_system_score_codex":0.00001456324,"about_ca_system_score_gemma":0.00020105112,"threshold_uncertainty_score":0.9999748},"labels":[],"label_agreement":null},{"id":"W3035506638","doi":"10.21203/rs.3.rs-120780/v1","title":"AMPlify: attentive deep learning model for discovery of novel antimicrobial peptides effective against WHO priority pathogens","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 British Columbia; BC Cancer Agency; University of Victoria; Canada's Michael Smith Genome Sciences Centre","funders":"National Institutes of Health; British Columbia Centre for Disease Control; Genome British Columbia; Genome Canada","keywords":"Antimicrobial; Drug discovery; Antimicrobial peptides; Computational biology; Deep learning; Computer science; Artificial intelligence; Chemistry; Biology; Data science; Microbiology; Bioinformatics","score_opus":0.03668465973951013,"score_gpt":0.36085030294056136,"score_spread":0.32416564320105123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035506638","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66297734,0.00022620385,0.33186334,0.00015212099,0.00010842717,0.002612403,0.0014731743,0.00003307738,0.00055390317],"genre_scores_gemma":[0.9804084,0.00048963656,0.014493045,0.00006275816,0.0003820455,0.00026981527,0.0033563646,0.000097827266,0.0004401425],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969454,0.00039019273,0.000534773,0.00083853846,0.0006022916,0.00068882195],"domain_scores_gemma":[0.9975666,0.00026598797,0.00040772575,0.0006665959,0.0009378192,0.00015529539],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001362734,0.00041803715,0.00062037056,0.0001851086,0.00028406843,0.0001653572,0.00066736573,0.00069400936,0.0000014601276],"category_scores_gemma":[0.003036994,0.00041650137,0.00046590727,0.00017399176,0.00032123795,0.000014634645,0.0025740068,0.0019566708,0.000004578482],"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":[0.0010485379,0.00037396757,0.009073558,0.008772915,0.00059102615,0.0000052108744,0.0029378983,0.24051395,0.7302511,0.00030421987,0.001154962,0.0049726693],"study_design_scores_gemma":[0.0016915172,0.0009820481,0.003796914,0.0011159782,0.000073910865,0.0000038359753,0.0005811735,0.9430929,0.046318654,0.00016846666,0.0014164167,0.00075820094],"about_ca_topic_score_codex":0.000041822957,"about_ca_topic_score_gemma":0.000035241123,"teacher_disagreement_score":0.70257896,"about_ca_system_score_codex":0.00011095755,"about_ca_system_score_gemma":0.00046317303,"threshold_uncertainty_score":0.9998287},"labels":[],"label_agreement":null},{"id":"W3037787710","doi":"10.1002/minf.202000033","title":"Using Language Representation Learning Approach to Efficiently Identify Protein Complex Categories in Electron Transport Chain","year":2020,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Feature learning; Representation (politics); Word embedding; Natural language processing; Machine learning; Feature (linguistics); Pattern recognition (psychology); Support vector machine; Categorization; Multi-task learning; Embedding; Task (project management)","score_opus":0.02120448430788708,"score_gpt":0.3007711008899546,"score_spread":0.27956661658206755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037787710","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6733504,0.000030320154,0.32294935,0.00006135764,0.00001254293,0.00051046564,0.000004257813,0.000033848366,0.0030474744],"genre_scores_gemma":[0.9486059,0.0000026239723,0.049884044,0.0007838116,0.000036255566,0.000029811677,0.0005861628,0.000032819808,0.000038563758],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838984,0.00008886103,0.00061719643,0.00019247147,0.0003327182,0.00037892922],"domain_scores_gemma":[0.99931616,0.000004847772,0.00020222514,0.0002748138,0.000063526015,0.00013842569],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029851095,0.00022596706,0.00023164596,0.00012015055,0.000086458225,0.00006326551,0.0002883544,0.0001357568,0.0000059565227],"category_scores_gemma":[0.00022967682,0.00024213945,0.000084631974,0.0004651608,0.000041355455,0.00002048597,0.00012065695,0.00031684394,0.00001798744],"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":[0.00006707812,0.00003906804,0.0015075698,0.00023999679,0.000027696986,0.000005851279,0.009521412,0.4426733,0.5452502,0.00021636025,0.0000331042,0.000418402],"study_design_scores_gemma":[0.0013500411,0.00049335166,0.0020688619,0.00005008744,0.000037541708,0.00003415267,0.005199778,0.6635243,0.32233885,0.000013975771,0.004122808,0.0007662158],"about_ca_topic_score_codex":0.00004652137,"about_ca_topic_score_gemma":0.000006649594,"teacher_disagreement_score":0.27525553,"about_ca_system_score_codex":0.000036916626,"about_ca_system_score_gemma":0.0000666849,"threshold_uncertainty_score":0.987416},"labels":[],"label_agreement":null},{"id":"W3042645205","doi":"10.1093/bioinformatics/btaa442","title":"AITL: Adversarial Inductive Transfer Learning with input and output space adaptation for pharmacogenomics","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"University of British Columbia; Simon Fraser University","funders":"Canadian Institutes of Health Research; Terry Fox Foundation; Canada Foundation for Innovation","keywords":"Pharmacogenomics; Adaptation (eye); Adversarial system; Computer science; Transfer of learning; Space (punctuation); Artificial intelligence; Machine learning; Biology; Bioinformatics; Neuroscience","score_opus":0.01805784941033034,"score_gpt":0.23809088593746033,"score_spread":0.22003303652713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042645205","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34250003,0.00006464646,0.6539189,0.0007347241,0.00013788608,0.00078800705,0.00007564621,0.00006215831,0.0017180117],"genre_scores_gemma":[0.8534362,0.00011092167,0.1441498,0.0012110738,0.00042021775,0.000032657048,0.00040984293,0.000047862122,0.00018144652],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912995,0.000026595844,0.00030625716,0.00016025227,0.00014385575,0.00023305889],"domain_scores_gemma":[0.99948585,0.000027506108,0.000121794175,0.00011477664,0.00010643796,0.00014364187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015202316,0.00020755,0.00017801659,0.000038049413,0.00013795192,0.000057073532,0.000125526,0.00013957167,0.0000041663698],"category_scores_gemma":[0.00015036383,0.00018346935,0.000054129952,0.00008048737,0.00008062366,0.00002949844,0.000061654646,0.00020176028,0.000008382663],"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":[0.014192301,0.00034677674,0.015454873,0.005804185,0.002868255,0.000011734436,0.1771482,0.27384144,0.13101536,0.006421468,0.015631976,0.35726342],"study_design_scores_gemma":[0.0049012955,0.0024941296,0.00018510732,0.000030002484,0.00016338578,0.000022104605,0.0050286725,0.6784739,0.023122868,0.000016745118,0.28488937,0.0006724075],"about_ca_topic_score_codex":0.0000052110695,"about_ca_topic_score_gemma":0.0000042719066,"teacher_disagreement_score":0.51093614,"about_ca_system_score_codex":0.000014244027,"about_ca_system_score_gemma":0.0000965688,"threshold_uncertainty_score":0.7481663},"labels":[],"label_agreement":null},{"id":"W3043520506","doi":"10.1038/s41597-020-00589-w","title":"Author Correction: COVID-19 Disease Map, building a computational repository of SARS-CoV-2 virus-host interaction mechanisms","year":2020,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Ontario Institute for Cancer Research","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Host (biology); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Computer science; Virology; Virus; Computational biology; Biology; Disease; Medicine; Infectious disease (medical specialty); Ecology; Outbreak","score_opus":0.04901385862372627,"score_gpt":0.3529667561876381,"score_spread":0.30395289756391186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043520506","genre_codex":"methods","genre_gemma":"dataset","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":[0.00056845683,0.0010523932,0.61778426,0.003686065,0.34836352,0.0012978148,0.021265823,0.00023412498,0.0057475325],"genre_scores_gemma":[0.01640848,0.00005273284,0.061541468,0.003267802,0.0053132838,0.0000681806,0.5852589,0.00023233815,0.3278568],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973083,0.00016247082,0.0006232425,0.0010425702,0.0006262175,0.00023720539],"domain_scores_gemma":[0.99700296,0.000040196108,0.0007551579,0.0017747902,0.00019869751,0.00022818777],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00075209385,0.00029363495,0.00027925847,0.00017934182,0.0004230351,0.00032242475,0.001437084,0.0002959384,0.00004142986],"category_scores_gemma":[0.0016551043,0.00031058514,0.00012542967,0.00026799805,0.00028580162,0.000032172542,0.0016012368,0.00058221736,0.00004862581],"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":[0.00009862504,0.000049604638,0.000007277197,0.0004333097,0.000074898766,0.000010347117,0.00008390054,0.0007474326,0.050792396,0.00009715984,0.94744927,0.00015579916],"study_design_scores_gemma":[0.00015675231,0.00006969447,0.000022710485,0.00011517767,0.00008719499,0.000027963139,0.000057454134,0.099683374,0.0067922766,0.00015181975,0.8925568,0.00027879604],"about_ca_topic_score_codex":0.00006589258,"about_ca_topic_score_gemma":0.00003271859,"teacher_disagreement_score":0.5639931,"about_ca_system_score_codex":0.000081027945,"about_ca_system_score_gemma":0.0013203003,"threshold_uncertainty_score":0.9999346},"labels":[],"label_agreement":null},{"id":"W3047430701","doi":"10.1128/msystems.00288-20","title":"T3SEpp: an Integrated Prediction Pipeline for Bacterial Type III Secreted Effectors","year":2020,"lang":"en","type":"article","venue":"mSystems","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Saskatchewan","funders":"Shenzhen Peacock Plan; Shenzhen Municipal Human Resources and Social Security Bureau","keywords":"Effector; Computational biology; Pipeline (software); Computer science; Machine learning; Artificial intelligence; Biology; Software; False positive rate; Signal peptide; Bioinformatics; Peptide sequence; Gene; Genetics; Cell biology; Programming language","score_opus":0.01235728440646873,"score_gpt":0.2518619254134165,"score_spread":0.2395046410069478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047430701","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93737805,0.000061030045,0.059289552,0.00012029468,0.0014231084,0.00082093367,0.0001761739,0.00013240852,0.00059843867],"genre_scores_gemma":[0.9931807,0.0000046055616,0.0008367431,0.00019725443,0.0013883923,0.000029595334,0.0040113125,0.00002958204,0.00032180184],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991742,0.00008365151,0.00028021983,0.0002083644,0.00009072459,0.00016287807],"domain_scores_gemma":[0.99943936,0.000012887995,0.00011260738,0.00020274952,0.00011455686,0.00011784364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019468558,0.00014279138,0.00016489874,0.000020996187,0.00005870812,0.000039844967,0.00014542934,0.00017485456,0.000032364194],"category_scores_gemma":[0.00029267234,0.00012334417,0.000055456487,0.000098186305,0.000019814202,0.0000053003337,0.00003734177,0.000091392045,0.000016977348],"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":[0.001160048,0.000032698586,0.0026877658,0.00032344917,0.00008238306,8.637679e-7,0.00046109816,0.00080622156,0.964164,0.00003404706,0.027856778,0.0023906007],"study_design_scores_gemma":[0.0020444158,0.0021975462,0.0003133489,0.000038349797,0.000042148797,0.000011525658,0.00015937035,0.24551454,0.058330663,0.0000015842044,0.6910709,0.00027560955],"about_ca_topic_score_codex":0.000032629818,"about_ca_topic_score_gemma":0.000012649637,"teacher_disagreement_score":0.90583336,"about_ca_system_score_codex":0.0000127337935,"about_ca_system_score_gemma":0.000046977788,"threshold_uncertainty_score":0.502983},"labels":[],"label_agreement":null},{"id":"W3048259272","doi":"10.1093/bib/bbaa157","title":"A survey on predicting microbe-disease associations: biological data and computational methods","year":2020,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Computer science; Similarity (geometry); Machine learning; Experimental data; Data mining; Computational model; Artificial intelligence; Mathematics; Statistics","score_opus":0.06557991238572453,"score_gpt":0.3490915658475703,"score_spread":0.28351165346184576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048259272","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":[0.53149027,0.0007567543,0.45215437,0.00703502,0.0002563689,0.0012479443,0.0038485976,0.00021952829,0.0029911706],"genre_scores_gemma":[0.3313686,0.00019218495,0.6343536,0.021356065,0.00017364178,0.000011429984,0.01248105,0.0000383502,0.000025111754],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985884,0.00021327492,0.0005493995,0.00025276144,0.00016665323,0.00022949904],"domain_scores_gemma":[0.9988692,0.00031510397,0.00026445204,0.0003234528,0.000067204535,0.0001605818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013169138,0.00017928572,0.00019941323,0.000052224223,0.00010491446,0.000085560445,0.00039236055,0.00014383516,0.0000056922117],"category_scores_gemma":[0.0077270437,0.00016949607,0.000030142428,0.00017848106,0.00008976377,0.00002264031,0.0006368145,0.00024057656,0.000009894131],"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":[0.00045164887,0.00026347334,0.86177003,0.00045912506,0.0002076988,0.0000047375274,0.0031701322,0.022304896,0.0008608278,0.0010149471,0.0375134,0.07197905],"study_design_scores_gemma":[0.0006140311,0.00017213171,0.23668592,0.000029811561,0.000009785866,0.0000032748248,0.000061136474,0.750211,0.00006411064,0.00010339924,0.011803718,0.00024171664],"about_ca_topic_score_codex":0.0000363942,"about_ca_topic_score_gemma":0.00001072186,"teacher_disagreement_score":0.72790605,"about_ca_system_score_codex":0.000015197076,"about_ca_system_score_gemma":0.00008168978,"threshold_uncertainty_score":0.9250551},"labels":[],"label_agreement":null},{"id":"W3048577206","doi":"10.1002/prot.25993","title":"A new method for protein characterization and classification using geometrical features for <scp>3D</scp> face analysis: An example of tubulin structures","year":2020,"lang":"en","type":"article","venue":"Proteins Structure Function and Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University; University of Alberta","funders":"","keywords":"Pattern recognition (psychology); Support vector machine; Artificial intelligence; Classifier (UML); Computer science; Feature extraction; Face (sociological concept); Kernel (algebra); Machine learning; Mathematics","score_opus":0.027098891143814405,"score_gpt":0.284335727532021,"score_spread":0.2572368363882066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048577206","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":[0.18406367,0.000060217728,0.81411433,0.00007193668,0.000039075298,0.0014100892,0.00020799675,0.000023933844,0.000008757164],"genre_scores_gemma":[0.24212837,0.000011088529,0.7549507,0.00026523654,0.00020406854,0.00003719035,0.0023215848,0.000021610564,0.000060117145],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987878,0.000046851444,0.000506156,0.0002721412,0.00018017719,0.00020684251],"domain_scores_gemma":[0.99884754,0.00003407237,0.00053070055,0.00021907275,0.00019110374,0.00017748149],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002109887,0.0002395175,0.0003187825,0.00020296252,0.00015864665,0.000108619104,0.000118887685,0.0002951958,0.000004573295],"category_scores_gemma":[0.00049716467,0.0002010397,0.00008910074,0.00044411948,0.00004385234,0.000053162865,0.0000640178,0.00013512092,1.3871421e-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":[0.0003266144,0.000019311754,0.0010583019,0.001191109,0.00044865746,3.5064975e-8,0.0018131763,0.001952784,0.91979825,0.0014470387,0.00014174527,0.07180299],"study_design_scores_gemma":[0.0016959549,0.0018672482,0.016104868,0.000019339093,0.0006462467,0.00001209416,0.0007890049,0.893572,0.07122186,0.00042140426,0.013392933,0.00025706665],"about_ca_topic_score_codex":0.000024836965,"about_ca_topic_score_gemma":0.000011677564,"teacher_disagreement_score":0.8916192,"about_ca_system_score_codex":0.000011060768,"about_ca_system_score_gemma":0.000076658886,"threshold_uncertainty_score":0.8198161},"labels":[],"label_agreement":null},{"id":"W3081097618","doi":"10.1101/2020.08.21.260109","title":"Relabeling metabolic pathway data with groups to improve prediction outcomes","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; Compute Canada; Genome Canada","keywords":"Computer science; Scalability; Inference; Metabolic pathway; Set (abstract data type); Artificial intelligence; Machine learning; Biology; Genetics; Gene","score_opus":0.013515365648818091,"score_gpt":0.23204939299528313,"score_spread":0.21853402734646504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081097618","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.937604,0.0011716386,0.052003823,0.0012353688,0.0019513922,0.0019287271,0.0034935342,0.0005546739,0.00005684496],"genre_scores_gemma":[0.94669104,0.00018227666,0.050690193,0.0011020191,0.00091690844,0.00016210781,0.000037900416,0.0002034542,0.000014085464],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99675506,0.00012068224,0.00066682993,0.0014335967,0.00047691658,0.0005469124],"domain_scores_gemma":[0.99537003,0.00002406587,0.0004915553,0.0033740753,0.00033190585,0.00040837965],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00064466026,0.00068490417,0.0006316006,0.00014526148,0.00015984858,0.00022602748,0.0014998717,0.00060305605,0.000010532863],"category_scores_gemma":[0.000880568,0.0006281078,0.000111783724,0.000312349,0.00007478128,0.000025948057,0.0028440554,0.0009343964,0.000065323795],"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":[0.00012787919,0.000100813275,0.03195398,0.00046587942,0.0007138203,0.00001929333,0.000024314037,0.00083750195,0.96410483,0.0003216668,0.0013126051,0.000017417951],"study_design_scores_gemma":[0.002577153,0.0010544724,0.17473952,0.0005644664,0.0008421707,1.9742026e-7,0.000017054344,0.013060287,0.63022965,0.000003880151,0.17354837,0.0033627516],"about_ca_topic_score_codex":0.000031644944,"about_ca_topic_score_gemma":0.0000059698236,"teacher_disagreement_score":0.33387515,"about_ca_system_score_codex":0.000052570344,"about_ca_system_score_gemma":0.00055218674,"threshold_uncertainty_score":0.99961704},"labels":[],"label_agreement":null},{"id":"W3081661859","doi":"10.1080/15398285.2020.1794193","title":"Influenza Pandemic: A Webliography","year":2020,"lang":"fr","type":"article","venue":"Journal of Consumer Health on the Internet","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Pandemic; Outbreak; Human mortality from H5N1; Isolation (microbiology); Influenza pandemic; China; Coronavirus disease 2019 (COVID-19); Coronavirus; Influenza A virus subtype H5N1; Geography; Virology; Disease; Infectious disease (medical specialty); Medicine; Virus; Biology; Pathology","score_opus":0.04261524690534653,"score_gpt":0.3253403259615426,"score_spread":0.2827250790561961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081661859","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50647074,0.19041552,0.0077398582,0.2867125,0.0037727156,0.00068316824,0.00010918479,0.00002567035,0.004070657],"genre_scores_gemma":[0.8381821,0.013461662,0.0015081587,0.14495535,0.0010741237,0.0000028183258,0.00000739428,0.00004323442,0.0007651525],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99751455,0.00049547176,0.0011281595,0.00014866557,0.0003358526,0.00037727787],"domain_scores_gemma":[0.9975188,0.00016698822,0.0014112853,0.0002678012,0.00022142648,0.00041370155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011845216,0.00024196584,0.00039485624,0.000122029705,0.000056152916,0.00007072731,0.0006257508,0.00019737013,0.0002868573],"category_scores_gemma":[0.0006560498,0.00016774541,0.00033588076,0.0002461921,0.00022718699,0.000011347764,0.00012980531,0.0011232657,0.00013296472],"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":[0.0012473443,0.00017454814,0.053558465,0.00060297153,0.0010013528,0.000021465627,0.0035911791,0.00035776128,0.0005126454,0.0019161239,0.8821397,0.05487647],"study_design_scores_gemma":[0.0007700356,0.0024661978,0.00091914367,0.00034881197,0.000045813737,0.00025262695,0.00018642399,0.0009533942,0.00060221157,0.00006528044,0.99323535,0.0001547052],"about_ca_topic_score_codex":0.00004797059,"about_ca_topic_score_gemma":0.0000099356075,"teacher_disagreement_score":0.33171135,"about_ca_system_score_codex":0.00003967406,"about_ca_system_score_gemma":0.00047184256,"threshold_uncertainty_score":0.684046},"labels":[],"label_agreement":null},{"id":"W3083386021","doi":"10.1101/2020.09.04.283929","title":"Self-Supervised Contrastive Learning of Protein Representations By Mutual Information Maximization","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; Vector Institute; Microsoft Research","keywords":"Maximization; Computer science; Mutual information; Embedding; Artificial intelligence; Hyperparameter; Machine learning; Autoregressive model; Supervised learning; Contrast (vision); Mathematics; Artificial neural network","score_opus":0.006008598428195527,"score_gpt":0.21242160158295761,"score_spread":0.20641300315476208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3083386021","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73343796,0.00043174106,0.261691,0.00037971383,0.0003832433,0.0024229018,0.000645529,0.0004064252,0.00020147518],"genre_scores_gemma":[0.9661594,0.00012263421,0.033131503,0.00013585037,0.00015918972,0.00016604572,0.000055213848,0.00006222323,0.000007964288],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99797297,0.00020136763,0.0007548267,0.00042299496,0.00035507337,0.00029276402],"domain_scores_gemma":[0.99771416,0.000023347782,0.00086352346,0.0005964241,0.0006431088,0.000159408],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003288266,0.0003857314,0.00037961642,0.00012889852,0.00012696987,0.0001223487,0.00040320656,0.00052801816,0.000021114929],"category_scores_gemma":[0.001099314,0.00044403112,0.00012955813,0.00027048294,0.00008666023,0.000041918916,0.00046894414,0.00066149666,0.000031364478],"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":[0.00011315747,0.00009416912,0.005397572,0.001064921,0.0002878229,0.000001652327,0.00012941053,0.0026429936,0.9888855,0.00038885942,0.0009813192,0.0000125963315],"study_design_scores_gemma":[0.0016190482,0.00042239964,0.0070478865,0.0002505897,0.00018017026,3.875742e-8,0.00004813848,0.09015203,0.87012357,0.0000022755594,0.029100334,0.0010535135],"about_ca_topic_score_codex":0.000023297818,"about_ca_topic_score_gemma":3.8616946e-7,"teacher_disagreement_score":0.23272142,"about_ca_system_score_codex":0.00006211838,"about_ca_system_score_gemma":0.0004028775,"threshold_uncertainty_score":0.99980116},"labels":[],"label_agreement":null},{"id":"W3084144361","doi":"10.3389/fmolb.2020.571696","title":"High Speed AFM and NanoInfrared Spectroscopy Investigation of Aβ1–42 Peptide Variants and Their Interaction With POPC/SM/Chol/GM1 Model Membranes","year":2020,"lang":"en","type":"article","venue":"Frontiers in Molecular Biosciences","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"H2020 Marie Skłodowska-Curie Actions","keywords":"POPC; Membrane; Atomic force microscopy; Peptide; Force spectroscopy; Chemistry; Biophysics; Spectroscopy; Analytical Chemistry (journal); Nanotechnology; Chromatography; Materials science; Biochemistry; Physics; Biology; Lipid bilayer","score_opus":0.006225943301420278,"score_gpt":0.21127890851108308,"score_spread":0.2050529652096628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3084144361","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9352368,0.00027595888,0.06340216,0.00058101054,0.00010074,0.00018414136,0.000015681453,0.000011240865,0.0001922556],"genre_scores_gemma":[0.8935064,0.00015856944,0.105825625,0.00041103322,0.000021086415,0.0000032417515,0.000037251757,0.000011998253,0.000024769259],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998965,0.00006933949,0.0002507084,0.00035235073,0.00017193986,0.0001906252],"domain_scores_gemma":[0.9994952,0.0000073687647,0.00018362138,0.00016654746,0.000042997995,0.00010423206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019604931,0.00018450708,0.0002146212,0.00010009956,0.00006618601,0.000058520014,0.00019368132,0.00009809473,0.0000018915727],"category_scores_gemma":[0.0001242162,0.00014464815,0.000027561795,0.0002432487,0.00040363026,0.00003510698,0.00010151905,0.00012090066,3.081547e-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":[0.00010315461,0.000010996272,0.018125825,0.00007903467,0.00002398876,0.000002099422,0.0008959094,0.0036364628,0.97661895,0.00005433733,0.00021796132,0.00023131305],"study_design_scores_gemma":[0.00071480655,0.000589209,0.003627051,0.00006214849,0.000019318404,0.000015817473,0.0012566171,0.1311416,0.86177915,0.00038632596,0.00013110605,0.00027682877],"about_ca_topic_score_codex":0.00003097979,"about_ca_topic_score_gemma":0.000008762003,"teacher_disagreement_score":0.12750515,"about_ca_system_score_codex":0.000010406773,"about_ca_system_score_gemma":0.00007179498,"threshold_uncertainty_score":0.58985806},"labels":[],"label_agreement":null},{"id":"W3088578860","doi":"10.1016/j.cels.2020.08.016","title":"Fast and Flexible Protein Design Using Deep Graph Neural Networks","year":2020,"lang":"en","type":"article","venue":"Cell Systems","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":230,"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; Fonds de recherche du Québec – Nature et technologies; Canadian Institutes of Health Research; Nvidia","keywords":"Computer science; In silico; Benchmark (surveying); Protein design; Graph; Artificial neural network; Constraint (computer-aided design); Algorithm; Protein structure prediction; Protein sequencing; Sequence (biology); Protein structure; Theoretical computer science; Artificial intelligence; Peptide sequence; Mathematics; Biology; Gene; Genetics","score_opus":0.018471109120259815,"score_gpt":0.22463906818269538,"score_spread":0.20616795906243557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088578860","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22633119,0.0021136566,0.7697571,0.000043285352,0.00015609425,0.0005738259,0.0000021034843,0.000041142597,0.0009815906],"genre_scores_gemma":[0.9951259,0.0000138322075,0.0041645127,0.00015212229,0.000304163,0.000013874658,0.000021417844,0.00002372279,0.00018048316],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992149,0.000100542435,0.0002054925,0.00019120905,0.00008404225,0.0002038248],"domain_scores_gemma":[0.9995679,0.000007116946,0.00011168935,0.00016387102,0.00003079202,0.00011859428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013931673,0.00013725036,0.00013565824,0.000017624578,0.00008501803,0.00007160568,0.00012436791,0.00012249478,0.0000036194735],"category_scores_gemma":[0.000026287235,0.00012677441,0.00003620279,0.000084329884,0.000038782997,0.0000042863176,0.00008940027,0.00011935633,0.0000040620785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066124056,0.000014741231,0.0018585647,0.0003675339,0.000031126383,0.0000050329477,0.0002606055,0.76024246,0.23534982,0.000035851925,0.00067977444,0.0010883843],"study_design_scores_gemma":[0.00027619125,0.00019656529,0.00003159909,0.000016331198,0.00001155661,0.000019556383,0.00012759978,0.98486215,0.012363916,0.0000019178135,0.0019212221,0.00017140902],"about_ca_topic_score_codex":0.000019384192,"about_ca_topic_score_gemma":5.872547e-7,"teacher_disagreement_score":0.76879466,"about_ca_system_score_codex":0.000005182838,"about_ca_system_score_gemma":0.000014510975,"threshold_uncertainty_score":0.516971},"labels":[],"label_agreement":null},{"id":"W3089740292","doi":"10.1371/journal.pcbi.1008174","title":"Metabolic pathway inference using multi-label classification with rich pathway features","year":2020,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; Compute Canada; Genome Canada","keywords":"Inference; Computer science; Artificial intelligence; Machine learning; Genome; Metabolic pathway; Computational biology; Data mining; Biology; Gene","score_opus":0.0545152962563078,"score_gpt":0.3025090959104504,"score_spread":0.2479937996541426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089740292","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77086025,0.00036222723,0.22724108,0.00065514643,0.000060268314,0.00026015865,0.000101274105,0.000059668408,0.00039993817],"genre_scores_gemma":[0.85677546,0.000013118623,0.14065814,0.0012558361,0.00014760882,0.0000142258805,0.0010906283,0.000018885357,0.000026107791],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895567,0.00012392405,0.00025427045,0.00032793105,0.00012808303,0.00021010904],"domain_scores_gemma":[0.999278,0.00006005898,0.00019642191,0.00015354923,0.00021390126,0.00009807797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000078733356,0.0001911093,0.00019379555,0.000046902947,0.00011366124,0.000027896604,0.00021451902,0.00016576736,0.000015300622],"category_scores_gemma":[0.00027900664,0.00015611616,0.000034381363,0.00016269473,0.00012009304,0.0000081697735,0.000106400876,0.00019231263,0.000027169863],"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":[0.00021535913,0.00027558685,0.057380773,0.00008256942,0.00032802531,0.000003458047,0.00059570814,0.032374345,0.88721335,0.012412535,0.00013672131,0.008981563],"study_design_scores_gemma":[0.002034724,0.000877305,0.034020048,0.000022818553,0.00005352687,0.000041659023,0.000120275705,0.91958296,0.035579015,0.00033204284,0.0067049507,0.0006306674],"about_ca_topic_score_codex":0.0000063183325,"about_ca_topic_score_gemma":0.000004906855,"teacher_disagreement_score":0.88720864,"about_ca_system_score_codex":0.0000101800215,"about_ca_system_score_gemma":0.00018129357,"threshold_uncertainty_score":0.6366232},"labels":[],"label_agreement":null},{"id":"W3092695394","doi":"10.1186/s12859-020-03794-x","title":"Implementation of homology based and non-homology based computational methods for the identification and annotation of orphan enzymes: using Mycobacterium tuberculosis H37Rv as a case study","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Dalhousie University","funders":"Council of Scientific and Industrial Research, India","keywords":"In silico; Computational biology; Sequence alignment; Annotation; Biology; Genome; Homology (biology); Context (archaeology); Genetics; Mycobacterium tuberculosis; Homology modeling; Bioinformatics; Gene; Peptide sequence; Tuberculosis; Enzyme; Medicine","score_opus":0.027311041487814994,"score_gpt":0.37450429355805614,"score_spread":0.34719325207024115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092695394","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47321752,0.000042376072,0.5259826,0.000082795785,0.00003264425,0.0005860032,0.00004797932,0.000004419522,0.000003646812],"genre_scores_gemma":[0.6574883,0.0000047134918,0.34205064,0.00021127702,0.000018318091,0.00002847619,0.00018771953,0.000009615207,9.276677e-7],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986422,0.00016208507,0.00080249755,0.00014646837,0.000112062444,0.00013467763],"domain_scores_gemma":[0.99849826,0.0003277047,0.00067137275,0.0001933943,0.00025560573,0.000053635387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007649722,0.00015250716,0.00022523905,0.00008742083,0.00012487247,0.00003024594,0.000102390266,0.00010367725,0.000007791002],"category_scores_gemma":[0.00029587568,0.0001297127,0.00005693438,0.00014250448,0.00014335106,0.000023613855,0.00007549021,0.00006682085,3.6645525e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021206911,0.00090042397,0.32707265,0.013010406,0.0015883999,0.000014395818,0.053255197,0.27797928,0.21607435,0.00085292995,0.00056462706,0.10656665],"study_design_scores_gemma":[0.0016755149,0.0009967731,0.008183252,0.000009181857,0.00018455392,0.00010634038,0.008591539,0.9616368,0.018397016,0.000023274022,0.00006388743,0.00013186099],"about_ca_topic_score_codex":0.00012561986,"about_ca_topic_score_gemma":0.00004594546,"teacher_disagreement_score":0.6836575,"about_ca_system_score_codex":0.000010698951,"about_ca_system_score_gemma":0.00016692637,"threshold_uncertainty_score":0.5289531},"labels":[],"label_agreement":null},{"id":"W3093433836","doi":"10.22541/au.160266787.79641281/v1","title":"Protein secondary structure assignment using pc-polyline and convolutional neuron network","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Protein secondary structure; Pairwise comparison; Computer science; Dihedral angle; Bundle; Artificial intelligence; Physics","score_opus":0.013156122213887891,"score_gpt":0.25145492382823736,"score_spread":0.23829880161434946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093433836","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.917417,0.0014200563,0.07507855,0.0011392904,0.0006782191,0.0012316114,0.0003222682,0.00008283681,0.0026301893],"genre_scores_gemma":[0.9271794,0.000039621915,0.06759634,0.0014057234,0.00140345,0.000015743179,0.001641832,0.00005208525,0.0006658361],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862194,0.00008380833,0.00038521364,0.0004573142,0.00019227696,0.00025942142],"domain_scores_gemma":[0.9991953,0.000007654797,0.00026844154,0.000349889,0.000050996437,0.00012774055],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00012231972,0.000322541,0.00025711046,0.00002332971,0.00010067747,0.000069724614,0.00021436776,0.0004417555,0.00018050242],"category_scores_gemma":[0.000070110276,0.0003010628,0.000077573946,0.000036479527,0.00009171512,0.0000024806027,0.0013812283,0.0007559066,0.0000024770777],"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":[0.0004002176,0.00007448679,0.010357551,0.0021471283,0.0007722806,0.000023562057,0.00018655733,0.16656168,0.7893192,0.0024025766,0.02144257,0.0063121747],"study_design_scores_gemma":[0.0030898515,0.0013261053,0.016855046,0.0005119179,0.00033210492,0.00028760883,0.00009739777,0.67586154,0.07605666,0.0073418585,0.2148058,0.003434091],"about_ca_topic_score_codex":0.000026415368,"about_ca_topic_score_gemma":0.000012364966,"teacher_disagreement_score":0.71326256,"about_ca_system_score_codex":0.000024545394,"about_ca_system_score_gemma":0.00025895605,"threshold_uncertainty_score":0.99994415},"labels":[],"label_agreement":null},{"id":"W3101574558","doi":"10.1186/s13040-016-0108-2","title":"ProtNN: fast and accurate protein 3D-structure classification in structural and topological space","year":2016,"lang":"en","type":"article","venue":"BioData Mining","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Space (punctuation); Topology (electrical circuits); Topological space; Data mining; Pattern recognition (psychology); Artificial intelligence; Mathematics; Pure mathematics; Combinatorics","score_opus":0.016169668764608368,"score_gpt":0.2731470377325991,"score_spread":0.2569773689679907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3101574558","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.997902,0.00010719903,0.00076090643,0.0006712601,0.00003083632,0.00025656118,0.000054331853,0.000011329722,0.00020562245],"genre_scores_gemma":[0.9849529,0.000030133197,0.014622772,0.000054070868,0.00006699149,0.000013360796,0.00007895111,0.00000791714,0.0001728997],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.999288,0.000048034064,0.00016719925,0.0002581444,0.00006680194,0.00017181435],"domain_scores_gemma":[0.9996044,0.000013318274,0.00009546259,0.0002171801,0.000019487932,0.000050145773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011721412,0.00012454008,0.00010000819,0.000034779292,0.000057046847,0.00004156224,0.00011247415,0.00014862671,0.000019370731],"category_scores_gemma":[0.0002719962,0.000080265396,0.000009272518,0.00004583746,0.00013443305,0.000016310072,0.0001857671,0.00007860058,0.0000014081947],"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":[0.00008421532,0.000005244339,0.10438586,0.00005200848,0.000011518793,0.0000023053994,0.00021659363,0.0000015864144,0.841424,0.0008054814,0.00011131247,0.05289991],"study_design_scores_gemma":[0.00375592,0.0010150385,0.8217405,0.00033109172,0.000027134161,0.00028225893,0.0013114985,0.0098505085,0.13228053,0.00044660983,0.027705051,0.0012538685],"about_ca_topic_score_codex":0.000008002297,"about_ca_topic_score_gemma":0.000032652013,"teacher_disagreement_score":0.71735466,"about_ca_system_score_codex":0.000008499168,"about_ca_system_score_gemma":0.000020204054,"threshold_uncertainty_score":0.3273128},"labels":[],"label_agreement":null},{"id":"W3115382283","doi":"10.1093/nar/gkaa1095","title":"PSORTdb 4.0: expanded and redesigned bacterial and archaeal protein subcellular localization database incorporating new secondary localizations","year":2020,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Biology; RefSeq; Proteome; Genome; Database; Hypothetical protein; Bacterial genome size; Computational biology; Annotation; Bacterial protein; Proteomics; Bioinformatics; Genetics; Bacteria; Gene","score_opus":0.03474046784770293,"score_gpt":0.30337903430905977,"score_spread":0.26863856646135686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3115382283","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.822408,0.0003173682,0.17382957,0.00143228,0.00003629561,0.0008484471,0.000045357512,0.000050491075,0.0010321944],"genre_scores_gemma":[0.9842466,0.00008671272,0.013741211,0.0002574478,0.00038014798,0.00002109373,0.00091222295,0.00004280521,0.00031176652],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99838704,0.00028104146,0.00029858763,0.00038658062,0.00033948096,0.0003072984],"domain_scores_gemma":[0.9991338,0.00002669743,0.00008099616,0.00028540636,0.00013806277,0.0003349863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006062329,0.00015649812,0.00015486153,0.00007857866,0.00029914576,0.00013835815,0.00019741598,0.00016670022,0.00011735575],"category_scores_gemma":[0.0008339179,0.00015653696,0.00002212368,0.00025387155,0.0002960519,0.000025979745,0.0005539336,0.00034576462,0.000011250305],"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":[0.00036191728,0.000031077703,0.005145872,0.0003321568,0.00003724043,0.0000120958575,0.0010845101,0.000114054375,0.9749083,0.0009711924,0.005440264,0.011561309],"study_design_scores_gemma":[0.008056339,0.0044926796,0.0026851888,0.0003134748,0.00005720341,0.000118283264,0.0020609533,0.34825778,0.4677938,0.0017687166,0.16284095,0.0015546557],"about_ca_topic_score_codex":0.000072234376,"about_ca_topic_score_gemma":0.000026736194,"teacher_disagreement_score":0.5071145,"about_ca_system_score_codex":0.000014904035,"about_ca_system_score_gemma":0.00027719612,"threshold_uncertainty_score":0.63833916},"labels":[],"label_agreement":null},{"id":"W3115881671","doi":"10.1109/bibe50027.2020.00027","title":"Chaos Game Representations &amp; Deep Learning for Proteome-Wide Protein Prediction","year":2020,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Carleton University","funders":"","keywords":"Computer science; Leverage (statistics); Artificial intelligence; Convolutional neural network; Deep learning; Proteome; Machine learning; Theoretical computer science; Bioinformatics; Biology","score_opus":0.01594613404217509,"score_gpt":0.26996885269591886,"score_spread":0.25402271865374376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3115881671","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20469542,0.000041684307,0.7851457,0.0024588816,0.000053818003,0.0017591444,0.000011218551,0.00013845734,0.0056956713],"genre_scores_gemma":[0.9321205,0.000014140345,0.057582095,0.0009421468,0.00045273473,0.0006018159,0.00087793317,0.0000417205,0.0073668836],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99913627,0.000046681318,0.00025288234,0.00024838687,0.000120930046,0.00019482484],"domain_scores_gemma":[0.9994741,0.000017484255,0.00011491456,0.0001969955,0.000096238306,0.00010026219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013840388,0.00012256336,0.0001012444,0.000025440208,0.00011103477,0.00003876686,0.00013311217,0.00011153511,0.000081038124],"category_scores_gemma":[0.0014718041,0.00011629882,0.00007988949,0.00008919796,0.00003263614,0.000007411946,0.00008496848,0.00015729226,0.00004805229],"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":[0.00033943052,0.00007405553,0.023918247,0.0004177,0.00014980654,7.230109e-7,0.0016546552,0.027190052,0.9300029,0.00047221663,0.009548273,0.006231939],"study_design_scores_gemma":[0.0016012732,0.0011807749,0.004053766,0.000025376592,0.000037735183,0.000009622346,0.00037768687,0.11378644,0.15720926,0.00014789056,0.72112066,0.00044949714],"about_ca_topic_score_codex":0.0000070574397,"about_ca_topic_score_gemma":0.000010457414,"teacher_disagreement_score":0.77279365,"about_ca_system_score_codex":0.000008216517,"about_ca_system_score_gemma":0.000029979485,"threshold_uncertainty_score":0.47425282},"labels":[],"label_agreement":null},{"id":"W3116224340","doi":"10.1186/s12859-020-03891-x","title":"Integrative approach for detecting membrane proteins","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; King Saud University; Saudi Arabian Cultural Bureau; Genome Canada","keywords":"Transmembrane protein; Membrane topology; Membrane protein; Computer science; Topology (electrical circuits); Integral membrane protein; Transmembrane domain; Computational biology; Feature (linguistics); Artificial intelligence; Data mining; Bioinformatics; Pattern recognition (psychology); Machine learning; Membrane; Biology; Mathematics; Biochemistry","score_opus":0.02162475551480415,"score_gpt":0.257806208504307,"score_spread":0.23618145298950288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116224340","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":[0.005484814,0.00004299287,0.98039645,0.00011929341,0.000060690207,0.0010962684,0.000047977726,0.000079538164,0.01267196],"genre_scores_gemma":[0.049830556,0.00001166427,0.9477741,0.001199016,0.0003048872,0.00012955767,0.00044394293,0.000037609916,0.00026868074],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875766,0.00003251135,0.0005164757,0.00018725936,0.00017943498,0.00032664492],"domain_scores_gemma":[0.9990882,0.000036258225,0.00028045126,0.00030451897,0.00013271584,0.00015782918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027529724,0.0002578267,0.00023486208,0.00004191936,0.00015543617,0.00007363824,0.00035113716,0.00019260652,0.000010064559],"category_scores_gemma":[0.0012083866,0.00021171063,0.00016325006,0.00015858657,0.00007200234,0.00001827299,0.00016499814,0.0002065684,0.000024117297],"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":[0.0063472767,0.0012320238,0.018585982,0.040086765,0.0023516424,0.0000044823896,0.08643458,0.25259247,0.33289966,0.014155685,0.08917322,0.15613621],"study_design_scores_gemma":[0.0009160735,0.00062906236,0.000035582543,0.00001798523,0.00002733681,0.000013132768,0.0020667557,0.92794585,0.04583135,0.000014331569,0.02215053,0.000352024],"about_ca_topic_score_codex":0.0000024740075,"about_ca_topic_score_gemma":0.000004162969,"teacher_disagreement_score":0.67535335,"about_ca_system_score_codex":0.000014926096,"about_ca_system_score_gemma":0.0001102948,"threshold_uncertainty_score":0.8633309},"labels":[],"label_agreement":null},{"id":"W3119864298","doi":"10.1016/j.compbiomed.2021.104212","title":"Incorporating a transfer learning technique with amino acid embeddings to efficiently predict N-linked glycosylation sites in ion channels","year":2021,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Artificial Intelligence in Medicine (Canada)","funders":"Ministry of Science and Technology, Taiwan","keywords":"Glycosylation; Hyperparameter; Chemistry; Amino acid; Computer science; Embedding; Computational biology; Artificial intelligence; Biological system; Biochemistry; Biology","score_opus":0.007960776197928825,"score_gpt":0.2747291888283461,"score_spread":0.2667684126304173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119864298","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8071294,0.00022027014,0.19162752,0.00044592106,0.00011395255,0.00023969328,0.0000011018658,0.000017724073,0.00020443181],"genre_scores_gemma":[0.9848069,0.000055686607,0.014141389,0.00050616433,0.000150441,0.000028517688,0.00027520175,0.000010530376,0.000025192134],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990103,0.0001322764,0.00028587764,0.00030361282,0.00006437352,0.00020352817],"domain_scores_gemma":[0.99964726,0.00004914724,0.000056025616,0.00012772773,0.000056485216,0.000063369815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047524017,0.00015104043,0.00023169808,0.00016104437,0.0000570144,0.0000079657575,0.00009045496,0.00019184615,0.0000043335754],"category_scores_gemma":[0.00022230487,0.00012249596,0.000015469395,0.00026939274,0.00012563799,0.0000054095976,0.00008613764,0.00027921872,6.9627174e-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":[0.0002432008,0.000049637056,0.20359269,0.00010022599,0.000023753664,0.000027289381,0.0016699171,0.008702463,0.7778665,0.00041086145,0.000057286285,0.007256213],"study_design_scores_gemma":[0.018762939,0.02087362,0.18607394,0.004762667,0.00010836109,0.0012319817,0.0024949098,0.2550029,0.49532747,0.0013453787,0.011673581,0.00234224],"about_ca_topic_score_codex":0.000014785198,"about_ca_topic_score_gemma":0.000052954205,"teacher_disagreement_score":0.28253898,"about_ca_system_score_codex":0.000018616094,"about_ca_system_score_gemma":0.000035849513,"threshold_uncertainty_score":0.499524},"labels":[],"label_agreement":null},{"id":"W3126273660","doi":"10.2139/ssrn.3671737","title":"Most Non-Canonical Proteins Uniquely Populate the Proteome or Immunopeptidome","year":2020,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Institute for Research in Immunology and Cancer","funders":"","keywords":"Proteome; Computational biology; Chemistry; Biology; Bioinformatics","score_opus":0.00823150179227611,"score_gpt":0.24646948988487155,"score_spread":0.23823798809259544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126273660","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9224591,0.0017150277,0.048672564,0.02104863,0.00023055762,0.001962644,0.000014465616,0.00007529117,0.0038216924],"genre_scores_gemma":[0.9926582,0.0010794761,0.0010657522,0.0019394971,0.00051228894,0.0000363295,0.00003311778,0.000051322917,0.0026239885],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974967,0.00013982694,0.0004203087,0.00021449912,0.00026092713,0.0014677327],"domain_scores_gemma":[0.9991652,0.000011896248,0.00025513658,0.00032293116,0.00010911226,0.00013576138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009882222,0.00023007608,0.0001926743,0.000027352764,0.00031913703,0.000096350916,0.0007199234,0.0001579127,0.00004394895],"category_scores_gemma":[0.00038786003,0.00013957074,0.000117139796,0.00023090997,0.00009315288,0.000012341035,0.0002057745,0.002170873,0.00005369614],"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":[0.005795269,0.00041312262,0.0061224047,0.0002518998,0.0023766342,0.000061599014,0.0019275987,0.0033222334,0.88162184,0.03217614,0.007881349,0.058049895],"study_design_scores_gemma":[0.017210174,0.037061423,0.0072328686,0.000344815,0.00056010816,0.013636299,0.0063822684,0.02602115,0.106306024,0.029022725,0.7511021,0.0051200343],"about_ca_topic_score_codex":0.000036633617,"about_ca_topic_score_gemma":0.00014993417,"teacher_disagreement_score":0.7753158,"about_ca_system_score_codex":0.00012528748,"about_ca_system_score_gemma":0.0025994522,"threshold_uncertainty_score":0.94314843},"labels":[],"label_agreement":null},{"id":"W3128211347","doi":"10.1038/s41467-021-21052-3","title":"Author Correction: Characterising the loss-of-function impact of 5’ untranslated region variants in 15,708 individuals","year":2021,"lang":"en","type":"erratum","venue":"Nature Communications","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Montreal Heart Institute; University of Ottawa","funders":"British Heart Foundation","keywords":"Function (biology); Computational biology; Untranslated region; Biology; Loss function; Genetics; Gene; Messenger RNA; Phenotype","score_opus":0.017690916452770086,"score_gpt":0.3247044778474423,"score_spread":0.3070135613946722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128211347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32994348,0.31934366,0.013323799,0.03606378,0.13525829,0.009944137,0.0034684313,0.00043502604,0.15221941],"genre_scores_gemma":[0.97591907,0.0038932886,0.0008917497,0.0001471034,0.00031483825,0.000026434254,0.010779266,0.000049206574,0.007979051],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982931,0.0004735829,0.0006342584,0.0002058916,0.00021495721,0.0001781967],"domain_scores_gemma":[0.9963191,0.00011491543,0.0008318748,0.0023265325,0.00037211066,0.000035431636],"candidate_categories":["research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0004930214,0.00024250323,0.000359944,0.00016883457,0.000149864,0.000033652497,0.0010791833,0.0015481652,0.000024828443],"category_scores_gemma":[0.0007002925,0.00019544965,0.00024555626,0.00056176924,0.00018789794,0.0000104538985,0.0003514478,0.0027505343,0.0000016041339],"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":[0.00018738853,0.0005382224,0.052984633,0.00033436445,0.0012869244,0.0000031869874,0.0018429026,0.00057620736,0.009249304,0.00038747213,0.92572874,0.006880667],"study_design_scores_gemma":[0.00069726096,0.0004272466,0.39979586,0.001082928,0.0003230278,0.0001441725,0.00020927195,0.004267727,0.0007259528,0.000070335365,0.5916883,0.00056792476],"about_ca_topic_score_codex":0.00010230394,"about_ca_topic_score_gemma":0.00031631498,"teacher_disagreement_score":0.6459756,"about_ca_system_score_codex":0.00004988763,"about_ca_system_score_gemma":0.000510586,"threshold_uncertainty_score":0.99974805},"labels":[],"label_agreement":null},{"id":"W3128943784","doi":"10.1109/bibm49941.2020.9313229","title":"TportHMM: Predicting the substrate class of transmembrane transport proteins using profile Hidden Markov Models","year":2020,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Hidden Markov model; Multiple sequence alignment; Computer science; Classifier (UML); Artificial intelligence; Markov chain; Naive Bayes classifier; Class (philosophy); Machine learning; Sequence (biology); Transmembrane protein; Pattern recognition (psychology); Computational biology; Bioinformatics; Sequence alignment; Support vector machine; Biology; Peptide sequence; Genetics; Gene","score_opus":0.019311235319386225,"score_gpt":0.23816320701982469,"score_spread":0.21885197170043846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128943784","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94211257,0.00008230756,0.042820923,0.000646447,0.000034441266,0.00066296896,0.000046427707,0.00003904956,0.013554897],"genre_scores_gemma":[0.97995967,0.000023342234,0.019201254,0.00033717472,0.00011539612,0.000016383228,0.000108808425,0.00002802145,0.00020997935],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988115,0.000049576374,0.00045813434,0.00022152188,0.00022459343,0.00023470416],"domain_scores_gemma":[0.99936634,0.000009541627,0.00018021994,0.0002796088,0.00007655101,0.00008772125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024572734,0.00017594555,0.00018778036,0.00001738689,0.00008439399,0.000012839617,0.00029204928,0.00013929677,0.00008014816],"category_scores_gemma":[0.000027889928,0.00012521206,0.00012430424,0.00012756995,0.00009598693,0.000010893082,0.00003620036,0.00020318897,0.0000019224785],"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":[0.00049979455,0.000111170615,0.01957954,0.0011334139,0.00030262265,0.000009308362,0.0037029933,0.02688242,0.9427812,0.000516966,0.0003142157,0.004166377],"study_design_scores_gemma":[0.0008136678,0.00041059466,0.0016089975,0.000042769017,0.00008905459,0.000027882206,0.0006309625,0.66512036,0.32988194,0.000032198084,0.0010073519,0.0003342392],"about_ca_topic_score_codex":0.00006064854,"about_ca_topic_score_gemma":0.000023996317,"teacher_disagreement_score":0.63823795,"about_ca_system_score_codex":0.0000050140475,"about_ca_system_score_gemma":0.00012608811,"threshold_uncertainty_score":0.5105999},"labels":[],"label_agreement":null},{"id":"W3129155125","doi":"10.1016/j.compbiomed.2021.104258","title":"FAD-BERT: Improved prediction of FAD binding sites using pre-training of deep bidirectional transformers","year":2021,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Artificial Intelligence in Medicine (Canada)","funders":"Ministry of Science and Technology, Taiwan","keywords":"Transformer; Computer science; Artificial intelligence; Training set; Training (meteorology); Machine learning; Electrical engineering; Engineering; Voltage; Physics","score_opus":0.016176598536231407,"score_gpt":0.30240815568688045,"score_spread":0.2862315571506491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129155125","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93707377,0.0008188283,0.061251726,0.00008363038,0.00034412812,0.00007970378,0.0000124895905,0.0000061659102,0.0003295845],"genre_scores_gemma":[0.9869662,0.0003066281,0.01223975,0.00008562385,0.00012256682,0.0000019169363,0.00025157776,0.0000061244223,0.000019636307],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925166,0.000059521648,0.0003378618,0.00016633484,0.0000480815,0.00013654375],"domain_scores_gemma":[0.9996218,0.000057366477,0.00012886155,0.00009116896,0.0000658298,0.00003497308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025740164,0.00009978449,0.0002305232,0.00010242916,0.000037976137,0.0000014824282,0.000059229365,0.00015758096,0.000010430543],"category_scores_gemma":[0.00015090915,0.000086742475,0.000034000157,0.000126186,0.00025469318,0.0000046018495,0.000045074423,0.00011214658,5.9216664e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057526093,0.00002153908,0.05692557,0.0001078621,0.00006718304,7.7874904e-7,0.0010905917,0.00022731924,0.92745066,0.00011294804,0.000018394212,0.013919608],"study_design_scores_gemma":[0.0096393,0.0043431213,0.17939089,0.0011642262,0.00025185593,0.00061971793,0.0043793367,0.40773037,0.3867422,0.0007325727,0.0042664693,0.00073993654],"about_ca_topic_score_codex":0.000021909038,"about_ca_topic_score_gemma":0.00002042885,"teacher_disagreement_score":0.5407085,"about_ca_system_score_codex":0.00000957785,"about_ca_system_score_gemma":0.000045549215,"threshold_uncertainty_score":0.35372555},"labels":[],"label_agreement":null},{"id":"W3135313273","doi":"10.22541/au.158697112.27465963","title":"A new method for protein characterization and classification using geometrical features for 3D face analysis: an example of tubulin structures","year":2020,"lang":"en","type":"dataset","venue":"Authorea","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"MacEwan University; University of Alberta","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Support vector machine; Classifier (UML); Computer science; Feature extraction; Face (sociological concept); Kernel (algebra); Machine learning; Mathematics","score_opus":0.041850393280666774,"score_gpt":0.34799019868332637,"score_spread":0.3061398054026596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135313273","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010358548,0.000040796993,0.5867846,0.000034727636,0.00002790044,0.00065142004,0.41141835,0.000005803741,5.3358144e-7],"genre_scores_gemma":[0.0003886476,0.000014298751,0.3225292,0.000044664434,0.00016566325,0.000038213908,0.6767646,0.00001566941,0.000039045106],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99880916,0.00009562706,0.00037927405,0.00041475575,0.00014039794,0.00016079386],"domain_scores_gemma":[0.9987989,0.00003853086,0.0005425556,0.00040046222,0.0001147625,0.000104786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028968908,0.00022727267,0.00039336234,0.00023362739,0.000070221766,0.000057498313,0.00022112552,0.00047541363,0.0000058752835],"category_scores_gemma":[0.0005229608,0.00021012693,0.00012540417,0.00033112834,0.00002616115,0.000007671888,0.0000791892,0.00014822734,3.2806167e-7],"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":[0.00076772965,0.00007603236,0.000084560736,0.001797713,0.001664351,4.0342826e-7,0.00033523425,0.000818757,0.56627005,0.0002729706,0.3814382,0.046474002],"study_design_scores_gemma":[0.0005716803,0.00070546207,0.002412958,0.000023514525,0.0014080928,0.0000054469433,0.000039551265,0.07606463,0.010568123,0.00007777921,0.9077113,0.00041141955],"about_ca_topic_score_codex":0.00024075746,"about_ca_topic_score_gemma":0.000043040254,"teacher_disagreement_score":0.5557019,"about_ca_system_score_codex":0.0000120950735,"about_ca_system_score_gemma":0.00011120672,"threshold_uncertainty_score":0.8568728},"labels":[],"label_agreement":null},{"id":"W3153274311","doi":"10.24908/iqurcp.10056","title":"4. The Role of Glycosylation in Cardiac Arrhythmias","year":2018,"lang":"en","type":"article","venue":"Inquiry Queen s Undergraduate Research Conference Proceedings","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"hERG; Glycosylation; Chemistry; Serine protease; Long QT syndrome; Potassium channel; Protease; Biochemistry; Pharmacology; QT interval; Biology; Enzyme; Medicine; Biophysics; Internal medicine","score_opus":0.029856278320043707,"score_gpt":0.34275173699107603,"score_spread":0.3128954586710323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153274311","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96926147,0.00026638113,0.0005523136,0.0034186225,0.00015292707,0.0005158056,0.0000046850673,0.000021882382,0.025805907],"genre_scores_gemma":[0.9978563,0.0007126623,0.0005058389,0.00001809829,0.00038941752,0.000047844376,0.000015597603,0.000019915527,0.00043430057],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99806774,0.00011528235,0.00038904723,0.00029413053,0.0006001116,0.0005337123],"domain_scores_gemma":[0.99805504,0.00009242234,0.00015053654,0.00026919195,0.0013426382,0.00009019534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022590668,0.00014877689,0.00017593314,0.00016228804,0.0002524115,0.0001323264,0.00047275354,0.00015955599,0.000006033975],"category_scores_gemma":[0.0011649781,0.00011673546,0.000060280658,0.0004440192,0.0010125353,0.000023679358,0.00033888346,0.00039737616,0.000034546916],"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":[0.001077593,0.00013439394,0.17417173,0.00025453934,0.00020001465,0.0000020451805,0.008423003,0.000021346994,0.4637854,0.24959378,0.0066597555,0.0956764],"study_design_scores_gemma":[0.0011128677,0.002475894,0.02193423,0.0003109865,0.000018333709,0.000017283739,0.00909666,0.014078954,0.5471866,0.1199331,0.28309545,0.0007396598],"about_ca_topic_score_codex":0.00018613125,"about_ca_topic_score_gemma":0.000068756686,"teacher_disagreement_score":0.2764357,"about_ca_system_score_codex":0.000047687183,"about_ca_system_score_gemma":0.0002734525,"threshold_uncertainty_score":0.47603336},"labels":[],"label_agreement":null},{"id":"W3157410578","doi":"10.30862/jn.v15i1.26","title":"Karakterisasi Nukleotida Daerah Ekson 5 dan 6 Gen LDLR Penduduk Papua","year":2019,"lang":"id","type":"article","venue":"Jurnal Natural","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Purdue Pharma (Canada)","funders":"","keywords":"Internal medicine; Molecular biology; Chemistry; Biology; Medicine","score_opus":0.0036970783387687317,"score_gpt":0.23529091768770474,"score_spread":0.23159383934893601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157410578","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9659809,0.004596075,0.000045406578,0.0006722738,0.003398505,0.0004802651,0.0000390543,0.000041384606,0.024746154],"genre_scores_gemma":[0.96754557,0.00046716566,0.0010707095,0.0012376602,0.0012221708,0.000005346342,0.0005382175,0.00008171701,0.027831424],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99702287,0.00020253035,0.0007550771,0.0006059379,0.0005570085,0.0008565562],"domain_scores_gemma":[0.99803144,0.00004458055,0.0005357749,0.0009165997,0.00019585007,0.0002757737],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003957093,0.00059870264,0.00051891315,0.00011290666,0.00020496442,0.00024863935,0.0008427545,0.00060405186,0.0003950441],"category_scores_gemma":[0.00019295583,0.0005411583,0.0004163002,0.00019540341,0.00012985496,0.000036070818,0.0005168024,0.0014172958,0.000976711],"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":[0.0014652156,0.0004361003,0.19711907,0.0012742656,0.0012784147,0.00013042276,0.0017172954,0.00034864058,0.7127256,0.00068869634,0.04832353,0.03449274],"study_design_scores_gemma":[0.003500682,0.00168675,0.10365829,0.00027867345,0.00019593313,0.0007081784,0.0005624807,0.0056045544,0.048477534,0.000024814137,0.83344746,0.0018546295],"about_ca_topic_score_codex":0.000025396428,"about_ca_topic_score_gemma":0.000023200888,"teacher_disagreement_score":0.78512394,"about_ca_system_score_codex":0.00009318566,"about_ca_system_score_gemma":0.00020976007,"threshold_uncertainty_score":0.99980116},"labels":[],"label_agreement":null},{"id":"W3157437194","doi":"10.1002/cpz1.113","title":"Learned Embeddings from Deep Learning to Visualize and Predict Protein Sets","year":2021,"lang":"en","type":"article","venue":"Current Protocols","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":123,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"Deutsche Forschungsgemeinschaft","keywords":"Computer science; Workflow; Artificial intelligence; Pipeline (software); ENCODE; Classifier (UML); Protocol (science); Machine learning; Inference; Natural language processing; Programming language; Biology","score_opus":0.02184703544408889,"score_gpt":0.36336791763347315,"score_spread":0.34152088218938426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157437194","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.938684,0.00049834675,0.01486524,0.0003544708,0.00014227336,0.043604616,0.000036056706,0.00013269992,0.0016822852],"genre_scores_gemma":[0.7334429,0.0001315328,0.051103476,0.0010370894,0.0015806201,0.20497555,0.00231997,0.00028377085,0.005125082],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99860996,0.00015199477,0.0003034358,0.00042639303,0.0002144573,0.00029378483],"domain_scores_gemma":[0.99921036,0.000017089953,0.0001320796,0.00033656444,0.0001222208,0.00018169856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002322891,0.00020914279,0.00019645187,0.000036439993,0.00012776615,0.00013717436,0.00018169566,0.00012925883,0.00010974218],"category_scores_gemma":[0.00083067274,0.00020763696,0.00006085936,0.000118993026,0.000042368873,0.000009800011,0.00041922758,0.00031262447,0.00004917585],"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":[0.00045706928,0.00036559423,0.04560076,0.0009958436,0.00015771619,0.000016852398,0.0021292083,0.0008737925,0.62546325,0.00036579423,0.0040298295,0.31954432],"study_design_scores_gemma":[0.0014231411,0.00062466675,0.0041153734,0.00048400406,0.000017613873,0.00001520742,0.00016992702,0.004880822,0.14081526,0.00017020166,0.8467857,0.00049808476],"about_ca_topic_score_codex":0.0000047320273,"about_ca_topic_score_gemma":0.0000053294934,"teacher_disagreement_score":0.84275585,"about_ca_system_score_codex":0.000015492742,"about_ca_system_score_gemma":0.00007578169,"threshold_uncertainty_score":0.8467189},"labels":[],"label_agreement":null},{"id":"W3180707480","doi":"10.1007/978-3-030-76732-7_5","title":"Adaptive Machine Learning Algorithm and Analytics of Big Genomic Data for Gene Prediction","year":2021,"lang":"en","type":"book-chapter","venue":"Intelligent systems reference library","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Manitoba","funders":"","keywords":"Computer science; Big data; Genome; Gene; Genomics; Machine learning; Confusion matrix; Computational genomics; Artificial intelligence; Coding (social sciences); Gene prediction; Computational biology; Data mining; Biology; Genetics; Mathematics","score_opus":0.05479591821128172,"score_gpt":0.2542025929547279,"score_spread":0.1994066747434462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3180707480","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014839433,0.096014395,0.6781615,0.00013115042,0.002919439,0.0040498525,0.04204422,0.00025875852,0.17493674],"genre_scores_gemma":[0.025076373,0.043228123,0.06162535,0.00015290327,0.002853198,0.000077338445,0.14533336,0.0004948727,0.7211585],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980689,0.0000617269,0.0008220355,0.0006119727,0.00021729789,0.00021804325],"domain_scores_gemma":[0.9980462,0.00006480503,0.0006914603,0.00096496346,0.0001237754,0.00010878296],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022533177,0.00039155892,0.0005450968,0.00014602668,0.00007723346,0.00007656887,0.0005531643,0.0005700205,0.00004202651],"category_scores_gemma":[0.000067217166,0.00037441487,0.00010290199,0.00003422506,0.00010605771,0.000021157803,0.0009411449,0.00043086856,0.000006629572],"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":[0.0022094643,0.00052862265,0.009755462,0.017136669,0.016463593,0.00012971337,0.0012872224,0.024801983,0.03185224,0.086781986,0.053194698,0.75585836],"study_design_scores_gemma":[0.00027498679,0.0007386899,0.000031948963,0.0005617113,0.00021931314,0.00008692629,0.00010800933,0.17897579,0.003043952,0.00018992355,0.8152405,0.00052826473],"about_ca_topic_score_codex":0.000024462935,"about_ca_topic_score_gemma":0.0000032674338,"teacher_disagreement_score":0.7620458,"about_ca_system_score_codex":0.0000178225,"about_ca_system_score_gemma":0.00020788955,"threshold_uncertainty_score":0.9998708},"labels":[],"label_agreement":null},{"id":"W3185589835","doi":"10.3819/ccbr.2021.160002","title":"From Saliva to Faeces and Everything in Between: A Guide to Biochemical Analysis Using Animal Samples for Biomarker Detection","year":2021,"lang":"en","type":"article","venue":"Comparative Cognition & Behavior Reviews","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Dogs Trust","keywords":"Margin (machine learning); White (mutation); Psychology; Biology; Computer science; Machine learning; Genetics","score_opus":0.12741900568565315,"score_gpt":0.42720036569488085,"score_spread":0.2997813600092277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185589835","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90831697,0.0014425828,0.08929851,0.00003868567,0.000026815103,0.0006940655,0.00014374415,0.000008484052,0.000030122388],"genre_scores_gemma":[0.94514924,0.00009369621,0.053123273,0.00022847376,0.00009959739,0.00018691721,0.0010914754,0.000011662985,0.000015646558],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99858505,0.00018359236,0.00054893846,0.0004049282,0.00009847049,0.0001790293],"domain_scores_gemma":[0.99926805,0.000064225605,0.00015430588,0.0002043201,0.00019439255,0.00011472302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003065802,0.00019108596,0.0004712313,0.00014791188,0.00008574792,0.000065801694,0.00008685606,0.0001002303,0.000028065519],"category_scores_gemma":[0.00042274513,0.00019142925,0.00014749393,0.00054378324,0.000031293133,0.00001206708,0.0001288365,0.00008665599,0.000007974925],"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":[0.00005944161,0.00004252755,0.02030267,0.000034970424,0.00008709572,0.0000010079987,0.0003931719,0.000019897958,0.97033554,9.861227e-7,0.00041360463,0.008309072],"study_design_scores_gemma":[0.00085464725,0.00030530884,0.20222013,0.0002527493,0.0016586402,0.000011652689,0.00080785016,0.0016815346,0.7366724,0.000015187346,0.05482713,0.0006928021],"about_ca_topic_score_codex":0.000047262925,"about_ca_topic_score_gemma":0.00023794004,"teacher_disagreement_score":0.23366319,"about_ca_system_score_codex":0.000033134387,"about_ca_system_score_gemma":0.000027259008,"threshold_uncertainty_score":0.7806259},"labels":[],"label_agreement":null},{"id":"W3196067893","doi":"10.7554/elife.69719","title":"A proteome-wide genetic investigation identifies several SARS-CoV-2-exploited host targets of clinical relevance","year":2021,"lang":"en","type":"article","venue":"eLife","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"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":"Medical Research Council; Academy of Medical Sciences; Medical Research Council Canada; Wellcome Trust","keywords":"ABO blood group system; Proteome; Biology; Computational biology; Genetics","score_opus":0.027209362550509156,"score_gpt":0.32400535332943264,"score_spread":0.2967959907789235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196067893","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.994063,0.00042913124,0.0042189104,0.00035895497,0.00033685565,0.000188593,0.0000135128685,0.000022150565,0.00036890063],"genre_scores_gemma":[0.96014684,0.00032864022,0.036190145,0.0018567722,0.00033907167,0.00002341842,0.00023765494,0.000028141023,0.0008493104],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99840075,0.00016927754,0.000704531,0.0002740212,0.00025955352,0.0001918477],"domain_scores_gemma":[0.99882257,0.000050677187,0.00032441944,0.00044615028,0.00029671812,0.000059463564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037413609,0.00014287826,0.00023817955,0.00003316434,0.00005347617,0.000026174068,0.0001775584,0.0001811737,0.000012182513],"category_scores_gemma":[0.0034655074,0.00014500234,0.00012235474,0.00014063256,0.00013825281,0.000008723656,0.00016964205,0.00019131035,0.000034487424],"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":[0.00005451033,0.00005675294,0.15090919,0.00014282536,0.000079465026,0.000009052451,0.00016606033,0.00023000754,0.83667713,0.00001729424,0.011323142,0.0003345934],"study_design_scores_gemma":[0.00050467695,0.00013623982,0.11912147,0.000046750025,0.000017228595,0.0000135466225,0.000044545788,0.0015057205,0.8594032,0.000046635716,0.018978696,0.00018130666],"about_ca_topic_score_codex":0.00001844253,"about_ca_topic_score_gemma":0.00003789236,"teacher_disagreement_score":0.03391614,"about_ca_system_score_codex":0.000007401854,"about_ca_system_score_gemma":0.0001883678,"threshold_uncertainty_score":0.59130234},"labels":[],"label_agreement":null},{"id":"W3199268518","doi":"10.1038/s41598-021-97669-7","title":"Deep neural network for detecting arbitrary precision peptide features through attention based segmentation","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bioinformatics Solutions (Canada); University of Waterloo","funders":"National Key Research and Development Program of China; University of Waterloo; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Segmentation; Artificial neural network; Deep neural networks; Pattern recognition (psychology)","score_opus":0.010501164850782237,"score_gpt":0.2745427136113076,"score_spread":0.2640415487605254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199268518","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.765118,0.00054061017,0.22569358,0.00013625038,0.0057278485,0.00052577385,0.0000034725454,0.00005029535,0.0022041465],"genre_scores_gemma":[0.842921,0.0000041391286,0.1517733,0.00030020403,0.000406623,0.000049833714,0.0022235566,0.000027516333,0.002293811],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985239,0.0000675192,0.00038731116,0.0004962959,0.00026055166,0.00026445952],"domain_scores_gemma":[0.99886626,0.000031551444,0.00031475408,0.0005267193,0.00021288906,0.000047825506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007544012,0.0001293706,0.000109045664,0.000028037188,0.00041743557,0.0002262513,0.000081999606,0.000105680294,0.000016614202],"category_scores_gemma":[0.00048204235,0.00012466054,0.00014483776,0.00019658246,0.000056530647,0.000019322733,0.00007218782,0.000103748636,0.0000022281617],"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":[0.00007703275,0.00008947772,0.013436839,0.00017156341,0.00005138664,0.00004478099,0.00022183018,0.111876264,0.8280247,0.000037717484,0.031507514,0.014460933],"study_design_scores_gemma":[0.00085361383,0.00024202072,0.010421223,0.00011682866,0.00009671882,0.00072959624,0.000379794,0.12288938,0.79357684,0.004310258,0.06572559,0.00065817544],"about_ca_topic_score_codex":0.000003939418,"about_ca_topic_score_gemma":0.000038627604,"teacher_disagreement_score":0.07780299,"about_ca_system_score_codex":0.000017603445,"about_ca_system_score_gemma":0.00008514941,"threshold_uncertainty_score":0.50835097},"labels":[],"label_agreement":null},{"id":"W3200919677","doi":"10.1007/978-3-030-79290-9_4","title":"Metabolic Pathway Prediction using Non-negative Matrix Factorization with Improved Precision","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 British Columbia","funders":"","keywords":"Non-negative matrix factorization; Inference; Computer science; Probabilistic logic; Matrix decomposition; Cluster analysis; Metabolic pathway; Graph; Artificial intelligence; Genome; Computational biology; Machine learning; Data mining; Theoretical computer science; Biology; Gene; Genetics; Eigenvalues and eigenvectors","score_opus":0.007803126388566362,"score_gpt":0.24468162849882738,"score_spread":0.236878502110261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200919677","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":[0.007832774,0.00021724947,0.9904232,0.000015677582,0.00058616506,0.00035573146,0.000027109918,0.000017217495,0.0005248841],"genre_scores_gemma":[0.5335792,0.000106139756,0.4641468,0.00019566427,0.0009576234,0.000008061831,0.00027384388,0.00007054901,0.00066217687],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831,0.00002670116,0.0003319008,0.0006478905,0.0004113726,0.00027210056],"domain_scores_gemma":[0.998713,0.000051975258,0.0003102335,0.00054441614,0.00030733988,0.00007304264],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002832733,0.00033474868,0.0002844796,0.00020569123,0.00015088203,0.00014410567,0.000395331,0.000293011,0.000012350407],"category_scores_gemma":[0.00015913484,0.000274269,0.000066540066,0.00021781908,0.000224642,0.000024058503,0.00035425252,0.0004049378,0.0000020596644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012265936,0.000054782653,0.0014957947,0.00017061734,0.000117181386,0.000016702297,0.0011190644,0.44796064,0.33214658,0.00035257608,0.000008273769,0.21643512],"study_design_scores_gemma":[0.00055619556,0.00057692267,0.0005187796,0.00037688296,0.000037462178,0.00007678533,0.0000011839288,0.7642394,0.2301983,0.0009241045,0.0018913364,0.00060270145],"about_ca_topic_score_codex":0.000014314877,"about_ca_topic_score_gemma":0.000032715798,"teacher_disagreement_score":0.5262764,"about_ca_system_score_codex":0.00007251215,"about_ca_system_score_gemma":0.00047447093,"threshold_uncertainty_score":0.999971},"labels":[],"label_agreement":null},{"id":"W3201602850","doi":"10.17762/de.vi.4293","title":"Sars-Cov-2 Spike protein function prediction using a convolutional neural network ensemble","year":2021,"lang":"en","type":"article","venue":"Design Engineering","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Deep learning; Spike (software development); Focus (optics); Machine learning; Artificial neural network; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Function (biology); Protein sequencing; Field (mathematics); Protein function prediction; Coronavirus disease 2019 (COVID-19); Computational biology; Peptide sequence; Protein function; Biology; Medicine","score_opus":0.020263610420587032,"score_gpt":0.23151391880255925,"score_spread":0.21125030838197223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201602850","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32647374,0.00017597573,0.67282146,0.000012496316,0.0002589105,0.000118681695,0.0000029031078,0.000044770397,0.00009104968],"genre_scores_gemma":[0.92855155,0.0000043135196,0.070492454,0.00009835654,0.0005833668,0.000019271238,0.00012368066,0.000028940083,0.00009808382],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992378,0.00004094657,0.00018869157,0.00017492464,0.000119657634,0.00023798228],"domain_scores_gemma":[0.99965566,0.000009203826,0.00005270605,0.00017778597,0.00007317248,0.000031481402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017603778,0.00013276664,0.00009523199,0.000028323164,0.00007519912,0.000032433712,0.000059853224,0.00011978748,0.0000064282544],"category_scores_gemma":[0.00010308845,0.00015152177,0.00005414888,0.00012697224,0.000011973751,0.0000097948605,0.000052682906,0.00014100852,0.0000055604573],"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":[0.000017052478,0.0000058128885,0.00017236169,0.000019288556,0.000020800746,0.000002205487,0.0000064378937,0.41306108,0.5861126,0.00010462584,0.0003453976,0.00013231608],"study_design_scores_gemma":[0.00021976791,0.00008631816,0.00060089806,0.000028607066,0.000016816015,0.000073405645,0.0000038021726,0.7479379,0.24698564,0.000027091839,0.003880811,0.00013892702],"about_ca_topic_score_codex":0.000004227476,"about_ca_topic_score_gemma":0.0000013861559,"teacher_disagreement_score":0.602329,"about_ca_system_score_codex":0.000028703953,"about_ca_system_score_gemma":0.00006073481,"threshold_uncertainty_score":0.61788785},"labels":[],"label_agreement":null},{"id":"W3205986286","doi":"10.1109/cibcb49929.2021.9562938","title":"Genome-scale prediction of bacterial promoters","year":2021,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Promoter; Genome; Computational biology; Gene; Biology; Genetics; Transcription (linguistics); False positive paradox; DNA; RNA polymerase II; Consensus sequence; Computer science; Gene expression; Artificial intelligence; Base sequence","score_opus":0.0052511590125378736,"score_gpt":0.21406366595680879,"score_spread":0.20881250694427092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205986286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9761451,0.000030460713,0.0057275533,0.00006114805,0.00015644616,0.00005923509,0.000026751835,0.00001091632,0.017782392],"genre_scores_gemma":[0.9827843,0.000031359905,0.013346848,0.000074786934,0.00018449551,0.000003433367,0.00076791964,0.000009646127,0.0027972632],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995927,0.000021036389,0.00014799915,0.0000948624,0.000064009415,0.000079355814],"domain_scores_gemma":[0.9996705,0.0000020192547,0.000047177422,0.00019214915,0.00006112919,0.000027014454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006692672,0.000052484276,0.0000628767,0.000011515722,0.000017707835,0.000007861068,0.000058057773,0.00006715845,0.00029617222],"category_scores_gemma":[0.000041171883,0.000048819275,0.00003982037,0.000037675865,0.000024510704,0.0000016621706,0.00006745249,0.000036259953,0.00000671736],"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":[0.00001426081,0.000024298668,0.0025270407,0.000025784831,0.000018037988,3.488689e-7,0.00006742624,0.000044302775,0.99629277,0.000017259272,0.00039262278,0.0005758495],"study_design_scores_gemma":[0.00042527379,0.00021319276,0.022697277,0.0000058200967,0.000012551484,0.000026869488,0.000093021365,0.0005094652,0.8916986,0.0000128554475,0.08421612,0.000088944376],"about_ca_topic_score_codex":0.0000021216217,"about_ca_topic_score_gemma":0.0000062303147,"teacher_disagreement_score":0.104594156,"about_ca_system_score_codex":0.000003644457,"about_ca_system_score_gemma":0.000042152347,"threshold_uncertainty_score":0.32428783},"labels":[],"label_agreement":null},{"id":"W3207684739","doi":"10.1101/2020.09.14.297424","title":"leADS: improved metabolic pathway inference based on active dataset subsampling","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; Compute Canada; Genome Canada","keywords":"Inference; Computer science; Machine learning; Artificial intelligence; Class (philosophy); License; Feature (linguistics); MIT License; Set (abstract data type); Training set; Data mining; Programming language","score_opus":0.016073216006060834,"score_gpt":0.2517440644266227,"score_spread":0.2356708484205619,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207684739","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8807421,0.0009915545,0.088790804,0.0010162289,0.002187458,0.0026588861,0.022842048,0.000662696,0.00010826411],"genre_scores_gemma":[0.9820623,0.00010617582,0.014919209,0.0017711207,0.00063244253,0.00017241605,0.000174567,0.00015925145,0.0000025597199],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99694026,0.0002001191,0.0006246043,0.0012163423,0.00039469782,0.0006240058],"domain_scores_gemma":[0.9964587,0.00007623821,0.0006670283,0.0021275238,0.0003120207,0.0003584663],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045475893,0.0007982195,0.000644594,0.00017678538,0.00017265373,0.00022610615,0.0010747387,0.0007850555,0.000037959053],"category_scores_gemma":[0.0014665006,0.00083649025,0.00020576012,0.00028654232,0.00013564073,0.000015615462,0.0009776683,0.0013406131,0.000091254],"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":[0.00017432564,0.00012005371,0.0016285424,0.0003627296,0.00018062229,0.000012220298,0.000008475518,0.0016114183,0.9949706,0.00022298364,0.0006947583,0.000013230083],"study_design_scores_gemma":[0.0008994406,0.0002921673,0.012490101,0.00021234718,0.00013417077,1.5354777e-8,0.000003343453,0.031131636,0.88078755,0.0000017303804,0.07268119,0.0013662822],"about_ca_topic_score_codex":0.00003720515,"about_ca_topic_score_gemma":0.000003292842,"teacher_disagreement_score":0.11418307,"about_ca_system_score_codex":0.00007201752,"about_ca_system_score_gemma":0.00097409304,"threshold_uncertainty_score":0.9994086},"labels":[],"label_agreement":null},{"id":"W3211711919","doi":"","title":"On minimizers and convolutional filters: a partial justification for the unreasonable effectiveness of CNNs in categorical sequence analysis.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Convolutional neural network; Categorical variable; Hash function; Pooling; Sequence (biology); Pattern recognition (psychology); Artificial intelligence; Initialization; Mathematics; Computer science; Gaussian; Algorithm; Statistics; Physics","score_opus":0.05336097870848226,"score_gpt":0.23010728968241811,"score_spread":0.17674631097393584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211711919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81758523,0.000072236915,0.18186136,0.000028326547,0.00006705225,0.00026803304,0.000047178255,0.000004575078,0.00006602929],"genre_scores_gemma":[0.9989123,0.00010301211,0.00029768102,0.000020324504,0.000019194133,0.000006617647,0.0005378395,0.0000064111455,0.00009662955],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912757,0.00017509062,0.00014754036,0.00037287446,0.000047464695,0.0001294387],"domain_scores_gemma":[0.99902105,0.0003098593,0.00016403724,0.0003550176,0.000113376875,0.000036636175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003875576,0.00013296925,0.00021487781,0.00008805765,0.0000549761,0.00001767343,0.0002090115,0.0001961477,0.0000065227564],"category_scores_gemma":[0.00025710973,0.00012435752,0.00014250199,0.0002325136,0.00014793401,0.0000046824343,0.00020620874,0.00018001585,4.3153125e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055866805,0.00007796165,0.02097761,0.000305528,0.000507779,0.0000054340244,0.00008722305,0.9638744,0.002669114,0.010827056,0.00003987484,0.000069324444],"study_design_scores_gemma":[0.0010609131,0.00016427864,0.044003345,0.00007691473,0.00077449746,0.0000026937196,0.00028362445,0.94803184,0.004155046,0.0010249029,0.00013811878,0.00028381264],"about_ca_topic_score_codex":0.00017878535,"about_ca_topic_score_gemma":0.000055003053,"teacher_disagreement_score":0.18156368,"about_ca_system_score_codex":0.00005592849,"about_ca_system_score_gemma":0.0001430632,"threshold_uncertainty_score":0.50711524},"labels":[],"label_agreement":null},{"id":"W3213380372","doi":"10.18280/ria.350506","title":"Q3 Accuracy and SOV Measure Analysis of Application of GA in Protein Secondary Structure Prediction","year":2021,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Soft computing; Artificial intelligence; Fuzzy logic; Measure (data warehouse); Machine learning; Class (philosophy); Value (mathematics); Data mining; Artificial neural network; Genetic algorithm; Face (sociological concept)","score_opus":0.009462598032123463,"score_gpt":0.2562440670326762,"score_spread":0.24678146900055276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213380372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9421427,0.00045433603,0.05657352,0.000056162713,0.000019705036,0.0001774516,0.000054633896,0.000004220749,0.00051723636],"genre_scores_gemma":[0.99763626,0.000058163772,0.0019548885,0.00001562092,0.00001714106,0.000009034632,0.00020892985,0.0000058396568,0.000094149946],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99916655,0.000048361755,0.00042126107,0.00018509722,0.00008818127,0.00009052165],"domain_scores_gemma":[0.9992794,0.000021103197,0.00020701665,0.00032591049,0.00014161615,0.000024949994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020313478,0.00007825505,0.00017128656,0.000096953336,0.000022652528,0.0000073855686,0.00009383412,0.000106993044,0.00005382881],"category_scores_gemma":[0.00029881028,0.00008035362,0.000058923702,0.00046699253,0.00005646149,0.000006600499,0.000060628463,0.00011140293,9.079653e-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":[0.000023240525,0.000041664807,0.013846507,0.00016512827,0.00008968971,3.809934e-7,0.00042550932,0.04045225,0.92228305,0.0002770056,0.000011199015,0.02238436],"study_design_scores_gemma":[0.000040111438,0.000057450976,0.0060215904,0.000031362484,0.000057501515,0.000004428253,0.00037140254,0.19068828,0.8017627,0.00011951491,0.0007754226,0.00007023235],"about_ca_topic_score_codex":0.000024545736,"about_ca_topic_score_gemma":0.00011220689,"teacher_disagreement_score":0.15023604,"about_ca_system_score_codex":0.0000073654196,"about_ca_system_score_gemma":0.00004891789,"threshold_uncertainty_score":0.32767254},"labels":[],"label_agreement":null},{"id":"W408182588","doi":"10.1007/978-3-319-08846-4_25","title":"Pairwise Rational Kernels Obtained by Automaton Operations","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Pairwise comparison; Computer science; Automaton; Finite-state machine; Sequence (biology); Theoretical computer science; Algorithm; Kernel (algebra); State (computer science); Artificial intelligence; Mathematics; Discrete mathematics","score_opus":0.006041113190459282,"score_gpt":0.23842748043244924,"score_spread":0.23238636724198997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W408182588","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":[0.0008886158,0.00015687774,0.9942468,0.00046641193,0.00039529635,0.00022404094,0.000020762742,0.00003891012,0.003562292],"genre_scores_gemma":[0.55381453,0.00008878291,0.4246412,0.0073819226,0.0017408604,0.000031872118,0.0013047287,0.000111113826,0.010885001],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984084,0.000027484342,0.00034912105,0.00054135773,0.00039017445,0.00028350286],"domain_scores_gemma":[0.99900746,0.000054848315,0.000121195306,0.0005698755,0.0001540152,0.00009260989],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043476556,0.00029980997,0.00022051424,0.00013963087,0.00018524982,0.00016022056,0.0006776404,0.00032175347,0.0000555903],"category_scores_gemma":[0.00018620923,0.00027576464,0.00007596354,0.00008549292,0.000363574,0.000009456754,0.0003397592,0.0003476253,0.000036607784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003643517,0.00007160958,0.00060176064,0.00016417775,0.00007710252,0.0000088394745,0.00055681163,0.6573034,0.03877659,0.011892362,0.005949242,0.28456166],"study_design_scores_gemma":[0.00044384517,0.00034960633,0.00010969351,0.00012046949,0.000013298695,0.000055467295,1.6023766e-7,0.8976054,0.011607421,0.0029982908,0.08591123,0.00078507466],"about_ca_topic_score_codex":0.000007949885,"about_ca_topic_score_gemma":0.000038893682,"teacher_disagreement_score":0.5696056,"about_ca_system_score_codex":0.00005595085,"about_ca_system_score_gemma":0.000311844,"threshold_uncertainty_score":0.9999695},"labels":[],"label_agreement":null},{"id":"W4200475779","doi":"10.1016/j.mlwa.2021.100225","title":"Alzheimer’s disease diagnosis using genetic programming based on higher order spectra features","year":2021,"lang":"en","type":"article","venue":"Machine Learning with Applications","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Genetic programming; Computer science; Artificial intelligence; Machine learning; Disease; Linear discriminant analysis; Set (abstract data type); Computer-aided diagnosis; Field (mathematics); Pattern recognition (psychology); Medicine; Pathology; Mathematics","score_opus":0.010607035762924613,"score_gpt":0.2680442803859967,"score_spread":0.2574372446230721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200475779","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":[0.19497864,0.011829923,0.76493573,0.009845699,0.00031216518,0.004307824,0.00017525419,0.00085844647,0.01275631],"genre_scores_gemma":[0.76539725,0.00006039816,0.23011164,0.0011704208,0.0003408483,0.0007028055,0.0011342568,0.000107947526,0.0009744584],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.998606,0.00011178233,0.00022161433,0.0004712446,0.0002584313,0.00033088],"domain_scores_gemma":[0.9988161,0.000048168964,0.00015692561,0.00063211797,0.00015573093,0.0001909694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000096625285,0.00026909227,0.00016271345,0.00006887654,0.00037281626,0.00010732683,0.00020477039,0.000099268786,0.00014736896],"category_scores_gemma":[0.000109947505,0.0002401709,0.00008083603,0.00040337388,0.00008830186,0.000005134542,0.00008419857,0.00040011154,0.000024918616],"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":[0.00018458953,0.0005576792,0.3902928,0.00012134236,0.00022057649,0.000033389006,0.000062968815,0.570916,0.0027372101,0.00084572803,0.0005751876,0.033452533],"study_design_scores_gemma":[0.0015066725,0.0005114487,0.13417843,0.00010751011,0.00049257185,0.00005463796,0.000043864566,0.108839005,0.0062454543,0.000052664007,0.7468975,0.0010702275],"about_ca_topic_score_codex":0.000035890924,"about_ca_topic_score_gemma":0.000023528888,"teacher_disagreement_score":0.74632233,"about_ca_system_score_codex":0.00002197576,"about_ca_system_score_gemma":0.00018158478,"threshold_uncertainty_score":0.97938854},"labels":[],"label_agreement":null},{"id":"W4205272967","doi":"10.1109/bibm52615.2021.9669606","title":"Improving human essential protein prediction using only protein sequences via ensemble learning","year":2021,"lang":"en","type":"article","venue":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","topic":"Machine Learning in Bioinformatics","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":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Computer science; Ensemble learning; Machine learning; Boosting (machine learning); Artificial intelligence; Centrality; Data mining; Mathematics","score_opus":0.023492429156375547,"score_gpt":0.29623687718337544,"score_spread":0.2727444480269999,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205272967","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93687963,0.000054697928,0.05348958,0.00062509644,0.00052019407,0.0004253597,0.000053849693,0.000038244067,0.007913327],"genre_scores_gemma":[0.9845877,0.000072347844,0.011445616,0.00017460503,0.00063687935,0.000015006269,0.0008312963,0.000022817243,0.0022136744],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808687,0.00006899308,0.0006726465,0.00031872647,0.0005444246,0.00030835447],"domain_scores_gemma":[0.9987085,0.000011755912,0.00043455398,0.00025532243,0.00045151712,0.00013835458],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039782014,0.00028695428,0.0002440627,0.00021608676,0.0002769475,0.00021225361,0.00025513765,0.00021438338,0.00019668342],"category_scores_gemma":[0.00018804503,0.000255761,0.000079397745,0.00019834143,0.00019156495,0.000051832445,0.00018224324,0.0003885615,0.000016393911],"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":[0.000045301993,0.000057212335,0.0004037449,0.00014806117,0.0000928619,0.000011517034,0.0002165442,0.00016961135,0.98500586,0.0011839478,0.00010854268,0.012556818],"study_design_scores_gemma":[0.0017468018,0.0012818543,0.00022559507,0.0007261543,0.000058671787,0.0003135843,0.0014634434,0.56334704,0.42401406,0.00036663451,0.005830378,0.00062579784],"about_ca_topic_score_codex":0.00009602024,"about_ca_topic_score_gemma":0.00003095851,"teacher_disagreement_score":0.5631774,"about_ca_system_score_codex":0.000049914943,"about_ca_system_score_gemma":0.0002856139,"threshold_uncertainty_score":0.99998945},"labels":[],"label_agreement":null},{"id":"W4210342685","doi":"10.1101/2022.01.25.477715","title":"TooT-SC: Predicting Eleven Substrate Classes of Transmembrane Transport Proteins","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; King Saud University; Concordia University; Saudi Arabian Cultural Bureau; Genome Canada","keywords":"Pairwise comparison; Substrate (aquarium); Proteome; Computational biology; Computer science; Genome; Sequence (biology); Substrate specificity; Chemistry; Biology; Artificial intelligence; Biochemistry; Gene; Enzyme","score_opus":0.009160644691717061,"score_gpt":0.22229735756074026,"score_spread":0.2131367128690232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210342685","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99308926,0.0007130589,0.0033551743,0.000085981075,0.00054211734,0.0011573116,0.00073346816,0.00016774728,0.00015588115],"genre_scores_gemma":[0.99003756,0.00031810201,0.008711182,0.00009318474,0.00033653836,0.0002930996,0.0000147526625,0.00016168381,0.000033900862],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9967829,0.00018211389,0.0010262416,0.00085822045,0.00056359736,0.0005869242],"domain_scores_gemma":[0.9972097,0.000026741553,0.0008130096,0.0014428729,0.00030545064,0.00020221404],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00087424566,0.000629482,0.00066162826,0.00018618825,0.00018231543,0.000053216234,0.00095465383,0.00066784624,0.00015155172],"category_scores_gemma":[0.00016788683,0.0007068627,0.00033770024,0.00031238943,0.00016758504,0.00001526279,0.00034939742,0.0011516898,0.0000052110713],"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":[0.00012367597,0.00018337503,0.044254526,0.0015908944,0.00034341693,0.000020900627,0.000033733297,0.002939191,0.9502931,0.00013694161,0.000076963304,0.0000032782225],"study_design_scores_gemma":[0.000973611,0.00045768314,0.118125424,0.00031322349,0.00024832357,1.2463694e-7,0.000014652976,0.0010718388,0.85805064,0.0000013565939,0.01959062,0.0011525146],"about_ca_topic_score_codex":0.000070794165,"about_ca_topic_score_gemma":0.000011364214,"teacher_disagreement_score":0.09224248,"about_ca_system_score_codex":0.00006845562,"about_ca_system_score_gemma":0.0009040247,"threshold_uncertainty_score":0.99953824},"labels":[],"label_agreement":null},{"id":"W4210826824","doi":"10.2142/biophysico.bppb-v19.0002","title":"Information quantity for secondary structure propensities of protein subsequences in the Protein Data Bank","year":2022,"lang":"en","type":"article","venue":"Biophysics and Physicobiology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Institute of Genetics; University of Tokyo","keywords":"Subsequence; Protein Data Bank; Protein Data Bank (RCSB PDB); Protein secondary structure; Sequence (biology); Protein structure; Proteome; Computer science; Biology; Computational biology; Mathematics; Bioinformatics; Genetics; Biochemistry","score_opus":0.015794659497090656,"score_gpt":0.25222189513027427,"score_spread":0.2364272356331836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210826824","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9972442,0.00010434427,0.00024409572,0.00017571727,0.000048524667,0.0008889425,0.0011517426,0.0000040330424,0.00013840527],"genre_scores_gemma":[0.99622434,0.000005234987,0.0006725699,0.00019992063,0.000073543095,0.00011066902,0.0026894498,0.0000056850554,0.000018568831],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999287,0.00012718834,0.00022522827,0.00013640031,0.00008164108,0.0001425386],"domain_scores_gemma":[0.9993184,0.000017677194,0.00020973195,0.00039709307,0.000045464596,0.00001164108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002946774,0.00011165904,0.00015067395,0.000028933418,0.00014138749,0.000021539361,0.0004424944,0.00005159308,0.00000618033],"category_scores_gemma":[0.00003640865,0.0000821224,0.000030122324,0.00009473172,0.00014624941,0.000027457754,0.0003515435,0.00016338805,3.6054584e-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":[0.00031849334,0.00011780553,0.0010880216,0.00042416097,0.000059913287,3.3687013e-7,0.0013736222,0.00021106754,0.95569664,0.030042231,0.00056674104,0.010100935],"study_design_scores_gemma":[0.0069336533,0.013506388,0.024764208,0.00012699344,0.0001385681,0.00010934731,0.013252067,0.015825389,0.53893375,0.041040465,0.34298953,0.0023796463],"about_ca_topic_score_codex":0.00011225049,"about_ca_topic_score_gemma":0.000034808276,"teacher_disagreement_score":0.41676292,"about_ca_system_score_codex":0.000005223114,"about_ca_system_score_gemma":0.00009897304,"threshold_uncertainty_score":0.33488542},"labels":[],"label_agreement":null},{"id":"W4226070976","doi":"10.3389/frobt.2022.876814","title":"An Invitation to Greater Use of Matthews Correlation Coefficient in Robotics and Artificial Intelligence","year":2022,"lang":"en","type":"article","venue":"Frontiers in Robotics and AI","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Robotics; Artificial intelligence; Computer science; Correlation coefficient; Correlation; Machine learning; Robot; Mathematics","score_opus":0.0154577435544143,"score_gpt":0.26118271107865065,"score_spread":0.24572496752423637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226070976","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4346487,0.000055205073,0.564474,0.00036241297,0.00023972409,0.00019135428,0.000012016371,0.0000032777,0.000013334776],"genre_scores_gemma":[0.92256844,0.0000266333,0.07687793,0.00037760503,0.000014834416,0.0000071135737,0.00008213939,0.000010304589,0.000034994064],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992417,0.00007427975,0.00028579636,0.00016589527,0.00010498148,0.00012734243],"domain_scores_gemma":[0.999693,0.000010497604,0.000077636454,0.00014502172,0.000028847558,0.00004503531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023330442,0.000089285786,0.0001246586,0.00015006294,0.00005426905,0.000030471827,0.00007528537,0.00005772703,0.0000028254424],"category_scores_gemma":[0.00006427284,0.000095582654,0.000013769146,0.00014704076,0.000047227386,0.000010198377,0.000109791974,0.00013432482,2.89541e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060699236,0.00005074359,0.09851808,0.000017259885,0.000004321478,0.0000010415625,0.0007931559,0.8950122,0.0008530109,0.00053058885,0.00028204735,0.003876875],"study_design_scores_gemma":[0.00012824325,0.00044992703,0.0147100445,0.000015590736,0.000008840705,0.0000048749584,0.0008797306,0.9819394,0.00072815974,0.0005087848,0.0004688087,0.00015763975],"about_ca_topic_score_codex":0.000023373434,"about_ca_topic_score_gemma":0.000027618635,"teacher_disagreement_score":0.48791978,"about_ca_system_score_codex":0.000021253843,"about_ca_system_score_gemma":0.000017595868,"threshold_uncertainty_score":0.38977474},"labels":[],"label_agreement":null},{"id":"W4231686096","doi":"10.1145/956790.956800","title":"Frequent-subsequence-based prediction of outer membrane proteins","year":2003,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"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":"Bacterial outer membrane; Subsequence; Support vector machine; Computational biology; Classifier (UML); Bacteria; Membrane protein; Computer science; Artificial intelligence; Biology; Bioinformatics; Machine learning; Pattern recognition (psychology); Membrane; Biochemistry; Mathematics; Gene; Genetics","score_opus":0.01055053056386303,"score_gpt":0.22808657895268855,"score_spread":0.2175360483888255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231686096","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8171511,0.00007872345,0.10291007,0.00016034699,0.00020270095,0.00053288235,0.00004070929,0.000050303566,0.07887315],"genre_scores_gemma":[0.96946603,0.000008325266,0.029045478,0.0002446443,0.000033462416,0.000018462219,0.00009551673,0.000011570086,0.0010765361],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99933225,0.000050571183,0.00022719782,0.00012761255,0.00012728914,0.00013507898],"domain_scores_gemma":[0.999497,0.0000053101435,0.00009317716,0.00029097454,0.00007032444,0.00004323408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018885966,0.00009668761,0.0000896571,0.000033637054,0.000029539482,0.000008461321,0.00010003397,0.00010909448,0.00018327154],"category_scores_gemma":[0.00015565887,0.0000818679,0.000058979545,0.00006010253,0.000057593876,0.0000031156799,0.000014938509,0.000069638394,0.00001188627],"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":[0.000027512438,0.00007618079,0.014222803,0.0000862284,0.000036624955,0.0000010151425,0.00003646425,0.0013174694,0.98088527,0.0021507263,0.0006379659,0.00052173954],"study_design_scores_gemma":[0.00051163044,0.00027480614,0.00095963385,0.000012561238,0.000009519371,0.000008973685,0.000018122404,0.0013615969,0.97523445,0.000042717027,0.021467505,0.00009848314],"about_ca_topic_score_codex":0.000013241676,"about_ca_topic_score_gemma":0.000007089957,"teacher_disagreement_score":0.15231489,"about_ca_system_score_codex":0.000008280776,"about_ca_system_score_gemma":0.00007449434,"threshold_uncertainty_score":0.33384758},"labels":[],"label_agreement":null},{"id":"W4233843323","doi":"10.1142/18609475730015","title":"PROTEIN FOLD RECOGNITION USING THE GRADIENT BOOST ALGORITHM","year":2006,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Bioinformatics Solutions (Canada); University of Alberta","funders":"","keywords":"Fold (higher-order function); Computer science; Algorithm; Programming language","score_opus":0.010847453596249258,"score_gpt":0.23837099948997534,"score_spread":0.2275235458937261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233843323","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83711404,0.00011898019,0.14072666,0.00027502546,0.00012176795,0.00047414697,0.000015850743,0.000036896636,0.021116631],"genre_scores_gemma":[0.8046215,0.000010612443,0.18876508,0.0007235316,0.00072918076,0.0000415596,0.00042691125,0.000035631056,0.004645978],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99945724,0.000033505887,0.00015282723,0.00011110896,0.00009286385,0.00015246948],"domain_scores_gemma":[0.99967206,0.0000040137993,0.000062125895,0.00019675709,0.00004461182,0.000020449696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014766413,0.00008938897,0.000051647723,0.000017102182,0.000110661684,0.000032244163,0.0000995975,0.00006761578,0.000037569647],"category_scores_gemma":[0.000024615518,0.000060390288,0.000047259135,0.000051894927,0.000039594273,0.0000025303286,0.000058105245,0.00007589416,0.00002073064],"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":[0.00005481306,0.00023498318,0.0019445134,0.00007843105,0.00010306727,0.000006009683,0.00013481121,0.0011520573,0.7683963,0.00096941635,0.017395237,0.20953032],"study_design_scores_gemma":[0.001059679,0.00043634768,0.0014427634,0.00004887792,0.000052449694,0.0001461877,0.00022291522,0.16682576,0.6499024,0.0017043457,0.17744897,0.0007092991],"about_ca_topic_score_codex":0.00016892178,"about_ca_topic_score_gemma":0.000033034943,"teacher_disagreement_score":0.20882101,"about_ca_system_score_codex":0.000010105136,"about_ca_system_score_gemma":0.000018546307,"threshold_uncertainty_score":0.24626444},"labels":[],"label_agreement":null},{"id":"W4233935614","doi":"10.1101/462812","title":"PSL-Recommender: Protein Subcellular Localization Prediction using Recommender System","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Recommender system; PSL; Computer science; Matrix decomposition; Machine learning; Subcellular localization; Artificial intelligence; Information retrieval; Mathematics; Biology; Gene","score_opus":0.013288493950086482,"score_gpt":0.22495588502775804,"score_spread":0.21166739107767155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233935614","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6241857,0.0006739934,0.370196,0.000102368416,0.0022151715,0.0017408697,0.00032119005,0.00048351902,0.00008118182],"genre_scores_gemma":[0.9770705,0.00007878201,0.020806748,0.00019556873,0.001444773,0.00015930027,0.000021465372,0.00020931954,0.000013549884],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9967876,0.0003440028,0.00088824355,0.00097450806,0.0004078239,0.00059780973],"domain_scores_gemma":[0.99669564,0.0000111321115,0.00082303456,0.0016100444,0.0006215776,0.00023855428],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009923833,0.00067999924,0.00048772464,0.00022381822,0.00033320152,0.00023085614,0.0005913995,0.0011852738,0.00003574502],"category_scores_gemma":[0.00021428493,0.00075851777,0.00019302565,0.00027671416,0.00012490852,0.00002123224,0.00079480413,0.0006764684,0.000050443705],"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":[0.00011513099,0.00018998652,0.0126798805,0.00307018,0.00052997255,0.000013720663,0.00002572421,0.005242686,0.9729046,0.00023996993,0.0049827653,0.0000053853073],"study_design_scores_gemma":[0.0011457035,0.00035384166,0.0018465408,0.0015119562,0.00029269606,3.8399097e-7,0.000021394639,0.24642873,0.69741845,0.0000020593652,0.049247842,0.0017304356],"about_ca_topic_score_codex":0.000049926144,"about_ca_topic_score_gemma":0.0000017741913,"teacher_disagreement_score":0.3528848,"about_ca_system_score_codex":0.0003889213,"about_ca_system_score_gemma":0.00043728398,"threshold_uncertainty_score":0.99948657},"labels":[],"label_agreement":null},{"id":"W4233999394","doi":"10.32920/ryerson.14657172","title":"Protein structural class prediction using predicted secondary structure and hydropathy profile","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Support vector machine; Artificial intelligence; Computer science; Class (philosophy); Machine learning; Feature (linguistics); Sequence (biology); Pattern recognition (psychology); Protein structure prediction; Data mining; Protein folding; Protein structure; Biology","score_opus":0.005863915885939899,"score_gpt":0.23447385058648523,"score_spread":0.22860993470054533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233999394","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9931754,0.00040875454,0.0028237065,0.000044673172,0.0004519094,0.00088150555,0.00081161706,0.00007484529,0.0013275822],"genre_scores_gemma":[0.956843,0.00002213591,0.035620835,0.000110118366,0.00047544553,0.00002741154,0.006325421,0.000053689782,0.0005219532],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982569,0.00012971298,0.0004579538,0.0006147381,0.00024923254,0.0002914413],"domain_scores_gemma":[0.998773,0.000004760978,0.00030399772,0.000630078,0.00016903455,0.00011912256],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001181283,0.00041133226,0.0003182333,0.00007289625,0.00013818506,0.00017533655,0.00022903807,0.0008828766,0.00027013122],"category_scores_gemma":[0.00011912961,0.0003760661,0.00009799919,0.00006738442,0.0001108619,0.000010177116,0.001257002,0.0009926327,5.22731e-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":[0.00015283686,0.000023065499,0.013090949,0.0025013937,0.00050638674,0.000016568647,0.0006418749,0.007648197,0.968767,0.00007439358,0.00085023005,0.005727145],"study_design_scores_gemma":[0.0015166563,0.00048563554,0.02000012,0.000466624,0.0002045356,0.0004826038,0.0003974895,0.63822424,0.33349544,0.0003043298,0.00306043,0.0013618943],"about_ca_topic_score_codex":0.000046005087,"about_ca_topic_score_gemma":0.000023482156,"teacher_disagreement_score":0.63527155,"about_ca_system_score_codex":0.00004029878,"about_ca_system_score_gemma":0.00038694718,"threshold_uncertainty_score":0.9998691},"labels":[],"label_agreement":null},{"id":"W4234840673","doi":"10.1007/978-3-642-24797-2_1","title":"Introduction","year":2012,"lang":"en","type":"book-chapter","venue":"Studies in computational intelligence","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 New Brunswick; University of Toronto","funders":"","keywords":"Computer science; Sequence (biology); Labelling; Artificial intelligence; Natural language processing; Set (abstract data type); Speech recognition; Biology; Genetics","score_opus":0.04486943339293821,"score_gpt":0.3442040878256094,"score_spread":0.2993346544326712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234840673","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":[0.0005793807,0.06519945,0.1559252,0.0029582493,0.0073709292,0.0012278616,0.00009770507,0.00011819127,0.766523],"genre_scores_gemma":[0.15529172,0.01914538,0.07651488,0.0014812327,0.015230715,0.00008389976,0.0025180094,0.00023695164,0.7294972],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989643,0.000016633001,0.00039239123,0.00026003085,0.0002004233,0.00016619099],"domain_scores_gemma":[0.9993087,0.000058613394,0.00018546067,0.00020731318,0.00020801448,0.000031871627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023927582,0.00022537573,0.00020822043,0.0000953571,0.000057712743,0.000009326484,0.00016872812,0.00017529825,0.00015434188],"category_scores_gemma":[0.00019364356,0.00022739207,0.00007101699,0.000027798951,0.0002512957,0.000004091682,0.00023180855,0.00027541374,0.00023683687],"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":[0.00010336504,0.000069783826,0.00037012313,0.0005187651,0.00075433374,0.00000846843,0.0013004892,0.31633565,0.00006295093,0.5076216,0.078737296,0.09411717],"study_design_scores_gemma":[0.000081927916,0.00018454473,0.00008885744,0.0001382661,0.000035893194,0.00006722398,0.00015305835,0.0024044602,0.00029746126,0.06251889,0.9334327,0.0005967378],"about_ca_topic_score_codex":0.0000011726052,"about_ca_topic_score_gemma":0.0000084082885,"teacher_disagreement_score":0.8546954,"about_ca_system_score_codex":0.00006068313,"about_ca_system_score_gemma":0.000042386873,"threshold_uncertainty_score":0.927278},"labels":[],"label_agreement":null},{"id":"W4238654208","doi":"10.1109/iembs.2006.4397454","title":"FRET Evidence that an Isoform of Caspase-7 Binds but Does Not Cleave its Substrate","year":2006,"lang":"en","type":"article","venue":"Conference proceedings","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Cleave; Förster resonance energy transfer; Gene isoform; Substrate (aquarium); Chemistry; Cell biology; Focus (optics); Biophysics; Biology; Fluorescence; Physics; Biochemistry; Enzyme; Gene; Optics","score_opus":0.03238882096476913,"score_gpt":0.27160260188080615,"score_spread":0.239213780916037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238654208","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.994929,0.00009424986,0.00052368885,0.00020751338,0.00008680446,0.00019269809,0.000037665082,0.00003739246,0.0038909658],"genre_scores_gemma":[0.9968101,0.00011513757,0.0013444527,0.00012901523,0.00015617028,0.000017483073,0.00005381473,0.000021866117,0.0013519627],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987117,0.000009955093,0.00035386425,0.0003281984,0.00026183669,0.00033447007],"domain_scores_gemma":[0.9988001,0.000015023746,0.00040787846,0.00021052509,0.00047056642,0.00009591862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030278903,0.00023272364,0.00021706051,0.00006707415,0.00008652136,0.000106343905,0.00045324783,0.00022068116,0.00006303921],"category_scores_gemma":[0.00020768082,0.00018515484,0.00006782377,0.000093251925,0.00015324217,0.000054197822,0.0001374432,0.00019063365,0.00001561482],"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":[0.000096336174,0.00004526842,0.05249469,0.00024312564,0.000016907608,0.0000012529235,0.000393342,0.00000894045,0.94283855,0.0023704297,0.00035570172,0.0011354673],"study_design_scores_gemma":[0.00025413142,0.00039878988,0.020330044,0.00011276635,0.000023244325,0.000020559488,0.00056365086,0.0029281436,0.974206,0.00026649988,0.00059628097,0.00029993086],"about_ca_topic_score_codex":0.0001089878,"about_ca_topic_score_gemma":0.000056724242,"teacher_disagreement_score":0.032164644,"about_ca_system_score_codex":0.000014083837,"about_ca_system_score_gemma":0.0001071057,"threshold_uncertainty_score":0.7550396},"labels":[],"label_agreement":null},{"id":"W4239646953","doi":"10.1142/18609475730045","title":"AN ITERATIVE ALGORITHM TO QUANTIFY THE FACTORS INFLUENCING PEPTIDE FRAGMENTATION FOR MS/MS SPECTRUM","year":2006,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Fragmentation (computing); Algorithm; Computer science; Iterative method","score_opus":0.008144909553516195,"score_gpt":0.28398687478536905,"score_spread":0.27584196523185284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239646953","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7711421,0.000009880519,0.2267961,0.0002715127,0.00007681469,0.00032458015,0.000024733352,0.000020690553,0.001333578],"genre_scores_gemma":[0.9515119,0.0000017860251,0.046228327,0.000615525,0.00023497335,0.000029634344,0.0004790347,0.000018270552,0.0008805093],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99925166,0.00003551537,0.00021724681,0.00018105043,0.00011005161,0.00020445995],"domain_scores_gemma":[0.99954,0.000027244725,0.00008214226,0.00024947355,0.000054917167,0.00004624123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015376894,0.00013874086,0.00008717533,0.00003516787,0.00016475945,0.00009016824,0.00017018041,0.00007347213,0.000036371453],"category_scores_gemma":[0.000042412663,0.00009460899,0.000057253434,0.00006941819,0.000026189005,0.00001052588,0.000039924274,0.000072668685,0.0000087690205],"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":[0.00022476158,0.00028452597,0.114221126,0.00010560455,0.0002200362,0.0000023078192,0.0056439866,0.031208765,0.8108023,0.0066116787,0.018938622,0.011736317],"study_design_scores_gemma":[0.0007223941,0.0013244859,0.10206717,0.000016046171,0.000031807267,0.0000092677565,0.0019743831,0.04200692,0.79468197,0.00049882586,0.05611345,0.0005532727],"about_ca_topic_score_codex":0.0004176046,"about_ca_topic_score_gemma":0.00046437274,"teacher_disagreement_score":0.18056779,"about_ca_system_score_codex":0.000019178378,"about_ca_system_score_gemma":0.000023769147,"threshold_uncertainty_score":0.38580427},"labels":[],"label_agreement":null},{"id":"W4239931746","doi":"10.1007/978-1-4614-6170-8_100636","title":"Link-Based Classification","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":69,"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","score_opus":0.013851742003556962,"score_gpt":0.2444461637120755,"score_spread":0.23059442170851854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239931746","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":[0.000022453212,0.00006736926,0.04799492,0.00039680794,0.00012937504,0.00013418736,0.000009846032,0.000038720562,0.9512063],"genre_scores_gemma":[0.010108523,0.000049702998,0.0068904697,0.0015580727,0.00066509825,0.000006473064,0.001718308,0.00006484557,0.9789385],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99924123,0.000010805578,0.0002537172,0.00023017795,0.00014208432,0.00012195921],"domain_scores_gemma":[0.99905753,0.0000103829825,0.0002037666,0.00058656884,0.000083857005,0.000057866215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013401579,0.00021767545,0.00015131227,0.00005057893,0.000041192092,0.00002267449,0.00020476182,0.00055599597,0.0004358837],"category_scores_gemma":[0.00005167072,0.00019906579,0.000119944925,0.0000064779492,0.00005975752,4.6144686e-7,0.000054911237,0.00021460606,0.00046441928],"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":[0.00012838587,0.00002801157,0.00037687572,0.00055946416,0.00029804744,0.0000019407275,0.000024126444,0.0007098727,0.01837916,0.57655585,0.24678606,0.15615219],"study_design_scores_gemma":[0.00016772626,0.00012745042,0.000052558073,0.000023927976,0.000021590482,0.0000025273991,6.256086e-7,0.00402039,0.0010381925,0.00032138132,0.9939622,0.0002613908],"about_ca_topic_score_codex":0.0000013942893,"about_ca_topic_score_gemma":0.000006166287,"teacher_disagreement_score":0.7471762,"about_ca_system_score_codex":0.000012208987,"about_ca_system_score_gemma":0.00007133619,"threshold_uncertainty_score":0.81176674},"labels":[],"label_agreement":null},{"id":"W4240815580","doi":"10.1109/ijcnn.2006.1716163","title":"Neural and Statistical Classification to Families of Bio-sequences","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Family Process Institute","keywords":"Computer science; Generalization; Property (philosophy); Artificial intelligence; Artificial neural network; Entropy (arrow of time); Feature (linguistics); Pattern recognition (psychology); Feature vector; String (physics); Machine learning; Mathematics","score_opus":0.027900896080192715,"score_gpt":0.2816318045052348,"score_spread":0.2537309084250421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240815580","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98493,0.00002372047,0.0012849106,0.003671526,0.00029852882,0.0002147638,0.00003393218,0.000020602974,0.009522059],"genre_scores_gemma":[0.99688363,0.000037932983,0.0016318355,0.0005555025,0.00044839614,0.00001842374,0.00005602941,0.000010814532,0.00035741745],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989806,0.000018376557,0.00033532892,0.00021675894,0.00025808878,0.00019085653],"domain_scores_gemma":[0.99940515,0.000026299587,0.00019263256,0.00009727756,0.00023324908,0.0000454151],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019663511,0.00015174391,0.0001301759,0.000052365438,0.00008013644,0.00007825201,0.00027684105,0.00006493688,0.000019764084],"category_scores_gemma":[0.00008742868,0.000110122346,0.000034619745,0.00008798034,0.00020881534,0.00001316674,0.00007768463,0.00014409621,0.000007972083],"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":[0.0007865092,0.00015535773,0.051362168,0.0001068407,0.000113989576,0.0000029513014,0.00041495904,0.023201928,0.57647073,0.25457042,0.07095627,0.021857895],"study_design_scores_gemma":[0.0013117824,0.0022860256,0.28840414,0.00027282798,0.000076545206,0.00016642753,0.00080636353,0.62351453,0.05127065,0.011210156,0.019549698,0.0011308152],"about_ca_topic_score_codex":0.00005651544,"about_ca_topic_score_gemma":0.000019522327,"teacher_disagreement_score":0.60031265,"about_ca_system_score_codex":0.000012001942,"about_ca_system_score_gemma":0.000020132802,"threshold_uncertainty_score":0.4490659},"labels":[],"label_agreement":null},{"id":"W4242991188","doi":"10.32920/ryerson.14657172.v1","title":"Protein structural class prediction using predicted secondary structure and hydropathy profile","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Support vector machine; Artificial intelligence; Class (philosophy); Computer science; Machine learning; Feature (linguistics); Sequence (biology); Pattern recognition (psychology); Protein structure prediction; Data mining; Protein folding; Folding (DSP implementation); Protein structure; Engineering; Biology","score_opus":0.005863915885939899,"score_gpt":0.23447385058648523,"score_spread":0.22860993470054533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242991188","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9931754,0.00040875454,0.0028237065,0.000044673172,0.0004519094,0.00088150555,0.00081161706,0.00007484529,0.0013275822],"genre_scores_gemma":[0.956843,0.00002213591,0.035620835,0.000110118366,0.00047544553,0.00002741154,0.006325421,0.000053689782,0.0005219532],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982569,0.00012971298,0.0004579538,0.0006147381,0.00024923254,0.0002914413],"domain_scores_gemma":[0.998773,0.000004760978,0.00030399772,0.000630078,0.00016903455,0.00011912256],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001181283,0.00041133226,0.0003182333,0.00007289625,0.00013818506,0.00017533655,0.00022903807,0.0008828766,0.00027013122],"category_scores_gemma":[0.00011912961,0.0003760661,0.00009799919,0.00006738442,0.0001108619,0.000010177116,0.001257002,0.0009926327,5.22731e-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":[0.00015283686,0.000023065499,0.013090949,0.0025013937,0.00050638674,0.000016568647,0.0006418749,0.007648197,0.968767,0.00007439358,0.00085023005,0.005727145],"study_design_scores_gemma":[0.0015166563,0.00048563554,0.02000012,0.000466624,0.0002045356,0.0004826038,0.0003974895,0.63822424,0.33349544,0.0003043298,0.00306043,0.0013618943],"about_ca_topic_score_codex":0.000046005087,"about_ca_topic_score_gemma":0.000023482156,"teacher_disagreement_score":0.63527155,"about_ca_system_score_codex":0.00004029878,"about_ca_system_score_gemma":0.00038694718,"threshold_uncertainty_score":0.9998691},"labels":[],"label_agreement":null},{"id":"W4243632465","doi":"10.32920/ryerson.14654334","title":"Structural Classification of Proteins Using Image Based Machine Learning","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Structural Classification of Proteins database; Convolutional neural network; Computer science; Artificial intelligence; Pattern recognition (psychology); Machine learning; Visualization; Rendering (computer graphics); Artificial neural network; Contextual image classification; Image (mathematics); Protein structure; Chemistry","score_opus":0.021765406013970413,"score_gpt":0.2890749217975099,"score_spread":0.26730951578353945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243632465","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89560515,0.00018255516,0.10160495,0.00006651487,0.00014025872,0.00034587114,0.000027494469,0.000029325261,0.001997872],"genre_scores_gemma":[0.84117323,0.000012969826,0.15629967,0.00004322032,0.00008665281,0.000010737418,0.0021037925,0.000032158823,0.00023759839],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986532,0.00015474789,0.00045303162,0.0003430405,0.00021401503,0.00018199495],"domain_scores_gemma":[0.9985898,0.000010973616,0.0005137095,0.0005818054,0.00025175945,0.000051967425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023403786,0.0002526724,0.000270891,0.000073033334,0.00007127415,0.000066672226,0.0002720836,0.0003750815,0.00016314328],"category_scores_gemma":[0.00033241292,0.0002394706,0.00017316533,0.000070264425,0.000082904946,0.0000036865042,0.0005447373,0.00057773903,0.0000014251343],"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":[0.000037404596,0.000025885523,0.013845955,0.00072197994,0.000080069,0.0000014766905,0.00008082066,0.035968743,0.94839764,0.000037104062,0.000026070386,0.0007768254],"study_design_scores_gemma":[0.0002733873,0.00007919442,0.0047088554,0.00008791733,0.000039621937,0.000007835164,0.00008113862,0.78253126,0.21151021,0.000009370288,0.0003818452,0.00028937517],"about_ca_topic_score_codex":0.00017812119,"about_ca_topic_score_gemma":0.000038282895,"teacher_disagreement_score":0.7465625,"about_ca_system_score_codex":0.00002801077,"about_ca_system_score_gemma":0.00028693464,"threshold_uncertainty_score":0.97653276},"labels":[],"label_agreement":null},{"id":"W4243839871","doi":"10.32920/ryerson.14654334.v1","title":"Structural Classification of Proteins Using Image Based Machine Learning","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Structural Classification of Proteins database; Convolutional neural network; Computer science; Artificial intelligence; Pattern recognition (psychology); Visualization; Machine learning; Rendering (computer graphics); Artificial neural network; Contextual image classification; Class (philosophy); Image (mathematics); Protein structure; Chemistry","score_opus":0.021765406013970413,"score_gpt":0.2890749217975099,"score_spread":0.26730951578353945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243839871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89560515,0.00018255516,0.10160495,0.00006651487,0.00014025872,0.00034587114,0.000027494469,0.000029325261,0.001997872],"genre_scores_gemma":[0.84117323,0.000012969826,0.15629967,0.00004322032,0.00008665281,0.000010737418,0.0021037925,0.000032158823,0.00023759839],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986532,0.00015474789,0.00045303162,0.0003430405,0.00021401503,0.00018199495],"domain_scores_gemma":[0.9985898,0.000010973616,0.0005137095,0.0005818054,0.00025175945,0.000051967425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023403786,0.0002526724,0.000270891,0.000073033334,0.00007127415,0.000066672226,0.0002720836,0.0003750815,0.00016314328],"category_scores_gemma":[0.00033241292,0.0002394706,0.00017316533,0.000070264425,0.000082904946,0.0000036865042,0.0005447373,0.00057773903,0.0000014251343],"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":[0.000037404596,0.000025885523,0.013845955,0.00072197994,0.000080069,0.0000014766905,0.00008082066,0.035968743,0.94839764,0.000037104062,0.000026070386,0.0007768254],"study_design_scores_gemma":[0.0002733873,0.00007919442,0.0047088554,0.00008791733,0.000039621937,0.000007835164,0.00008113862,0.78253126,0.21151021,0.000009370288,0.0003818452,0.00028937517],"about_ca_topic_score_codex":0.00017812119,"about_ca_topic_score_gemma":0.000038282895,"teacher_disagreement_score":0.7465625,"about_ca_system_score_codex":0.00002801077,"about_ca_system_score_gemma":0.00028693464,"threshold_uncertainty_score":0.97653276},"labels":[],"label_agreement":null},{"id":"W4244238354","doi":"10.1109/grc.2007.4403141","title":"Comparison of Machine Learning and Pattern Discovery Algorithms for the Prediction of Human Single Nucleotide Polymorphisms","year":2007,"lang":"en","type":"article","venue":"2007 IEEE International Conference on Granular Computing (GRC 2007)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Computer science; Machine learning; Single-nucleotide polymorphism; Artificial intelligence; Computational biology; Algorithm; Biology; Genetics; Genotype; Gene","score_opus":0.03891084354732889,"score_gpt":0.33018313861519055,"score_spread":0.2912722950678617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244238354","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5479661,0.00015312558,0.44893375,0.00008506536,0.0008550264,0.0002263355,0.000080453465,0.000015279526,0.0016848479],"genre_scores_gemma":[0.99693054,0.00002877001,0.0020184186,0.00007539993,0.00043144397,0.0000020298048,0.0002089116,0.000020325091,0.00028413907],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865055,0.000044130516,0.0005686692,0.00021986157,0.00031304493,0.00020372555],"domain_scores_gemma":[0.99892557,0.00013184262,0.00048715857,0.00017331021,0.00023863926,0.000043467622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006307536,0.0001715426,0.00021324307,0.00009825068,0.00014749562,0.0000441635,0.00027928397,0.00010344021,0.00002456064],"category_scores_gemma":[0.00011078471,0.00014544338,0.00009865807,0.00005048379,0.00016602148,0.000012059742,0.00008599892,0.00022269959,0.0000015412966],"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":[0.0003530306,0.00050099473,0.34094024,0.00014523508,0.00033352058,0.0000024473122,0.0007791281,0.0044911606,0.5935403,0.0017536656,0.0011147425,0.05604554],"study_design_scores_gemma":[0.0021153288,0.0023723196,0.032024898,0.00032750829,0.00008793915,0.00002764896,0.0005813856,0.71523356,0.2387079,0.00016114164,0.007930737,0.00042960906],"about_ca_topic_score_codex":0.0000773013,"about_ca_topic_score_gemma":0.000019676943,"teacher_disagreement_score":0.7107424,"about_ca_system_score_codex":0.000020781623,"about_ca_system_score_gemma":0.00002076206,"threshold_uncertainty_score":0.5931009},"labels":[],"label_agreement":null},{"id":"W4244478947","doi":"10.1007/978-1-4939-7131-2_100605","title":"Link-Based Classification","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":55,"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","score_opus":0.01748414886493301,"score_gpt":0.25787640179751614,"score_spread":0.24039225293258312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244478947","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":[0.00008115089,0.00007515646,0.009327678,0.0002748313,0.00016671856,0.00014960406,0.000017633096,0.000040063504,0.98986715],"genre_scores_gemma":[0.0032720028,0.000053278927,0.008791582,0.0011268187,0.0009979716,0.000005774955,0.0016165952,0.00006245735,0.9840735],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99923676,0.000008080269,0.000245574,0.00024055535,0.00014284074,0.00012616949],"domain_scores_gemma":[0.99903136,0.000006820115,0.00019275103,0.0005878004,0.00012515078,0.000056085377],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001137217,0.00021495565,0.00013175652,0.000051597217,0.000046849105,0.000024215451,0.00021211937,0.00056681246,0.0018939588],"category_scores_gemma":[0.00004479611,0.00019591385,0.000110082314,0.000007995947,0.000104216924,8.1460956e-7,0.00006638588,0.00017852605,0.0009545616],"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":[0.00022317178,0.00005378461,0.00036311767,0.0004884444,0.00044896416,0.000003556134,0.00008036515,0.0001225901,0.025587652,0.121043146,0.7962037,0.055381518],"study_design_scores_gemma":[0.00015439652,0.00019051724,0.00004451305,0.000025727371,0.000022142602,0.000002985368,0.0000017210034,0.0017349259,0.0020666835,0.00054060505,0.99495447,0.00026128715],"about_ca_topic_score_codex":0.0000011582268,"about_ca_topic_score_gemma":0.000008110822,"teacher_disagreement_score":0.19875081,"about_ca_system_score_codex":0.000014179117,"about_ca_system_score_gemma":0.00009815953,"threshold_uncertainty_score":0.99982333},"labels":[],"label_agreement":null},{"id":"W4247376798","doi":"10.3410/f.738428614.793578998","title":"Faculty Opinions recommendation of Hidden kinetic traps in multidomain folding highlight the presence of a misfolded but functionally competent intermediate.","year":2020,"lang":"en","type":"dataset","venue":"Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Montreal Clinical Research Institute","funders":"Associazione Italiana per la Ricerca sul Cancro; Sapienza Università di Roma; European Commission","keywords":"PDZ domain; Folding (DSP implementation); Protein folding; Computational biology; Proteome; Tandem; Human proteome project; Chemistry; Biophysics; Tandem repeat; Native state; Biology; Biochemistry; Proteomics; Genome; Gene","score_opus":0.019208514034268143,"score_gpt":0.31351700873706057,"score_spread":0.2943084947027924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247376798","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000024024512,0.0006673952,0.0001293256,0.07149397,0.0005715625,0.0011680342,0.9259082,0.000010640748,0.000026866426],"genre_scores_gemma":[0.00042028824,0.00051270105,0.0011234457,0.0019811396,0.00021913902,0.00015404844,0.9953538,0.00002059592,0.00021482908],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99599963,0.0005791065,0.0017179699,0.00046705827,0.0009697415,0.00026647025],"domain_scores_gemma":[0.994977,0.00017095581,0.0017077052,0.0010575741,0.0019333004,0.00015345658],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011089683,0.00041000656,0.000695338,0.00019677522,0.0001036056,0.000052101972,0.0016754846,0.00050976506,0.00009626335],"category_scores_gemma":[0.007589968,0.00024887134,0.00047152818,0.000972334,0.00038295757,0.000028703416,0.0006716924,0.0008266672,0.0000113333],"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":[0.000038795086,0.0001997486,0.000031650634,0.0045998343,0.00013524735,1.6725255e-7,0.00015928505,0.000001646977,0.00019298347,0.000110374414,0.99357843,0.00095185573],"study_design_scores_gemma":[0.00075531425,0.00022745029,0.0041844086,0.004498632,0.00009915723,0.00001873496,0.00005509358,0.00012814013,0.00016817162,0.000008606326,0.98962784,0.00022846766],"about_ca_topic_score_codex":0.00005015072,"about_ca_topic_score_gemma":0.000015163157,"teacher_disagreement_score":0.06951282,"about_ca_system_score_codex":0.000047112277,"about_ca_system_score_gemma":0.00035613065,"threshold_uncertainty_score":0.99999636},"labels":[],"label_agreement":null},{"id":"W4252292706","doi":"10.22215/etd/2011-06845","title":"Targeted optimizatino of computational and classification performance of a protein-protein interaction predictor","year":2011,"lang":"en","type":"dissertation","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Humanities; Art","score_opus":0.009266706375626686,"score_gpt":0.24886039736270182,"score_spread":0.23959369098707514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252292706","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98946273,0.00007893813,0.0020511004,0.0000041478347,0.00006799003,0.0005035456,0.000028579949,0.000010990519,0.0077919764],"genre_scores_gemma":[0.9617825,0.000035541958,0.029443806,0.000005421822,0.000029059309,0.000045753633,0.0039098486,0.00002171824,0.004726333],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990753,0.00003489926,0.00047279638,0.00017580755,0.00015482093,0.00008638069],"domain_scores_gemma":[0.9987836,0.000005787649,0.00069982297,0.00017706568,0.00030250568,0.000031225132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000103354556,0.00015982208,0.00018716317,0.000092567614,0.000030252042,0.0000071400473,0.00011274115,0.0002512526,0.00008737136],"category_scores_gemma":[0.00008484315,0.00015117585,0.000047054535,0.00006168582,0.000048218266,0.000008639481,0.000028097202,0.00013666804,0.0000020768643],"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":[0.0019956112,0.00029181503,0.005337899,0.005683712,0.00035628316,2.1217939e-7,0.0011876029,0.0051732017,0.9646374,0.0014934782,0.0003214415,0.013521363],"study_design_scores_gemma":[0.0010597968,0.0018723812,0.053721417,0.00072201726,0.00008128789,0.0000076127335,0.00056770747,0.17539233,0.7648811,0.00012755353,0.0010130791,0.000553733],"about_ca_topic_score_codex":0.00001747447,"about_ca_topic_score_gemma":0.000009047579,"teacher_disagreement_score":0.1997563,"about_ca_system_score_codex":0.000006653064,"about_ca_system_score_gemma":0.000093579714,"threshold_uncertainty_score":0.6164772},"labels":[],"label_agreement":null},{"id":"W4254982696","doi":"10.1139/bcb-78-5-537","title":"New thoughts on the role of the &lt;FONT FACE=\"SYMBOL\"&gt;bg&lt;/FONT&gt; subunit in G protein signal transduction","year":2000,"lang":"en","type":"article","venue":"Biochemistry and Cell Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Font; Protein subunit; Signal transduction; Biology; Genetics; Computer science; Artificial intelligence; Gene","score_opus":0.0037944439633549325,"score_gpt":0.19700101838035788,"score_spread":0.19320657441700295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254982696","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9851812,0.0013024991,0.00007455226,0.000525818,0.000048988295,0.0003360093,0.000034351062,0.000011705331,0.012484855],"genre_scores_gemma":[0.995122,0.00018573165,0.00017634456,0.00013416166,0.00029729144,0.000025158011,0.0001017518,0.000015148577,0.0039424105],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99877477,0.00014974472,0.00034276236,0.00032688855,0.00010984394,0.00029597993],"domain_scores_gemma":[0.99926054,0.000028200027,0.0001452822,0.00046375106,0.000029987421,0.00007220935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002523584,0.0002454959,0.00019809461,0.000021675474,0.00011121047,0.000015612493,0.00038366407,0.00040622582,0.00028179435],"category_scores_gemma":[0.000036530404,0.00015666903,0.00010784681,0.00012302147,0.00022019222,0.000004072964,0.00006601176,0.00029040145,0.000009625125],"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":[0.0001765505,0.000064776505,0.00056389783,0.000037533937,0.00002032783,3.940628e-7,0.0002095022,0.0000982516,0.98613554,0.00009151484,0.00028282718,0.012318869],"study_design_scores_gemma":[0.0004376994,0.00022601795,0.00034778158,0.000029396824,0.000013246277,0.000011069631,0.00015050231,0.00022305248,0.9093427,0.00022612933,0.08880951,0.00018291622],"about_ca_topic_score_codex":0.000027982549,"about_ca_topic_score_gemma":0.000019848147,"teacher_disagreement_score":0.08852668,"about_ca_system_score_codex":0.000014354365,"about_ca_system_score_gemma":0.000097205004,"threshold_uncertainty_score":0.63887775},"labels":[],"label_agreement":null},{"id":"W4255970554","doi":"10.21203/rs.3.rs-88429/v3","title":"A Hybrid Computational Framework for Intelligent Inter- continent SARS-CoV-2 Sub-strains Characterization and Prediction","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Royal University","funders":"","keywords":"Genome; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Pathogenicity; Biology; Computational biology; Adaptability; Coronavirus disease 2019 (COVID-19); Strain (injury); Lineage (genetic); Genetics; Evolutionary biology; Computer science; Disease; Gene; Infectious disease (medical specialty); Medicine","score_opus":0.0431936475099335,"score_gpt":0.38076197495376973,"score_spread":0.33756832744383625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255970554","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50293124,0.00017907938,0.49485457,0.00036847452,0.0002504043,0.0007303045,0.0006379424,0.00001900247,0.000029011428],"genre_scores_gemma":[0.9565901,0.00081136567,0.0146109965,0.0001508514,0.00070944504,0.00029356946,0.026709037,0.00004995562,0.00007466228],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99809235,0.00022099896,0.00042038775,0.0005095325,0.00041025403,0.00034648067],"domain_scores_gemma":[0.9984493,0.000091783455,0.00018165166,0.00039197406,0.0008054335,0.000079832345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007991551,0.00022633403,0.00023312811,0.00015615506,0.00015880584,0.00027696576,0.00022405932,0.00036114934,0.000009901075],"category_scores_gemma":[0.0011043978,0.00023867958,0.0001313462,0.000075023374,0.00013862649,0.000007398487,0.00084527454,0.0008295263,0.0000035163396],"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":[0.0013201664,0.0011728945,0.020718861,0.013431546,0.0017060022,0.000038608396,0.004671577,0.008128216,0.81036156,0.0057303375,0.013421918,0.11929828],"study_design_scores_gemma":[0.0018627836,0.0032001482,0.042318694,0.004882521,0.00012471109,0.00014133436,0.0011861598,0.3570644,0.4793969,0.0059878416,0.10219207,0.0016424272],"about_ca_topic_score_codex":0.000016115295,"about_ca_topic_score_gemma":0.000010379286,"teacher_disagreement_score":0.48024356,"about_ca_system_score_codex":0.000067132634,"about_ca_system_score_gemma":0.000260098,"threshold_uncertainty_score":0.97330713},"labels":[],"label_agreement":null},{"id":"W4281665783","doi":"10.3389/fgene.2022.885929","title":"ProtTrans-Glutar: Incorporating Features From Pre-trained Transformer-Based Models for Predicting Glutarylation Sites","year":2022,"lang":"en","type":"article","venue":"Frontiers in Genetics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"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 Genetics; Direktorat Jenderal Pendidikan Tinggi; University of Tokyo; Institute of Medical Science, University of Tokyo; Kementerian Pendidikan, Kebudayaan, Riset, dan Teknologi; Research Organization of Information and Systems","keywords":"Recall; Computer science; Artificial intelligence; Transformer; Machine learning; Random forest; Pattern recognition (psychology); Feature (linguistics); Engineering","score_opus":0.00852542584177125,"score_gpt":0.23603701690687165,"score_spread":0.2275115910651004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281665783","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50090766,0.00095529325,0.49583077,0.00014143722,0.00032037823,0.001168566,0.00040142232,0.000036747042,0.00023773557],"genre_scores_gemma":[0.730542,0.000018872173,0.26658797,0.00020153675,0.00014225235,0.00029685334,0.0021029566,0.00004275317,0.00006480546],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844414,0.00011100549,0.0004629399,0.0003658833,0.0002846897,0.00033134912],"domain_scores_gemma":[0.99934214,0.000032825348,0.00019963659,0.00030445936,0.00005557816,0.00006538243],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037730267,0.00023457997,0.00022241774,0.00012124547,0.00028236854,0.00003661633,0.000330814,0.00015842787,0.000010321298],"category_scores_gemma":[0.00007017595,0.00026530822,0.0001193982,0.00016930563,0.00006156072,0.000011255022,0.000051958727,0.00029393358,1.6410522e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046508914,0.00008374607,0.079459734,0.000102227124,0.00006737295,0.0000010771006,0.0013379268,0.87138855,0.038179558,0.000025298204,0.0016578329,0.007231598],"study_design_scores_gemma":[0.0018352167,0.0006742924,0.003844343,0.000019655019,0.000047533882,0.0000027492392,0.00056515733,0.96596116,0.02091879,0.0025670256,0.0031793234,0.00038475703],"about_ca_topic_score_codex":0.00003383746,"about_ca_topic_score_gemma":0.00006899174,"teacher_disagreement_score":0.22963434,"about_ca_system_score_codex":0.00006598796,"about_ca_system_score_gemma":0.00015512906,"threshold_uncertainty_score":0.9999799},"labels":[],"label_agreement":null},{"id":"W4281706710","doi":"10.1101/2022.06.01.494315","title":"Glycoproteomics Identifies Plexin-B3 as Targetable Cell Surface Protein Required for Growth and Invasion of Triple Negative Breast Cancer Cells","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre; University Health Network","funders":"Ontario Ministry of Health and Long-Term Care","keywords":"Triple-negative breast cancer; Cancer research; Glycoproteomics; Stathmin; Breast cancer; Cell growth; Biology; Proteomics; Cancer; Cell biology; Microtubule; Genetics","score_opus":0.008100762285841214,"score_gpt":0.22429864326916232,"score_spread":0.2161978809833211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281706710","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99236006,0.00095354795,0.0012764795,0.00012657371,0.000617366,0.0025075595,0.0020813728,0.00005675781,0.000020312807],"genre_scores_gemma":[0.9763199,0.00064821506,0.021927267,0.000090213594,0.00018577944,0.00055947946,0.000008352423,0.00013399881,0.00012681197],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975522,0.00016268829,0.00067472155,0.00081622537,0.0003321504,0.0004619928],"domain_scores_gemma":[0.997492,0.000029994177,0.000982355,0.0008539426,0.0004779807,0.00016372123],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006289304,0.0005190272,0.0005811428,0.000115501636,0.0002383495,0.000121665005,0.0005727296,0.0004914253,0.00006498085],"category_scores_gemma":[0.00027723922,0.0005679009,0.00017191515,0.00022408096,0.00018100497,0.000024357756,0.001132936,0.0005103231,0.0000030434524],"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":[0.00032939937,0.00009286636,0.0011516167,0.0020748223,0.00013367477,0.000002144754,0.000033526117,0.00066675065,0.9950064,0.00006691202,0.0004410766,8.5152914e-7],"study_design_scores_gemma":[0.001059994,0.0002011449,0.0018072292,0.00017990121,0.000088998975,4.110911e-8,0.000020518019,0.0009840302,0.9942107,0.00001033206,0.00083311315,0.00060398807],"about_ca_topic_score_codex":0.00068116974,"about_ca_topic_score_gemma":0.000008189892,"teacher_disagreement_score":0.02065079,"about_ca_system_score_codex":0.00009696588,"about_ca_system_score_gemma":0.0007928988,"threshold_uncertainty_score":0.99967724},"labels":[],"label_agreement":null},{"id":"W4281778232","doi":"10.1136/jnnp-2022-abn.313","title":"Genomic features specific to the human lineage are associated with neurological diseases and intelligence","year":2022,"lang":"en","type":"article","venue":"Journal of Neurology Neurosurgery & Psychiatry","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Biology; Human brain; Human genome; Genetics; Disease; Gene; Genome; Lineage (genetic); Phenotype; Genomics; Negative selection; Computational biology; Neuroscience; Medicine; Pathology","score_opus":0.00949215474206473,"score_gpt":0.2382827881698636,"score_spread":0.22879063342779887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281778232","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98711354,0.00084336393,0.000107169515,0.010309872,0.0013879723,0.00015238918,0.00003133426,0.000013429924,0.000040959345],"genre_scores_gemma":[0.98172206,0.00010775588,0.00010220675,0.017413275,0.000526737,0.000008818732,0.000012645405,0.00003376125,0.00007272639],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980228,0.00058508595,0.0005126788,0.0002982907,0.00028320344,0.00029797447],"domain_scores_gemma":[0.9985662,0.00014560572,0.0007069132,0.00035662387,0.00007286921,0.00015179523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004529115,0.00022070031,0.00029756516,0.00013690579,0.00045424252,0.00005102234,0.00053011894,0.00008580051,0.000030403664],"category_scores_gemma":[0.00024459243,0.00015253438,0.00014741524,0.00020727953,0.0001566026,0.000007176184,0.00036847577,0.0010497916,0.0000015802765],"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":[0.0010135749,0.00026540112,0.93910915,0.0000099071385,0.00007280252,0.00017735866,0.000055284305,0.012541093,0.004911999,0.00007551054,0.041439436,0.00032848777],"study_design_scores_gemma":[0.0002605616,0.003575949,0.9459283,0.000005542741,0.000043735454,0.0020434947,0.000039938015,0.000076256045,0.000057888396,0.000050740076,0.047746036,0.00017160915],"about_ca_topic_score_codex":6.9399334e-7,"about_ca_topic_score_gemma":0.000007093006,"teacher_disagreement_score":0.012464837,"about_ca_system_score_codex":0.0000056294957,"about_ca_system_score_gemma":0.000067734436,"threshold_uncertainty_score":0.62201715},"labels":[],"label_agreement":null},{"id":"W4285007839","doi":"10.1021/acs.jcim.2c00484","title":"Leveraging Protein Dynamics to Identify Functional Phosphorylation Sites using Deep Learning Models","year":2022,"lang":"en","type":"review","venue":"Journal of Chemical Information and Modeling","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Priority Academic Program Development of Jiangsu Higher Education Institutions; Chinese Academy of Sciences; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Allosteric regulation; Computational biology; Posttranslational modification; Computer science; Prioritization; Phosphorylation; Artificial intelligence; Machine learning; Chemistry; Biology; Biochemistry; Enzyme","score_opus":0.06886018583940012,"score_gpt":0.3299680967651382,"score_spread":0.2611079109257381,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285007839","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":[0.016779628,0.3171381,0.66531986,0.000018039296,0.00015193604,0.00034378355,0.000007407014,0.000014165656,0.00022707475],"genre_scores_gemma":[0.021523247,0.9417348,0.034142546,0.00026687572,0.0004963622,0.000031952495,0.0016665707,0.00007883969,0.000058814014],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998014,0.00006479569,0.0012188137,0.000118394346,0.00039524626,0.00018876976],"domain_scores_gemma":[0.9985089,0.000024506853,0.0010016286,0.00012165613,0.00021351618,0.00012983054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006834394,0.00025339774,0.0005051118,0.00026969553,0.00014951412,0.00014259596,0.00018346398,0.0002310147,0.00002662877],"category_scores_gemma":[0.0003228788,0.00023671988,0.00025003852,0.00015395891,0.00001634885,0.00010887113,0.0002439391,0.00076874444,0.000002310838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046623372,0.0000130897315,0.000002780155,0.0019422454,0.00011044992,6.3799e-7,0.00036539295,0.653754,0.00060627103,0.000059574497,0.0000312819,0.34306765],"study_design_scores_gemma":[0.00018955345,0.00005298714,6.321634e-8,0.00067934266,0.000120302015,0.00019266807,0.0001974443,0.877682,0.00006068637,0.000060974427,0.120515764,0.00024824683],"about_ca_topic_score_codex":0.0000032761588,"about_ca_topic_score_gemma":1.9560702e-7,"teacher_disagreement_score":0.6311773,"about_ca_system_score_codex":0.00018669677,"about_ca_system_score_gemma":0.00017791126,"threshold_uncertainty_score":0.96531564},"labels":[],"label_agreement":null},{"id":"W4285012250","doi":"10.1080/00949655.2022.2093873","title":"Robust ranking by ensembling of diverse models and assessment metrics","year":2022,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Thompson Rivers University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Feature selection; Classifier (UML); Artificial intelligence; Pattern recognition (psychology); Mathematics; Machine learning; Feature (linguistics); Ranking (information retrieval); Data mining; Computer science","score_opus":0.03701339128923762,"score_gpt":0.33213974648887096,"score_spread":0.2951263551996333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285012250","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25996578,0.00011631913,0.7397175,0.00002457978,0.000034210883,0.000035885278,0.000018357197,0.0000011107943,0.000086244625],"genre_scores_gemma":[0.91083497,0.00003480159,0.089012146,0.00004443485,0.000015375712,2.946728e-7,0.00004823256,0.0000039327906,0.0000057985853],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928284,0.0000871425,0.00029944454,0.00005740334,0.00022235171,0.000050828887],"domain_scores_gemma":[0.9993609,0.0001637294,0.0002842905,0.000026313626,0.00012695171,0.000037806985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003992235,0.00004946138,0.00010444798,0.00007828187,0.00009459428,0.000018822404,0.000030366398,0.000023199782,0.000008790783],"category_scores_gemma":[0.00012476675,0.000047942125,0.00001707215,0.00006692982,0.000025098745,0.000011157192,0.000057465568,0.00012189243,2.7139393e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005179381,0.000023918927,0.0009869586,0.000023352095,0.000018551003,8.561145e-7,0.00012786473,0.9809622,0.00073984574,0.0007173702,0.00013640916,0.016210876],"study_design_scores_gemma":[0.00061784807,0.00035052316,0.0015725213,0.000004587048,0.000023343893,0.0000130629705,0.00019790529,0.99575067,0.00003525386,0.001053093,0.0003323887,0.00004883201],"about_ca_topic_score_codex":0.0000027572314,"about_ca_topic_score_gemma":1.931718e-7,"teacher_disagreement_score":0.6508692,"about_ca_system_score_codex":0.000013919429,"about_ca_system_score_gemma":0.000025954698,"threshold_uncertainty_score":0.19550231},"labels":[],"label_agreement":null},{"id":"W4285023186","doi":"10.22215/etd/2022-15110","title":"Assessing and Improving Protein-Protein Interaction Prediction in E. coli","year":2022,"lang":"en","type":"dissertation","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Classifier (UML); Computer science; Artificial intelligence; Machine learning; Interactome; Data mining; Computational biology; Biology; Genetics","score_opus":0.007320059679875485,"score_gpt":0.29240075352306044,"score_spread":0.28508069384318496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285023186","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97958523,0.00012328968,0.00032882232,0.00002644193,0.00028007603,0.00063213776,0.000007645062,0.00002809714,0.018988274],"genre_scores_gemma":[0.9735322,0.000010852194,0.0024115674,0.000034436816,0.00011990227,0.00024916488,0.0033331942,0.000042309504,0.020266375],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989585,0.00007998886,0.00034122384,0.0002959217,0.00016222817,0.00016208256],"domain_scores_gemma":[0.99945766,0.0000059680497,0.00026905676,0.00018882874,0.000043431937,0.000035072862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026485903,0.00019194603,0.00014801811,0.0001355149,0.000116615905,0.00012814041,0.00009850397,0.0002593688,0.0002795209],"category_scores_gemma":[0.00017803322,0.00020488132,0.000041040847,0.00007754004,0.000012914548,0.000015561332,0.00008112135,0.00049007323,0.0000038977596],"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":[0.0001980205,0.000061428174,0.000686173,0.00079687877,0.000038307615,0.0000043870523,0.00038042126,0.00016341725,0.96730924,0.00012051448,0.0003755271,0.02986566],"study_design_scores_gemma":[0.0044096597,0.0029390347,0.052170206,0.0016464035,0.00018262796,0.00013480907,0.03445728,0.05091926,0.71803254,0.0002887848,0.1316496,0.0031697815],"about_ca_topic_score_codex":0.00022051297,"about_ca_topic_score_gemma":0.0002394238,"teacher_disagreement_score":0.2492767,"about_ca_system_score_codex":0.00006075715,"about_ca_system_score_gemma":0.000088077366,"threshold_uncertainty_score":0.83548176},"labels":[],"label_agreement":null},{"id":"W4285218787","doi":"10.1007/978-1-0716-2124-0_16","title":"Mining Proteomics Datasets to Uncover Functional Pseudogenes","year":2022,"lang":"en","type":"article","venue":"Methods in molecular biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Canadian Institutes of Health Research","keywords":"Pseudogene; Computational biology; Computer science; Proteomics; Biology; Genetics; Gene; Genome","score_opus":0.02048432241387272,"score_gpt":0.3699581426326024,"score_spread":0.3494738202187297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285218787","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":[0.14448495,0.00018901656,0.8533792,0.0002934636,0.00043731657,0.00036359605,0.00015771683,0.000017304494,0.000677439],"genre_scores_gemma":[0.011274076,0.00000672993,0.9831546,0.003185317,0.000088941095,0.00027670347,0.0017617281,0.00003528328,0.00021664663],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976157,0.0010659599,0.0003609596,0.0004609882,0.00012994386,0.00036646627],"domain_scores_gemma":[0.9991678,0.000053101703,0.000114256225,0.00055243116,0.000031757376,0.00008063956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015865194,0.00019985472,0.00021362166,0.00017858684,0.00013904201,0.000014497792,0.00041864102,0.00013388676,0.0001605568],"category_scores_gemma":[0.0006966852,0.00021318726,0.000082128616,0.00029584064,0.00006133827,0.000002567816,0.0010488689,0.00026760227,0.000008820448],"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":[0.00012028112,0.000045780453,0.00569727,0.000010660808,0.000037203663,0.000008706319,0.000061738334,0.015630381,0.9708113,0.0006823274,0.0016910783,0.005203268],"study_design_scores_gemma":[0.00108296,0.0011273823,0.0011021057,0.0000070074634,0.000023314855,0.00019988648,0.0002186489,0.002985045,0.42617473,0.0010522334,0.56531876,0.00070793735],"about_ca_topic_score_codex":0.00002090217,"about_ca_topic_score_gemma":0.000009586117,"teacher_disagreement_score":0.56362766,"about_ca_system_score_codex":0.000050729614,"about_ca_system_score_gemma":0.00010042655,"threshold_uncertainty_score":0.8693524},"labels":[],"label_agreement":null},{"id":"W4285231030","doi":"10.1007/978-1-0716-2124-0_8","title":"HUNTER: Sensitive Automated Characterization of Proteolytic Systems by N Termini Enrichment from Microscale Specimen","year":2022,"lang":"en","type":"article","venue":"Methods in molecular biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 British Columbia Hospital; BC Cancer Agency; BC Children's Hospital; University of British Columbia","funders":"","keywords":"Microscale chemistry; Proteolysis; Computational biology; Rendering (computer graphics); Cell biology; Biology; Chemistry; Biological system; Biophysics; Computer science; Biochemistry; Enzyme; Mathematics; Artificial intelligence","score_opus":0.006253111814596853,"score_gpt":0.3235772253727734,"score_spread":0.3173241135581765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285231030","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6030525,0.00015546693,0.39520437,0.000055895463,0.00029534477,0.0005498119,0.00036928346,0.000034162636,0.00028321162],"genre_scores_gemma":[0.6794389,0.000040418487,0.31286484,0.00058068626,0.00007982852,0.0003213143,0.0061467765,0.00006519026,0.0004620296],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99696195,0.0017212814,0.00055215793,0.0003821154,0.00011271272,0.00026981084],"domain_scores_gemma":[0.9990745,0.00004392494,0.00037236858,0.00041689837,0.000049028356,0.000043246633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008404072,0.00020086323,0.00034578767,0.00011079587,0.000061598446,0.00001240023,0.00028355728,0.00017124525,0.00003062424],"category_scores_gemma":[0.00014275263,0.00021028159,0.00007693989,0.00017755589,0.000098538934,0.00000294237,0.0004320364,0.00022211546,0.0000022834163],"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":[0.00006689438,0.000081554404,0.0023599714,0.000024475405,0.00006575053,0.0000042970023,0.00016203398,0.00026257485,0.99573517,0.000052613243,0.00009441268,0.0010902695],"study_design_scores_gemma":[0.0006408132,0.0005024982,0.001223322,0.000013807169,0.000020191605,0.000019602405,0.00013021327,0.013712827,0.96719253,0.00003224651,0.016257055,0.00025488343],"about_ca_topic_score_codex":0.000099402336,"about_ca_topic_score_gemma":0.0000010154396,"teacher_disagreement_score":0.0823395,"about_ca_system_score_codex":0.000060137867,"about_ca_system_score_gemma":0.000049896687,"threshold_uncertainty_score":0.8575034},"labels":[],"label_agreement":null},{"id":"W4285287188","doi":"10.2139/ssrn.4136029","title":"2-Stage Swarm Search Feature Selection for Classification of High Dimension Bioinformatics Dataset","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Lakehead University","funders":"","keywords":"Feature selection; Selection (genetic algorithm); Stage (stratigraphy); Artificial intelligence; Pattern recognition (psychology); Computer science; Swarm behaviour; Feature (linguistics); Data mining; Machine learning; Computational biology; Biology","score_opus":0.009869589778197062,"score_gpt":0.2760159001053437,"score_spread":0.26614631032714664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285287188","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8442615,0.0004835397,0.15252644,0.0008854298,0.00027570635,0.0005527937,0.0008338588,0.000019275874,0.0001614418],"genre_scores_gemma":[0.9869089,0.00040846175,0.005339264,0.00013064596,0.00015991765,0.000022338461,0.0055083204,0.00002690467,0.0014952441],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983673,0.00009683921,0.0003184463,0.00013217436,0.00029539937,0.0007898588],"domain_scores_gemma":[0.99925715,0.000020593418,0.00032682504,0.00022420291,0.00012496115,0.000046291952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001623813,0.00012585007,0.00013341017,0.00008818514,0.00039889425,0.00002292451,0.0002845682,0.00008723318,0.000019048555],"category_scores_gemma":[0.000090330155,0.00012009119,0.000080637124,0.00016300967,0.000033040164,0.000014198953,0.00013143706,0.001055155,0.0000023268378],"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":[0.003534021,0.0008376828,0.011917718,0.0006227998,0.0014071371,0.0000012319314,0.0011549123,0.0920259,0.63459456,0.1145884,0.08204827,0.057267368],"study_design_scores_gemma":[0.008254665,0.015206074,0.0035480312,0.00004108907,0.00030981677,0.002146028,0.012950357,0.29739904,0.09342273,0.008207283,0.55701333,0.0015015142],"about_ca_topic_score_codex":0.000024211238,"about_ca_topic_score_gemma":0.00006894517,"teacher_disagreement_score":0.54117185,"about_ca_system_score_codex":0.00025271613,"about_ca_system_score_gemma":0.0009009756,"threshold_uncertainty_score":0.48971766},"labels":[],"label_agreement":null},{"id":"W4286499967","doi":"10.1371/journal.pone.0270852","title":"NTD-DR: Nonnegative tensor decomposition for drug repositioning","year":2022,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pairwise comparison; Receiver operating characteristic; Drug; Drug discovery; Computer science; Similarity (geometry); Drug development; Disease; Artificial intelligence; Computational biology; Tensor (intrinsic definition); Machine learning; Medicine; Data mining; Bioinformatics; Mathematics; Biology; Pharmacology; Pathology","score_opus":0.016910426633277468,"score_gpt":0.25570719572580336,"score_spread":0.2387967690925259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286499967","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98942965,0.00010625517,0.005457065,0.0009858441,0.000061716906,0.0005066578,0.000070412716,0.000042482752,0.0033399074],"genre_scores_gemma":[0.9539596,0.000010533216,0.040929623,0.0007230373,0.00019040851,0.00030116638,0.0010075084,0.000027030383,0.002851126],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99923724,0.000060009177,0.00019038237,0.00017686076,0.00017485794,0.00016067871],"domain_scores_gemma":[0.9994991,0.00003056158,0.00013163089,0.00021039993,0.000089651425,0.000038685917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001924077,0.00009263959,0.000110053654,0.000036724665,0.00038483762,0.000023560844,0.00013172506,0.000033686676,0.00006548597],"category_scores_gemma":[0.00011991017,0.000104014915,0.00006070187,0.000060525585,0.000023936756,0.0000041769795,0.00013957938,0.00013038136,0.000007738774],"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":[0.00034703602,0.0010202125,0.0037409498,0.00020015043,0.00044065254,0.0000028831162,0.0009001476,0.0030773182,0.98089653,0.00053868553,0.008270081,0.0005653707],"study_design_scores_gemma":[0.0017824597,0.0014281307,0.0017641437,0.00008954712,0.0002237877,0.000041925705,0.0006879051,0.047872856,0.93300104,0.00048199217,0.012025194,0.0006010374],"about_ca_topic_score_codex":0.0000068903005,"about_ca_topic_score_gemma":0.000002615893,"teacher_disagreement_score":0.04789549,"about_ca_system_score_codex":0.000033603443,"about_ca_system_score_gemma":0.000027265622,"threshold_uncertainty_score":0.4241605},"labels":[],"label_agreement":null},{"id":"W4286797666","doi":"10.1101/2022.07.23.501263","title":"Predicting the specific substrate for transmembrane transport proteins using BERT language model","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"UniProt; Computer science; Classifier (UML); Transmembrane protein; Artificial intelligence; Language model; Machine learning; Chemistry; Biochemistry","score_opus":0.015208245553192596,"score_gpt":0.23872398100054273,"score_spread":0.22351573544735015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286797666","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93977576,0.0011044357,0.05526724,0.00013395048,0.00047349793,0.002102999,0.0009613631,0.00014541562,0.000035322093],"genre_scores_gemma":[0.97055835,0.0001781485,0.027672667,0.00018263081,0.00060282985,0.0005565436,0.000017000428,0.00020146462,0.000030348747],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9973497,0.00011517112,0.0006875445,0.0008189878,0.00040644372,0.0006221958],"domain_scores_gemma":[0.9977136,0.000029307308,0.00047888551,0.0014353999,0.00019414871,0.00014862487],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010150741,0.00058325153,0.0004346977,0.00010739738,0.00047390533,0.00011450574,0.00094797293,0.00048399981,0.00003799145],"category_scores_gemma":[0.000080568076,0.0005402139,0.00034258232,0.00020506784,0.00013328705,0.0000131941515,0.00026778204,0.0009849907,0.0000021957183],"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":[0.0001256943,0.00008340768,0.002977948,0.0007344951,0.00019549108,0.000008911119,0.00013430275,0.066506855,0.92902553,0.00013329301,0.000072246214,0.00000185362],"study_design_scores_gemma":[0.0017254724,0.00027763782,0.008337133,0.00028793977,0.0004113045,2.8124217e-7,0.00008531044,0.29430088,0.67822814,0.0000033086878,0.014412346,0.0019302721],"about_ca_topic_score_codex":0.000049118575,"about_ca_topic_score_gemma":0.000008496289,"teacher_disagreement_score":0.2507974,"about_ca_system_score_codex":0.000103049526,"about_ca_system_score_gemma":0.00061304204,"threshold_uncertainty_score":0.99970496},"labels":[],"label_agreement":null},{"id":"W4287662794","doi":"10.48550/arxiv.2009.10380","title":"PS8-Net: A Deep Convolutional Neural Network to Predict the Eight-State\\n Protein Secondary Structure","year":2020,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Benchmark (surveying); Computer science; Convolutional neural network; Protein secondary structure; Artificial intelligence; Deep learning; Feature (linguistics); Class (philosophy); Artificial neural network; Data mining; State (computer science); Pattern recognition (psychology); Machine learning; Algorithm","score_opus":0.01754635796380638,"score_gpt":0.17291595249964126,"score_spread":0.15536959453583488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287662794","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8939184,0.0005738472,0.09489198,0.001694575,0.0013085187,0.003162731,0.0009909236,0.00010206082,0.003356978],"genre_scores_gemma":[0.99161965,0.00013049909,0.0015343942,0.0020073971,0.0011421,0.000007678822,0.0011281824,0.00008598311,0.0023441138],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99576914,0.00058239675,0.0007570252,0.0016122584,0.00025502237,0.0010241376],"domain_scores_gemma":[0.9966037,0.0000743747,0.00078636233,0.0015744483,0.00034056877,0.000620536],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00037498018,0.0009608933,0.0006449063,0.00010713589,0.0007150994,0.00017928857,0.0021994468,0.0008734918,0.00065846683],"category_scores_gemma":[0.00022258043,0.0009044306,0.0005132297,0.000658193,0.00051712745,0.000026934667,0.0034519911,0.0024385117,0.00013206276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010783802,0.00005966884,0.004444392,0.00038072563,0.0007837305,0.00013936426,0.0005043035,0.97992647,0.0025320193,0.0040162313,0.0050938693,0.0010408591],"study_design_scores_gemma":[0.0020916227,0.0012320924,0.0073910453,0.00020668768,0.0004279788,0.000093823,0.00031527574,0.88001704,0.0013906002,0.00853154,0.09633394,0.0019683426],"about_ca_topic_score_codex":0.00006300452,"about_ca_topic_score_gemma":0.00018471795,"teacher_disagreement_score":0.09990941,"about_ca_system_score_codex":0.00017392103,"about_ca_system_score_gemma":0.00075130694,"threshold_uncertainty_score":0.9998629},"labels":[],"label_agreement":null},{"id":"W4289743973","doi":"10.48550/arxiv.1808.03227","title":"Identifying Protein-Protein Interaction using Tree LSTM and Structured\\n Attention","year":2018,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Benchmark (surveying); Computer science; Tree (set theory); Artificial intelligence; Machine learning; Recurrent neural network; Recall; Feature (linguistics); Deep learning; Precision and recall; Artificial neural network; Pattern recognition (psychology); Mathematics","score_opus":0.052268499372845986,"score_gpt":0.22704498869302173,"score_spread":0.17477648932017575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289743973","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87329096,0.00009890802,0.12387657,0.00002034998,0.00059026666,0.00096538034,0.000027493257,0.000040327723,0.001089772],"genre_scores_gemma":[0.99198455,0.00015373202,0.004872621,0.000028801533,0.0004499858,0.0000021343103,0.00022541253,0.000065821754,0.0022169522],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970443,0.00033936533,0.00056944316,0.0013536252,0.00014752428,0.00054569007],"domain_scores_gemma":[0.99725735,0.000013994367,0.0010964589,0.0010505674,0.00034893502,0.00023266487],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041638757,0.00068411836,0.00046399818,0.00024237439,0.0005204446,0.00026102943,0.00061199744,0.0009673035,0.00012947236],"category_scores_gemma":[0.00014890108,0.0008400813,0.00031031235,0.00029008262,0.00040620507,0.00007343887,0.0018624959,0.00095812074,0.000041018553],"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":[0.0012477324,0.00019739619,0.016591512,0.002499637,0.0011994174,0.00010472325,0.0005497076,0.02852717,0.9403783,0.0034754302,0.00008890755,0.0051400694],"study_design_scores_gemma":[0.0035783201,0.0011209555,0.00937603,0.0025128142,0.0010872596,0.00018896433,0.0018160212,0.8705207,0.0961629,0.0072971345,0.003175865,0.003163056],"about_ca_topic_score_codex":0.00018514995,"about_ca_topic_score_gemma":0.00013258368,"teacher_disagreement_score":0.8442154,"about_ca_system_score_codex":0.00023885912,"about_ca_system_score_gemma":0.00017273329,"threshold_uncertainty_score":0.999405},"labels":[],"label_agreement":null},{"id":"W4291033104","doi":"10.1016/j.compbiolchem.2022.107753","title":"PeSA 2.0: A software tool for peptide specificity analysis implementing positive and negative motifs and motif-based peptide scoring","year":2022,"lang":"en","type":"article","venue":"Computational Biology and Chemistry","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Peptide; Computational biology; Sequence motif; Motif (music); Computer science; Bioinformatics; Biology; Biochemistry; DNA","score_opus":0.006541357027320561,"score_gpt":0.2623197141176653,"score_spread":0.25577835709034474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291033104","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9393763,0.00018954727,0.059611395,0.00012350512,0.000016871214,0.00014278424,0.00040332056,0.000013824131,0.0001224509],"genre_scores_gemma":[0.974153,0.000008797805,0.023309933,0.00021832073,0.00006795149,0.00004080789,0.0020722123,0.000009423959,0.00011957842],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991052,0.000050584258,0.00022458348,0.00034751694,0.000071063645,0.00020102627],"domain_scores_gemma":[0.9993912,0.00021974776,0.00015411078,0.00009674645,0.00008445761,0.000053733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025450368,0.00015274716,0.00018284726,0.000042097392,0.00047831677,0.000029455032,0.00008057371,0.000074431126,0.00003924155],"category_scores_gemma":[0.00017921928,0.00016431265,0.00006761124,0.00009332084,0.00015332617,0.000005130261,0.00026446977,0.00014646989,1.620922e-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":[0.00044923282,0.000117231466,0.8575354,0.00039835813,0.0014159185,0.0000046733726,0.0006583969,0.061831746,0.06893646,0.000473136,0.00049776287,0.0076816594],"study_design_scores_gemma":[0.0064770197,0.0011897463,0.4999355,0.000056348086,0.001073125,0.00021486644,0.0024105178,0.40398884,0.06700085,0.007139648,0.008579188,0.0019343521],"about_ca_topic_score_codex":0.000010807667,"about_ca_topic_score_gemma":0.0000033337265,"teacher_disagreement_score":0.35759994,"about_ca_system_score_codex":0.000018569779,"about_ca_system_score_gemma":0.000049129434,"threshold_uncertainty_score":0.6700475},"labels":[],"label_agreement":null},{"id":"W4292227900","doi":"10.1021/acs.jproteome.2c00332","title":"Glycoproteomics Identifies Plexin-B3 as a Targetable Cell Surface Protein Required for the Growth and Invasion of Triple-Negative Breast Cancer Cells","year":2022,"lang":"en","type":"article","venue":"Journal of Proteome Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"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; Princess Margaret Cancer Centre; University Health Network","funders":"Canadian Cancer Society Research Institute; Ontario Ministry of Health and Long-Term Care","keywords":"Triple-negative breast cancer; Cancer research; Biology; Gene knockdown; Proteomics; Plexin; Cell; Cell growth; Glycoproteomics; Breast cancer; Cell culture; Computational biology; Semaphorin; Cancer; Receptor; Genetics","score_opus":0.025931162418058484,"score_gpt":0.32717102598227027,"score_spread":0.3012398635642118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292227900","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9934487,0.0010777042,0.0010508201,0.0015802426,0.00012898399,0.0024196913,0.00014304552,0.0000028617915,0.00014795842],"genre_scores_gemma":[0.98815286,0.00049280457,0.008403234,0.000032606502,0.00016325111,0.0002337855,0.0000076183233,0.00003155985,0.002482297],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99768394,0.00044494992,0.00053978333,0.00018203558,0.00079926715,0.00035003998],"domain_scores_gemma":[0.9981542,0.00012820626,0.00059942924,0.00025429443,0.00076863624,0.0000952007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037955635,0.00013774411,0.0002544695,0.00013460623,0.00048158743,0.000070698254,0.0005622383,0.00008598979,0.00008334597],"category_scores_gemma":[0.00067077816,0.00009891144,0.00012249807,0.00030120215,0.00023763464,0.000025703313,0.00053935556,0.0006867915,0.0000011095369],"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":[0.0016961494,0.00008398354,0.00023305473,0.0004178462,0.00008274359,0.0000028786062,0.0004909999,0.00082064595,0.994441,0.00003517281,0.0015052563,0.00019031913],"study_design_scores_gemma":[0.0015402292,0.0015313163,0.00029893915,0.00006404509,0.000019739431,0.000071364855,0.0011453287,0.0015651991,0.99177223,0.0007408014,0.0011288107,0.00012200351],"about_ca_topic_score_codex":0.00044943663,"about_ca_topic_score_gemma":0.000012070173,"teacher_disagreement_score":0.0073524136,"about_ca_system_score_codex":0.000067265304,"about_ca_system_score_gemma":0.00063314504,"threshold_uncertainty_score":0.40334913},"labels":[],"label_agreement":null},{"id":"W4293518025","doi":"10.1109/cibcb55180.2022.9863051","title":"Predicting the specific substrate for transmembrane transport proteins using BERT language model","year":2022,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Concordia University","funders":"","keywords":"UniProt; Computer science; Classifier (UML); Artificial intelligence; Transmembrane protein; Language model; Machine learning; Chemistry; Biochemistry","score_opus":0.015871984412463506,"score_gpt":0.2557313749277768,"score_spread":0.2398593905153133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293518025","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85184157,0.00014140489,0.1442881,0.00019963359,0.000062587744,0.00067978515,0.000090756825,0.000030504856,0.0026656785],"genre_scores_gemma":[0.98416317,0.000010178841,0.013521509,0.0002671767,0.000110911016,0.00011465897,0.00024477736,0.000030082545,0.001537526],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915195,0.000032753687,0.00023346717,0.0001847151,0.00016481604,0.00023228471],"domain_scores_gemma":[0.9995686,0.000011178319,0.00007383576,0.0002856119,0.000025005138,0.000035760026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003811544,0.00012653587,0.00009796826,0.0000225598,0.0003783705,0.000016066306,0.00026377564,0.00004858274,0.00007394445],"category_scores_gemma":[0.000009815936,0.00009730958,0.000112729984,0.00007039251,0.000038257574,0.0000038674634,0.000038018992,0.00017659341,6.2243225e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019815161,0.00006734897,0.0018051297,0.00009734913,0.00006265228,0.000002143289,0.0025763279,0.46220472,0.5316782,0.00043750706,0.00027822267,0.000592222],"study_design_scores_gemma":[0.0008753429,0.00025610634,0.00028127257,0.0000059547638,0.00003804419,0.000052309475,0.0017193081,0.8970367,0.08720378,0.00004268013,0.012205076,0.0002834468],"about_ca_topic_score_codex":0.000036673275,"about_ca_topic_score_gemma":0.00003597025,"teacher_disagreement_score":0.44447446,"about_ca_system_score_codex":0.000014338063,"about_ca_system_score_gemma":0.00006801334,"threshold_uncertainty_score":0.39681694},"labels":[],"label_agreement":null},{"id":"W4293518829","doi":"10.1109/cibcb55180.2022.9863025","title":"DeePSLiM: A Deep Learning Approach to Identify Predictive Short-linear Motifs for Protein Sequence Classification","year":2022,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Artificial intelligence; Matthews correlation coefficient; Machine learning; Deep learning; Pattern recognition (psychology); Data mining; Support vector machine","score_opus":0.03271664513823747,"score_gpt":0.3174253261703308,"score_spread":0.28470868103209335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293518829","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27946138,0.000028549399,0.7111926,0.00013518955,0.00006757806,0.001403447,0.000028228358,0.00007075577,0.0076122563],"genre_scores_gemma":[0.9295918,0.0000026258851,0.06548199,0.00022535423,0.00011177569,0.0012668348,0.0008325301,0.000033793287,0.0024533395],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986601,0.000120678764,0.00029086714,0.00038857904,0.00025565785,0.00028411407],"domain_scores_gemma":[0.99934566,0.000011025376,0.00009865549,0.00032844648,0.0001207893,0.00009544921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000550121,0.00016035208,0.00012866584,0.00007328481,0.0003765264,0.000036978166,0.00035090532,0.00008693548,0.000031551073],"category_scores_gemma":[0.00034255366,0.00016438749,0.000084308354,0.00017852953,0.000036704718,0.000007669654,0.00031454294,0.0002720854,0.000009288332],"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":[0.00033674084,0.00021516363,0.0036543952,0.00014277248,0.00011277859,5.617502e-7,0.0011721115,0.21750264,0.7644738,0.001882096,0.0011030195,0.009403902],"study_design_scores_gemma":[0.00045612943,0.0012622332,0.0024271095,0.0000069213197,0.000030226342,0.000027797603,0.0021107441,0.9232645,0.023003962,0.000078205245,0.046920557,0.00041159306],"about_ca_topic_score_codex":0.000009620073,"about_ca_topic_score_gemma":0.0000034225734,"teacher_disagreement_score":0.74146986,"about_ca_system_score_codex":0.000064903295,"about_ca_system_score_gemma":0.00005894256,"threshold_uncertainty_score":0.6703527},"labels":[],"label_agreement":null},{"id":"W4293519117","doi":"10.1109/cibcb55180.2022.9863026","title":"TooT-BERT-M: Discriminating Membrane Proteins from Non-Membrane Proteins using a BERT Representation of Protein Primary Sequences","year":2022,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Membrane protein; Membrane; Representation (politics); Vesicle-associated membrane protein 8; Cell membrane; Encoder; Chemistry; Computer science; Computational biology; Biophysics; Biochemistry; Artificial intelligence; Biology","score_opus":0.015732143625217233,"score_gpt":0.2700129842050316,"score_spread":0.25428084057981437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293519117","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9781658,0.0000706773,0.0114196995,0.00025942168,0.00008804844,0.0020169094,0.00007772661,0.000039519342,0.007862198],"genre_scores_gemma":[0.9076366,0.0000069691705,0.08946089,0.00017425645,0.00012802242,0.0003750107,0.00069308176,0.00004249391,0.0014826969],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977473,0.00022529502,0.0006621506,0.00046495532,0.0005725304,0.0003277856],"domain_scores_gemma":[0.9986549,0.000030242298,0.0005196707,0.0006062272,0.00011203851,0.00007689747],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004275288,0.00026384505,0.00033681252,0.00010058732,0.00031610316,0.000045605044,0.00044617304,0.00011852382,0.00030364288],"category_scores_gemma":[0.00026378094,0.00024813486,0.00014277024,0.00029472957,0.0001236198,0.000028055994,0.0006008712,0.0003131797,0.0000030611693],"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":[0.0001378071,0.0001267722,0.0014085318,0.00024484633,0.00007530233,0.000005085486,0.0007016085,0.004355722,0.9911832,0.000069355534,0.000040970455,0.0016507474],"study_design_scores_gemma":[0.00078608235,0.0004992691,0.0007658414,0.000077671706,0.000043573025,0.000027037173,0.0010127857,0.02156467,0.97388554,0.00008570027,0.0008776611,0.00037417214],"about_ca_topic_score_codex":0.0028834005,"about_ca_topic_score_gemma":0.00010032086,"teacher_disagreement_score":0.07804118,"about_ca_system_score_codex":0.00007169537,"about_ca_system_score_gemma":0.00023922083,"threshold_uncertainty_score":0.9999971},"labels":[],"label_agreement":null},{"id":"W4295067759","doi":"10.1016/j.csbj.2022.08.021","title":"Integrating knowledge of protein sequence with protein function for the prediction and validation of new MALT1 substrates","year":2022,"lang":"en","type":"article","venue":"Computational and Structural Biotechnology Journal","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"Canada Research Chairs; Canadian Institutes of Health Research; Institute of Neurosciences, Mental Health and Addiction; Genome British Columbia; Deutscher Akademischer Austauschdienst; Michael Smith Health Research BC","keywords":"Biology; Computational biology; Immunoprecipitation; Cell biology; Drug discovery; Function (biology); Transfection; Genetics; Gene; Bioinformatics","score_opus":0.010657948217908457,"score_gpt":0.24767428776653827,"score_spread":0.2370163395486298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295067759","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9320723,0.0003436797,0.0667167,0.0005399375,0.00003394423,0.00025955937,0.000022094619,0.0000056063845,0.0000061756436],"genre_scores_gemma":[0.98433185,0.0000068138484,0.0155158555,0.000009344676,0.000035836205,0.000012703176,0.00005066261,0.000004031861,0.000032925742],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995429,0.000030697785,0.00020136751,0.000085904496,0.00007264573,0.00006648342],"domain_scores_gemma":[0.9995599,0.000020641704,0.00025017114,0.000048771344,0.00010307238,0.00001746793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015287165,0.000068319554,0.00007583877,0.000052086132,0.00025794515,0.000012650169,0.0000779406,0.000059533086,0.0000052691794],"category_scores_gemma":[0.000055364315,0.000044625776,0.000019143034,0.00007552364,0.00014509597,0.000008910066,0.00005542949,0.00019314652,2.1056172e-8],"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":[0.0009247747,0.00002217467,0.008729277,0.00018898706,0.00023533744,4.6111361e-7,0.0006737527,0.04824403,0.8259246,0.018124312,0.00009632425,0.09683598],"study_design_scores_gemma":[0.003909996,0.010512323,0.03628443,0.00017217542,0.00015082542,0.0025539263,0.0036203288,0.32451475,0.54301775,0.07270792,0.0021068477,0.00044875924],"about_ca_topic_score_codex":0.0000051864504,"about_ca_topic_score_gemma":0.0000022058532,"teacher_disagreement_score":0.28290686,"about_ca_system_score_codex":0.0000086129985,"about_ca_system_score_gemma":0.00008750816,"threshold_uncertainty_score":0.19839317},"labels":[],"label_agreement":null},{"id":"W4295359093","doi":"10.1002/tpg2.20259","title":"ASRpro: A machine‐learning computational model for identifying proteins associated with multiple abiotic stress in plants","year":2022,"lang":"en","type":"article","venue":"The Plant Genome","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Support vector machine; Abiotic component; Abiotic stress; Random forest; Machine learning; Artificial intelligence; Computer science; Gene; Biology; Data mining; Computational biology; Ecology; Genetics","score_opus":0.021288834010939468,"score_gpt":0.24068663387100836,"score_spread":0.21939779986006888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295359093","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97263795,0.000109300585,0.024746481,0.00009539089,0.000033572567,0.00078160415,0.0014781668,0.000026594775,0.0000909525],"genre_scores_gemma":[0.99172676,0.0000047661456,0.0026850097,0.00010989795,0.000020716152,0.00014504505,0.0049095782,0.000024894061,0.00037336323],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901843,0.00011107176,0.0002124229,0.00018503246,0.0002137635,0.00025927552],"domain_scores_gemma":[0.9995402,0.00008684151,0.00017351817,0.00014198366,0.00002552402,0.00003191107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045866644,0.0001340659,0.00012992404,0.00005810387,0.00037145708,0.000031512882,0.00027693593,0.00004407454,0.000009977597],"category_scores_gemma":[0.00011431627,0.000105593135,0.000039528823,0.0000770458,0.000030459501,0.0000042832544,0.00018918663,0.00029836246,0.0000016142731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021637257,0.00006826352,0.011616258,0.000031541225,0.00006196526,0.0000032664743,0.0015490487,0.97775483,0.008599963,0.00002645652,0.00002559357,0.000046447287],"study_design_scores_gemma":[0.00096814113,0.00021185749,0.004941497,0.00001761609,0.000011618899,0.0000284073,0.00022947628,0.9927016,0.00026848068,0.00007864016,0.00037502107,0.00016767187],"about_ca_topic_score_codex":0.00004207666,"about_ca_topic_score_gemma":0.00028818275,"teacher_disagreement_score":0.02206147,"about_ca_system_score_codex":0.000047306003,"about_ca_system_score_gemma":0.00007383153,"threshold_uncertainty_score":0.43059632},"labels":[],"label_agreement":null},{"id":"W4297475121","doi":"10.1002/pro.4442","title":"CSM‐peptides: A computational approach to rapid identification of therapeutic peptides","year":2022,"lang":"en","type":"article","venue":"Protein Science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Health and Medical Research Council; Medical Research Council Canada; Medical Research Council; State Government of Victoria; University of Queensland","keywords":"Identification (biology); Computational biology; Peptide; Chemistry; Combinatorial chemistry; Biochemistry; Biology","score_opus":0.012378751060791345,"score_gpt":0.2690083737431696,"score_spread":0.25662962268237827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297475121","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88757807,0.00008866474,0.107832916,0.00017424666,0.000063096624,0.0006939866,0.000017362592,0.000017568716,0.0035340865],"genre_scores_gemma":[0.9707332,9.975759e-7,0.028563349,0.00019230605,0.000019396812,0.00014310272,0.000030273972,0.0000066166376,0.00031074235],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987955,0.000057679048,0.00025367894,0.00024713908,0.00048423497,0.00016178381],"domain_scores_gemma":[0.9993694,0.000008268922,0.00016045084,0.00028369244,0.00012758738,0.000050644365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011823627,0.00007506561,0.00007388196,0.00010444812,0.0002835853,0.000037523187,0.0005562587,0.00001781161,0.000016465494],"category_scores_gemma":[0.00018049961,0.000073809344,0.000034630826,0.00046297908,0.0002148959,0.00000948009,0.00031117824,0.00008386467,0.0000075175076],"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":[0.000024165389,0.00008309275,0.00062000856,0.00003278788,0.0000073224355,6.985084e-8,0.00060816336,0.05126841,0.9378583,0.0024562336,0.00009895479,0.0069425046],"study_design_scores_gemma":[0.00079617195,0.0016856361,0.024666851,0.000023856752,0.0000189168,0.00006216402,0.0020010713,0.2247551,0.7273762,0.0029885918,0.014893151,0.0007322881],"about_ca_topic_score_codex":0.000007125339,"about_ca_topic_score_gemma":2.4484387e-7,"teacher_disagreement_score":0.21048209,"about_ca_system_score_codex":0.000025740717,"about_ca_system_score_gemma":0.00016262977,"threshold_uncertainty_score":0.30098578},"labels":[],"label_agreement":null},{"id":"W4297996437","doi":"10.3389/fonc.2022.979336","title":"Functional and embedding feature analysis for pan-cancer classification","year":2022,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Chinese Academy of Sciences","keywords":"Feature selection; Computer science; Feature (linguistics); Artificial intelligence; Machine learning; KEGG; Word2vec; Pattern recognition (psychology); Computational biology; Embedding; Biology; Genetics; Gene ontology; Gene","score_opus":0.015255952781013514,"score_gpt":0.30941896191324414,"score_spread":0.29416300913223065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297996437","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4752448,0.0030776008,0.5106446,0.00529975,0.0024902597,0.0006804221,0.00016785807,0.000027586328,0.0023671016],"genre_scores_gemma":[0.930936,0.000226722,0.06315435,0.0010170578,0.00022506285,0.0005229927,0.0009456194,0.000016635071,0.0029555764],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993853,0.00007542442,0.00013807761,0.00019184336,0.00007058595,0.00013879944],"domain_scores_gemma":[0.99969876,0.000021147347,0.00010784748,0.00012010599,0.00002769406,0.00002447467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027435334,0.000072999486,0.00014986249,0.00014977547,0.00013308342,0.000007815498,0.000090209505,0.00010572886,0.000039532977],"category_scores_gemma":[0.000069634334,0.00007800988,0.0000591055,0.00019871452,0.000043010266,0.0000028068669,0.00009116924,0.00015791808,2.539148e-7],"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":[0.00056076224,0.0000988503,0.62090826,0.000036564164,0.00062689267,0.0000012827652,0.00037901956,0.04023971,0.008366758,0.00035581723,0.27519736,0.0532287],"study_design_scores_gemma":[0.0009118756,0.00035424583,0.1157056,0.0000012701756,0.00014579196,0.000007792875,0.0010659632,0.155608,0.0001773638,0.00017064423,0.72569084,0.00016064194],"about_ca_topic_score_codex":0.0000062065246,"about_ca_topic_score_gemma":0.00002928738,"teacher_disagreement_score":0.50520265,"about_ca_system_score_codex":0.00010459316,"about_ca_system_score_gemma":0.00007215036,"threshold_uncertainty_score":0.31811506},"labels":[],"label_agreement":null},{"id":"W4300581088","doi":"","title":"Quantitative sequence and open reading frame analysis based on codon bias","year":2006,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Open reading frame; Reading (process); Sequence (biology); Computer science; Frame (networking); Codon usage bias; Natural language processing; Artificial intelligence; Genetics; Linguistics; Biology; Peptide sequence; Philosophy; Telecommunications; Gene","score_opus":0.2384952510087565,"score_gpt":0.5596128224621899,"score_spread":0.32111757145343345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300581088","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97362554,0.0015531714,0.00775056,0.00017903978,0.00010783761,0.00044538252,0.00009438995,0.000015042675,0.016229063],"genre_scores_gemma":[0.99164975,0.00072295737,0.006317786,0.0006039,0.00006245516,0.00001912447,0.00017826911,0.000032933178,0.00041285183],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979272,0.00031488453,0.0006674941,0.0004144171,0.00039116776,0.00028482315],"domain_scores_gemma":[0.9979958,0.0002307926,0.000869678,0.0005364006,0.00022897276,0.000138371],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0014363546,0.00027982422,0.00059721567,0.0005587564,0.0002289287,0.001246998,0.0019236084,0.00015345069,0.00079055654],"category_scores_gemma":[0.0006391169,0.00025023535,0.00015554042,0.00088398287,0.00014888024,0.00012353834,0.0009161717,0.0003008984,0.000006271985],"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":[0.00044752384,0.00016932437,0.722471,0.00007744208,0.000503048,0.000015246118,0.00007483197,0.020437457,0.24145114,0.00042742013,0.012065188,0.0018603853],"study_design_scores_gemma":[0.0014023732,0.00021934793,0.7966106,0.0004390565,0.00060339866,0.000015463174,0.00015216878,0.051792838,0.12769157,0.0019589032,0.017975362,0.0011389242],"about_ca_topic_score_codex":0.0016424408,"about_ca_topic_score_gemma":0.00021574667,"teacher_disagreement_score":0.11375956,"about_ca_system_score_codex":0.000038407135,"about_ca_system_score_gemma":0.00010662903,"threshold_uncertainty_score":0.999995},"labels":[],"label_agreement":null},{"id":"W4306800518","doi":"10.1007/978-3-031-17024-9_1","title":"TooT-BERT-T: A BERT Approach on Discriminating Transport Proteins from Non-transport Proteins","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Concordia University","funders":"","keywords":"Transmembrane protein; Transporter; Transport protein; Classifier (UML); Representation (politics); Membrane transport protein; Membrane; Membrane protein; Chemistry; Computer science; Computational biology; Artificial intelligence; Biology; Biochemistry; Gene","score_opus":0.009424661949098445,"score_gpt":0.21567579477778392,"score_spread":0.20625113282868549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306800518","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019934824,0.01103297,0.6211657,0.00031225928,0.0025145868,0.0110327145,0.00082045596,0.00018294383,0.33300358],"genre_scores_gemma":[0.9801829,0.00041389547,0.0025457996,0.00032015226,0.00192772,0.000516685,0.0053322725,0.00022501321,0.008535568],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971372,0.00007764711,0.0008867801,0.00090198754,0.0004811224,0.0005152479],"domain_scores_gemma":[0.998496,0.000071190174,0.00047801557,0.0007683082,0.00005213586,0.00013437659],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004629639,0.0007739763,0.0008507022,0.00012843107,0.00023179567,0.000058786267,0.00041506957,0.0011046473,0.00006267507],"category_scores_gemma":[0.000039410592,0.00067659107,0.00024367768,0.000071682494,0.00011442768,0.0000087016015,0.000104630184,0.0015825036,0.0000018930259],"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":[0.00088091346,0.00029204955,0.008660894,0.0027749639,0.0009354518,0.00019418879,0.0031937496,0.9574736,0.0011924228,0.0043417024,0.00047288492,0.019587195],"study_design_scores_gemma":[0.005568726,0.0051509845,0.0039288,0.0062241014,0.0008450463,0.00034842925,0.00020303998,0.4469295,0.00049082126,0.0013057656,0.52153665,0.0074681086],"about_ca_topic_score_codex":0.000777076,"about_ca_topic_score_gemma":0.0004981694,"teacher_disagreement_score":0.96024805,"about_ca_system_score_codex":0.00007050271,"about_ca_system_score_gemma":0.000088244626,"threshold_uncertainty_score":0.9995685},"labels":[],"label_agreement":null},{"id":"W4307306496","doi":"10.3180/poster/20221027matthews","title":"Illuminating Dark Proteins using Reactome Pathways","year":2022,"lang":"en","type":"report","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Institutes of Health","keywords":"Human proteins; Computational biology; Context (archaeology); Druggability; Function (biology); Biology; Gene ontology; Gene; Bioinformatics; Genetics; Gene expression","score_opus":0.0405472090836094,"score_gpt":0.30856243238701375,"score_spread":0.2680152233034043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307306496","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10452117,0.0007634368,0.0037524179,0.000039707327,0.0013633472,0.0010582296,0.0002155758,0.00013279346,0.8881533],"genre_scores_gemma":[0.5682551,0.0025625117,0.21176521,0.0014115591,0.0075429757,0.00062409684,0.021588102,0.0011938704,0.18505654],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975995,0.000096991906,0.0006010515,0.00046448386,0.0008385081,0.00039946992],"domain_scores_gemma":[0.99817723,0.000016119362,0.0006421802,0.00081464584,0.00025656098,0.00009323421],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010532826,0.0003820546,0.0003601509,0.00012761654,0.00024804592,0.00005665367,0.00044098773,0.00045667475,0.0006789962],"category_scores_gemma":[0.0010545271,0.00036954953,0.00022078943,0.00013781349,0.00006617245,0.000003437653,0.0008665595,0.000740772,0.000011644198],"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":[0.00014264404,0.0006049687,0.010569054,0.0055416,0.0016200938,0.00025923146,0.0013941845,0.0033188488,0.70888186,0.00042772637,0.21428065,0.052959178],"study_design_scores_gemma":[0.00025750682,0.00034288623,0.00019797878,0.0000918792,0.00007676871,0.00051586656,0.00028774652,0.0015946985,0.009418528,0.000017781143,0.9863222,0.00087613263],"about_ca_topic_score_codex":0.00031907795,"about_ca_topic_score_gemma":0.000027067363,"teacher_disagreement_score":0.77204156,"about_ca_system_score_codex":0.00020165798,"about_ca_system_score_gemma":0.0013595698,"threshold_uncertainty_score":0.99987566},"labels":[],"label_agreement":null},{"id":"W4309242540","doi":"10.1109/biocas54905.2022.9948611","title":"Prediction of Protein-Protein Interactions through Deep Learning Based on Sequence Feature Extraction and Interaction Network","year":2022,"lang":"en","type":"article","venue":"2022 IEEE Biomedical Circuits and Systems Conference (BioCAS)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Artificial Intelligence in Medicine (Canada)","funders":"Ministry of Education; Ministry of Science and Technology","keywords":"Computer science; Artificial intelligence; Artificial neural network; Machine learning; Deep learning; Process (computing); Feature extraction; Cross-validation; Field (mathematics); Protein function prediction; Set (abstract data type); Sequence (biology); Test set; Pattern recognition (psychology); Data mining; Protein function; Mathematics","score_opus":0.03705778356705998,"score_gpt":0.2796034131993648,"score_spread":0.24254562963230486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309242540","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8980055,0.00061344565,0.09531568,0.00050022436,0.001959287,0.0013641509,0.00018136637,0.00008559854,0.0019747529],"genre_scores_gemma":[0.9981004,0.000047804533,0.00017349533,0.000076660916,0.00031301685,0.00019827585,0.00039908898,0.000020486355,0.00067078735],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808717,0.00040783294,0.00041838153,0.0004009456,0.0004336101,0.0002520343],"domain_scores_gemma":[0.99908215,0.00005197565,0.00040785316,0.00024438056,0.000101569945,0.00011207604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005890418,0.00021288336,0.00024959308,0.00010004764,0.0004302746,0.00007226263,0.00014204679,0.00017168623,0.00008699388],"category_scores_gemma":[0.00016907076,0.00020242574,0.00005835309,0.00021680034,0.00014843854,0.00003083154,0.00009022788,0.0007510924,0.000002031452],"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":[0.0003435455,0.00028214333,0.0030030243,0.00081250246,0.00015242539,0.000018002671,0.0009026518,0.013415715,0.938752,0.0013510017,0.0016014886,0.039365485],"study_design_scores_gemma":[0.0021160478,0.0054281275,0.002868797,0.00085130543,0.00010113179,0.0005520198,0.0038405003,0.73341256,0.008495771,0.00013985322,0.24138227,0.00081160193],"about_ca_topic_score_codex":0.00009411873,"about_ca_topic_score_gemma":0.000010315618,"teacher_disagreement_score":0.93025625,"about_ca_system_score_codex":0.00006154527,"about_ca_system_score_gemma":0.00008612303,"threshold_uncertainty_score":0.8254682},"labels":[],"label_agreement":null},{"id":"W4310594072","doi":"10.1093/bioinformatics/btac779","title":"DeepCellEss: cell line-specific essential protein prediction with attention-based interpretable deep learning","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Interpretability; Computer science; Artificial intelligence; Benchmark (surveying); Source code; Machine learning; Convolutional neural network; Deep learning; Code (set theory); Data mining","score_opus":0.004123358410521841,"score_gpt":0.19876093933838215,"score_spread":0.19463758092786032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310594072","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.525099,0.0002540197,0.46207425,0.000099096236,0.00033586746,0.0009662776,0.00006512066,0.00017597359,0.010930411],"genre_scores_gemma":[0.96130824,0.000022666149,0.03505035,0.00016413117,0.00014071347,0.0001663876,0.0013934834,0.000051149327,0.0017028822],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982858,0.00010178077,0.0005532446,0.00021490728,0.00047196477,0.00037231878],"domain_scores_gemma":[0.9989248,0.000017360304,0.0004089841,0.00043522107,0.00011373636,0.00009989896],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038900244,0.00026086546,0.00019041078,0.00013412522,0.0005581589,0.00011229373,0.00035474557,0.00011054365,0.00021902451],"category_scores_gemma":[0.000039805705,0.0002460299,0.00011291075,0.0002423191,0.00008158101,0.000025444408,0.00027186592,0.00049629225,0.00004655827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013392452,0.00072321086,0.014781177,0.0012227899,0.00022785409,0.000014086211,0.0026265362,0.8498707,0.1127407,0.00025679512,0.0055711023,0.010625824],"study_design_scores_gemma":[0.0021590923,0.0021992389,0.00029796964,0.000050264713,0.00004855103,0.00004567998,0.002322951,0.82347393,0.02242374,0.000007744162,0.14639048,0.0005803395],"about_ca_topic_score_codex":0.000006432938,"about_ca_topic_score_gemma":0.0000046296377,"teacher_disagreement_score":0.43620926,"about_ca_system_score_codex":0.00006399156,"about_ca_system_score_gemma":0.00011808761,"threshold_uncertainty_score":0.99999917},"labels":[],"label_agreement":null},{"id":"W4311890421","doi":"10.48084/etasr.5230","title":"Classification of Macromolecules Based on Amino Acid Sequences Using Deep Learning","year":2022,"lang":"en","type":"article","venue":"Engineering Technology & Applied Science Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Deep learning; Artificial intelligence; Computer science; Word2vec; Embedding; Word embedding; Task (project management); Machine learning; Convolutional neural network; Artificial neural network; Pattern recognition (psychology); Engineering","score_opus":0.022268222360469915,"score_gpt":0.3170238563315601,"score_spread":0.29475563397109017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311890421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9663767,0.000075462965,0.032249875,0.0001641761,0.00005131475,0.00021383457,0.0000039794027,0.00008162266,0.00078300404],"genre_scores_gemma":[0.97981316,0.0000062170984,0.020026458,0.000011744984,0.000017228744,0.000076351425,0.00001370837,0.000017237808,0.000017872102],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813503,0.000048888785,0.00021130762,0.00037012735,0.00074747007,0.00048715415],"domain_scores_gemma":[0.9992093,0.00003844361,0.000089418936,0.00048741672,0.00012210796,0.000053332024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021443327,0.000116850315,0.00012034444,0.0009772428,0.00056094746,0.000021688804,0.0009769717,0.00010750846,0.000015738964],"category_scores_gemma":[0.00057798467,0.00012445272,0.000029141931,0.0019028753,0.0006142085,0.000005345057,0.0005661826,0.00083967025,0.000004147762],"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":[0.000012510324,0.000020191985,0.0009363109,0.000016063204,0.0000036041833,0.0000010805362,0.000030004172,0.19916408,0.79502445,0.0028748778,0.0000041473418,0.0019126761],"study_design_scores_gemma":[0.00013203527,0.00030889682,0.0005222572,0.000008124502,0.0000021623468,0.0000111046165,0.000428118,0.53006494,0.46720567,0.000090516754,0.0011045623,0.00012160831],"about_ca_topic_score_codex":0.000004568516,"about_ca_topic_score_gemma":5.8918505e-7,"teacher_disagreement_score":0.33090088,"about_ca_system_score_codex":0.00017265382,"about_ca_system_score_gemma":0.00022796096,"threshold_uncertainty_score":0.50750345},"labels":[],"label_agreement":null},{"id":"W4312222567","doi":"10.1007/s11030-022-10584-5","title":"Subtractive sequence analysis aided druggable targets mining in Burkholderia cepacia complex and finding inhibitors through bioinformatics approach","year":2022,"lang":"en","type":"article","venue":"Molecular Diversity","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Waterloo","funders":"Penn Center for Musculoskeletal Disorders; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; University of Karachi","keywords":"Druggability; Burkholderia; Computational biology; Subtractive color; Burkholderia cepacia complex; Sequence (biology); Biology; Bioinformatics; Genetics; Gene; Bacteria","score_opus":0.026596208368976745,"score_gpt":0.26115004472237535,"score_spread":0.2345538363533986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312222567","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9791263,0.00010049694,0.013968048,0.000053097643,0.00005374206,0.00024582565,0.00008623323,0.000023386374,0.0063428986],"genre_scores_gemma":[0.9694843,0.000016704776,0.029407116,0.0003054573,0.000012567828,0.000010837023,0.00069509225,0.000011144172,0.00005672382],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985315,0.00015685559,0.00029151276,0.00033157726,0.0003427934,0.00034575906],"domain_scores_gemma":[0.9993163,0.000018992434,0.00022980107,0.00031546818,0.000044381235,0.00007506503],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042603866,0.00021335861,0.00027875678,0.00020284903,0.00061949325,0.000046997662,0.00032016909,0.000098896475,0.00005824718],"category_scores_gemma":[0.00008761427,0.0002515786,0.0001315293,0.0006384826,0.000111426576,0.000029864832,0.0017904082,0.00028110258,0.0000018810629],"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":[0.00029756452,0.00041926687,0.6181533,0.00029553007,0.0017238029,0.00013118688,0.027988426,0.18984427,0.15707435,0.0007273137,0.002036044,0.0013089542],"study_design_scores_gemma":[0.007625879,0.0013722065,0.17174815,0.000052410785,0.0017768604,0.00022683223,0.06443797,0.64063036,0.08766936,0.00031233954,0.01990718,0.004240486],"about_ca_topic_score_codex":0.00024526322,"about_ca_topic_score_gemma":0.000019202016,"teacher_disagreement_score":0.45078605,"about_ca_system_score_codex":0.00007826034,"about_ca_system_score_gemma":0.00004393666,"threshold_uncertainty_score":0.9999936},"labels":[],"label_agreement":null},{"id":"W4313052989","doi":"10.1145/3570773.3570779","title":"Prediction of Phosphorylation Sites in Amino Acid Sequences Using Convolutional Neural Networks","year":2022,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Phosphorylation; Convolutional neural network; Cascade; Computational biology; Protein phosphorylation; Computer science; Kinase; Artificial intelligence; Biochemistry; Bioinformatics; Protein kinase A; Biology; Chemistry","score_opus":0.018791705807201773,"score_gpt":0.24710985597863105,"score_spread":0.22831815017142928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313052989","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9897316,0.00025210372,0.009283234,0.00002348513,0.000109169465,0.000084229476,0.000018776867,0.000008086358,0.0004893163],"genre_scores_gemma":[0.99745476,0.000009151849,0.001964263,0.00007790489,0.000046600686,0.000006537938,0.0003660244,0.000004820731,0.000069905174],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99942774,0.000053023585,0.00020321026,0.00009680728,0.00012099649,0.00009820151],"domain_scores_gemma":[0.999759,0.000007720824,0.00009952566,0.00008994651,0.000028424396,0.000015393294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018306678,0.00005899154,0.000063341,0.000039557,0.00007073591,0.000005323072,0.000079045654,0.000042606087,0.000116556526],"category_scores_gemma":[0.00003084286,0.000060761915,0.00002910262,0.000104004794,0.000040744584,0.0000049709392,0.00009875874,0.00010345608,2.4507682e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036055964,0.00002149267,0.2681805,0.000008262077,0.000009079012,3.331798e-7,0.00005563374,0.5925853,0.13849106,0.00013868806,0.0001725585,0.00030098937],"study_design_scores_gemma":[0.00020667429,0.00014788525,0.03315413,0.0000019386846,0.000004500127,0.00001521251,0.00012251297,0.9574079,0.008536447,0.000022831613,0.00032123266,0.000058770896],"about_ca_topic_score_codex":0.000058248726,"about_ca_topic_score_gemma":0.000015012416,"teacher_disagreement_score":0.3648225,"about_ca_system_score_codex":0.000029283685,"about_ca_system_score_gemma":0.000031740223,"threshold_uncertainty_score":0.2477799},"labels":[],"label_agreement":null},{"id":"W4313452391","doi":"10.1109/bibm55620.2022.9995562","title":"S-PDB: Analysis and Classification of SARS-CoV-2 Spike Protein Structures","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Protein Data Bank (RCSB PDB); Protein Data Bank; Computer science; Protein structure; Artificial intelligence; Pattern recognition (psychology); Naive Bayes classifier; Protein structure prediction; Computational biology; Biology; Support vector machine","score_opus":0.040593229017798174,"score_gpt":0.3235066638355676,"score_spread":0.2829134348177694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313452391","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98546726,0.000059818518,0.0056137703,0.0012991637,0.00027137884,0.00031993317,0.00028144795,0.000016316968,0.006670898],"genre_scores_gemma":[0.99560636,0.000141722,0.0026195266,0.00048422988,0.000070933645,0.000031965614,0.00073616795,0.000009511725,0.00029958182],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856526,0.000043751734,0.0005358846,0.00019951302,0.00050198374,0.00015360974],"domain_scores_gemma":[0.9990923,0.000016190794,0.00043525355,0.00025737876,0.0001441289,0.000054769134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037060573,0.00018145035,0.00023801948,0.0005092703,0.00013284074,0.000045707875,0.00030049824,0.00007735203,0.00012598213],"category_scores_gemma":[0.00007092216,0.0001545074,0.00006962903,0.00035717047,0.00018893299,0.000015732552,0.00021363028,0.00021642518,0.0000021672786],"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":[0.00030850305,0.00012357511,0.0060383207,0.00018394523,0.00084946974,0.0000025797472,0.0008916143,0.00010598594,0.9508271,0.01710303,0.003715961,0.019849895],"study_design_scores_gemma":[0.0040659485,0.0046636323,0.04748738,0.00011707222,0.0005336719,0.00013830971,0.0051997807,0.7080713,0.16294175,0.0024713636,0.06304567,0.0012641138],"about_ca_topic_score_codex":0.000041472962,"about_ca_topic_score_gemma":0.000021132008,"teacher_disagreement_score":0.78788537,"about_ca_system_score_codex":0.000024438968,"about_ca_system_score_gemma":0.000057359357,"threshold_uncertainty_score":0.6300629},"labels":[],"label_agreement":null},{"id":"W4313493331","doi":"10.1155/2023/5333361","title":"Identification of Smoking‐Associated Transcriptome Aberration in Blood with Machine Learning Methods","year":2023,"lang":"en","type":"article","venue":"BioMed Research International","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"University of British Columbia","funders":"National Key Research and Development Program of China; Chinese Academy of Sciences","keywords":"Feature selection; Gene isoform; Computational biology; Alternative splicing; Computer science; Bioinformatics; Biology; Artificial intelligence; Gene; Genetics","score_opus":0.03938593079518336,"score_gpt":0.4078606339185214,"score_spread":0.368474703123338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313493331","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9936206,0.00005733706,0.004092179,0.0005931947,0.00023692737,0.00020769471,0.000035747573,0.00003365294,0.0011226846],"genre_scores_gemma":[0.9947833,0.00012974006,0.0015028534,0.000011119865,0.00006899593,0.000039848994,0.0011471311,0.000017717335,0.0022993109],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982002,0.00040319996,0.00036842463,0.00020518908,0.0005849273,0.00023809016],"domain_scores_gemma":[0.99922556,0.0000801111,0.00014399036,0.00015889705,0.00034956913,0.00004189618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035151755,0.000086644824,0.00010254408,0.0006357305,0.00007108491,0.000039150273,0.00030616965,0.000116105715,0.000038293045],"category_scores_gemma":[0.0013446991,0.00007848428,0.000039306655,0.00082436414,0.00012014416,0.000012488072,0.00008851345,0.00030561822,0.00000922663],"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":[0.00009567609,0.000104166225,0.047339898,0.000032332962,0.00013317818,0.000003113993,0.00040846184,0.0010803832,0.94794714,0.00021591378,0.00033141687,0.0023083212],"study_design_scores_gemma":[0.003643567,0.0009970007,0.22962008,0.00013703664,0.000026959302,0.000020455991,0.0006170995,0.15835035,0.5813915,0.00038767082,0.024414798,0.00039345917],"about_ca_topic_score_codex":0.000087005654,"about_ca_topic_score_gemma":0.00007122868,"teacher_disagreement_score":0.36655563,"about_ca_system_score_codex":0.000039153896,"about_ca_system_score_gemma":0.00007007488,"threshold_uncertainty_score":0.3200496},"labels":[],"label_agreement":null},{"id":"W4313544751","doi":"10.1089/cmb.2022.0395","title":"A Novel Information-Theory-Based Genetic Distance That Approximates Phenotypic Differences","year":2023,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"Centers for Disease Control and Prevention; National Institutes of Health","keywords":"Biology; Genetics; Phenotype; Entropy (arrow of time); Computational biology; Major histocompatibility complex; In silico; Distance matrix; Pairwise comparison; Mathematics; Combinatorics; Gene; Statistics","score_opus":0.011664451772865346,"score_gpt":0.2586015842894526,"score_spread":0.24693713251658728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313544751","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37006408,0.00009623402,0.62895703,0.00033026704,0.00022195729,0.00006768962,0.000043431108,0.000014236086,0.00020509343],"genre_scores_gemma":[0.9561005,0.000020381203,0.042891983,0.0004961757,0.00012799495,0.000004151698,0.0003118892,0.000007489106,0.00003943648],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99908096,0.00007206968,0.00043467848,0.00007926249,0.00016441006,0.00016864331],"domain_scores_gemma":[0.9989465,0.00017581426,0.0004898882,0.00010034406,0.00022981585,0.00005764646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035544002,0.0001222901,0.00017423091,0.00016105249,0.00007586856,0.000033203964,0.0002570565,0.00010139176,0.00002308981],"category_scores_gemma":[0.00027518178,0.00009635545,0.000093294984,0.00015074995,0.00011885489,0.000014098687,0.000052253672,0.00012792219,0.0000299297],"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":[0.0011248519,0.00026981905,0.20117383,0.00033989985,0.000618955,0.0000075247403,0.0008951035,0.6840904,0.024450053,0.04364287,0.005871525,0.03751517],"study_design_scores_gemma":[0.0057354853,0.0024451283,0.5240243,0.0001432698,0.00010909786,0.0004218616,0.0004938451,0.30649048,0.0039289263,0.07663309,0.07854313,0.0010314063],"about_ca_topic_score_codex":0.0000010711691,"about_ca_topic_score_gemma":8.39004e-7,"teacher_disagreement_score":0.58606505,"about_ca_system_score_codex":0.000012188641,"about_ca_system_score_gemma":0.00014293529,"threshold_uncertainty_score":0.39292613},"labels":[],"label_agreement":null},{"id":"W4317911177","doi":"10.1142/s021969132250045x","title":"Calibrating the classifier for protein family prediction with protein sequence using machine learning techniques: An empirical investigation","year":2023,"lang":"en","type":"article","venue":"International Journal of Wavelets Multiresolution and Information Processing","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Classifier (UML); Feature selection; Random forest; Artificial intelligence; Protein family; Computer science; Protein sequencing; Machine learning; Pattern recognition (psychology); Protein structure prediction; Computational biology; Data mining; Protein structure; Peptide sequence; Gene; Biology; Genetics","score_opus":0.03711071404583471,"score_gpt":0.32028275101134446,"score_spread":0.28317203696550974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317911177","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83950573,0.000029410738,0.15913971,0.000721889,0.00006623608,0.00040619518,0.000020658796,0.0000446391,0.0000655074],"genre_scores_gemma":[0.9434081,0.00001754171,0.05555686,0.00040482354,0.00023081334,0.0000306038,0.00029128854,0.000014163144,0.00004584449],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987423,0.00008129524,0.0005602043,0.00009240157,0.00038267646,0.0001411534],"domain_scores_gemma":[0.99834913,0.000014369614,0.00075560424,0.000069825415,0.0007488157,0.00006225105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000849671,0.00012459954,0.00009836674,0.00019625286,0.00029918438,0.00024184289,0.00017866903,0.00010441431,0.000001405375],"category_scores_gemma":[0.00043801183,0.00008703042,0.000036970418,0.0001613284,0.00010324813,0.00051492726,0.000053570686,0.00024376449,6.001698e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007178682,0.000037654954,0.010348197,0.00023956526,0.00009682869,0.0000021845149,0.0035587542,0.013525407,0.87516296,0.0002640597,0.00012842492,0.09591808],"study_design_scores_gemma":[0.00078208535,0.00049353414,0.0024207127,0.0003128574,0.000014727529,0.00015228566,0.00086329534,0.9435072,0.037233565,0.000067255285,0.014001385,0.00015108795],"about_ca_topic_score_codex":0.000013584657,"about_ca_topic_score_gemma":0.0000033225308,"teacher_disagreement_score":0.9299818,"about_ca_system_score_codex":0.000053915006,"about_ca_system_score_gemma":0.00020874967,"threshold_uncertainty_score":0.35489976},"labels":[],"label_agreement":null},{"id":"W4318019176","doi":"10.1021/acs.jproteome.2c00620","title":"CaspSites: A Database and Web Application for Experimentally Observed Human Caspase Substrates Using N-Terminomics","year":2023,"lang":"en","type":"article","venue":"Journal of Proteome Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Caspase; Cleavage (geology); World Wide Web; Web site; Computer science; Database; Apoptosis; Information retrieval; Biology; The Internet; Biochemistry; Programmed cell death","score_opus":0.1883632673709802,"score_gpt":0.4569847632528405,"score_spread":0.2686214958818603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318019176","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9979876,0.00016253265,0.001085146,0.00009334508,0.000023322173,0.00057837326,0.000027538468,0.000005445683,0.000036688376],"genre_scores_gemma":[0.98813564,0.00006103819,0.011283365,0.000014858607,0.00024075346,0.000045597237,0.00009571538,0.000022027707,0.000101033744],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998944,0.00008890735,0.00033553,0.00013474036,0.00025084717,0.00024597096],"domain_scores_gemma":[0.9991427,0.000046535115,0.00018984244,0.00021042161,0.00030146787,0.000109027904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018514083,0.00009005895,0.00012869752,0.00019217485,0.00023327865,0.00007024988,0.00021576782,0.0000825438,0.0000034446273],"category_scores_gemma":[0.00027143882,0.000080795515,0.000052950185,0.00016591026,0.00010732564,0.000017102133,0.00017099276,0.00022590479,0.0000029282874],"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":[0.00009667708,0.00002925538,0.0025968077,0.0001479175,0.000026963007,0.000010574128,0.0000817036,0.0000833262,0.9963716,0.000057033983,0.00026746685,0.00023062249],"study_design_scores_gemma":[0.0021640887,0.0015844249,0.00241809,0.0001376449,0.000024178467,0.0003926639,0.001237928,0.051933154,0.9358808,0.00027738285,0.0036682754,0.0002813698],"about_ca_topic_score_codex":0.000029932904,"about_ca_topic_score_gemma":0.0000223966,"teacher_disagreement_score":0.060490854,"about_ca_system_score_codex":0.000040950905,"about_ca_system_score_gemma":0.00017577819,"threshold_uncertainty_score":0.32947454},"labels":[],"label_agreement":null},{"id":"W4318328407","doi":"10.1145/3569192.3569196","title":"TooT-BERT-C: A study on discriminating ion channels from membrane proteins based on the primary sequence’s contextual representation from BERT models","year":2022,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Concordia University","funders":"","keywords":"Representation (politics); Sequence (biology); Computer science; Artificial intelligence; Chemistry; Biochemistry; Political science","score_opus":0.043504545123194654,"score_gpt":0.28550052412980625,"score_spread":0.2419959790066116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318328407","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97880286,0.000012029749,0.007945538,0.0014620804,0.00021147325,0.0014857592,0.00014738391,0.00004608639,0.009886783],"genre_scores_gemma":[0.9941229,0.0000018631591,0.00090951985,0.002399037,0.00017746192,0.00044046095,0.0011607474,0.000031622934,0.00075635733],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997947,0.00047189047,0.0003291313,0.0004590351,0.0005690873,0.00022389034],"domain_scores_gemma":[0.9987782,0.00018391309,0.00020547702,0.0007264664,0.000053088304,0.000052831798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004232032,0.00023232134,0.00019617319,0.0000508296,0.00039695707,0.00007236989,0.00040929424,0.00007196129,0.00025825083],"category_scores_gemma":[0.00021086841,0.00017022625,0.00009374129,0.00011072283,0.000046305293,0.000012027216,0.0002928535,0.00035441256,0.000009791544],"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":[0.0021444177,0.0019788172,0.0032517822,0.000037090922,0.00033439888,0.000025917228,0.010349528,0.32398343,0.643511,0.0010255576,0.0032744482,0.010083656],"study_design_scores_gemma":[0.0031943542,0.004132852,0.004238051,0.000053163643,0.00008519337,0.0000032987136,0.009418721,0.7862515,0.19032983,0.000614745,0.00096433255,0.000713969],"about_ca_topic_score_codex":0.001941445,"about_ca_topic_score_gemma":0.00007761647,"teacher_disagreement_score":0.46226805,"about_ca_system_score_codex":0.000069677524,"about_ca_system_score_gemma":0.000074095275,"threshold_uncertainty_score":0.69416255},"labels":[],"label_agreement":null},{"id":"W4318751336","doi":"10.48550/arxiv.2301.12068","title":"Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Prediction","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Samsung; Tencent; Canadian Institute for Advanced Research; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Microsoft Research","keywords":"Computer science; Encoder; Trajectory; Sequence (biology); Joint probability distribution; Conformational isomerism; Diffusion; Mutual information; Joint (building); Artificial intelligence; Algorithm; Mathematics; Engineering; Physics; Biology","score_opus":0.05094002654711007,"score_gpt":0.2090181692533215,"score_spread":0.15807814270621143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318751336","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9290862,0.000028476165,0.06872607,0.000031384418,0.00047906293,0.0006206954,0.000199812,0.0001974224,0.00063085207],"genre_scores_gemma":[0.9918868,0.00008375637,0.0012424083,0.00005243049,0.0003176422,0.0000044225026,0.0010987988,0.0000620168,0.0052517266],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998254,0.0001488209,0.0002821774,0.0008114165,0.00012795025,0.00037563557],"domain_scores_gemma":[0.9985629,0.0000162464,0.00032913886,0.00083689886,0.00011127876,0.00014357663],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020215393,0.000395473,0.00027695793,0.00016593882,0.0001715653,0.000044236807,0.0005885121,0.00083029066,0.000056894994],"category_scores_gemma":[0.00012333128,0.00043269657,0.00020127305,0.0002066513,0.00015364222,0.000013266165,0.00087811716,0.000852884,0.0000235108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003114662,0.0000887597,0.01726948,0.0007845296,0.00038666578,0.00011486452,0.0016751237,0.6781172,0.29826126,0.00048564363,0.00087243324,0.0016325507],"study_design_scores_gemma":[0.001847897,0.00067359617,0.016457593,0.00065450004,0.0003104228,0.00005190509,0.0007431812,0.9489755,0.015239224,0.0072553325,0.005890854,0.0018999752],"about_ca_topic_score_codex":0.00009359576,"about_ca_topic_score_gemma":0.00010273416,"teacher_disagreement_score":0.28302202,"about_ca_system_score_codex":0.00010640754,"about_ca_system_score_gemma":0.0002248521,"threshold_uncertainty_score":0.9998125},"labels":[],"label_agreement":null},{"id":"W4319772631","doi":"10.31234/osf.io/cbvjr","title":"Word length and frequency effects on text reading are highly similar in 12 alphabetic languages","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"McMaster University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Word lists by frequency; Eye movement; Computer science; Linguistics; Word (group theory); Fixation (population genetics); Universality (dynamical systems); Reading (process); Word length; Natural language processing; Artificial intelligence; Population","score_opus":0.010041982260883231,"score_gpt":0.27073119904171383,"score_spread":0.2606892167808306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319772631","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98251617,0.0008080406,0.00028237407,0.0012063103,0.00042459046,0.0006131741,0.000034133063,0.0001359068,0.013979323],"genre_scores_gemma":[0.9901536,0.00064919057,0.004581217,0.0008744392,0.00028362093,0.00006432279,0.00036534984,0.00007558309,0.0029526416],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998546,0.0001151755,0.00032913097,0.0005107743,0.00017189722,0.00032702385],"domain_scores_gemma":[0.99896157,0.00011553535,0.00019314529,0.0006172055,0.000028305834,0.00008426624],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031643535,0.00035585117,0.00034327002,0.00017268141,0.000047716574,0.0000654508,0.00028764634,0.0005272151,0.00001339358],"category_scores_gemma":[0.00059515866,0.00032168848,0.00007968084,0.000070356116,0.000047613918,0.0000026913,0.0006488079,0.0006486717,0.00004440559],"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":[0.00044838025,0.0005612945,0.6149103,0.01915354,0.0015005551,0.0009346717,0.00407065,0.011959647,0.14622653,0.0034413221,0.07774588,0.11904723],"study_design_scores_gemma":[0.006936608,0.003052326,0.6925538,0.010357367,0.0004520861,0.00009878529,0.0025554013,0.014269993,0.22102469,0.0063690506,0.03467683,0.0076530483],"about_ca_topic_score_codex":0.00016207734,"about_ca_topic_score_gemma":0.0002683177,"teacher_disagreement_score":0.11139418,"about_ca_system_score_codex":0.00003395496,"about_ca_system_score_gemma":0.000042788848,"threshold_uncertainty_score":0.9999235},"labels":[],"label_agreement":null},{"id":"W4320913459","doi":"10.1101/2023.02.13.528380","title":"Orthogonal outlier detection and dimension estimation for improved MDS embedding of biological datasets","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Outlier; Dimensionality reduction; Multidimensional scaling; Nonlinear dimensionality reduction; Anomaly detection; Embedding; Pattern recognition (psychology); Computer science; Dimension (graph theory); Curse of dimensionality; Clustering high-dimensional data; Artificial intelligence; Robust statistics; Data point; Data mining; Mathematics; Machine learning; Cluster analysis; Combinatorics","score_opus":0.016510005902052913,"score_gpt":0.26680836788261675,"score_spread":0.2502983619805638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320913459","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88949275,0.00018420252,0.10757803,0.000050413186,0.0005571914,0.0007781931,0.001253554,0.00010438257,0.000001286284],"genre_scores_gemma":[0.9481749,0.00013932491,0.051214777,0.000053385967,0.00018081233,0.00011587167,0.00005519763,0.00006329601,0.0000024418664],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99845475,0.000071213806,0.0004915958,0.000576221,0.00012577871,0.00028041148],"domain_scores_gemma":[0.9985204,0.000053373424,0.0004821199,0.0006272281,0.00021441505,0.000102461854],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00065341714,0.00032314516,0.00033667314,0.0001286743,0.000116542804,0.000057324614,0.00021306289,0.00061236403,0.0000023998803],"category_scores_gemma":[0.0008750429,0.00031536003,0.00010073896,0.00011238941,0.00010316304,0.000010045069,0.0005965129,0.00028970905,0.0000035309897],"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":[0.000098067336,0.000033200075,0.0015290481,0.00039689508,0.00009430574,7.325e-7,0.0000039082042,0.001141881,0.99648243,0.000057766913,0.00012810004,0.000033676723],"study_design_scores_gemma":[0.0010899617,0.00058402796,0.04218252,0.00026162862,0.00015616631,1.0057709e-7,0.0000049033024,0.25506222,0.6956006,0.000010719858,0.0041502295,0.0008969034],"about_ca_topic_score_codex":0.0000109455095,"about_ca_topic_score_gemma":0.0000025777429,"teacher_disagreement_score":0.3008818,"about_ca_system_score_codex":0.000032163425,"about_ca_system_score_gemma":0.00011215387,"threshold_uncertainty_score":0.99992985},"labels":[],"label_agreement":null},{"id":"W4321440330","doi":"10.1007/978-3-031-23210-7_14","title":"A Study on the Application of Protein Language Models in the Analysis of Membrane Proteins","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Concordia University","funders":"","keywords":"Membrane protein; Computational biology; Computer science; Chemistry; Membrane; Biology; Biochemistry","score_opus":0.015208448937323274,"score_gpt":0.25751456536177586,"score_spread":0.2423061164244526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321440330","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6368817,0.009924872,0.28481475,0.00062866684,0.00028211687,0.027676191,0.00023734357,0.00005889484,0.039495472],"genre_scores_gemma":[0.9989789,0.00004710505,0.000023652708,0.000034407094,0.000082132494,0.0001945615,0.000110561734,0.000021346992,0.0005073352],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998866,0.00014194644,0.0004561907,0.00020685757,0.00021488359,0.000114098286],"domain_scores_gemma":[0.9988793,0.00014228895,0.00036569763,0.0005648164,0.000036502857,0.000011390296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089640875,0.00018406806,0.00039889175,0.00014448601,0.000026483702,0.000016898774,0.00025659997,0.0002835598,0.0000010754161],"category_scores_gemma":[0.00006533596,0.00010303884,0.000089838846,0.00020398542,0.000050686278,0.0000013855487,0.00006182847,0.00034395687,2.5808362e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006137764,0.000051183586,0.0005929225,0.00020471743,0.0004869967,0.000003169558,0.0025587813,0.9879738,0.0008630882,0.005162993,0.0000070810293,0.0020338711],"study_design_scores_gemma":[0.00053584337,0.0007594468,0.00089233555,0.0005749522,0.00042944858,0.00000414851,0.00065771025,0.9944277,0.0002615467,0.000701552,0.00036049463,0.00039485304],"about_ca_topic_score_codex":0.0002643099,"about_ca_topic_score_gemma":0.00110546,"teacher_disagreement_score":0.36209717,"about_ca_system_score_codex":0.0000078968915,"about_ca_system_score_gemma":0.000014264798,"threshold_uncertainty_score":0.4201802},"labels":[],"label_agreement":null},{"id":"W4321606216","doi":"10.1101/2023.02.22.529597","title":"Retrieved Sequence Augmentation for Protein Representation Learning","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Preprocessor; Inference; Protein sequencing; Sequence (biology); Artificial intelligence; Representation (politics); Machine learning; Peptide sequence; Biology","score_opus":0.02938578089126726,"score_gpt":0.2844136217408884,"score_spread":0.25502784084962116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321606216","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95012057,0.00012885645,0.046043612,0.0002892432,0.0007454177,0.002093755,0.00017464321,0.00039051895,0.000013397186],"genre_scores_gemma":[0.969746,0.000102838494,0.028269123,0.00010003013,0.0005859351,0.0008013171,0.000034798955,0.00017072966,0.0001892277],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99765563,0.00016675107,0.00058324955,0.0008301361,0.0003270314,0.00043719067],"domain_scores_gemma":[0.9977585,0.00003562603,0.00067675894,0.0008999798,0.0004966099,0.00013251076],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008366945,0.000409381,0.00032218784,0.00012142301,0.00022365869,0.0001912991,0.00043695758,0.00061150175,0.000009108755],"category_scores_gemma":[0.0019337572,0.0004781575,0.00017102978,0.0002875148,0.00008187535,0.000016240403,0.000461323,0.00059537886,0.000045955792],"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":[0.00008818954,0.000024558349,0.0043122354,0.0004906067,0.00011019923,0.0000034232926,0.000013576553,0.0024415078,0.99176913,0.000115441064,0.0006245909,0.0000065287727],"study_design_scores_gemma":[0.000794104,0.00024613363,0.012532518,0.00028717075,0.00007734856,2.0112845e-8,0.000012022101,0.008632763,0.9680826,0.000008835013,0.008549971,0.00077649875],"about_ca_topic_score_codex":0.00003675223,"about_ca_topic_score_gemma":0.0000025533304,"teacher_disagreement_score":0.023686528,"about_ca_system_score_codex":0.0001202647,"about_ca_system_score_gemma":0.00036513366,"threshold_uncertainty_score":0.999767},"labels":[],"label_agreement":null},{"id":"W4365444089","doi":"10.1093/bioinformatics/btad189","title":"Structure-aware protein self-supervised learning","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Pairwise comparison; Leverage (statistics); Graph; Supervised learning; Artificial neural network; Theoretical computer science","score_opus":0.007098345358430243,"score_gpt":0.2367498723285093,"score_spread":0.22965152697007907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365444089","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98174554,0.000038624716,0.0065393145,0.00020593584,0.00028491748,0.0007280287,0.00005375586,0.0007627664,0.009641139],"genre_scores_gemma":[0.94066006,0.00007629182,0.053314954,0.00041991874,0.0003403173,0.000040873347,0.001653968,0.00007954453,0.0034140805],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851847,0.00005019768,0.00047947018,0.00016581222,0.0003198718,0.0004661755],"domain_scores_gemma":[0.9990985,0.000016134263,0.00019594593,0.00045830855,0.000101935984,0.00012916885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000291348,0.0002581594,0.00018736615,0.00014204587,0.00023133722,0.000093732204,0.000363216,0.00024438585,0.00006765454],"category_scores_gemma":[0.00025188664,0.00023548723,0.00010155159,0.0003807853,0.00004984011,0.000019076419,0.0002968168,0.00030107016,0.000483977],"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":[0.00059821806,0.00045984832,0.073690936,0.009458076,0.0019841816,0.000073580624,0.031084895,0.06977375,0.40234354,0.0052341563,0.19609791,0.20920089],"study_design_scores_gemma":[0.0014390239,0.00064714847,0.002101151,0.00007915552,0.000039810373,0.000057219804,0.0016876708,0.7189814,0.033850852,0.00011583996,0.2400074,0.0009933145],"about_ca_topic_score_codex":0.000004326531,"about_ca_topic_score_gemma":0.0000046351106,"teacher_disagreement_score":0.64920765,"about_ca_system_score_codex":0.000022245054,"about_ca_system_score_gemma":0.00010013436,"threshold_uncertainty_score":0.960289},"labels":[],"label_agreement":null},{"id":"W4366215728","doi":"10.22541/au.168170992.27078535/v1","title":"Improving Protein Structure Prediction with Extended Sequence Similarity Searches and Deep-Learning-Based Refinement in CASP15","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics; RIKEN; DeepMind","keywords":"Similarity (geometry); Artificial intelligence; Sequence (biology); Computer science; Deep learning; Protein structure prediction; Machine learning; Pattern recognition (psychology); Protein structure; Biology; Genetics","score_opus":0.018620413753430366,"score_gpt":0.2679550432471968,"score_spread":0.24933462949376645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366215728","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97523403,0.000107131214,0.022257758,0.00044686152,0.000079246114,0.001318222,0.000103575985,0.00014491881,0.00030826667],"genre_scores_gemma":[0.9723578,0.00003271474,0.025410146,0.000085049076,0.000078951736,0.000120023724,0.0011984026,0.000051266874,0.0006656246],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822646,0.00016256652,0.00035651543,0.00061532884,0.00030417595,0.00033492313],"domain_scores_gemma":[0.99904996,0.000018647397,0.00023883006,0.00048186106,0.000117290205,0.00009339058],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004893943,0.00033896364,0.00024900422,0.00013154745,0.000096858384,0.00010368932,0.0002250123,0.00050252845,0.000021612328],"category_scores_gemma":[0.0003613627,0.00028412987,0.000043068023,0.00010743588,0.00012165063,0.0000053454273,0.00064630876,0.0011913838,0.0000012576465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011518386,0.00020138624,0.13217627,0.007955726,0.00036910138,0.000104602914,0.0010455521,0.46912614,0.35319018,0.0001375036,0.0003021419,0.03423953],"study_design_scores_gemma":[0.0022021546,0.0017656861,0.04980976,0.000645759,0.00007345866,0.000036278845,0.00045128848,0.879227,0.06252454,0.00033749122,0.0017376338,0.0011889621],"about_ca_topic_score_codex":0.00063743116,"about_ca_topic_score_gemma":0.0020481264,"teacher_disagreement_score":0.41010085,"about_ca_system_score_codex":0.000075962795,"about_ca_system_score_gemma":0.00027665307,"threshold_uncertainty_score":0.9999611},"labels":[],"label_agreement":null},{"id":"W4366992370","doi":"10.1093/bioinformatics/btad163","title":"Correction to: Continuous chromatin state feature annotation of the human epigenome","year":2023,"lang":"en","type":"erratum","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Natural Sciences and Engineering Research Council of Canada; Michael Smith Health Research BC; Compute Canada; Genome Canada","keywords":"Epigenome; Chromatin; Feature (linguistics); Annotation; Computer science; State (computer science); Computational biology; Artificial intelligence; Biology; Genetics; DNA methylation; Programming language; DNA; Gene","score_opus":0.006974353029127545,"score_gpt":0.2547317770100916,"score_spread":0.24775742398096404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366992370","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":[0.18392454,0.0016846718,0.022120647,0.002837797,0.34729877,0.013068909,0.005391295,0.0012301359,0.42244324],"genre_scores_gemma":[0.0097892,0.0003110219,0.0070311045,0.000985999,0.0018070968,0.00009043031,0.008662861,0.00023312499,0.9710892],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979796,0.00007339393,0.0008645983,0.00020273996,0.0005009128,0.0003787788],"domain_scores_gemma":[0.9975178,0.000031311978,0.0011454234,0.0009164793,0.00029264198,0.00009629273],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040456027,0.00040134613,0.00042972653,0.00017492511,0.00022728859,0.00008009225,0.0007004401,0.00051969825,0.000013912343],"category_scores_gemma":[0.00074026646,0.00031426153,0.00024468557,0.00042521197,0.00010651107,0.000011079152,0.00044397303,0.00074694806,0.00011859742],"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":[0.000010486678,0.000017344879,0.00022504535,0.00053160056,0.0000841945,4.1113077e-7,0.0012380619,0.00051731436,0.0018145258,0.000011521723,0.9930583,0.0024911538],"study_design_scores_gemma":[0.00046357035,0.00061644224,0.011809063,0.00076964725,0.00009934429,0.00002016629,0.00062497135,0.008210149,0.0048722886,0.00004414931,0.97170097,0.0007692227],"about_ca_topic_score_codex":0.000052590887,"about_ca_topic_score_gemma":0.00018144178,"teacher_disagreement_score":0.5486459,"about_ca_system_score_codex":0.00006513208,"about_ca_system_score_gemma":0.00028098753,"threshold_uncertainty_score":0.9999309},"labels":[],"label_agreement":null},{"id":"W4368357625","doi":"10.1093/nar/gkad330","title":"DEPICTER2: a comprehensive webserver for intrinsic disorder and disorder function prediction","year":2023,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Science Foundation","keywords":"Biology; Function (biology); Computational biology; Genetics","score_opus":0.031247026386707125,"score_gpt":0.3301333404549639,"score_spread":0.2988863140682568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4368357625","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99378836,0.00021958101,0.004013759,0.0005522811,0.00015330357,0.00057928235,0.000044922293,0.00006869127,0.0005798391],"genre_scores_gemma":[0.9953364,0.00049096026,0.00069478166,0.0001256649,0.00032569587,0.00016373885,0.0006053765,0.000045035118,0.0022123493],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.998713,0.000113898735,0.000197218,0.0002949851,0.0002812114,0.00039965607],"domain_scores_gemma":[0.9992176,0.00007976651,0.000038957354,0.00030755263,0.00026950007,0.00008661777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048423762,0.00012426845,0.000115861105,0.00016173026,0.00031846942,0.000063831445,0.00015216532,0.00018063911,0.000040823277],"category_scores_gemma":[0.000312536,0.00011534838,0.00005239855,0.00031485362,0.00015647487,0.000012434374,0.00031738819,0.00025610658,0.000057632038],"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":[0.0022294852,0.00029817494,0.5026522,0.0015769243,0.00048395438,0.0000053847575,0.001451551,0.0021868856,0.08961876,0.0023067326,0.10523578,0.29195413],"study_design_scores_gemma":[0.001626228,0.0013106668,0.28188834,0.000023417411,0.00001562188,0.0000064960036,0.0008373149,0.02678448,0.0005186806,0.00034348795,0.68644285,0.0002024433],"about_ca_topic_score_codex":0.000031468615,"about_ca_topic_score_gemma":0.000038065653,"teacher_disagreement_score":0.58120704,"about_ca_system_score_codex":0.0000167594,"about_ca_system_score_gemma":0.000040859803,"threshold_uncertainty_score":0.47037706},"labels":[],"label_agreement":null},{"id":"W4375866628","doi":"10.18280/rces.100101","title":"Classification of Breast Cancer Using Ensemble Empirical Mode Decomposition and Autoencoder-Based Methods","year":2023,"lang":"en","type":"article","venue":"Review of Computer Engineering Studies","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Autoencoder; Breast cancer; Hilbert–Huang transform; Computer science; Artificial intelligence; Cancer; Pattern recognition (psychology); Decomposition; Mathematics; Medicine; Statistics; Internal medicine; Deep learning; Biology","score_opus":0.04537139729789715,"score_gpt":0.46364904162281956,"score_spread":0.4182776443249224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375866628","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":[0.15156552,0.025606064,0.8221781,0.00032669373,0.00012368363,0.00014983877,0.000012943307,0.000029841469,0.0000073082347],"genre_scores_gemma":[0.2831548,0.0501507,0.6662464,0.00020466464,0.00013555211,0.00002529638,0.000051881,0.00002567376,0.0000050642575],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944156,0.000044188175,0.00026039925,0.00009959554,0.00007099007,0.000083251216],"domain_scores_gemma":[0.9995848,0.000044847784,0.00011514798,0.00012943511,0.00010797937,0.000017821934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002540343,0.00009121056,0.00024572236,0.000048561236,0.000020014897,0.0000029155353,0.000057224486,0.000032543623,5.8420676e-7],"category_scores_gemma":[0.000040374063,0.000079976184,0.000051317864,0.00013091128,0.00002719491,0.000003253108,0.00007248932,0.0000413953,2.1600668e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001872046,0.000052219504,0.007041627,0.04737471,0.0005529474,8.0767137e-7,0.00031418947,0.6165342,0.25077492,0.00018029894,0.0021439556,0.07501144],"study_design_scores_gemma":[0.00009555302,0.000038447546,0.014134709,0.0024062109,0.000047690522,0.0000066622974,0.000004339977,0.978746,0.0037031241,0.0000045362012,0.0007251278,0.00008762379],"about_ca_topic_score_codex":0.000002174381,"about_ca_topic_score_gemma":3.150783e-7,"teacher_disagreement_score":0.36221182,"about_ca_system_score_codex":0.000011324291,"about_ca_system_score_gemma":0.000020754716,"threshold_uncertainty_score":0.3261334},"labels":[],"label_agreement":null},{"id":"W4378516289","doi":"10.3390/ijms24108723","title":"No Substrate Left behind—Mining of Shotgun Proteomics Datasets Rescues Evidence of Proteolysis by SARS-CoV-2 3CLpro Main Protease","year":2023,"lang":"en","type":"article","venue":"International Journal of Molecular Sciences","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research; Canada Research Chairs; Michael Smith Health Research BC","keywords":"Shotgun proteomics; Proteases; Proteomics; Protease; Proteolysis; Computational biology; Biology; Proteome; Function (biology); Shotgun; Bioinformatics; Cell biology; Biochemistry; Enzyme","score_opus":0.02537285628742965,"score_gpt":0.3378504284126606,"score_spread":0.312477572125231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378516289","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99375474,0.000255247,0.004887161,0.00042931281,0.00016871304,0.0002412998,0.00010870301,0.0000052793803,0.00014951466],"genre_scores_gemma":[0.97253776,0.00016104727,0.027000422,0.00011765836,0.000068237496,0.000006840666,0.00005866794,0.000010911882,0.0000384756],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99778837,0.000111121204,0.00073519954,0.00019931588,0.0009746855,0.00019128658],"domain_scores_gemma":[0.9982007,0.00003651969,0.0009785177,0.00021574582,0.0005188372,0.00004963547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017638651,0.0001423011,0.00020942683,0.00023847175,0.000052530686,0.000065153064,0.0012342263,0.00008165063,0.0000062961412],"category_scores_gemma":[0.0013270901,0.00012001113,0.00014054241,0.00015938492,0.0003411211,0.000058910922,0.00024938685,0.0001531584,0.000003905896],"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":[0.00014145878,0.000047230544,0.002309043,0.000049456532,0.000099099154,0.000026640533,0.00018105377,0.0017804565,0.99398965,0.000027432929,0.0008866719,0.000461822],"study_design_scores_gemma":[0.00033095767,0.0006652278,0.0003995039,0.00035145826,0.000019317165,0.000094280455,0.00010642916,0.0014561026,0.99573225,0.00011829373,0.00060007756,0.00012607669],"about_ca_topic_score_codex":0.000039520357,"about_ca_topic_score_gemma":0.000012764538,"teacher_disagreement_score":0.022113262,"about_ca_system_score_codex":0.00001840632,"about_ca_system_score_gemma":0.00030257425,"threshold_uncertainty_score":0.4893912},"labels":[],"label_agreement":null},{"id":"W4379518401","doi":"10.21428/594757db.033df5af","title":"An Explainable Deep Few-shot Network for Protein Family Classification","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"National Research Council Canada; Concordia University","keywords":"Shot (pellet); Artificial intelligence; Computer science; Pattern recognition (psychology); Chemistry","score_opus":0.027275231901544905,"score_gpt":0.3005732698457717,"score_spread":0.2732980379442268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379518401","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7536969,0.00007544367,0.22209696,0.00046266703,0.00022082853,0.0013611857,0.000014321125,0.00026271,0.021808948],"genre_scores_gemma":[0.94820184,0.000022180688,0.0422574,0.00050069805,0.000474743,0.00036448747,0.0015255682,0.00003746459,0.0066156113],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99918103,0.000034645494,0.00018905352,0.00020463092,0.00009112311,0.00029953037],"domain_scores_gemma":[0.99940455,0.000008553728,0.00007175982,0.00037444558,0.00007551847,0.000065156826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036736034,0.00011047729,0.00008537992,0.00003096076,0.00014943993,0.000043101198,0.00019507113,0.00013292683,0.00001824719],"category_scores_gemma":[0.00009232938,0.00010149437,0.00004924587,0.0001474337,0.000025334723,0.0000062329036,0.00004668011,0.0000615603,0.00005710003],"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":[0.00015264844,0.00006474716,0.0029852698,0.00014092626,0.000050563965,7.191248e-7,0.00014435306,0.013129797,0.89889014,0.00996702,0.06224059,0.0122332005],"study_design_scores_gemma":[0.0009660717,0.0011058823,0.013589092,0.000019474151,0.000019442754,0.0000043289165,0.0009996134,0.4621916,0.04238185,0.0012502618,0.47689924,0.00057313876],"about_ca_topic_score_codex":0.000008876165,"about_ca_topic_score_gemma":0.000020364669,"teacher_disagreement_score":0.8565083,"about_ca_system_score_codex":0.000009376803,"about_ca_system_score_gemma":0.000034351764,"threshold_uncertainty_score":0.41388202},"labels":[],"label_agreement":null},{"id":"W4381234500","doi":"10.23880/aii-16000136","title":"Are Peptides Truly Less Important than Proteins, or are Peptides and Proteins Mutually Inclusive of Each other?","year":2021,"lang":"en","type":"article","venue":"Annals of Immunology & Immunotherapy","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Chemistry; Computational biology; Biochemistry; Biology","score_opus":0.025035832991701718,"score_gpt":0.3034184239996953,"score_spread":0.2783825910079936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381234500","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97836626,0.01904423,0.0002538908,0.0012047644,0.00007955355,0.00060224085,0.00011639666,0.00002606089,0.00030659974],"genre_scores_gemma":[0.9866677,0.0072695496,0.0036501687,0.0011051091,0.00007662704,0.00008965991,0.00008964409,0.00007608112,0.0009754446],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99768364,0.0002847974,0.00094608235,0.00042102832,0.00022516758,0.00043929793],"domain_scores_gemma":[0.9967347,0.00005993974,0.0016238625,0.0009089026,0.00062113756,0.000051489347],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000516518,0.0003893529,0.00071419985,0.0001260246,0.0001745402,0.000030614297,0.0004879846,0.0004132244,0.00006989247],"category_scores_gemma":[0.000498897,0.000328154,0.00023097632,0.00020047114,0.0005806553,0.000022689934,0.00032511473,0.00032515175,0.0000032826629],"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":[0.0014830307,0.00034314956,0.04013598,0.00024151431,0.0011633353,0.000025239298,0.0012235714,0.0000137146,0.94744956,0.00019961112,0.00027003113,0.0074512297],"study_design_scores_gemma":[0.0016445322,0.0015705785,0.07578703,0.0003575542,0.000024459621,0.00013942398,0.0034271502,0.000018552788,0.90277684,0.00022617118,0.01359162,0.0004360671],"about_ca_topic_score_codex":0.00018415033,"about_ca_topic_score_gemma":0.00027380968,"teacher_disagreement_score":0.044672735,"about_ca_system_score_codex":0.00001121488,"about_ca_system_score_gemma":0.00027887712,"threshold_uncertainty_score":0.99991703},"labels":[],"label_agreement":null},{"id":"W4382501959","doi":"10.1002/pmic.202300011","title":"Leveraging transformers‐based language models in proteome bioinformatics","year":2023,"lang":"en","type":"review","venue":"PROTEOMICS","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Ministry of Science and Technology, Taiwan","keywords":"Computer science; Proteome; Proteomics; Artificial intelligence; Machine learning; Transformer; Bioinformatics; Computational biology; Data science; Biology; Engineering","score_opus":0.04552720635235382,"score_gpt":0.3288887288577784,"score_spread":0.2833615225054246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382501959","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":[0.00024033837,0.9100832,0.07891382,0.000043319953,0.00031850033,0.006528598,0.00020237121,0.00019717103,0.0034726968],"genre_scores_gemma":[0.000019980747,0.9553931,0.041183632,0.00010468295,0.00020681541,0.0008102948,0.0015701264,0.00018756415,0.0005238038],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99753255,0.00011070417,0.0011216007,0.0003773493,0.0002747674,0.0005830597],"domain_scores_gemma":[0.9987628,0.000033982255,0.000468051,0.0005854087,0.000042495438,0.00010726994],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00071585894,0.00058767846,0.0010288742,0.0004090977,0.00007430635,0.000082597675,0.0005821755,0.0006745518,0.000008811672],"category_scores_gemma":[0.0001576185,0.00052945083,0.00041856905,0.00045874552,0.00006572377,0.0000150566,0.00017014272,0.00077103596,0.000111074674],"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":[0.000045735185,0.00011453994,0.000012615211,0.1007651,0.000297704,0.000031028583,0.001511043,0.0070942105,0.000097991215,0.00008390979,0.000484947,0.88946116],"study_design_scores_gemma":[0.0016063903,0.0003227558,0.0000015044218,0.015381487,0.0003020005,0.00008006599,0.00039363836,0.17858776,0.00055540947,0.0001220485,0.8004369,0.0022100245],"about_ca_topic_score_codex":0.000028043467,"about_ca_topic_score_gemma":0.00001945577,"teacher_disagreement_score":0.88725114,"about_ca_system_score_codex":0.000108808585,"about_ca_system_score_gemma":0.00057118526,"threshold_uncertainty_score":0.9997157},"labels":[],"label_agreement":null},{"id":"W4384133699","doi":"10.1101/2023.07.11.548644","title":"Exploiting protein language models for the precise classification of ion channels and ion transporters","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Task (project management); Computer science; Parallels; Artificial intelligence; Machine learning; Ion channel; Engineering; Biology; Systems engineering; Biochemistry","score_opus":0.024099935119933358,"score_gpt":0.24573618257733504,"score_spread":0.22163624745740168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384133699","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9142951,0.00055325433,0.08262241,0.00021717775,0.00042865478,0.0015887284,0.00020557332,0.00008526552,0.000003881794],"genre_scores_gemma":[0.9937587,0.00021055607,0.004903887,0.000027795973,0.0003990048,0.00059007877,0.000007634436,0.000086038235,0.000016305627],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985904,0.000059547543,0.00045118993,0.00045253985,0.00018934016,0.000256996],"domain_scores_gemma":[0.99846554,0.000042194115,0.00047678308,0.000734663,0.00021004581,0.00007077897],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007226283,0.00028027012,0.00025693106,0.00009153766,0.000112913905,0.000063981126,0.00033404885,0.00037524177,0.0000015054221],"category_scores_gemma":[0.0002077008,0.00024728465,0.00011409931,0.00011388906,0.000091779686,0.000012328019,0.00017110814,0.00027486,0.0000014315804],"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":[0.000058059413,0.000025247473,0.0002683941,0.0008225438,0.0000893622,7.0020826e-7,0.00009486346,0.002733528,0.9955603,0.00026204917,0.00006578195,0.00001920111],"study_design_scores_gemma":[0.0005728443,0.00013573372,0.0071299807,0.0005145307,0.000113694645,1.858413e-8,0.00007951384,0.084658615,0.9055623,0.000010679807,0.00072867697,0.0004933992],"about_ca_topic_score_codex":0.000025900714,"about_ca_topic_score_gemma":0.0000029284834,"teacher_disagreement_score":0.08999796,"about_ca_system_score_codex":0.000025676914,"about_ca_system_score_gemma":0.00012097435,"threshold_uncertainty_score":0.9999979},"labels":[],"label_agreement":null},{"id":"W4385255511","doi":"10.1007/978-3-031-36886-8_7","title":"Incorporating Natural Language-Based and Sequence-Based Features to Predict Protein Sumoylation Sites","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"SUMO protein; Computational biology; Biology; Phosphorylation; Proteomics; Cell biology; Bioinformatics; Genetics; Gene; Ubiquitin","score_opus":0.011104906238596762,"score_gpt":0.24437904694310866,"score_spread":0.2332741407045119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385255511","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3897065,0.10867244,0.44653168,0.0032633343,0.005488452,0.020220563,0.0009119453,0.0012099392,0.02399514],"genre_scores_gemma":[0.99299884,0.000023594299,0.0014120886,0.00030059845,0.0007136701,0.000050505256,0.0013179489,0.000072434734,0.003110294],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871504,0.000067947716,0.00037258296,0.00040210361,0.00019823445,0.00024406031],"domain_scores_gemma":[0.99917823,0.00011888718,0.00026646903,0.00028721607,0.00006605068,0.00008314818],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003614777,0.00036369922,0.00034898042,0.00014264348,0.00009503011,0.00013635228,0.00012577094,0.00065335335,0.0000020682562],"category_scores_gemma":[0.0002503512,0.00030928466,0.000055393455,0.00007273461,0.000073097624,0.0000043134,0.00008574281,0.000568377,0.0000014344073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024876636,0.000012555875,0.007813052,0.0015044813,0.000114422255,0.000054391166,0.00027618022,0.9565449,0.013188725,0.0007920856,0.00052683527,0.018923631],"study_design_scores_gemma":[0.00091652246,0.0006070649,0.0008662344,0.0025898202,0.00005302199,0.00003537169,0.000020648014,0.98923856,0.0009152923,0.0002660667,0.0034336215,0.0010577745],"about_ca_topic_score_codex":0.00008142334,"about_ca_topic_score_gemma":0.000634115,"teacher_disagreement_score":0.60329235,"about_ca_system_score_codex":0.000028920475,"about_ca_system_score_gemma":0.00006218883,"threshold_uncertainty_score":0.9999359},"labels":[],"label_agreement":null},{"id":"W4385294814","doi":"10.1515/jib-2022-0055","title":"Enhanced identification of membrane transport proteins: a hybrid approach combining ProtBERT-BFD and convolutional neural networks","year":2023,"lang":"en","type":"article","venue":"Berichte aus der medizinischen Informatik und Bioinformatik/Journal of integrative bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Convolutional neural network; Transporter; Computer science; Classifier (UML); Artificial intelligence; Deep learning; Encoder; Transmembrane protein; Computational biology; Machine learning; Chemistry; Biochemistry; Biology; Gene","score_opus":0.009999736582629051,"score_gpt":0.25892556611506856,"score_spread":0.24892582953243952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385294814","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37826484,0.00084502995,0.6070604,0.00023156108,0.00093071104,0.0028126745,0.00029811717,0.00017560377,0.009381081],"genre_scores_gemma":[0.94974005,0.00073642854,0.04709371,0.00039878036,0.00020045163,0.00010396783,0.0014546483,0.00005754719,0.0002144201],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9929961,0.00011643104,0.0046992106,0.00021412391,0.0012184675,0.0007556847],"domain_scores_gemma":[0.9926847,0.00015642848,0.004625952,0.0005854574,0.001573052,0.00037436094],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0023280717,0.0007643758,0.0010883453,0.0008143023,0.00027374673,0.00016200953,0.0009212572,0.0003925591,0.000018880126],"category_scores_gemma":[0.0009317479,0.00056694687,0.0003835441,0.0011311421,0.0006989957,0.0007031663,0.00030046323,0.0009081983,0.000022254433],"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":[0.010821632,0.0025042132,0.013095973,0.027791025,0.018683536,0.00007686293,0.30044997,0.27555797,0.09495695,0.016931638,0.03291365,0.20621656],"study_design_scores_gemma":[0.0042072427,0.002068687,0.002447597,0.0004897216,0.00038543635,0.0008023232,0.0140043385,0.9155663,0.052263148,0.000064442786,0.006596846,0.0011038948],"about_ca_topic_score_codex":0.0000086671525,"about_ca_topic_score_gemma":0.0000034919017,"teacher_disagreement_score":0.64000833,"about_ca_system_score_codex":0.00006780926,"about_ca_system_score_gemma":0.00046784835,"threshold_uncertainty_score":0.9996782},"labels":[],"label_agreement":null},{"id":"W4385304433","doi":"10.21203/rs.3.rs-3161256/v1","title":"GeneAI 3.0: Powerful, Novel, Generalized Hybrid and Ensemble Deep Learning Frameworks for miRNA Classification of species-specific Stationary Patterns from Nucleotides","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Computer science; Convolutional neural network; Entropy (arrow of time); Binary classification; Machine learning; Binary number; In silico; Mathematics; Support vector machine; Biology; Gene; Genetics","score_opus":0.06757190838014623,"score_gpt":0.36593750714686485,"score_spread":0.29836559876671864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385304433","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8269332,0.0013886605,0.16870454,0.00036464698,0.00023325102,0.0010127283,0.0011131058,0.000045644345,0.00020424191],"genre_scores_gemma":[0.9514025,0.005055188,0.028944558,0.0000334895,0.000604796,0.00016095335,0.012746865,0.0001239062,0.0009277731],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9970795,0.0003838147,0.00062097755,0.00073898,0.0006747526,0.0005019546],"domain_scores_gemma":[0.9973345,0.00056732644,0.00039259912,0.0007794617,0.00078253524,0.00014359583],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013992627,0.00031068252,0.00039043903,0.00026841825,0.0002288172,0.00017275188,0.0004866778,0.00065014756,0.00009221114],"category_scores_gemma":[0.001325575,0.00032549314,0.00018098707,0.00011914559,0.00019984215,0.000009580848,0.0009985787,0.00154513,0.000020021535],"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":[0.0018114777,0.0004866936,0.08622601,0.005166963,0.0010217509,0.000017520582,0.0025751677,0.049597513,0.803963,0.0020958881,0.023047121,0.023990896],"study_design_scores_gemma":[0.0032169386,0.0015463748,0.5313541,0.0017993723,0.00009419899,0.0000109381335,0.0032867673,0.2793173,0.058565147,0.004197226,0.114909746,0.0017018628],"about_ca_topic_score_codex":0.00013499804,"about_ca_topic_score_gemma":0.000043908018,"teacher_disagreement_score":0.74539787,"about_ca_system_score_codex":0.00007249,"about_ca_system_score_gemma":0.00014857612,"threshold_uncertainty_score":0.9999197},"labels":[],"label_agreement":null},{"id":"W4385373960","doi":"10.1093/bib/bbad289","title":"Artificial intelligence-aided protein engineering: from topological data analysis to deep protein language models","year":2023,"lang":"en","type":"review","venue":"Briefings in Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of General Medical Sciences; Bristol-Myers Squibb Canada; Michigan State University Foundation; Nuclear Safety and Security Commission; Bristol-Myers Squibb; National Aeronautics and Space Administration; National Institutes of Health; National Science Foundation; Michigan Economic Development Corporation; National Institute of Allergy and Infectious Diseases; Pfizer","keywords":"Computer science; Artificial intelligence; Topological data analysis; Protein engineering; Natural language processing; Computational biology; Biology; Algorithm","score_opus":0.08793799256485617,"score_gpt":0.3524052727944185,"score_spread":0.26446728022956234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385373960","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011155958,0.4356805,0.5528654,0.0002650018,0.00027161406,0.006450762,0.002124841,0.00044198975,0.0007843237],"genre_scores_gemma":[0.0002772762,0.49816802,0.47043002,0.0006328632,0.00074190355,0.0009189324,0.027922312,0.0003110139,0.0005976589],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99576885,0.00010477001,0.0022295292,0.000690665,0.0004946404,0.0007115305],"domain_scores_gemma":[0.9967106,0.00009972414,0.00069262634,0.0022034233,0.00006822196,0.0002253884],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009526258,0.000746408,0.0016390925,0.00074067194,0.00008151499,0.00022549313,0.0021486173,0.00090919953,0.000043776145],"category_scores_gemma":[0.0016154248,0.0006641797,0.00042231663,0.0017533052,0.00008070757,0.000040216266,0.0020779546,0.0007920215,0.0002487048],"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":[0.000051332085,0.00017360847,0.0000033639542,0.010801473,0.002423106,0.00004831041,0.0017877946,0.021527473,0.0000740876,0.0025048207,0.0007155444,0.9598891],"study_design_scores_gemma":[0.00013248595,0.00023517868,0.0000029074733,0.0041139047,0.0013447742,0.000017236322,0.00039276594,0.64423084,0.00024146304,0.0006495393,0.34665117,0.0019877478],"about_ca_topic_score_codex":0.0003676045,"about_ca_topic_score_gemma":0.00029731935,"teacher_disagreement_score":0.95790136,"about_ca_system_score_codex":0.00009004574,"about_ca_system_score_gemma":0.00021425159,"threshold_uncertainty_score":0.9995809},"labels":[],"label_agreement":null},{"id":"W4385573184","doi":"10.18653/v1/2022.sustainlp-1.2","title":"Efficient Two-Stage Progressive Quantization of BERT","year":2022,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Zhàng; Computer science; Simple (philosophy); Quantization (signal processing); Chen; Stage (stratigraphy); Artificial intelligence; Art history; Speech recognition; Art; History; Algorithm; Philosophy; China; Archaeology; Epistemology; Geology","score_opus":0.005993728044813621,"score_gpt":0.27126861294531157,"score_spread":0.26527488490049794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385573184","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9779539,0.000104102975,0.00806629,0.00007396924,0.00009084166,0.00017466386,0.000017323364,0.000014112004,0.013504808],"genre_scores_gemma":[0.994307,0.0000015602162,0.0033807822,0.00013845012,0.00002132133,0.000017778262,0.00014977936,0.000008232388,0.001975143],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946374,0.000043564218,0.00015486259,0.00009635487,0.00014826789,0.00009322813],"domain_scores_gemma":[0.99963176,0.000005309379,0.0001179511,0.0001834487,0.00004112711,0.000020411428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015402753,0.00005791235,0.000061337174,0.000028999377,0.00007556692,0.000004893498,0.00011960968,0.000019620376,0.00034396525],"category_scores_gemma":[0.00004919596,0.00005333575,0.000036343867,0.00008185969,0.000029822275,4.4276698e-7,0.00020202623,0.00006099692,0.000003409934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016544177,0.00049255404,0.02173183,0.00011737081,0.000086241096,0.000003845834,0.00066265336,0.7246317,0.23265332,0.013028087,0.0037263012,0.002700648],"study_design_scores_gemma":[0.0021914884,0.0021431067,0.0031607433,0.000012522126,0.00003370663,0.000052285173,0.0014406919,0.546801,0.29755276,0.000034737575,0.14602382,0.0005531309],"about_ca_topic_score_codex":0.000012688164,"about_ca_topic_score_gemma":0.0000020671328,"teacher_disagreement_score":0.17783073,"about_ca_system_score_codex":0.0000074909026,"about_ca_system_score_gemma":0.00003260072,"threshold_uncertainty_score":0.37661782},"labels":[],"label_agreement":null},{"id":"W4386305688","doi":"10.1093/bib/bbad319","title":"Sequence-based prediction model of protein crystallization propensity using machine learning and two-level feature selection","year":2023,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Science and Technology Council","keywords":"Feature selection; Pipeline (software); Protein crystallization; Computer science; Support vector machine; Hyperparameter; Dimensionality reduction; Artificial intelligence; Machine learning; Sequence (biology); Selection (genetic algorithm); Linear discriminant analysis; Feature (linguistics); Data mining; Crystallization; Engineering; Chemistry","score_opus":0.03691560672882826,"score_gpt":0.2716449149048197,"score_spread":0.2347293081759914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386305688","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8651489,0.000026349002,0.13378683,0.00011720991,0.000026585414,0.0005256039,0.0000650793,0.000078113706,0.00022534066],"genre_scores_gemma":[0.8175345,0.000055150045,0.18115675,0.00015919968,0.000032763823,0.000017439017,0.00070963486,0.000032555447,0.00030202293],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988533,0.000048957296,0.00045705086,0.00015770097,0.00023982862,0.00024312729],"domain_scores_gemma":[0.99929863,0.000012390819,0.00035309032,0.00013729474,0.00014925847,0.00004932182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053056644,0.00018328035,0.00019149898,0.00021100792,0.00014038628,0.000043713866,0.000098495264,0.00019770607,0.000002101555],"category_scores_gemma":[0.00036433077,0.00018293054,0.00004035017,0.000434508,0.000085522515,0.000038734477,0.00011625204,0.00026706271,0.0000013563074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010019748,0.000029784824,0.03027627,0.00058928685,0.000022770097,5.921248e-7,0.000537308,0.5871272,0.37892112,0.00013740236,0.00007744306,0.0021806166],"study_design_scores_gemma":[0.00069846195,0.00013591809,0.0009500949,0.00012818578,0.000012557291,0.000014353459,0.000044607794,0.9645515,0.03285777,0.00004445423,0.0003898332,0.00017227829],"about_ca_topic_score_codex":0.00010882228,"about_ca_topic_score_gemma":0.00006015053,"teacher_disagreement_score":0.37742427,"about_ca_system_score_codex":0.000044236833,"about_ca_system_score_gemma":0.00014009928,"threshold_uncertainty_score":0.74596906},"labels":[],"label_agreement":null},{"id":"W4386348348","doi":"10.1101/2023.08.30.555602","title":"Scoring alignments by embedding vector similarity","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Leverage (statistics); Similarity (geometry); Embedding; Computer science; Cosine similarity; Artificial intelligence; Context (archaeology); Sequence alignment; Sequence (biology); Source code; Machine learning; Pattern recognition (psychology); Data mining; Natural language processing; Peptide sequence; Biology","score_opus":0.01342372707161297,"score_gpt":0.25297865010481424,"score_spread":0.23955492303320128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386348348","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98380446,0.0008003708,0.0104026655,0.0002666456,0.0025720852,0.0008255933,0.000704722,0.00057440234,0.000049051403],"genre_scores_gemma":[0.9895336,0.00038969883,0.008426518,0.0003417152,0.0007936977,0.00015180526,0.000012583322,0.00026011548,0.00009028896],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9968572,0.00014211095,0.0006680328,0.0010657097,0.0004989909,0.0007679458],"domain_scores_gemma":[0.9972447,0.000034389835,0.00052620936,0.0016539545,0.00023759724,0.00030314407],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007740302,0.000686643,0.0005054987,0.0001546977,0.00023126772,0.00025864955,0.00090741,0.0009002511,0.000027562968],"category_scores_gemma":[0.0006401696,0.000793331,0.00022164558,0.00025006337,0.00010912168,0.000013713973,0.0016514667,0.0009190397,0.00014808476],"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":[0.000027605294,0.000081538274,0.014495777,0.0005369601,0.00030389326,0.000016426473,0.000009166617,0.0009935049,0.97115827,0.000056389657,0.012318355,0.0000020898963],"study_design_scores_gemma":[0.000876857,0.0001744605,0.02711382,0.0005834253,0.00017363495,4.6358853e-8,0.000006827489,0.0065964246,0.9051462,0.0000028632937,0.057268374,0.0020570671],"about_ca_topic_score_codex":0.000050144798,"about_ca_topic_score_gemma":0.0000021240633,"teacher_disagreement_score":0.06601209,"about_ca_system_score_codex":0.0001568162,"about_ca_system_score_gemma":0.0003023935,"threshold_uncertainty_score":0.99945176},"labels":[],"label_agreement":null},{"id":"W4386809570","doi":"10.18280/ria.370411","title":"Anomaly Detection in Human Disease: A Hybrid Approach Using GWO-SVM for Gene Selection","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Selection (genetic algorithm); Support vector machine; Anomaly detection; Gene selection; Vector (molecular biology); Gene; Computer science; Biology; Artificial intelligence; Computational biology; Pattern recognition (psychology); Genetics; Gene expression","score_opus":0.03286057273742221,"score_gpt":0.301396503875041,"score_spread":0.2685359311376188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386809570","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59861124,0.000054231823,0.4005098,0.000020371499,0.00008644503,0.00031536832,0.000008787602,0.000040528696,0.00035320877],"genre_scores_gemma":[0.9950294,0.000026296764,0.0036045336,0.00003331518,0.00018521404,0.000074535965,0.0002182189,0.000028762586,0.00079974363],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889964,0.000052001946,0.00033720853,0.00032090393,0.0000872373,0.00030301925],"domain_scores_gemma":[0.99948096,0.00002053086,0.000104072766,0.00025977733,0.00006677798,0.000067866196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046958085,0.00013937944,0.00012313412,0.0001542098,0.00018978692,0.000038022852,0.00015437347,0.00007711208,0.0000105624185],"category_scores_gemma":[0.00020082656,0.00015551577,0.00009245008,0.00038140462,0.000041451953,0.0000095725945,0.000068019675,0.00011276416,0.000020383031],"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":[0.000062585095,0.000069053014,0.0021784066,0.00015105176,0.000014486052,0.0000017370833,0.00013250453,0.3946795,0.59747344,0.00007144831,0.00017363786,0.004992166],"study_design_scores_gemma":[0.000044540953,0.00008111778,0.00031727558,0.000013232235,0.00000852919,0.000012181698,0.0000933199,0.65687954,0.34063277,0.000094760886,0.0016910076,0.0001317008],"about_ca_topic_score_codex":0.000033281376,"about_ca_topic_score_gemma":0.000016883747,"teacher_disagreement_score":0.39690527,"about_ca_system_score_codex":0.000041356747,"about_ca_system_score_gemma":0.000035235185,"threshold_uncertainty_score":0.6341749},"labels":[],"label_agreement":null},{"id":"W4387951177","doi":"10.1109/ccece58730.2023.10288894","title":"STACKION: Ion Channel-Modulating Peptides Identification Using Stacking-Based Ensemble Machine Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Peptide; Feature extraction; Computer science; Pseudo amino acid composition; Chemistry; Machine learning; Computational biology; Dipeptide; Biochemistry; Biology","score_opus":0.023516742192215924,"score_gpt":0.2886698406946826,"score_spread":0.26515309850246666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387951177","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87946916,0.00006263208,0.1185518,0.00014203863,0.0002144371,0.00019981034,0.000007642946,0.00022221103,0.0011302669],"genre_scores_gemma":[0.99176353,0.000022507318,0.0051632114,0.00012524912,0.00020211858,0.000009460596,0.00090972905,0.000045887857,0.0017582905],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985987,0.000105933665,0.0003890735,0.00031079462,0.00025238757,0.00034309865],"domain_scores_gemma":[0.99920064,0.00003322484,0.00023681225,0.00033690492,0.000121547586,0.000070853515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068607356,0.00019358813,0.00014452249,0.00015218943,0.00032400852,0.000099399535,0.00017204402,0.0001395965,0.000035176883],"category_scores_gemma":[0.000395672,0.00019286806,0.00008834565,0.00033614293,0.000038772276,0.000012807724,0.00013949288,0.00019664278,0.00008331846],"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":[0.000028114342,0.000019380117,0.009809525,0.000093164905,0.000025740359,0.0000022693146,0.0001430052,0.43998185,0.5472383,0.000052312676,0.00032256616,0.0022837662],"study_design_scores_gemma":[0.00032146665,0.000106415784,0.002037088,0.000030109624,0.000012777866,0.000006624119,0.00015992916,0.84589124,0.1482406,0.000044138655,0.0029065304,0.00024308328],"about_ca_topic_score_codex":0.00005986445,"about_ca_topic_score_gemma":0.000032401498,"teacher_disagreement_score":0.40590942,"about_ca_system_score_codex":0.000029023991,"about_ca_system_score_gemma":0.000052221298,"threshold_uncertainty_score":0.7864931},"labels":[],"label_agreement":null},{"id":"W4388023124","doi":"10.18280/ts.400548","title":"Experimental Investigations to Detection of Liver Cancer Using ResUNet","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cancer; Cancer detection; Computer science; Artificial intelligence; Medicine; Internal medicine","score_opus":0.02975683163637803,"score_gpt":0.3037616246967139,"score_spread":0.27400479306033587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388023124","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9941541,0.000056490782,0.0053051906,0.000052457744,0.000077246135,0.0001566218,0.000020100919,0.000019349227,0.0001584366],"genre_scores_gemma":[0.9975291,0.0000073276346,0.0019884743,0.00016713426,0.000117151605,0.000025783736,0.00004805478,0.0000104496385,0.00010650818],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994448,0.00002656336,0.00017362012,0.00010900622,0.00012464519,0.0001213824],"domain_scores_gemma":[0.9997473,0.0000057507277,0.00006186614,0.00009688941,0.000035024652,0.000053183503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011671329,0.00007409229,0.00006402067,0.00006638305,0.000060986244,0.00000931063,0.00007761357,0.000042885476,0.00008148783],"category_scores_gemma":[0.000020474616,0.000075608696,0.000034508474,0.00015245324,0.000032910008,0.0000038903486,0.00006132595,0.00003862129,0.000013659968],"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":[0.000023861505,0.000016918173,0.0009294721,0.000016805338,0.000020861979,5.0413695e-7,0.00040480588,0.014965963,0.98215187,0.000024253626,0.0006593318,0.0007853664],"study_design_scores_gemma":[0.00023277664,0.0002028762,0.005756291,0.000017792614,0.000010700447,0.0000025506506,0.00012358617,0.032719124,0.95529896,0.0000047007943,0.0055309664,0.00009969031],"about_ca_topic_score_codex":0.000118434655,"about_ca_topic_score_gemma":0.00003225008,"teacher_disagreement_score":0.026852911,"about_ca_system_score_codex":0.000019748406,"about_ca_system_score_gemma":0.0000315942,"threshold_uncertainty_score":0.30832332},"labels":[],"label_agreement":null},{"id":"W4388283999","doi":"10.1038/s42003-023-05454-1","title":"Identification of circulating proteins associated with general cognitive function among middle-aged and older adults","year":2023,"lang":"en","type":"article","venue":"Communications Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill Genome Centre","funders":"National Institute of Neurological Disorders and Stroke; National Institute on Deafness and Other Communication Disorders; National Human Genome Research Institute; National Institute on Drug Abuse; National Heart, Lung, and Blood Institute; National Institute on Aging; Biotechnology and Biological Sciences Research Council; National Center for Advancing Translational Sciences; Medical Research Council; Hjartavernd; Age UK; Université de Bordeaux; Fondation de France; Bundesministerium für Bildung und Forschung; Fondation pour la Recherche Médicale; Institut National de la Santé et de la Recherche Médicale; Deutsches Zentrum für Neurodegenerative Erkrankungen; Deutsche Forschungsgemeinschaft; U.S. Department of Health and Human Services; Economic and Social Research Council; National Institute of Diabetes and Digestive and Kidney Diseases; Sanofi; European Commission; National Center for Research Resources; Agence Nationale de la Recherche; Scottish Government; Mutuelle Générale de l'Education Nationale; Royal Society; Directorate for Biological Sciences; National Institutes of Health","keywords":"Mendelian randomization; Cognition; Biology; Disease; Dementia; Alzheimer's disease; Function (biology); Neuroscience; Genetics; Bioinformatics; Medicine; Internal medicine; Gene; Genotype","score_opus":0.0174086657713284,"score_gpt":0.2693452914268503,"score_spread":0.25193662565552194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388283999","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9951672,0.00015963805,0.0038014196,0.00006944452,0.000025789755,0.0003757733,0.000038197588,0.000040633084,0.00032193164],"genre_scores_gemma":[0.99629796,0.00009410412,0.00051210955,0.000034545243,0.000017399767,0.000099547244,0.0027782384,0.000013403501,0.00015272168],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991536,0.00021970892,0.00028752556,0.00015829489,0.00004971896,0.0001311225],"domain_scores_gemma":[0.9988878,0.00008204876,0.00031284636,0.0005229928,0.00016659213,0.00002773433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034656178,0.00009435298,0.00011415259,0.00008258625,0.00017828346,0.000011505291,0.00020950963,0.00014643911,0.000003647367],"category_scores_gemma":[0.0005147654,0.00008705523,0.000027247583,0.00023412032,0.00032623688,0.0000070425226,0.00022041998,0.00013198983,0.0000036773404],"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":[0.00013104898,0.00016883848,0.6944276,0.00010723573,0.00039343722,3.662633e-7,0.0018169741,0.00016417551,0.29272035,0.0011159795,0.000093145,0.0088608675],"study_design_scores_gemma":[0.0010741255,0.00032334888,0.97031397,0.00013322105,0.000072209594,0.000004961905,0.00081552047,0.02243745,0.004449794,0.000091364134,0.00008558592,0.00019848013],"about_ca_topic_score_codex":0.000021889287,"about_ca_topic_score_gemma":0.0001399987,"teacher_disagreement_score":0.28827053,"about_ca_system_score_codex":0.000007376659,"about_ca_system_score_gemma":0.000026293052,"threshold_uncertainty_score":0.3550009},"labels":[],"label_agreement":null},{"id":"W4388635688","doi":"10.3390/ijms242216182","title":"Discovery and Visualization of the Hidden Relationships among N-Glycosylation, Disulfide Bonds, and Membrane Topology","year":2023,"lang":"en","type":"article","venue":"International Journal of Molecular Sciences","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"British Columbia Knowledge Development Fund; Alliance de recherche numérique du Canada","keywords":"SSS*; Transmembrane protein; Disulfide bond; Computational biology; Glycosylation; Chemistry; Proteome; Membrane protein; Topology (electrical circuits); Biology; Bioinformatics; Membrane; Biochemistry; Computer science; Mathematics; Artificial intelligence","score_opus":0.012404391472934644,"score_gpt":0.2877201479271097,"score_spread":0.27531575645417505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388635688","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99432766,0.00019036292,0.004035271,0.0008706609,0.00020694858,0.000041708565,0.0000033937567,0.0000024878025,0.00032147643],"genre_scores_gemma":[0.99893516,0.00018612908,0.0006464474,0.00007602229,0.000049165184,6.582399e-7,0.000007037436,0.0000038001465,0.000095571435],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991749,0.00009314873,0.00026854943,0.000082257415,0.00031445172,0.000066688175],"domain_scores_gemma":[0.9993839,0.000050080136,0.0003220268,0.000068116926,0.0001523635,0.000023502987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063277927,0.000055121767,0.000070505484,0.00011674966,0.00008354059,0.00005466746,0.0002615754,0.000045995435,0.000002073928],"category_scores_gemma":[0.00067597145,0.00003852238,0.00003411877,0.0001609355,0.0003322823,0.00003621615,0.00014848233,0.000072550196,3.3184156e-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":[0.00004638922,0.00002594837,0.67099994,0.000022539863,0.00012012388,0.000007185175,0.00073484966,0.0046189865,0.30157265,0.01957619,0.00027968644,0.0019954802],"study_design_scores_gemma":[0.00069378555,0.00032018824,0.86590767,0.00010753175,0.000042104777,0.00025983783,0.00066393043,0.010744388,0.11507229,0.004940119,0.0010704066,0.00017773628],"about_ca_topic_score_codex":0.000011811017,"about_ca_topic_score_gemma":0.000014815887,"teacher_disagreement_score":0.19490772,"about_ca_system_score_codex":0.000005565615,"about_ca_system_score_gemma":0.00005636096,"threshold_uncertainty_score":0.15708971},"labels":[],"label_agreement":null},{"id":"W4389028818","doi":"10.1101/2023.11.26.568742","title":"Learning sequence, structure, and function representations of proteins with language models","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Canadian Institute for Advanced Research","funders":"Flatiron Health; Division of Chemical, Bioengineering, Environmental, and Transport Systems; Samsung Advanced Institute of Technology; Samsung; National Institutes of Health; National Science Foundation","keywords":"Sequence (biology); Function (biology); Computer science; Computational biology; Natural language processing; Artificial intelligence; Biology; Evolutionary biology; Genetics","score_opus":0.012774117298856793,"score_gpt":0.24045328508497107,"score_spread":0.22767916778611427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389028818","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.983358,0.00023260716,0.015357617,0.000037004214,0.00013993615,0.00054863753,0.0001735006,0.00012900108,0.00002366435],"genre_scores_gemma":[0.98563,0.00011071659,0.013876291,0.000031347387,0.0001451714,0.000071954484,0.000009531235,0.00008685576,0.00003814423],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985753,0.000095063944,0.0003332695,0.0005102749,0.0002431308,0.00024291952],"domain_scores_gemma":[0.9984958,0.000017412218,0.0004270601,0.00070163625,0.00026319656,0.0000948588],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024387139,0.00029595182,0.00027195705,0.0001506572,0.00010629131,0.000069914444,0.0002137453,0.00035346544,0.000006621863],"category_scores_gemma":[0.0001964467,0.00028302099,0.00005384748,0.00021640773,0.00013366956,0.0000147166775,0.0003860689,0.00054001313,0.0000027438753],"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":[0.00006666028,0.0000200804,0.013610425,0.0005755351,0.00019776025,0.000006632713,0.000054098695,0.025792973,0.9592937,0.00031810315,0.00005848397,0.000005517661],"study_design_scores_gemma":[0.0012694777,0.0008984758,0.08595781,0.00067234004,0.0003284468,2.5475163e-7,0.00009970536,0.036364604,0.8718711,0.000030549716,0.0011052673,0.0014019571],"about_ca_topic_score_codex":0.00009945224,"about_ca_topic_score_gemma":0.000010654997,"teacher_disagreement_score":0.08742262,"about_ca_system_score_codex":0.000024045652,"about_ca_system_score_gemma":0.00023334075,"threshold_uncertainty_score":0.9999622},"labels":[],"label_agreement":null},{"id":"W4390262185","doi":"10.1016/j.jns.2023.121482","title":"An exploratory analysis of cognitive phenotypes in temporal lobe epilepsy and genetic generalized epilepsy using fuzzy c-means clustering of robotic assessment","year":2023,"lang":"en","type":"article","venue":"Journal of the Neurological Sciences","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Queen's University","funders":"","keywords":"Epilepsy; Temporal lobe; Fuzzy cognitive map; Cluster analysis; Mesial temporal lobe epilepsy; Neuroscience; Cognition; Artificial intelligence; Fuzzy logic; Exploratory analysis; Psychology; Computer science; Cognitive psychology; Neuro-fuzzy; Data science; Fuzzy control system","score_opus":0.03196893117746584,"score_gpt":0.32205815090752665,"score_spread":0.2900892197300608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390262185","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99595845,0.00007693199,0.003641396,0.00011386132,0.0001033332,0.000070510454,0.000005310579,0.0000023882258,0.000027843418],"genre_scores_gemma":[0.99250054,0.000090247195,0.0072334055,0.00013453327,0.0000331973,7.8870147e-7,0.0000021401133,0.0000035945702,0.0000015397542],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99851406,0.0003916226,0.0005017051,0.00014488069,0.00028809317,0.00015961655],"domain_scores_gemma":[0.99905205,0.00013192647,0.00056523347,0.00011716636,0.000080264115,0.000053367974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094085676,0.00009538353,0.00029928656,0.00020117672,0.00007455553,0.00002124126,0.00036134088,0.0000664422,0.000007050811],"category_scores_gemma":[0.000411524,0.000057381425,0.000119491364,0.00076718506,0.00036495438,0.00001630188,0.00018865774,0.00014746313,9.0679514e-8],"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":[0.000041984367,0.00003619444,0.5792349,0.000008724181,0.000044418615,0.0000036643878,0.000119671655,0.39102224,0.029175058,0.000007556866,0.00000214122,0.00030344297],"study_design_scores_gemma":[0.00024114025,0.0009874285,0.59814197,0.000020749036,0.00012757754,0.000013798237,0.00022068029,0.39938396,0.0006679677,0.0001290007,0.0000033200754,0.000062373205],"about_ca_topic_score_codex":0.00001815568,"about_ca_topic_score_gemma":0.000049083974,"teacher_disagreement_score":0.028507091,"about_ca_system_score_codex":0.0000055345836,"about_ca_system_score_gemma":0.000066183675,"threshold_uncertainty_score":0.23399466},"labels":[],"label_agreement":null},{"id":"W4390663837","doi":"10.1038/s41467-023-44271-2","title":"Gene-SGAN: discovering disease subtypes with imaging and genetic signatures via multi-view weakly-supervised deep clustering","year":2024,"lang":"en","type":"article","venue":"Nature Communications","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Genentech; National Institute of Neurological Disorders and Stroke; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; F. Hoffmann-La Roche; Pfizer; Biogen; BioClinica; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; National Institute on Drug Abuse; Bristol-Myers Squibb; Eli Lilly and Company; Canadian Institutes of Health Research; National Science Foundation; National Institutes of Health; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; U.S. Department of Health and Human Services; National Institute on Aging; Alzheimer's Association","keywords":"Cluster analysis; Computational biology; Artificial intelligence; Computer science; Gene; Pattern recognition (psychology); Biology; Genetics","score_opus":0.006602106932561773,"score_gpt":0.2687702865863528,"score_spread":0.2621681796537911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390663837","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27183765,0.56327415,0.15766649,0.0044359905,0.00041760277,0.00097391946,0.000094048715,0.00030080526,0.0009993821],"genre_scores_gemma":[0.90293497,0.0031458347,0.09303957,0.00040100634,0.000073577714,0.00003518396,0.0002565676,0.000041488718,0.00007180696],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999164,0.00007541142,0.0001893092,0.000259203,0.000117125535,0.0001949572],"domain_scores_gemma":[0.99862546,0.00004778489,0.000048499238,0.0011060839,0.00006067538,0.00011147327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000092339775,0.00019768403,0.00011960242,0.00006749751,0.00024011299,0.0001584363,0.0005519272,0.00013275906,0.00000583094],"category_scores_gemma":[0.00007754397,0.00016526399,0.000054622426,0.00014260822,0.00014249871,0.000019003814,0.00058697135,0.000605163,0.000005032113],"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":[0.00045175166,0.00061674224,0.18211572,0.0042119473,0.001417725,0.00016122378,0.004546344,0.047820807,0.46710747,0.0019964152,0.0023487,0.28720516],"study_design_scores_gemma":[0.00038003665,0.000051703657,0.036058575,0.00025955925,0.00013958968,0.00007677243,0.00011083936,0.92153215,0.0015961673,0.000026895505,0.039266042,0.00050167233],"about_ca_topic_score_codex":0.000012861575,"about_ca_topic_score_gemma":0.00034721417,"teacher_disagreement_score":0.87371135,"about_ca_system_score_codex":0.000018017818,"about_ca_system_score_gemma":0.0000575203,"threshold_uncertainty_score":0.673927},"labels":[],"label_agreement":null},{"id":"W4390669187","doi":"10.1038/s42003-023-05671-8","title":"A revised nomenclature for the lemur family of protein kinases","year":2024,"lang":"en","type":"review","venue":"Communications Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta Hospital; Alberta Hospital Edmonton","funders":"National Heart, Lung, and Blood Institute; National Institute of Diabetes and Digestive and Kidney Diseases; Nemzeti Kutatási Fejlesztési és Innovációs Hivatal; Biotechnology and Biological Sciences Research Council; Alzheimer’s Society; Medical Research Council; Nemzeti Kutatási, Fejlesztési és Innovaciós Alap; Hungarian Scientific Research Fund; Magyar Tudományos Akadémia; Alzheimer’s Research UK; Alzheimer's Society; National Institutes of Health; U.S. Department of Health and Human Services","keywords":"Lemur; Kinase; Biology; Computational biology; Nomenclature; Protein-Serine-Threonine Kinases; Neuroscience; Bioinformatics; Protein kinase A; Cell biology; Taxonomy (biology); Zoology; Primate","score_opus":0.08742798607953607,"score_gpt":0.4258811564942678,"score_spread":0.3384531704147317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390669187","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":[0.0000024811213,0.99472445,0.0012555297,0.0002927036,0.00010547056,0.0016697582,0.0005276289,0.000018451852,0.0014035051],"genre_scores_gemma":[0.00006843085,0.98511225,0.009214894,0.000080161844,0.0001153766,0.0010739209,0.0034338334,0.00003907421,0.0008620301],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986957,0.000268845,0.00060355046,0.00021687351,0.00004077087,0.0001743085],"domain_scores_gemma":[0.9964844,0.00024986846,0.00043499138,0.002690044,0.00011480407,0.000025869133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042658162,0.00026224938,0.0006118618,0.000084574735,0.00014170111,0.000019467843,0.0019997233,0.00047881866,0.000004833361],"category_scores_gemma":[0.00047267802,0.00015679018,0.00044203215,0.00019731522,0.00037860087,0.0000013754931,0.00096679776,0.00044489128,0.000019623285],"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":[0.000012411022,0.00006345924,0.0000031557572,0.013925991,0.0007278677,9.960457e-8,0.000058997914,8.5616006e-7,0.0006610005,0.023215542,0.011061317,0.9502693],"study_design_scores_gemma":[0.000070591384,0.00014642856,5.459265e-7,0.0014540554,0.00048042822,0.00000756915,0.000013110106,0.00007404239,0.000009678083,0.00025437868,0.9973289,0.00016030928],"about_ca_topic_score_codex":0.000008022466,"about_ca_topic_score_gemma":0.000009257158,"teacher_disagreement_score":0.98626757,"about_ca_system_score_codex":0.000016713508,"about_ca_system_score_gemma":0.00025895925,"threshold_uncertainty_score":0.6393718},"labels":[],"label_agreement":null},{"id":"W4390970477","doi":"10.1109/bibm58861.2023.10386052","title":"Prediction of piRNA-mRNA interactions based on an interactive inference network","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Science Basic Research Program of Shaanxi Province; Science and Engineering Research Council; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Piwi-interacting RNA; Messenger RNA; Computer science; Inference; Computational biology; Benchmark (surveying); Construct (python library); Biology; RNA; Artificial intelligence; Genetics; RNA interference; Gene; Computer network","score_opus":0.017623856190355565,"score_gpt":0.3033508537376159,"score_spread":0.28572699754726033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390970477","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88112956,0.0000053102985,0.05467952,0.00028680806,0.0008677672,0.00028155834,0.000062380626,0.00017988855,0.062507235],"genre_scores_gemma":[0.99612576,0.0000089109835,0.002167011,0.00026774293,0.00016269935,0.000012435454,0.0004546878,0.000011155537,0.0007895897],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936855,0.000056486977,0.00019883222,0.00013796774,0.00010354161,0.00013462346],"domain_scores_gemma":[0.99942654,0.000056332352,0.00010588238,0.00028730548,0.0000771125,0.000046794987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016247809,0.000091270624,0.00008177602,0.000069651105,0.000052065134,0.000014181611,0.00011879587,0.000062225496,0.00011393628],"category_scores_gemma":[0.00020831866,0.00008153975,0.000046683945,0.000169525,0.000030571624,0.000008686459,0.000056661644,0.0001341544,0.00003877417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071763253,0.00042304123,0.106245264,0.00010680518,0.00017684473,0.0000032512462,0.0006284193,0.69923156,0.12168603,0.0013702096,0.048883572,0.020527357],"study_design_scores_gemma":[0.0005097143,0.0014487715,0.055648673,0.00007494342,0.000017760263,0.0000037002408,0.00021839036,0.88696384,0.026725953,0.0001250915,0.028078077,0.00018505892],"about_ca_topic_score_codex":0.000020480156,"about_ca_topic_score_gemma":0.00003280947,"teacher_disagreement_score":0.1877323,"about_ca_system_score_codex":0.000010456398,"about_ca_system_score_gemma":0.00003648557,"threshold_uncertainty_score":0.33250943},"labels":[],"label_agreement":null},{"id":"W4391216324","doi":"10.1109/jbhi.2024.3358632","title":"Anti-Cancer Peptides Identification and Activity Type Classification With Protein Sequence Pre-Training","year":2024,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Machine Learning in Bioinformatics","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":"University of Waterloo","funders":"","keywords":"Identification (biology); Sequence (biology); Cancer; Computer science; Artificial intelligence; Protein sequencing; Pattern recognition (psychology); Computational biology; Peptide sequence; Medicine; Biology; Gene; Internal medicine; Genetics","score_opus":0.05267022293871846,"score_gpt":0.37076969358306355,"score_spread":0.3180994706443451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391216324","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9655272,0.0006017742,0.031077221,0.0024032732,0.00017223539,0.00015760846,0.00001166319,0.000010345784,0.00003871212],"genre_scores_gemma":[0.9909862,0.0018768924,0.0065967655,0.00022986344,0.0002028864,0.0000039265487,0.000014029803,0.000007705545,0.000081682614],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989501,0.000028970715,0.0005625432,0.000065392785,0.00024383538,0.00014914882],"domain_scores_gemma":[0.999172,0.000014245206,0.00045475355,0.00008579305,0.0001113818,0.00016187267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000916341,0.00009616057,0.0001630506,0.00009569889,0.000090955604,0.000087942884,0.000080355225,0.000093048126,0.000002899601],"category_scores_gemma":[0.0000572449,0.00006583423,0.000019444238,0.0001272724,0.00016644823,0.00004817433,0.000021446565,0.00025260472,0.0000012212432],"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":[0.0002549311,0.00010303228,0.0034441084,0.006646866,0.0002462011,0.00000534384,0.009534838,0.0001686577,0.35338053,0.00039469686,0.0041612303,0.6216596],"study_design_scores_gemma":[0.004039874,0.013371452,0.14647016,0.0081112245,0.000263723,0.003218827,0.0061391774,0.4655464,0.06494892,0.0005720468,0.28564796,0.0016702446],"about_ca_topic_score_codex":0.000007793492,"about_ca_topic_score_gemma":0.0000033037056,"teacher_disagreement_score":0.61998934,"about_ca_system_score_codex":0.000026063546,"about_ca_system_score_gemma":0.00042264356,"threshold_uncertainty_score":0.2684642},"labels":[],"label_agreement":null},{"id":"W4391233758","doi":"10.1016/j.biosystems.2024.105129","title":"2022 IEEE conference on computational intelligence in bioinformatics and computational biology (IEEE CIBCB, 2022)","year":2024,"lang":"en","type":"editorial","venue":"Biosystems","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University; Thompson Rivers University","funders":"","keywords":"Computer science; Computational intelligence; Computational biology; Biology; Bioinformatics; Artificial intelligence","score_opus":0.012247990912356472,"score_gpt":0.2944983689390053,"score_spread":0.2822503780266488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391233758","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00926323,0.0021518504,0.038861413,0.0002563899,0.9391395,0.0015134079,0.0036176268,0.00014541636,0.005051191],"genre_scores_gemma":[0.37686834,0.0022919294,0.017821413,0.0006725601,0.56536347,0.0003093973,0.032219086,0.000358207,0.0040955986],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972932,0.00015687384,0.0010185541,0.0005852588,0.0005547346,0.00039141567],"domain_scores_gemma":[0.9985061,0.00030697128,0.000437916,0.00037285034,0.00025385787,0.00012230336],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00070185657,0.00051009934,0.0005300723,0.00035823297,0.00009422129,0.00016609975,0.00047197175,0.0011651841,0.000026329764],"category_scores_gemma":[0.00033570555,0.00048198827,0.000112905065,0.00023587099,0.00020254124,0.000010137733,0.00019660908,0.00097121985,0.00017328748],"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":[0.00009535462,0.000072459516,0.00017660196,0.0015531835,0.0001821069,0.000011030496,0.0003899212,0.01769396,0.00041479422,0.0016611941,0.9755663,0.0021830807],"study_design_scores_gemma":[0.0007344433,0.0010722668,0.000046205216,0.0009375737,0.00005131492,0.000049748436,0.000255547,0.43652555,0.00027881825,0.0014295502,0.5574537,0.0011652817],"about_ca_topic_score_codex":0.000051237752,"about_ca_topic_score_gemma":0.00006543691,"teacher_disagreement_score":0.41883162,"about_ca_system_score_codex":0.000091479254,"about_ca_system_score_gemma":0.00047945417,"threshold_uncertainty_score":0.9997632},"labels":[],"label_agreement":null},{"id":"W4391380207","doi":"10.1101/2024.01.28.577662","title":"Predicting protein functions using positive-unlabeled ranking with ontology-based priors","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto; University of New Brunswick","funders":"King Abdullah University of Science and Technology","keywords":"Computer science; Prior probability; Classifier (UML); Benchmark (surveying); Ranking (information retrieval); Artificial intelligence; Machine learning; Gene ontology; Ontology; Data mining; Function (biology); Pattern recognition (psychology); Bayesian probability","score_opus":0.0075455923117984875,"score_gpt":0.22084478054469836,"score_spread":0.21329918823289987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391380207","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9779682,0.00078852853,0.018479154,0.00017450697,0.00063479884,0.0013217041,0.00022481126,0.0003581636,0.000050118444],"genre_scores_gemma":[0.96106875,0.000008814363,0.037724216,0.000205303,0.00054001197,0.00020451643,0.000006983121,0.00021832927,0.00002308634],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99697316,0.00019879482,0.00063423783,0.0010905509,0.0004156303,0.00068762666],"domain_scores_gemma":[0.99755317,0.000028858169,0.0005629802,0.0011579122,0.00048292315,0.0002141725],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00063243817,0.00074348337,0.00053211814,0.00030333587,0.00032465416,0.00028039815,0.00049326546,0.000865778,0.000018782219],"category_scores_gemma":[0.00028914958,0.000723592,0.00020185871,0.0004106477,0.00020972647,0.000011913312,0.00075161253,0.001447194,0.000029345754],"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":[0.00016657518,0.0000786488,0.017281372,0.0010250245,0.000495027,0.00004554364,0.0000162762,0.005503219,0.9752181,0.00009470856,0.00007207962,0.0000034073307],"study_design_scores_gemma":[0.0022106732,0.00078050734,0.01617725,0.0037589269,0.0009886844,7.7699576e-7,0.000019759096,0.08363421,0.8867436,0.0000029592777,0.0030754192,0.0026072245],"about_ca_topic_score_codex":0.00008021349,"about_ca_topic_score_gemma":0.000016026197,"teacher_disagreement_score":0.08847451,"about_ca_system_score_codex":0.00020626704,"about_ca_system_score_gemma":0.001441982,"threshold_uncertainty_score":0.9995215},"labels":[],"label_agreement":null},{"id":"W4391390112","doi":"10.1093/bioinformatics/btae034","title":"GeNLP: a web tool for NLP-based exploration and prediction of microbial gene function","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Azrieli Foundation; Israel Science Foundation","keywords":"Computer science; MIT License; Context (archaeology); Function (biology); License; Source code; Interface (matter); Semantics (computer science); World Wide Web; Artificial intelligence; Web application; Natural language processing; Programming language; Biology; Genetics","score_opus":0.011154803564037847,"score_gpt":0.23325216432045523,"score_spread":0.2220973607564174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391390112","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24782622,0.00034299213,0.74942905,0.00016425338,0.0006222232,0.0006534818,0.00044470446,0.00008115333,0.00043594316],"genre_scores_gemma":[0.8807448,0.00021632138,0.115196474,0.00032831178,0.00044122775,0.00008452115,0.0026345064,0.000040322273,0.0003134954],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921083,0.000013742391,0.00041939356,0.00010794413,0.00011090164,0.0001371925],"domain_scores_gemma":[0.99954724,0.000022843047,0.00011704438,0.00018535795,0.00009312544,0.000034382974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026953616,0.00012964879,0.00011096001,0.00009732095,0.00006223588,0.000060852533,0.00006624616,0.0001515409,0.000006818615],"category_scores_gemma":[0.00009371231,0.00011956661,0.00007337843,0.000089927584,0.000049681657,0.00003294927,0.000037060177,0.00006629655,0.0000068435043],"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":[0.000596433,0.00010127911,0.0011641248,0.0049983156,0.00028399428,5.8616735e-7,0.0012210343,0.005857409,0.8824775,0.0013586653,0.035491243,0.0664494],"study_design_scores_gemma":[0.0008447273,0.000891924,0.0002795705,0.00007747868,0.00009072254,0.0000143716625,0.000106706204,0.8192417,0.07720463,0.0000871953,0.100968264,0.00019272834],"about_ca_topic_score_codex":0.0000011739768,"about_ca_topic_score_gemma":0.000002095732,"teacher_disagreement_score":0.8133843,"about_ca_system_score_codex":0.000014471222,"about_ca_system_score_gemma":0.00011542903,"threshold_uncertainty_score":0.48757848},"labels":[],"label_agreement":null},{"id":"W4391852472","doi":"10.1007/978-3-031-53969-5_21","title":"ProVolOne – Protein Volume Prediction Using a Multi-attention, Multi-resolution Deep Neural Network and Finite Element Analysis","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"National Research Council Canada; University of Ottawa","funders":"","keywords":"Computer science; Artificial neural network; Volume (thermodynamics); Finite element method; Artificial intelligence; Physics; Thermodynamics","score_opus":0.011549174236569142,"score_gpt":0.25023006386637403,"score_spread":0.23868088962980488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391852472","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":[0.0057436796,0.00092077034,0.99221957,0.00008249337,0.00038225602,0.000563414,0.000018855122,0.000036656824,0.000032335454],"genre_scores_gemma":[0.38725042,0.000038695365,0.6103826,0.00022696004,0.0007018598,0.000025324869,0.00028184924,0.00004603368,0.0010462574],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981053,0.000032314463,0.0004398508,0.0007339648,0.00031830108,0.00037025203],"domain_scores_gemma":[0.99909866,0.000016399785,0.00024062132,0.00042178688,0.00014236911,0.00008019181],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000523318,0.00032342938,0.0002735348,0.00035083512,0.00020407587,0.00018265781,0.00030083422,0.00029746312,0.000007273441],"category_scores_gemma":[0.00007549292,0.00030166734,0.00012319446,0.0003702146,0.00031106806,0.000017498825,0.0005270482,0.0004410214,0.000004102699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011735455,0.00001669365,0.0038787995,0.00009081623,0.00011197067,0.0000050596905,0.00010278972,0.98158103,0.0016884725,0.000030112731,0.0000035885635,0.012478955],"study_design_scores_gemma":[0.00022347576,0.00016941705,0.0016868594,0.00012749969,0.00014614852,0.000016229575,3.066593e-7,0.996543,0.00011524221,0.0002113022,0.00048054327,0.0002800062],"about_ca_topic_score_codex":0.000028779403,"about_ca_topic_score_gemma":0.00023042086,"teacher_disagreement_score":0.38183695,"about_ca_system_score_codex":0.000089695655,"about_ca_system_score_gemma":0.000076482334,"threshold_uncertainty_score":0.99994355},"labels":[],"label_agreement":null},{"id":"W4392332354","doi":"","title":"Incorporating biological information into genomic prediction models","year":2023,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Computational biology; Artificial intelligence; Biology","score_opus":0.011115336372544892,"score_gpt":0.2202926280799335,"score_spread":0.2091772917073886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392332354","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7043181,0.000067336936,0.26633206,0.0013950989,0.00009615155,0.00021987515,0.000026131118,0.00022148858,0.027323721],"genre_scores_gemma":[0.9652815,0.00016273442,0.031516463,0.00013531305,0.000026005377,0.00002875442,0.002025134,0.000013447569,0.00081066263],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811184,0.0009986251,0.00035175265,0.00019264597,0.00015871841,0.00018643933],"domain_scores_gemma":[0.9984805,0.00014125032,0.00022766349,0.0005748137,0.0004990543,0.000076712604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031046506,0.00012912067,0.00010316304,0.00010510689,0.00025967526,0.00011200878,0.00035680158,0.00015868299,0.000014494444],"category_scores_gemma":[0.0012281586,0.00012701095,0.00006425652,0.00028368345,0.00010124697,0.000043536846,0.00038556068,0.00015435871,0.00010183783],"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":[0.00015416826,0.00039007506,0.060217045,0.0003529366,0.00022087837,0.0000033308013,0.026150418,0.027568778,0.47889093,0.17224494,0.016100114,0.21770638],"study_design_scores_gemma":[0.0010575528,0.000005542349,0.025894336,0.00020937424,0.000018123128,0.000022815086,0.00048587262,0.82737,0.07913615,0.0074330457,0.05782273,0.0005444423],"about_ca_topic_score_codex":0.00009819695,"about_ca_topic_score_gemma":0.00006855241,"teacher_disagreement_score":0.79980123,"about_ca_system_score_codex":0.000027871625,"about_ca_system_score_gemma":0.00007220171,"threshold_uncertainty_score":0.51793563},"labels":[],"label_agreement":null},{"id":"W4392850383","doi":"10.7554/elife.91415.3.sa0","title":"eLife assessment: Sensitive remote homology search by local alignment of small positional embeddings from protein language models","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Homology (biology); Computational biology; Computer science; Homology modeling; Artificial intelligence; Biology; Genetics; Amino acid; Biochemistry","score_opus":0.012320718025111073,"score_gpt":0.31368207557884226,"score_spread":0.30136135755373117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392850383","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017483387,0.04264342,0.79507875,0.028853167,0.0011953058,0.004033127,0.01974232,0.00016282446,0.09080768],"genre_scores_gemma":[0.04229027,0.006295814,0.19392003,0.015664125,0.0014290294,0.00014895394,0.1834088,0.00038856716,0.5564544],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974193,0.00024648017,0.000702298,0.0006371241,0.0006078127,0.00038698793],"domain_scores_gemma":[0.99863833,0.00004453939,0.00027523548,0.00060089375,0.00031022893,0.00013077045],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000571433,0.0004625648,0.0006601608,0.00008742391,0.00004732815,0.000033995977,0.0003857575,0.0006596884,0.00029300028],"category_scores_gemma":[0.000051584357,0.0004144235,0.00028257907,0.00009798609,0.0001923821,0.000004115939,0.00062555325,0.00076807284,0.000049681217],"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":[0.00006236724,0.00011583003,0.0000015468735,0.003898201,0.00096012594,0.000054519787,0.00022273911,0.00090490264,0.0686465,0.0005531059,0.91680366,0.007776518],"study_design_scores_gemma":[0.0012501531,0.001486991,0.000011953896,0.008093952,0.0008654197,0.00021220214,0.0005134241,0.19001757,0.16817617,0.00072514435,0.62658614,0.0020608574],"about_ca_topic_score_codex":0.0016182861,"about_ca_topic_score_gemma":0.00008268459,"teacher_disagreement_score":0.60115874,"about_ca_system_score_codex":0.00010099415,"about_ca_system_score_gemma":0.00040917538,"threshold_uncertainty_score":0.9998308},"labels":[],"label_agreement":null},{"id":"W4392944270","doi":"10.1109/icaml60083.2023.00046","title":"Node Classification of Protein Interaction Network Based on Convolutional Neural Network","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Computer science; Convolutional neural network; Node (physics); Artificial intelligence; Artificial neural network; Engineering","score_opus":0.016947867230923147,"score_gpt":0.2768059959959968,"score_spread":0.25985812876507364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392944270","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9400852,0.000025604806,0.032122765,0.0015304085,0.00062963105,0.00057064154,0.0000133648555,0.00013661168,0.024885824],"genre_scores_gemma":[0.9940823,0.0000028563388,0.0036458513,0.00035047895,0.00035543225,0.00002725036,0.00057090004,0.000012156304,0.0009527844],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992601,0.000064081556,0.00022464001,0.00013669506,0.00013749117,0.00017697352],"domain_scores_gemma":[0.99951357,0.000027886415,0.00013776253,0.00022638089,0.000062588944,0.0000317931],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002491393,0.00009070958,0.000080943355,0.000033150587,0.000061990424,0.000010572233,0.00010088852,0.00009377208,0.00006178436],"category_scores_gemma":[0.000096080636,0.000082618586,0.000056717407,0.00018501622,0.00003707618,0.0000032282082,0.000040330553,0.00010753058,0.000057152298],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020619473,0.00003489584,0.013481454,0.000039792463,0.0000187855,3.5648117e-7,0.000009220103,0.9193391,0.030705031,0.0020159143,0.03270462,0.0014446229],"study_design_scores_gemma":[0.00027110454,0.00020878851,0.04863217,0.000027975258,0.000005135675,0.0000012448633,0.000016014896,0.9337815,0.0022634296,0.00008007429,0.0146050565,0.000107491695],"about_ca_topic_score_codex":0.000006214939,"about_ca_topic_score_gemma":0.000007740836,"teacher_disagreement_score":0.05399714,"about_ca_system_score_codex":0.000011654441,"about_ca_system_score_gemma":0.00003445914,"threshold_uncertainty_score":0.33690882},"labels":[],"label_agreement":null},{"id":"W4393212108","doi":"10.1038/s41598-024-56786-9","title":"GeneAI 3.0: powerful, novel, generalized hybrid and ensemble deep learning frameworks for miRNA species classification of stationary patterns from nucleotides","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Artificial intelligence; Pattern recognition (psychology); Computer science; Convolutional neural network; Binary classification; Entropy (arrow of time); In silico; Machine learning; Deep learning; Support vector machine; Biology; Gene; Genetics","score_opus":0.012096368042860321,"score_gpt":0.2633443942355905,"score_spread":0.2512480261927302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393212108","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8242739,0.0007984229,0.17276864,0.000086748674,0.0014227295,0.00020565465,0.000040605086,0.000028027504,0.00037530132],"genre_scores_gemma":[0.975373,0.000063835054,0.02091177,0.000032524666,0.00014106059,0.000014136978,0.001763155,0.000024594634,0.001675887],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986066,0.000036764664,0.0004618828,0.00049056514,0.00022720784,0.00017697805],"domain_scores_gemma":[0.99907434,0.00006694259,0.00025630096,0.0003825982,0.00016106007,0.000058755348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068452104,0.00013472339,0.00014462376,0.000090738904,0.00014809064,0.00023936552,0.00009378692,0.000123895,0.000047976875],"category_scores_gemma":[0.0003839421,0.0001271721,0.00008287859,0.00008365894,0.0001450475,0.000017934426,0.00008090277,0.00016127354,0.0000033335473],"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":[0.000029192219,0.000040803196,0.009061132,0.000160059,0.00007839165,0.000008312679,0.00047832113,0.0019098583,0.9772211,0.00034411607,0.005463592,0.0052051316],"study_design_scores_gemma":[0.00043774978,0.0002156639,0.041656364,0.00022892213,0.00011350349,0.00015064955,0.0005702067,0.22754243,0.3750512,0.0041375407,0.34928516,0.0006106225],"about_ca_topic_score_codex":0.000016160518,"about_ca_topic_score_gemma":0.000009523643,"teacher_disagreement_score":0.6021699,"about_ca_system_score_codex":0.0000138062,"about_ca_system_score_gemma":0.00006413874,"threshold_uncertainty_score":0.5185927},"labels":[],"label_agreement":null},{"id":"W4393441456","doi":"10.5281/zenodo.7489187","title":"Rice genetic variants using dbSNP and PseudoDB","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"dbSNP; Genetics; Biology; Gene; Single-nucleotide polymorphism; Genotype","score_opus":0.020705616497308222,"score_gpt":0.2574237260203901,"score_spread":0.23671810952308187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393441456","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056864214,0.00040689428,0.0012293119,0.0000910716,0.00025150992,0.0005477966,0.9869391,0.00014673306,0.0047011822],"genre_scores_gemma":[0.00068968005,0.00057423627,0.0010889872,0.0002375616,0.00018840678,5.7417257e-8,0.9960766,0.00084887416,0.00029561095],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99819446,0.00037063778,0.00029718137,0.00046748435,0.00033238644,0.0003378519],"domain_scores_gemma":[0.99869925,0.000009772149,0.00022622217,0.00073354173,0.00018420393,0.00014700525],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004724578,0.00023316816,0.00018095589,0.00017849519,0.0017042487,0.00044192706,0.0010258971,0.00017861744,0.025039151],"category_scores_gemma":[0.0006089267,0.0002648176,0.00005063861,0.00022641587,0.00013477345,0.000009671121,0.0033598596,0.00048899715,0.00048647085],"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":[0.000033950477,0.00004790954,9.517538e-7,0.00017888105,0.00006470829,0.000012141709,0.000054729444,0.00019050133,0.0023533928,0.000010713921,0.99457216,0.002479973],"study_design_scores_gemma":[0.00030994567,0.00029578718,0.000113156406,0.000015159014,0.000046075304,0.00053521007,0.000054278185,0.0005229837,0.000043996002,0.000007789138,0.9977723,0.00028335906],"about_ca_topic_score_codex":0.000043763783,"about_ca_topic_score_gemma":3.4721134e-7,"teacher_disagreement_score":0.02455268,"about_ca_system_score_codex":0.00006477482,"about_ca_system_score_gemma":0.000010784567,"threshold_uncertainty_score":0.9999804},"labels":[],"label_agreement":null},{"id":"W4393452961","doi":"10.5281/zenodo.7489188","title":"Rice genetic variants using dbSNP and PseudoDB","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"dbSNP; Biology; Genetics; Gene; Single-nucleotide polymorphism; Genotype","score_opus":0.020705616497308222,"score_gpt":0.2574237260203901,"score_spread":0.23671810952308187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393452961","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056864214,0.00040689428,0.0012293119,0.0000910716,0.00025150992,0.0005477966,0.9869391,0.00014673306,0.0047011822],"genre_scores_gemma":[0.00068968005,0.00057423627,0.0010889872,0.0002375616,0.00018840678,5.7417257e-8,0.9960766,0.00084887416,0.00029561095],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99819446,0.00037063778,0.00029718137,0.00046748435,0.00033238644,0.0003378519],"domain_scores_gemma":[0.99869925,0.000009772149,0.00022622217,0.00073354173,0.00018420393,0.00014700525],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004724578,0.00023316816,0.00018095589,0.00017849519,0.0017042487,0.00044192706,0.0010258971,0.00017861744,0.025039151],"category_scores_gemma":[0.0006089267,0.0002648176,0.00005063861,0.00022641587,0.00013477345,0.000009671121,0.0033598596,0.00048899715,0.00048647085],"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":[0.000033950477,0.00004790954,9.517538e-7,0.00017888105,0.00006470829,0.000012141709,0.000054729444,0.00019050133,0.0023533928,0.000010713921,0.99457216,0.002479973],"study_design_scores_gemma":[0.00030994567,0.00029578718,0.000113156406,0.000015159014,0.000046075304,0.00053521007,0.000054278185,0.0005229837,0.000043996002,0.000007789138,0.9977723,0.00028335906],"about_ca_topic_score_codex":0.000043763783,"about_ca_topic_score_gemma":3.4721134e-7,"teacher_disagreement_score":0.02455268,"about_ca_system_score_codex":0.00006477482,"about_ca_system_score_gemma":0.000010784567,"threshold_uncertainty_score":0.9999804},"labels":[],"label_agreement":null},{"id":"W4393511271","doi":"10.5281/zenodo.8101701","title":"MetaPep: A core peptide database for faster human gut metaproteomics database searches","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Metaproteomics; Database; Computer science; Core (optical fiber); Computational biology; Information retrieval; Chemistry; Biology; Proteomics; Biochemistry","score_opus":0.06709769633482267,"score_gpt":0.3102441220615064,"score_spread":0.24314642572668377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393511271","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00057866063,0.000079034304,0.0033059784,0.00016456492,0.00017131706,0.0014607128,0.99237406,0.00027886388,0.0015868302],"genre_scores_gemma":[0.00010326521,0.00029109925,0.0025876553,0.00026983503,0.0005558806,0.0000012586097,0.9915641,0.0017458263,0.0028810594],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968632,0.00035753922,0.0006029779,0.00088603026,0.000575857,0.0007144334],"domain_scores_gemma":[0.9966671,0.000046426434,0.00039068947,0.0019406131,0.0006625179,0.00029268544],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017886242,0.00046662687,0.00040893318,0.00038361072,0.0019497449,0.0007487932,0.002433178,0.0003096581,0.0015856029],"category_scores_gemma":[0.0028191523,0.0004829761,0.00020315086,0.000376236,0.0002855838,0.000037291466,0.0046740333,0.0007739846,0.006692948],"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":[0.00012014605,0.000099798766,4.1598705e-7,0.0007957203,0.00026136727,0.000011682409,0.000055328477,0.000039809234,0.02024873,0.00011895702,0.9771151,0.0011329382],"study_design_scores_gemma":[0.0007845562,0.00051085226,0.000012267555,0.0000894363,0.00014206533,0.00007140668,0.00011682027,0.00037822188,0.00090493297,0.00002378908,0.9964573,0.0005083473],"about_ca_topic_score_codex":0.0000831177,"about_ca_topic_score_gemma":0.000012408024,"teacher_disagreement_score":0.019343797,"about_ca_system_score_codex":0.0000889618,"about_ca_system_score_gemma":0.000023324388,"threshold_uncertainty_score":0.9997622},"labels":[],"label_agreement":null},{"id":"W4393556885","doi":"10.5281/zenodo.7534968","title":"Sequences used for building HMMER profiles to search for SNAREs proteins","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computational biology; Biology","score_opus":0.03637866290741216,"score_gpt":0.3077233307083554,"score_spread":0.27134466780094324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393556885","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001201132,0.00004424523,0.013159504,0.0008173474,0.00021007379,0.0039441753,0.9799364,0.000279507,0.00040761736],"genre_scores_gemma":[0.0003776537,0.000067492,0.005059828,0.00020181769,0.00062039617,0.0000047633666,0.99124014,0.001306695,0.0011212182],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99773085,0.00020228668,0.00039917778,0.00064497604,0.00040630673,0.000616372],"domain_scores_gemma":[0.9980719,0.000050539118,0.00018367104,0.00074051734,0.00074646383,0.00020688916],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011774597,0.00030085578,0.00026560525,0.0003147646,0.0015739488,0.0006815644,0.0016363038,0.0002764247,0.00041696924],"category_scores_gemma":[0.002215452,0.00030498332,0.00013370039,0.00034908167,0.00012959224,0.00001617031,0.0016374519,0.00031614455,0.0021088114],"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":[0.00012560611,0.000044728444,6.0108175e-7,0.0007645436,0.000097049924,0.0000016180454,0.00011680333,0.00028175992,0.016666178,0.00011637598,0.9785169,0.0032678577],"study_design_scores_gemma":[0.0004417223,0.0010965278,0.000009328914,0.00009670698,0.000029435692,0.000018634371,0.00012848135,0.00027710767,0.008720928,0.00002306581,0.98879844,0.00035962852],"about_ca_topic_score_codex":0.000049788265,"about_ca_topic_score_gemma":0.0000038184553,"teacher_disagreement_score":0.011303738,"about_ca_system_score_codex":0.0000812219,"about_ca_system_score_gemma":0.000026038773,"threshold_uncertainty_score":0.9999402},"labels":[],"label_agreement":null},{"id":"W4393575358","doi":"10.5281/zenodo.5034912","title":"Metabolic pathway prediction using non-negative matrix factorization with improved precision","year":2020,"lang":"en","type":"dataset","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Matrix decomposition; Computer science; Matrix (chemical analysis); Factorization; Non-negative matrix factorization; Algorithm; Artificial intelligence; Chemistry; Physics; Chromatography","score_opus":0.014300831627891279,"score_gpt":0.2654121728666503,"score_spread":0.25111134123875906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393575358","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005509838,0.00008189966,0.00057536346,0.000004136596,0.00012084414,0.00060251384,0.99849844,0.000023326746,0.000038363414],"genre_scores_gemma":[0.00037246023,0.00002797055,0.0012822179,0.000067025816,0.0006463602,0.00008226593,0.99741584,0.00004514429,0.0000607279],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99871963,0.000060821294,0.00032321658,0.00040839062,0.0002661717,0.00022179408],"domain_scores_gemma":[0.99867195,0.000026177966,0.00050721166,0.00048047348,0.00020684587,0.00010736057],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00004188004,0.00036376595,0.0002847355,0.000074914904,0.000109554036,0.000089797526,0.00032576115,0.00042351978,0.0032926293],"category_scores_gemma":[0.0011861634,0.00030689113,0.00008931714,0.00017665236,0.000009580724,0.000013618536,0.00027663092,0.00039872693,0.00030425523],"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":[0.00006164886,0.000016621823,0.0000064395413,0.00034123275,0.00008596822,0.000002059014,0.000026701719,0.00053129485,0.004156508,5.6856898e-8,0.99456286,0.00020861227],"study_design_scores_gemma":[0.00039203357,0.00038306537,0.00010064973,0.0005397837,0.000061609586,0.000012568567,0.0000125021625,0.0058321096,0.015552167,8.5626095e-7,0.9767785,0.0003341658],"about_ca_topic_score_codex":0.000017955064,"about_ca_topic_score_gemma":0.000013856768,"teacher_disagreement_score":0.017784368,"about_ca_system_score_codex":0.00002819405,"about_ca_system_score_gemma":0.0002529649,"threshold_uncertainty_score":0.9999383},"labels":[],"label_agreement":null},{"id":"W4393737653","doi":"10.5281/zenodo.3711137","title":"Metabolic pathway prediction using non-negative matrix factorization with improved precision","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Matrix decomposition; Factorization; Matrix (chemical analysis); Computer science; Non-negative matrix factorization; Algorithm; Mathematics; Chemistry; Physics; Chromatography","score_opus":0.016222413438958395,"score_gpt":0.25281496166983325,"score_spread":0.23659254823087486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393737653","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012563446,0.00005670423,0.050841693,0.000042069012,0.0002108418,0.0010459188,0.94535434,0.00017719722,0.0010148799],"genre_scores_gemma":[0.0049417955,0.00021729253,0.0016501822,0.00006337951,0.00049318356,1.4449014e-7,0.99162346,0.0008733041,0.00013728144],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979979,0.00029429322,0.00039684767,0.0005611828,0.0004257398,0.00032406632],"domain_scores_gemma":[0.9981347,0.000013072139,0.00042707313,0.00064776157,0.0005955422,0.00018186052],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00034829363,0.00032555763,0.00026739977,0.00019188174,0.0010652796,0.0005044617,0.00085737323,0.00025223152,0.0007982784],"category_scores_gemma":[0.0010030746,0.0003042103,0.00007368719,0.0004154883,0.000114944254,0.000033916705,0.0011397882,0.0005189772,0.00089863915],"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":[0.00024145373,0.000070941074,0.0000019062985,0.0001930947,0.00015575861,0.0000034656093,0.00018869613,0.0007084809,0.03477909,0.000009878454,0.9597628,0.0038844242],"study_design_scores_gemma":[0.000621395,0.0008482368,0.000057385314,0.00005776723,0.00007297061,0.000064992375,0.00007142739,0.003636753,0.0055715987,0.0000051444763,0.9886892,0.0003031198],"about_ca_topic_score_codex":0.000027831571,"about_ca_topic_score_gemma":8.871448e-7,"teacher_disagreement_score":0.04919151,"about_ca_system_score_codex":0.00007771824,"about_ca_system_score_gemma":0.000024385827,"threshold_uncertainty_score":0.999941},"labels":[],"label_agreement":null},{"id":"W4393895133","doi":"10.5281/zenodo.8101702","title":"MetaPep: A core peptide database for faster human gut metaproteomics database searches","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Metaproteomics; Database; Computer science; Core (optical fiber); Computational biology; Chemistry; Biology; Proteomics; Biochemistry","score_opus":0.06709769633482267,"score_gpt":0.3102441220615064,"score_spread":0.24314642572668377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393895133","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00057866063,0.000079034304,0.0033059784,0.00016456492,0.00017131706,0.0014607128,0.99237406,0.00027886388,0.0015868302],"genre_scores_gemma":[0.00010326521,0.00029109925,0.0025876553,0.00026983503,0.0005558806,0.0000012586097,0.9915641,0.0017458263,0.0028810594],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968632,0.00035753922,0.0006029779,0.00088603026,0.000575857,0.0007144334],"domain_scores_gemma":[0.9966671,0.000046426434,0.00039068947,0.0019406131,0.0006625179,0.00029268544],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017886242,0.00046662687,0.00040893318,0.00038361072,0.0019497449,0.0007487932,0.002433178,0.0003096581,0.0015856029],"category_scores_gemma":[0.0028191523,0.0004829761,0.00020315086,0.000376236,0.0002855838,0.000037291466,0.0046740333,0.0007739846,0.006692948],"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":[0.00012014605,0.000099798766,4.1598705e-7,0.0007957203,0.00026136727,0.000011682409,0.000055328477,0.000039809234,0.02024873,0.00011895702,0.9771151,0.0011329382],"study_design_scores_gemma":[0.0007845562,0.00051085226,0.000012267555,0.0000894363,0.00014206533,0.00007140668,0.00011682027,0.00037822188,0.00090493297,0.00002378908,0.9964573,0.0005083473],"about_ca_topic_score_codex":0.0000831177,"about_ca_topic_score_gemma":0.000012408024,"teacher_disagreement_score":0.019343797,"about_ca_system_score_codex":0.0000889618,"about_ca_system_score_gemma":0.000023324388,"threshold_uncertainty_score":0.9997622},"labels":[],"label_agreement":null},{"id":"W4394071307","doi":"10.6084/m9.figshare.20415819","title":"Malaise_trap_ReadME.txt","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Trap (plumbing); Malaise; Geography; Meteorology; Medicine","score_opus":0.020379460966921763,"score_gpt":0.28550295480474425,"score_spread":0.26512349383782247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394071307","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000019387298,0.00009521099,2.5422304e-7,0.0000192105,0.00016256249,0.00019011776,0.99862444,0.000055010478,0.0008512552],"genre_scores_gemma":[0.0000015250411,0.00005915536,0.000045116827,0.0003276694,0.00059676263,0.00014268834,0.9965892,0.00004862001,0.0021893077],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989131,0.000031764175,0.0002405084,0.00030578277,0.00021080267,0.00029800352],"domain_scores_gemma":[0.99883634,0.000026725193,0.0001848078,0.00078569225,0.0000707611,0.00009570208],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000047644113,0.0002908209,0.00019843905,0.000079072655,0.000065038344,0.000058698723,0.0005994509,0.00057934097,0.058887098],"category_scores_gemma":[0.0012969623,0.00028328848,0.00014641187,0.00011005985,0.000008498784,0.000001681448,0.00045311803,0.00037918292,0.105754174],"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":[0.000005229772,0.000010646339,9.4400684e-7,0.0004966481,0.000045355704,0.000012925676,0.0000015854832,0.000022816146,0.000015382611,1.296532e-7,0.9992219,0.00016643394],"study_design_scores_gemma":[0.000120196586,0.00008267253,0.00006478517,0.00048270484,0.000015231719,0.000017025657,0.0000026198516,0.000022239985,0.00012420604,0.0000012484235,0.9987401,0.00032698826],"about_ca_topic_score_codex":0.00001573198,"about_ca_topic_score_gemma":0.00004748566,"teacher_disagreement_score":0.046867076,"about_ca_system_score_codex":0.000011372802,"about_ca_system_score_gemma":0.00011474093,"threshold_uncertainty_score":0.9999619},"labels":[],"label_agreement":null},{"id":"W4394104236","doi":"10.6084/m9.figshare.20486767","title":"Additional file 2 of Mendelian randomization of circulating proteome identifies actionable targets in heart failure","year":2022,"lang":"en","type":"dataset","venue":"Open MIND","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Institut universitaire de cardiologie et de pneumologie de Québec","funders":"","keywords":"Mendelian randomization; Heart failure; Computational biology; Proteome; Bioinformatics; Computer science; Biology; Genetics; Medicine; Internal medicine; Gene; Genetic variants","score_opus":0.009597533935198193,"score_gpt":0.269653126541891,"score_spread":0.2600555926066928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394104236","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010131401,0.000012331731,0.000009316091,0.000022466042,0.000041502168,0.000510948,0.998957,3.1258256e-7,0.00034481668],"genre_scores_gemma":[0.000032868316,0.000004272292,0.009155257,0.000012857588,0.00003973611,0.00029787442,0.9896349,0.000009706688,0.0008125442],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99888855,0.00010332366,0.0004646619,0.00020638811,0.00022022534,0.00011687206],"domain_scores_gemma":[0.99896884,0.00010082752,0.00054203894,0.00028710463,0.00007852702,0.000022634957],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00025073733,0.00013233158,0.0002791646,0.0001147526,0.000059327285,0.00002945272,0.0003399074,0.00016641163,0.90629774],"category_scores_gemma":[0.0010136875,0.00014168663,0.00007077455,0.00013157364,0.00004088821,0.000012358774,0.0003962511,0.00020184903,0.00002523017],"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":[0.00006981679,0.000044123703,0.0000031922843,0.000097509364,0.000038056703,6.9390245e-7,0.000015299798,0.0011062905,0.0018800393,7.1302324e-8,0.996624,0.000120941106],"study_design_scores_gemma":[0.0006180345,0.00005809048,0.000028119852,0.00010997539,0.000011483357,0.000008768125,0.00008796181,0.0001164809,0.0024887808,0.0000041141498,0.9963375,0.00013073439],"about_ca_topic_score_codex":0.00008855506,"about_ca_topic_score_gemma":0.00015700192,"teacher_disagreement_score":0.90627253,"about_ca_system_score_codex":0.000020598109,"about_ca_system_score_gemma":0.00022881717,"threshold_uncertainty_score":0.5777813},"labels":[],"label_agreement":null},{"id":"W4394420788","doi":"10.6084/m9.figshare.5123815","title":"Supplementary Material for: Detection of Phenotype Modifier Genes Using Two-Locus Linkage Analysis in Complex Disorders Such as Major Psychosis","year":2012,"lang":"en","type":"dataset","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychosis; Locus (genetics); Phenotype; Genetics; Genetic linkage; Gene; Linkage (software); Psychology; Biology; Computational biology; Psychiatry","score_opus":0.024512006684689492,"score_gpt":0.3171049134520692,"score_spread":0.2925929067673797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394420788","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049888096,0.0001327472,0.00006876119,0.00000748165,0.00012359039,0.0004518046,0.9942058,0.0000052053756,0.000015853455],"genre_scores_gemma":[0.016411182,0.000030880077,0.00071333104,0.00006603488,0.00033882892,0.000123874,0.98227566,0.000029955378,0.000010219466],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99863154,0.00007435824,0.0004890041,0.0003011173,0.00018079451,0.00032319422],"domain_scores_gemma":[0.99885017,0.000022209364,0.00043982585,0.0005497666,0.00007752619,0.000060502418],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00010314698,0.00030155905,0.00038423244,0.0002623848,0.0000689677,0.00003402036,0.00035008925,0.000366083,0.047936257],"category_scores_gemma":[0.0001305699,0.00031432067,0.0002372405,0.00023245488,0.0000143851275,0.000006398046,0.00020593562,0.00015998422,0.000028124654],"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":[0.000166038,0.000086580345,0.00020935768,0.0009817175,0.00060536055,4.2505346e-7,0.000021485244,0.0012810528,0.01236723,1.6229153e-7,0.9831359,0.0011447112],"study_design_scores_gemma":[0.0006776508,0.00015119783,0.00026275762,0.000102379476,0.00052322866,0.0000021012766,0.000020099564,0.0020055522,0.009659455,0.0000043902146,0.9861782,0.0004129488],"about_ca_topic_score_codex":0.0015071023,"about_ca_topic_score_gemma":0.004437483,"teacher_disagreement_score":0.04790813,"about_ca_system_score_codex":0.000035883557,"about_ca_system_score_gemma":0.000041089854,"threshold_uncertainty_score":0.99993086},"labels":[],"label_agreement":null},{"id":"W4394490698","doi":"10.6084/m9.figshare.14955745","title":"An enhanced methodology for predicting protein-protein interactions between human and hepatitis C virus via ensemble learning algorithms","year":2021,"lang":"en","type":"dataset","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Hepatitis a virus; Ensemble learning; Artificial intelligence; Machine learning; Algorithm; Computational biology; Virology; Virus; Biology","score_opus":0.04760507165260212,"score_gpt":0.35514465215657076,"score_spread":0.3075395805039686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394490698","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027701196,0.00014063875,0.0035982067,0.000011101074,0.000065012944,0.0008961471,0.99243337,0.000042001833,0.000043395252],"genre_scores_gemma":[0.0014546477,0.00001663113,0.012446246,0.000052437772,0.0009206028,0.0010540198,0.983731,0.00005812444,0.00026633136],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99801403,0.0003917306,0.00047284138,0.00059044524,0.00015381201,0.00037711556],"domain_scores_gemma":[0.9983871,0.00013056511,0.0005465685,0.0005636264,0.00023443252,0.00013773642],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00023872565,0.0003795561,0.00044687444,0.00009998464,0.00038859583,0.0001233221,0.00034952283,0.000598376,0.0037144888],"category_scores_gemma":[0.002999909,0.0004207837,0.00012860839,0.0000800331,0.000020589137,0.00001928272,0.00037853254,0.0008091368,0.000034853074],"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":[0.00002446687,0.00005176542,0.000031648375,0.001599757,0.0002473658,0.000006761615,0.00007123076,0.00005737544,0.22813839,5.3361464e-7,0.7594403,0.010330427],"study_design_scores_gemma":[0.00029304955,0.0006979303,0.00008485214,0.0009296668,0.00005811988,0.000018837729,0.00002195814,0.00033536632,0.14492957,0.00001444523,0.8521608,0.00045536974],"about_ca_topic_score_codex":0.0002601679,"about_ca_topic_score_gemma":0.00058394106,"teacher_disagreement_score":0.09272055,"about_ca_system_score_codex":0.000029293295,"about_ca_system_score_gemma":0.000096783035,"threshold_uncertainty_score":0.9998244},"labels":[],"label_agreement":null},{"id":"W4394543423","doi":"10.6084/m9.figshare.22188034","title":"An approach combining deep learning and molecule docking for drug discovery of cathepsin L","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Ottawa","funders":"","keywords":"Drug discovery; Docking (animal); Computational biology; Computer science; Chemistry; Artificial intelligence; Biology; Biochemistry; Medicine","score_opus":0.01470448301920448,"score_gpt":0.2860187244589894,"score_spread":0.27131424143978494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394543423","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032838245,0.000345596,0.00006217357,0.0000037006428,0.00004569962,0.00031963707,0.99877566,0.000023833807,0.00009529573],"genre_scores_gemma":[0.0010864155,0.000045094734,0.0007088781,0.00004012346,0.00015184694,0.00015617235,0.99758184,0.000056539786,0.00017307611],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988238,0.0000729849,0.00030920206,0.0003709885,0.0001573703,0.00026564393],"domain_scores_gemma":[0.9989761,0.00007736753,0.00038915797,0.00040929555,0.000084648185,0.00006340139],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015023378,0.00027243956,0.00030007618,0.00008928788,0.000121436664,0.00010217853,0.000374118,0.0003061299,0.00014918785],"category_scores_gemma":[0.0011960847,0.00027438204,0.000104588755,0.00008312241,0.000018785715,0.000010850141,0.0003573742,0.0003425304,0.000035184454],"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":[0.000020895148,0.00003090793,0.000014516229,0.0018743082,0.000058932816,0.0000012525269,0.00006901351,0.00089028064,0.00036250424,0.0000013711114,0.9964122,0.00026377427],"study_design_scores_gemma":[0.00049588736,0.0002998136,0.000052628504,0.00086758734,0.000057807134,0.000014100905,0.00025085255,0.009700613,0.0012930721,0.000006771512,0.9864187,0.0005421612],"about_ca_topic_score_codex":0.0000342568,"about_ca_topic_score_gemma":0.00002212954,"teacher_disagreement_score":0.009993539,"about_ca_system_score_codex":0.000009753066,"about_ca_system_score_gemma":0.000054264445,"threshold_uncertainty_score":0.99997085},"labels":[],"label_agreement":null},{"id":"W4394571530","doi":"10.1080/15376516.2024.2338907","title":"A QSAR study for predicting malformation in zebrafish embryo","year":2024,"lang":"en","type":"article","venue":"Toxicology Mechanisms and Methods","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Artificial intelligence; Quantitative structure–activity relationship; Gradient boosting; Machine learning; Test set; Computer science; Artificial neural network; Multilayer perceptron; Random forest; Logistic regression; Boosting (machine learning); Set (abstract data type); Data mining; Pattern recognition (psychology)","score_opus":0.01488848232790524,"score_gpt":0.3627183023871743,"score_spread":0.34782982005926905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394571530","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":[0.42514724,0.00021287221,0.5727882,0.00011222779,0.00041718007,0.00065455836,0.00000764278,0.00003983025,0.0006202517],"genre_scores_gemma":[0.53960276,0.000024955514,0.45914388,0.0003918952,0.0001189492,0.00020455028,0.000040908177,0.000025397741,0.0004466954],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896187,0.0002332185,0.0002851842,0.00024366364,0.00005466836,0.0002213725],"domain_scores_gemma":[0.9996164,0.000109459004,0.000053643224,0.00014979382,0.000025047773,0.000045663503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021937871,0.00012971938,0.00016886748,0.00011037208,0.000072682225,0.00004122431,0.00009443713,0.00019141527,0.000015391268],"category_scores_gemma":[0.00034251533,0.000118269985,0.000043133554,0.00009230887,0.000022775745,0.00001002138,0.000108268345,0.00015370651,0.0000017810166],"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":[0.00017783161,0.00021321737,0.0011584663,0.0004456441,0.00016170103,0.000008694217,0.0034419799,0.00039923278,0.85656756,0.021215813,0.00052822614,0.115681656],"study_design_scores_gemma":[0.0056220265,0.0132432,0.013123966,0.00017431828,0.00030733584,0.00032253747,0.007964222,0.59560096,0.26233956,0.026108254,0.07383895,0.0013546227],"about_ca_topic_score_codex":0.0000063605485,"about_ca_topic_score_gemma":0.00003056714,"teacher_disagreement_score":0.59520173,"about_ca_system_score_codex":0.000016673235,"about_ca_system_score_gemma":0.000040506908,"threshold_uncertainty_score":0.48229098},"labels":[],"label_agreement":null},{"id":"W4394769874","doi":"10.1093/bioinformatics/btae196","title":"Effect of tokenization on transformers for biological sequences","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"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; Azrieli Foundation; Israel Science Foundation","keywords":"Lexical analysis; Computer science; Artificial intelligence; Natural language processing; Biological network; Inference; Security token; Machine learning; Computational biology; Biology","score_opus":0.009661397653894933,"score_gpt":0.2905729843578977,"score_spread":0.28091158670400274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394769874","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73067147,0.00044915028,0.2509752,0.0002148511,0.0008066813,0.0013327765,0.00021669529,0.00013254555,0.015200628],"genre_scores_gemma":[0.9914115,0.00015694032,0.007494724,0.00013632957,0.00011206434,0.000036390058,0.00048134147,0.0000160827,0.00015461698],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999221,0.000030633473,0.00035278115,0.00009998439,0.00012447487,0.00017110104],"domain_scores_gemma":[0.99960977,0.00011416038,0.00007425448,0.00011844656,0.000039993567,0.000043388023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048193248,0.00014927675,0.00015847679,0.00007657011,0.000046863242,0.00003243941,0.00012335464,0.00016518762,0.00001243461],"category_scores_gemma":[0.00023561704,0.00010182254,0.00013197157,0.00011399437,0.00007814601,0.000010434945,0.00002078402,0.000079205456,0.000019236972],"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":[0.0018605442,0.00012951884,0.0033180104,0.012153691,0.00063975,0.00000282062,0.0023874226,0.0055032843,0.10392743,0.0116519,0.022442082,0.8359836],"study_design_scores_gemma":[0.001263536,0.014036489,0.00016174022,0.00029518924,0.00009400266,0.000034376335,0.00019513356,0.29477412,0.5435262,0.00010620904,0.1449502,0.0005628031],"about_ca_topic_score_codex":0.0000011201664,"about_ca_topic_score_gemma":5.676803e-7,"teacher_disagreement_score":0.8354207,"about_ca_system_score_codex":0.000012083636,"about_ca_system_score_gemma":0.000043207587,"threshold_uncertainty_score":0.41522026},"labels":[],"label_agreement":null},{"id":"W4394930608","doi":"10.1101/2024.04.15.589672","title":"ProSST: Protein Language Modeling with Quantized Structure and Disentangled Attention","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Shanghai Jiao Tong University; Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Linguistics; Natural language processing; Philosophy","score_opus":0.005088720207963003,"score_gpt":0.21787876026098393,"score_spread":0.21279004005302093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394930608","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9925385,0.0015395745,0.004205679,0.000109845525,0.00021652783,0.000998395,0.00021410327,0.00016734924,0.000010023116],"genre_scores_gemma":[0.9864587,0.00004533333,0.012836574,0.000055240387,0.0003299475,0.000112734444,0.000007487984,0.00013178423,0.00002215079],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981963,0.000073870026,0.00036374587,0.00074243767,0.00027097418,0.0003526554],"domain_scores_gemma":[0.99864197,0.0000046258037,0.0002291502,0.00080947473,0.00017156902,0.00014321759],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023380607,0.00048602663,0.00034179108,0.000120737226,0.00010693206,0.00028078846,0.0002637844,0.0004974758,0.000008515438],"category_scores_gemma":[0.00009146493,0.00042035137,0.00008728209,0.0001561636,0.0000890162,0.000008394884,0.0007193645,0.0007393782,0.000008556524],"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":[0.00009257745,0.000025776413,0.0019464247,0.0013453858,0.0001880912,0.000022857841,0.000022374932,0.0006184507,0.9953846,0.00032010503,0.000030862273,0.0000025143233],"study_design_scores_gemma":[0.0027426335,0.0005415477,0.008390356,0.002970503,0.0006482844,7.424844e-7,0.000051211784,0.18043973,0.80023885,0.000031814914,0.0008835239,0.003060828],"about_ca_topic_score_codex":0.000025303872,"about_ca_topic_score_gemma":0.000007630857,"teacher_disagreement_score":0.19514574,"about_ca_system_score_codex":0.00004588994,"about_ca_system_score_gemma":0.00023153586,"threshold_uncertainty_score":0.9998248},"labels":[],"label_agreement":null},{"id":"W4394989484","doi":"10.1038/s41598-024-59487-5","title":"DeepReg: a deep learning hybrid model for predicting transcription factors in eukaryotic and prokaryotic genomes","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Wilfrid Laurier University","funders":"Dirección General de Asuntos del Personal Académico, Universidad Nacional Autónoma de México; Consejo Nacional de Ciencia y Tecnología","keywords":"Overfitting; Convolutional neural network; Deep learning; Computer science; Artificial intelligence; Computational biology; Transcription factor; Variance (accounting); Genome; Machine learning; Promoter; Artificial neural network; Biology; Gene; Genetics; Gene expression","score_opus":0.011261885128348324,"score_gpt":0.24753977752620726,"score_spread":0.23627789239785893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394989484","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9505953,0.0015499624,0.045899622,0.000030195632,0.0010843995,0.00044554324,0.0000029747869,0.000058235615,0.000333771],"genre_scores_gemma":[0.9952809,0.000027908838,0.002503703,0.000009714085,0.00004989333,0.0000374846,0.00025983131,0.000025741909,0.001804778],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985639,0.00002985709,0.0003985713,0.00055305014,0.00017455792,0.00028007815],"domain_scores_gemma":[0.99950904,0.000020524849,0.000096402226,0.00025518713,0.000048811922,0.00007006247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000927769,0.00014960064,0.00013082327,0.00015999818,0.00018153309,0.00026814692,0.000075643366,0.0000747171,0.0000036578383],"category_scores_gemma":[0.00025446634,0.00013589812,0.00007610027,0.00013709922,0.00009968574,0.000023654737,0.00005200408,0.00016400694,0.0000010413962],"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":[0.000058303263,0.00012342051,0.39406022,0.002175558,0.0001327386,0.0000974112,0.012323089,0.27199715,0.29341435,0.00020601203,0.0010016405,0.024410076],"study_design_scores_gemma":[0.000113320944,0.00006858934,0.0020611982,0.00007375678,0.000026636004,0.0001506436,0.00016852084,0.98433733,0.008982409,0.0010730778,0.0027611011,0.00018344354],"about_ca_topic_score_codex":0.0000047499652,"about_ca_topic_score_gemma":0.000025666672,"teacher_disagreement_score":0.7123401,"about_ca_system_score_codex":0.00002566716,"about_ca_system_score_gemma":0.000086356,"threshold_uncertainty_score":0.55417645},"labels":[],"label_agreement":null},{"id":"W4395082224","doi":"10.1002/prot.26694","title":"Exploiting protein language models for the precise classification of ion channels and ion transporters","year":2024,"lang":"en","type":"article","venue":"Proteins Structure Function and Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Robustness (evolution); Computer science; Random forest; Generalization; Artificial intelligence; Machine learning; Biology; Mathematics","score_opus":0.011842120339021248,"score_gpt":0.23731795898509514,"score_spread":0.2254758386460739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395082224","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40867993,0.00093302433,0.5878195,0.00029468542,0.0003158481,0.0016260498,0.00009392826,0.00004613598,0.00019091065],"genre_scores_gemma":[0.9870985,0.0000837725,0.012131492,0.000052970285,0.0002004479,0.00009085734,0.00021294453,0.000015884356,0.000113127615],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992589,0.000015740688,0.0003292086,0.0001310001,0.00013010726,0.00013508831],"domain_scores_gemma":[0.9995674,0.000021119236,0.0001402976,0.00017106271,0.000060126597,0.000039987488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022789568,0.000147379,0.00011209882,0.000066184606,0.00012692067,0.000083159866,0.00007310859,0.00013856275,0.0000054798084],"category_scores_gemma":[0.000048509173,0.000097398486,0.000049734354,0.00008712497,0.00007636856,0.00004072393,0.000029910016,0.00012540017,3.4556228e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045536854,0.000024595558,0.00014152272,0.0049584494,0.00021176988,3.0723686e-7,0.007734193,0.0023280038,0.6922941,0.007971707,0.00033557604,0.28354436],"study_design_scores_gemma":[0.00070432766,0.0006482533,0.00050791015,0.0002523428,0.000103517326,0.000030820873,0.0029392266,0.90122885,0.086326584,0.0015716454,0.005392452,0.00029406647],"about_ca_topic_score_codex":0.0000059804397,"about_ca_topic_score_gemma":0.0000070418428,"teacher_disagreement_score":0.89890087,"about_ca_system_score_codex":0.0000075555554,"about_ca_system_score_gemma":0.000028875787,"threshold_uncertainty_score":0.39717948},"labels":[],"label_agreement":null},{"id":"W4395956350","doi":"10.1101/2024.04.23.590744","title":"An AI-informed NMR structure reveals a LETM1 F-EF-hand for two-way mitochondrial calcium regulation.","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"EF hand; Calcium; Chemistry; Calcium-binding protein; Organic chemistry","score_opus":0.00955399890042232,"score_gpt":0.2689555653909858,"score_spread":0.2594015664905635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395956350","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9551118,0.0010809996,0.03244219,0.0005066559,0.004579786,0.003025706,0.00283396,0.00036955607,0.000049330207],"genre_scores_gemma":[0.96141034,0.000027207228,0.0333285,0.00061700644,0.0039268686,0.00030323328,0.000059278667,0.00024170602,0.00008585732],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9965756,0.0001273849,0.00093950145,0.001168783,0.0004384222,0.00075029],"domain_scores_gemma":[0.9962812,0.000046988644,0.0005799755,0.0020240506,0.0007021268,0.00036564338],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042131878,0.00083955616,0.0006598211,0.00026436307,0.00029188566,0.00067366636,0.0008695549,0.001265932,0.000056552315],"category_scores_gemma":[0.00060841226,0.00084233715,0.00033429035,0.00027260947,0.00020065247,0.000026401087,0.000738532,0.0010405345,0.000032746688],"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":[0.0001703144,0.000044208027,0.00038965952,0.0012450706,0.0002660404,0.000005105778,0.000028977793,0.0019596478,0.98700756,0.00079930824,0.008076011,0.000008084693],"study_design_scores_gemma":[0.0019195256,0.00043217008,0.00428591,0.00048351465,0.00036418866,2.563118e-7,0.0000059167364,0.011677449,0.90844125,0.00008578194,0.070526704,0.0017773304],"about_ca_topic_score_codex":0.000028056218,"about_ca_topic_score_gemma":0.000018262168,"teacher_disagreement_score":0.07856632,"about_ca_system_score_codex":0.00017361616,"about_ca_system_score_gemma":0.001060047,"threshold_uncertainty_score":0.99940276},"labels":[],"label_agreement":null},{"id":"W4396515244","doi":"10.1089/cmb.2024.0483","title":"On Minimizers and Convolutional Filters: Theoretical Connections and Applications to Genome Analysis","year":2024,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Convolutional neural network; Categorical variable; Computer science; Pooling; Sequence (biology); Initialization; Hash function; Pattern recognition (psychology); Artificial intelligence; Mathematics; Algorithm; Biology; Machine learning; Genetics","score_opus":0.00539845112460039,"score_gpt":0.28790181847405233,"score_spread":0.2825033673494519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396515244","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.403716,0.00061363773,0.5928514,0.0021283748,0.00009087423,0.00009807022,0.000085522515,0.000007652567,0.00040846426],"genre_scores_gemma":[0.985846,0.00004098137,0.013153667,0.00062489405,0.00016779432,0.000005527108,0.00012829782,0.000004877078,0.00002797237],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99943537,0.000050959217,0.00024157333,0.00012011642,0.00007137779,0.00008061587],"domain_scores_gemma":[0.9994412,0.00024151443,0.00006760917,0.00005392318,0.00011038861,0.00008533295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021050137,0.00007443074,0.00012844996,0.00023622357,0.000057479818,0.000030168441,0.000063606756,0.00006689366,0.000043500262],"category_scores_gemma":[0.000107844804,0.000060805465,0.000068190326,0.0001582812,0.0001748302,0.0000037560562,0.000040368755,0.00010745024,0.0000058361616],"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":[0.0001771893,0.000056416444,0.0021750955,0.000033552275,0.0013953629,0.0000033427207,0.0001610284,0.12989861,0.0062952247,0.8551042,0.0011157463,0.0035842455],"study_design_scores_gemma":[0.002618771,0.006929037,0.10094893,0.000093253606,0.0015585456,0.002070193,0.0004373578,0.19674219,0.00052964134,0.37171048,0.31525275,0.0011088706],"about_ca_topic_score_codex":5.804894e-7,"about_ca_topic_score_gemma":6.0975907e-7,"teacher_disagreement_score":0.58213,"about_ca_system_score_codex":0.000011609137,"about_ca_system_score_gemma":0.000056125882,"threshold_uncertainty_score":0.24795748},"labels":[],"label_agreement":null},{"id":"W4398160571","doi":"10.1101/2024.05.17.594647","title":"<i>π</i> -PrimeNovo: An Accurate and Efficient Non-Autoregressive Deep Learning Model for De Novo Peptide Sequencing","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Autoregressive model; Computational biology; Deep learning; Artificial intelligence; Computer science; STAR model; Machine learning; Biology; Econometrics; Autoregressive integrated moving average; Mathematics; Time series","score_opus":0.010988509871869525,"score_gpt":0.25011411746013207,"score_spread":0.23912560758826254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398160571","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88596076,0.0012242057,0.11117677,0.000066961475,0.000384404,0.00080391724,0.00015130831,0.00019851852,0.000033169825],"genre_scores_gemma":[0.9434289,0.0001625841,0.055150364,0.00024447957,0.0004911037,0.00025280926,0.0000071887825,0.000217135,0.00004547344],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997188,0.00010463714,0.00057878136,0.0010996984,0.0002660777,0.0007628424],"domain_scores_gemma":[0.9977864,0.00004224884,0.00046650463,0.0009542038,0.0004007913,0.0003498224],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009377337,0.0006896806,0.0004890723,0.0001857657,0.00029016365,0.0003936002,0.00054126116,0.0007811175,0.0000033981632],"category_scores_gemma":[0.000444992,0.0007229225,0.00017575185,0.0001333551,0.00014937315,0.000012746438,0.0012189791,0.0011466296,0.0000111146],"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":[0.000060061622,0.000037673137,0.0005803366,0.0010331548,0.0001655996,0.000016767443,0.00016628807,0.23872168,0.75895077,0.00017234612,0.00008624149,0.0000090511985],"study_design_scores_gemma":[0.00046734538,0.00016609197,0.00049229,0.0003385345,0.00015971802,3.1293465e-7,0.000020482006,0.8348566,0.16184953,0.000007816735,0.00083154003,0.00080972345],"about_ca_topic_score_codex":0.00001968628,"about_ca_topic_score_gemma":0.000005740899,"teacher_disagreement_score":0.5971013,"about_ca_system_score_codex":0.00024538825,"about_ca_system_score_gemma":0.00096524134,"threshold_uncertainty_score":0.9995222},"labels":[],"label_agreement":null},{"id":"W4398163671","doi":"10.1109/dcc58796.2024.00076","title":"Another virtue of wavelet forests","year":2024,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Cache; Locality of reference; Parallel computing; Theoretical computer science","score_opus":0.005198010677047838,"score_gpt":0.25374267929763294,"score_spread":0.2485446686205851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398163671","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.687889,0.0008247842,0.09349806,0.0004988196,0.00036400105,0.00018886491,0.00002155383,0.000080853504,0.21663406],"genre_scores_gemma":[0.9882697,0.000013798654,0.0043404414,0.00020356294,0.00007253591,0.0000023728057,0.000028755732,0.00001259742,0.007056272],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996559,0.000009393786,0.00011561821,0.00008389196,0.000060413207,0.00007478877],"domain_scores_gemma":[0.99977785,0.000006919897,0.000017665225,0.00016467397,0.000017173383,0.000015726288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000082317725,0.000058562175,0.000052748543,0.00002515642,0.000009545936,0.00001177164,0.00008230769,0.000061234,0.00013765588],"category_scores_gemma":[0.00003221366,0.00004500176,0.000045268025,0.000045212248,0.000029197014,0.0000013938242,0.0000483002,0.0000446023,0.000043561646],"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":[0.00007733402,0.000085704196,0.015421324,0.00073658786,0.00030553187,0.000009569036,0.0003182907,0.00053161534,0.72187287,0.04769989,0.14964277,0.063298546],"study_design_scores_gemma":[0.0002614277,0.00037471793,0.004687936,0.000048153917,0.000017083043,0.000032788343,0.000038693266,0.021457989,0.41461435,0.0004513204,0.5577686,0.0002469666],"about_ca_topic_score_codex":0.000007902577,"about_ca_topic_score_gemma":0.000018350298,"teacher_disagreement_score":0.40812582,"about_ca_system_score_codex":0.0000023341838,"about_ca_system_score_gemma":0.000023837483,"threshold_uncertainty_score":0.18351187},"labels":[],"label_agreement":null},{"id":"W4398201885","doi":"10.1016/j.foodchem.2024.139747","title":"Feature fusion-based food protein subcellular prediction for drug composition","year":2024,"lang":"en","type":"article","venue":"Food Chemistry","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Lockheed Martin (Canada)","funders":"AlMaarefa University","keywords":"Composition (language); Feature (linguistics); Fusion; Computational biology; Pseudo amino acid composition; Artificial intelligence; Chemistry; Computer science; Pattern recognition (psychology); Subcellular localization; Biology; Biochemistry","score_opus":0.0043135967850967735,"score_gpt":0.21193287786760293,"score_spread":0.20761928108250616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398201885","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97434783,0.0014111534,0.019428315,0.0011536323,0.00024356149,0.0006378994,0.00059068965,0.00019102563,0.0019958871],"genre_scores_gemma":[0.99030226,0.0000052986493,0.0032859812,0.00008656683,0.0005728066,0.00015445391,0.0037970692,0.000039935014,0.0017556188],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99913687,0.000014852715,0.00016887736,0.00030397557,0.0001592049,0.00021623397],"domain_scores_gemma":[0.99946606,0.000015115024,0.00006337854,0.00030976848,0.00007200579,0.000073663214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013862118,0.00019150716,0.00011057456,0.000022278171,0.00010780843,0.000072627416,0.00016172693,0.00025707725,0.000029631507],"category_scores_gemma":[0.000045132423,0.00018800616,0.00014618838,0.00008240352,0.00003967585,0.0000051515185,0.000049578735,0.0002184733,0.000005483303],"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":[0.00006715299,0.000037115013,0.000044239117,0.0009548903,0.00006599572,9.195331e-7,0.000031126434,0.00030439146,0.98592544,0.000036302583,0.012123065,0.00040938467],"study_design_scores_gemma":[0.00040756178,0.00034617286,0.000008494275,0.00012869168,0.00003056743,0.000012088847,0.000022514687,0.014829181,0.8902308,0.000068383975,0.093730636,0.00018491596],"about_ca_topic_score_codex":5.694307e-7,"about_ca_topic_score_gemma":9.833717e-7,"teacher_disagreement_score":0.095694624,"about_ca_system_score_codex":0.000031904437,"about_ca_system_score_gemma":0.000099678284,"threshold_uncertainty_score":0.7666669},"labels":[],"label_agreement":null},{"id":"W4399303086","doi":"10.1038/s42003-024-06332-0","title":"SOFB is a comprehensive ensemble deep learning approach for elucidating and characterizing protein-nucleic-acid-binding residues","year":2024,"lang":"en","type":"article","venue":"Communications Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"University of Toronto","funders":"Fundamental Research Funds for the Central Universities; People's Government of Jilin Province; National Natural Science Foundation of China","keywords":"Interpretability; Nucleic acid; Artificial intelligence; Computer science; Deep learning; Machine learning; Sequence (biology); Computational biology; Chemistry; Biology; Biochemistry","score_opus":0.02940020867987616,"score_gpt":0.3119802113803305,"score_spread":0.28258000270045436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399303086","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8122747,0.0138411755,0.16362765,0.0019214445,0.00013115001,0.0013873134,0.00008492024,0.00025159636,0.006480071],"genre_scores_gemma":[0.8541277,0.0006723524,0.14275126,0.0002551531,0.0000920108,0.00020999867,0.0015404922,0.000037162983,0.00031387922],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988856,0.00018401936,0.00030871673,0.00031080283,0.00004213466,0.00026877545],"domain_scores_gemma":[0.99887884,0.00010954006,0.00013072346,0.00073210563,0.000096907446,0.000051882063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000304396,0.00017885686,0.00019226618,0.00009816319,0.0004873552,0.000105161416,0.0004579868,0.0002061924,0.0000063673774],"category_scores_gemma":[0.00024827124,0.00017439053,0.00007200041,0.00011426601,0.00022245887,0.00001300586,0.00067411724,0.00033905936,0.000009490131],"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":[0.000020155856,0.000019160421,0.0011913052,0.00021227419,0.000092933464,1.6654921e-7,0.0008681108,0.000014629949,0.9709016,0.0029731493,0.00012896513,0.023577558],"study_design_scores_gemma":[0.0007741566,0.0008333718,0.0007600389,0.00022648554,0.00009518706,0.000119994205,0.002011199,0.23884425,0.1557978,0.0006501971,0.5990036,0.0008837163],"about_ca_topic_score_codex":0.0000074615727,"about_ca_topic_score_gemma":0.0000052430064,"teacher_disagreement_score":0.81510377,"about_ca_system_score_codex":0.000017290953,"about_ca_system_score_gemma":0.000036975576,"threshold_uncertainty_score":0.7111439},"labels":[],"label_agreement":null},{"id":"W4399758963","doi":"10.21203/rs.3.rs-4514116/v1","title":"Non-hemolytic Peptide Classification Using a Quantum Support Vector Machine","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Support vector machine; Peptide; Quantum; Computer science; Artificial intelligence; Vector (molecular biology); Machine learning; Computational biology; Chemistry; Physics; Biology; Biochemistry; Gene; Quantum mechanics","score_opus":0.060070767687712336,"score_gpt":0.4097219323551926,"score_spread":0.34965116466748025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399758963","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9739851,0.0020009694,0.0033019022,0.001333295,0.001061496,0.0021231312,0.00049993256,0.0001464666,0.015547707],"genre_scores_gemma":[0.99082464,0.00030088192,0.0020055273,0.000060473165,0.00079099456,0.00011941392,0.0023126248,0.00012817106,0.003457303],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99667394,0.00025335717,0.0005556859,0.00081634487,0.00095298176,0.0007477096],"domain_scores_gemma":[0.9976638,0.00005732865,0.00018449561,0.0013795693,0.0004815936,0.0002331954],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0018159471,0.00039633707,0.00035031547,0.00040183097,0.00020844379,0.00029864852,0.0007400312,0.0006994586,0.00016350557],"category_scores_gemma":[0.0006827163,0.00037590906,0.0002765987,0.00031652878,0.00020842568,0.0000044056474,0.0029888425,0.0024635843,0.0004275946],"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":[0.0009935745,0.0010686265,0.027499173,0.04430226,0.0017374165,0.00037917815,0.0036413018,0.0139605645,0.7193036,0.005105263,0.17119369,0.010815355],"study_design_scores_gemma":[0.0007966108,0.001218912,0.009058567,0.0021221212,0.00013907565,0.00014792958,0.0006397109,0.8993841,0.017755419,0.0025042074,0.06477971,0.0014536784],"about_ca_topic_score_codex":0.00023280959,"about_ca_topic_score_gemma":0.0000431061,"teacher_disagreement_score":0.8854235,"about_ca_system_score_codex":0.00023037747,"about_ca_system_score_gemma":0.0011635877,"threshold_uncertainty_score":0.9998693},"labels":[],"label_agreement":null},{"id":"W4400228131","doi":"10.1109/tai.2024.3421176","title":"StackAMP: Stacking-Based Ensemble Classifier for Antimicrobial Peptide Identification","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Classifier (UML); Stacking; Identification (biology); Artificial intelligence; Antimicrobial; Computational biology; Computer science; Ensemble learning; Machine learning; Pattern recognition (psychology); Biology; Chemistry; Microbiology","score_opus":0.033656301419975644,"score_gpt":0.3175476373886711,"score_spread":0.2838913359686954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400228131","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029643336,0.00003153721,0.96764785,0.00043784003,0.001349768,0.00039333114,0.00012657327,0.00009843756,0.0002713063],"genre_scores_gemma":[0.9926149,0.000028410788,0.0053725797,0.00028868674,0.00018971579,0.00007620636,0.00008686836,0.000042488256,0.0013001465],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998678,0.00004484069,0.00045441336,0.0003890238,0.00016014569,0.0002735765],"domain_scores_gemma":[0.9992881,0.00008397446,0.00007119032,0.00035992006,0.00012852866,0.00006831407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031770143,0.00019210344,0.00012233012,0.00014899584,0.0002221473,0.00020519744,0.00020315897,0.00016628516,0.00007071296],"category_scores_gemma":[0.000038357717,0.00019742582,0.0001917112,0.00020674744,0.00010246161,0.000015773112,0.0000019353522,0.00022250232,0.0002162217],"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":[0.00027150157,0.00018383187,0.0000033717224,0.00019287961,0.00007124277,0.0000020726297,0.00021041889,0.15020649,0.7201477,0.0010625423,0.0023896915,0.12525825],"study_design_scores_gemma":[0.000032076372,0.00019611916,0.000003333307,0.000046135265,0.000031275664,0.000004033789,0.000060926173,0.17862663,0.80627036,0.00030187893,0.0142304795,0.00019676612],"about_ca_topic_score_codex":0.0000124027065,"about_ca_topic_score_gemma":0.00011408782,"teacher_disagreement_score":0.96297157,"about_ca_system_score_codex":0.00004133855,"about_ca_system_score_gemma":0.00013703428,"threshold_uncertainty_score":0.8050791},"labels":[],"label_agreement":null},{"id":"W4400317002","doi":"10.1038/s41597-024-03585-6","title":"Author Correction: PLAS-20k: Extended Dataset of Protein-Ligand Affinities from MD Simulations for Machine Learning Applications","year":2024,"lang":"en","type":"erratum","venue":"Scientific Data","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Affinities; Binding affinities; Ligand (biochemistry); Computer science; Computational biology; Artificial intelligence; Chemistry; Biology; Stereochemistry; Biochemistry; Receptor","score_opus":0.035606005382448236,"score_gpt":0.3239491444120766,"score_spread":0.2883431390296284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400317002","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001663232,0.0055849575,0.06727933,0.0002523505,0.030251114,0.002447688,0.89061034,0.000118883785,0.003288983],"genre_scores_gemma":[0.0012915191,0.000046013836,0.006501336,0.000019678375,0.0009675696,0.00012628852,0.7630114,0.000053471107,0.22798273],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975558,0.00006997776,0.0006564376,0.0010441623,0.00038244305,0.0002912136],"domain_scores_gemma":[0.99636817,0.000093574046,0.00051001686,0.0027282822,0.0002109485,0.00008899658],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00074471266,0.00032093315,0.00032294044,0.00020621724,0.0004824552,0.00041162476,0.0015604022,0.00040079196,0.00012623746],"category_scores_gemma":[0.0009951049,0.00031165493,0.0000921304,0.00030854403,0.00034237688,0.000026453632,0.0014479397,0.00068124203,0.00006780475],"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":[0.000026548934,0.000051947707,0.000007308477,0.00036225107,0.00013331862,4.2267624e-7,0.00006808028,0.00040025526,0.004226077,0.00006544673,0.9921429,0.0025154],"study_design_scores_gemma":[0.00016716556,0.00007710013,0.0000043285277,0.00014823583,0.00016448188,0.0000034083912,0.000081532184,0.09556891,0.0019587358,0.00021750032,0.901321,0.0002876089],"about_ca_topic_score_codex":0.00006827178,"about_ca_topic_score_gemma":0.00038655318,"teacher_disagreement_score":0.22469375,"about_ca_system_score_codex":0.00002064301,"about_ca_system_score_gemma":0.00050370564,"threshold_uncertainty_score":0.99993354},"labels":[],"label_agreement":null},{"id":"W4400519468","doi":"10.1007/978-981-97-5128-0_30","title":"Novel Fine-Tuning Strategy on Pre-trained Protein Model Enhances ACP Functional Type Classification","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.026989205554936,"score_gpt":0.27514997047628315,"score_spread":0.24816076492134714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400519468","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":[0.0037510507,0.00013797857,0.98552626,0.00024388258,0.0004753754,0.00032769205,0.000014948211,0.000042991054,0.009479814],"genre_scores_gemma":[0.8756486,0.000019882948,0.11204659,0.0005346286,0.00090302364,0.00002247767,0.00026184824,0.000059672326,0.010503237],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982866,0.000008786916,0.0003155802,0.00068871136,0.00042904698,0.00027125864],"domain_scores_gemma":[0.9990887,0.0000347715,0.00017159735,0.00048541382,0.00015673772,0.000062786],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000326775,0.00032121254,0.00018676385,0.00020934406,0.00011474909,0.00015603195,0.0005065613,0.00034536354,0.00001935878],"category_scores_gemma":[0.00010371522,0.0002786704,0.00006793076,0.00015188409,0.00027147014,0.000013322357,0.00023282607,0.00059636397,0.00002795488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061731575,0.000026585265,0.000004682495,0.00011002485,0.000023233819,0.0000020821278,0.00011927379,0.6353947,0.30229232,0.009733283,0.00006500959,0.05216706],"study_design_scores_gemma":[0.00014009658,0.00039945956,0.00005816781,0.0002681175,0.000009122199,0.000014806867,2.7328318e-7,0.97112983,0.017336037,0.009151344,0.001129163,0.00036356586],"about_ca_topic_score_codex":0.000003112867,"about_ca_topic_score_gemma":0.00003097687,"teacher_disagreement_score":0.87347966,"about_ca_system_score_codex":0.000069461414,"about_ca_system_score_gemma":0.00044437707,"threshold_uncertainty_score":0.99996656},"labels":[],"label_agreement":null},{"id":"W4400723454","doi":"10.1016/j.arbres.2024.07.007","title":"Protein Biomarkers in Lung Cancer Screening: Technical Considerations and Feasibility Assessment","year":2024,"lang":"es","type":"review","venue":"Archivos de Bronconeumología","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Public Health Ontario; University of Toronto","funders":"National Cancer Institute; Instituto de Salud Carlos III; Ministerio de Universidades; Centro de Investigación Biomédica en Red de Cáncer; Fundación Científica Asociación Española Contra el Cáncer; World Health Organization","keywords":"Lung cancer; Medicine; Context (archaeology); Lung cancer screening; Intensive care medicine; Cancer; Prognostics; Biomarker; Stage (stratigraphy); Biomarker discovery; Bioinformatics; Oncology; Internal medicine; Biology; Computer science; Proteomics","score_opus":0.02799291633436322,"score_gpt":0.38426187899453906,"score_spread":0.3562689626601758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400723454","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":[0.039670095,0.9419687,0.0029631683,0.0025881422,0.0003183609,0.006305992,0.00063480885,0.00012768865,0.005423046],"genre_scores_gemma":[0.23655707,0.709883,0.049719896,0.00044826118,0.00033619438,0.0016485043,0.0007623645,0.00018277243,0.00046194938],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959864,0.0008558231,0.0011875053,0.0010226102,0.00024443402,0.0007032322],"domain_scores_gemma":[0.9982853,0.0002294447,0.00039958284,0.000787775,0.000053237876,0.0002446858],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011340171,0.0007192187,0.0010828413,0.000281605,0.00017105127,0.0002016404,0.00035452604,0.00075300783,0.000059137416],"category_scores_gemma":[0.00060731755,0.0006416274,0.00033718577,0.00022596758,0.0006223879,0.000012004913,0.0008814841,0.0015484726,0.00000823701],"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":[0.00045115786,0.0016132573,0.20851462,0.17668445,0.008665372,0.0010639668,0.0010606371,0.00068176567,0.060435183,0.019496001,0.018726392,0.50260717],"study_design_scores_gemma":[0.005301232,0.0028810226,0.08411905,0.058787648,0.0065347166,0.0048424816,0.00026139244,0.046899837,0.00073748495,0.0046139536,0.77759314,0.0074280663],"about_ca_topic_score_codex":0.00028104128,"about_ca_topic_score_gemma":0.0003395889,"teacher_disagreement_score":0.7588667,"about_ca_system_score_codex":0.00027897552,"about_ca_system_score_gemma":0.001597901,"threshold_uncertainty_score":0.9996035},"labels":[],"label_agreement":null},{"id":"W4401769107","doi":"10.18280/isi.290419","title":"Using Neural Networks to Forecast the Configuration of Proteins","year":2024,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Computer science; Artificial intelligence","score_opus":0.017434958281580502,"score_gpt":0.2657189968654543,"score_spread":0.2482840385838738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401769107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15999126,0.0038435094,0.8250602,0.0006927403,0.0019901826,0.001126545,0.000080719314,0.00004611051,0.007168719],"genre_scores_gemma":[0.99380875,0.00008120352,0.0045728283,0.00034285162,0.0004360908,0.000041162933,0.00028822361,0.000022919125,0.00040597143],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983779,0.00011979313,0.0008101483,0.0001273961,0.00022407364,0.00034064165],"domain_scores_gemma":[0.9989677,0.000041766052,0.00029332418,0.00033047833,0.00028448363,0.0000822442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006183391,0.00023425155,0.00018677826,0.00013340196,0.00021682335,0.0003690176,0.00024578025,0.00026966832,0.000056987483],"category_scores_gemma":[0.00032626302,0.00019373163,0.0001290846,0.00043029632,0.0003038051,0.00019085206,0.00013410921,0.00025903556,0.000036244684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011137829,0.000022769143,0.00031364072,0.0027436647,0.00019858679,0.0000020814452,0.0094782645,0.5799943,0.004936298,0.01230202,0.0030163077,0.38688067],"study_design_scores_gemma":[0.00013847176,0.0003347714,0.00023018905,0.00052606064,0.000060678278,0.00012049996,0.00066720677,0.92666835,0.008163121,0.0001531118,0.0627083,0.00022926327],"about_ca_topic_score_codex":0.0001312412,"about_ca_topic_score_gemma":0.000022541295,"teacher_disagreement_score":0.8338175,"about_ca_system_score_codex":0.00012510155,"about_ca_system_score_gemma":0.00015552223,"threshold_uncertainty_score":0.7900146},"labels":[],"label_agreement":null},{"id":"W4402101910","doi":"10.5539/jmr.v16n4p11","title":"Protein Secondary Structure Prediction Using Convolutional Bidirectional GRU","year":2024,"lang":"en","type":"article","venue":"Journal of Mathematics Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Algorithm; Applied mathematics","score_opus":0.039971106993963806,"score_gpt":0.3709332738411034,"score_spread":0.33096216684713964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402101910","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97760344,0.001215238,0.018705446,0.00021602777,0.00043709716,0.00020195857,0.000069313755,0.000012756547,0.0015387487],"genre_scores_gemma":[0.93617135,0.00006007988,0.060826644,0.00001817967,0.0013431993,0.0000037338218,0.000035409685,0.00003609584,0.0015052943],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827445,0.00011795427,0.0005026805,0.00011019021,0.0007852162,0.00020951705],"domain_scores_gemma":[0.9990472,0.00006777675,0.0001423291,0.00015203182,0.00050460047,0.00008603719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018220536,0.00010035692,0.00013314266,0.00028892647,0.00012997244,0.00011274853,0.00020666339,0.0001505046,0.00023371601],"category_scores_gemma":[0.00054196094,0.00007982938,0.000103364306,0.00020517789,0.000118085685,0.000019425092,0.00010345196,0.00079953484,0.000011502218],"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":[0.000060933446,0.00011819755,0.00037426053,0.0010470729,0.000296701,0.000026880947,0.00042451575,0.0018253357,0.9771498,0.0034867509,0.013324626,0.0018649497],"study_design_scores_gemma":[0.0018573395,0.0026077575,0.0018136515,0.0022761507,0.00012761969,0.009604573,0.0016092496,0.44659853,0.24226269,0.03451045,0.25601205,0.00071995164],"about_ca_topic_score_codex":0.0000027530739,"about_ca_topic_score_gemma":0.0000019718846,"teacher_disagreement_score":0.73488706,"about_ca_system_score_codex":0.00008580932,"about_ca_system_score_gemma":0.00063746044,"threshold_uncertainty_score":0.34736255},"labels":[],"label_agreement":null},{"id":"W4402436260","doi":"10.1016/j.heliyon.2024.e37820","title":"MLAFP-XN: Leveraging neural network model for development of antifungal peptide identification tool","year":2024,"lang":"en","type":"article","venue":"Heliyon","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Antifungal; Identification (biology); Artificial neural network; Computational biology; Peptide; Computer science; Artificial intelligence; Biology; Biochemistry; Microbiology; Botany","score_opus":0.02019447015707347,"score_gpt":0.28269909749165056,"score_spread":0.2625046273345771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402436260","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.633521,0.0011328812,0.36442778,0.000060664595,0.0002883292,0.00020179826,0.000010940202,0.000030607374,0.00032596596],"genre_scores_gemma":[0.9498304,0.00007201453,0.047553737,0.000090922484,0.00020564509,0.000030316769,0.00026081156,0.000023332022,0.001932812],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991612,0.000015010212,0.00034105033,0.00018634935,0.00011111804,0.00018529315],"domain_scores_gemma":[0.9996296,0.00001480765,0.00007667437,0.00019196545,0.00006180402,0.000025147681],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003124768,0.00010718326,0.00009562686,0.000034819845,0.00008086445,0.000046208726,0.00010269718,0.00007760714,0.000008241316],"category_scores_gemma":[0.000053044354,0.00010460259,0.00006758244,0.000065780434,0.000019212754,0.000007689869,0.0000693245,0.00007770864,0.000007641421],"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":[0.00013953751,0.000055464843,0.0020225933,0.003799327,0.00018097197,0.0000020646696,0.0020087813,0.28661808,0.6388897,0.0013116614,0.011342042,0.053629786],"study_design_scores_gemma":[0.00016837972,0.000041429277,0.0014011911,0.00016640851,0.000020319067,0.000008118901,0.000025018637,0.91524595,0.057064172,0.00006062456,0.02561112,0.00018725323],"about_ca_topic_score_codex":4.866327e-7,"about_ca_topic_score_gemma":0.0000037409468,"teacher_disagreement_score":0.6286279,"about_ca_system_score_codex":0.000014978673,"about_ca_system_score_gemma":0.000085404274,"threshold_uncertainty_score":0.426557},"labels":[],"label_agreement":null},{"id":"W4402511634","doi":"10.1016/j.rineng.2024.102878","title":"DeepQSP: Identification of Quorum Sensing Peptides Through Neural Network Model","year":2024,"lang":"en","type":"article","venue":"Results in Engineering","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Quorum sensing; Artificial neural network; Identification (biology); Computer science; Computational biology; Artificial intelligence; Biological system; Biology; Ecology; Bacteria; Biofilm","score_opus":0.007623267011142931,"score_gpt":0.24855483695647398,"score_spread":0.24093156994533105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402511634","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69221324,0.0013019239,0.30426222,0.00013238785,0.00050096447,0.00014714085,0.000021810127,0.000084566745,0.0013357697],"genre_scores_gemma":[0.97846824,0.00007685019,0.021076458,0.00001530088,0.0001446429,0.0000016017317,0.000064748885,0.00002059708,0.00013153619],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991944,0.00001156424,0.00037066225,0.00015474345,0.000088025125,0.00018061436],"domain_scores_gemma":[0.9996742,0.000024664392,0.000050613733,0.00021059524,0.000021952881,0.000017962659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002673771,0.00009966123,0.000093340874,0.000043537566,0.000016613463,0.000026992779,0.00009077402,0.00008276886,3.232671e-7],"category_scores_gemma":[0.00017743,0.00010230671,0.00004476518,0.00014573411,0.000015491136,0.000009759396,0.000060074184,0.00013641329,0.0000021641422],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011924622,0.0000027626124,0.00003459766,0.00012344737,0.000011094822,0.0000014729106,0.0002345337,0.8622532,0.13567454,0.00021158432,0.00021217953,0.001228694],"study_design_scores_gemma":[0.00011240926,0.00001821686,0.00015810393,0.00010439502,0.0000054339257,0.000008629072,0.000020450863,0.96576595,0.032612555,0.00004947118,0.0010432703,0.000101093196],"about_ca_topic_score_codex":0.000007901572,"about_ca_topic_score_gemma":0.000005946943,"teacher_disagreement_score":0.28625503,"about_ca_system_score_codex":0.000015308224,"about_ca_system_score_gemma":0.000017906683,"threshold_uncertainty_score":0.41719466},"labels":[],"label_agreement":null},{"id":"W4402652826","doi":"10.1530/endoabs.104.oc4","title":"Selective sweep mapping identifies obesity candidate mutations in labrador retrievers","year":2024,"lang":"en","type":"article","venue":"Endocrine Abstracts","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Geography; Genetics; Biology","score_opus":0.006884435566952463,"score_gpt":0.2628412982508177,"score_spread":0.25595686268386525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402652826","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98924905,0.00030680536,0.00033774367,0.00027962695,0.0002969941,0.00016221163,0.000022075079,0.000057527584,0.009287965],"genre_scores_gemma":[0.9963867,0.00007129556,0.0007751207,0.000077994526,0.00013170086,0.000012467609,0.0002262959,0.000019291652,0.0022991411],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99903286,0.00003349962,0.00029105807,0.00024094399,0.00013207053,0.00026959146],"domain_scores_gemma":[0.9996046,0.000040420724,0.000059818904,0.0001929081,0.0000441712,0.00005807598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018164961,0.00014044147,0.000113153576,0.0001407747,0.00006586427,0.00009114502,0.00013300724,0.000061212195,0.00004251446],"category_scores_gemma":[0.00033279503,0.0001434831,0.000055895067,0.00027434964,0.000044057673,0.00001947379,0.000062246036,0.000289695,0.00009310114],"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":[0.00021952088,0.000492334,0.05300872,0.001960771,0.0008917413,0.0012588617,0.009807432,0.036167398,0.8083162,0.0017490744,0.05858662,0.027541379],"study_design_scores_gemma":[0.0009511038,0.00018596275,0.5016533,0.00023414199,0.000040496536,0.0002248081,0.0013180859,0.0034914236,0.3792159,0.00066400034,0.11127709,0.00074369134],"about_ca_topic_score_codex":0.0005355193,"about_ca_topic_score_gemma":0.00059063407,"teacher_disagreement_score":0.44864458,"about_ca_system_score_codex":0.000041805248,"about_ca_system_score_gemma":0.00009783274,"threshold_uncertainty_score":0.58510715},"labels":[],"label_agreement":null},{"id":"W4402956197","doi":"10.5376/bm.2024.15.0010","title":"Breakthrough in Biomolecular Interaction Prediction with AlphaFold 3","year":2024,"lang":"en","type":"article","venue":"Bioscience Methods","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Data science","score_opus":0.014849574519337041,"score_gpt":0.37758777055998805,"score_spread":0.362738196040651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402956197","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":[0.18765311,0.0004170481,0.80576116,0.0003131148,0.0008011456,0.00017189248,0.0000075391963,0.0000687113,0.0048062755],"genre_scores_gemma":[0.7629656,0.000058701113,0.23629166,0.00019768518,0.00010037968,0.000018683433,0.000027355323,0.00001574611,0.0003241988],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99902546,0.0001480455,0.00018201013,0.0003092623,0.00014218494,0.0001930605],"domain_scores_gemma":[0.99962854,0.000026225947,0.000038597238,0.00023522707,0.00002696702,0.00004446157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008789549,0.00011643094,0.00008255166,0.00013020734,0.000046810215,0.0000928074,0.00016343234,0.00008863073,0.0000151436725],"category_scores_gemma":[0.00015784847,0.00009033264,0.000037112088,0.00048614343,0.00010418792,0.000023042634,0.00007288645,0.00013633698,0.000011111242],"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":[0.000025395777,0.000025187104,0.0018561471,0.00004607997,0.000012306863,0.0000072625385,0.0002156058,0.0003549013,0.94057626,0.00033212896,0.00036646254,0.05618228],"study_design_scores_gemma":[0.00033994092,0.0008266693,0.008856632,0.00017599133,0.000022870823,0.00027685406,0.0002768484,0.096107885,0.62888277,0.00015224805,0.26371562,0.00036565898],"about_ca_topic_score_codex":0.000037778504,"about_ca_topic_score_gemma":0.000013086486,"teacher_disagreement_score":0.5753125,"about_ca_system_score_codex":0.000037236066,"about_ca_system_score_gemma":0.00007099943,"threshold_uncertainty_score":0.36836582},"labels":[],"label_agreement":null},{"id":"W4403214303","doi":"10.2139/ssrn.4979436","title":"Classifying Covalent Protein Binders by Their Targeted Binding Site","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Covalent bond; Chemistry; Binding site; Nanotechnology; Computational biology; Biochemistry; Materials science; Biology; Organic chemistry","score_opus":0.006796499731547002,"score_gpt":0.24316356217467444,"score_spread":0.23636706244312744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403214303","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96057606,0.021065742,0.014241471,0.0011024653,0.0008347539,0.00065491564,0.00019092392,0.000091291644,0.0012423624],"genre_scores_gemma":[0.9835486,0.006361437,0.0007561822,0.00014894799,0.0007970631,0.000047110872,0.0012126185,0.0001529757,0.0069751022],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960603,0.00018677302,0.00061816635,0.00051859976,0.0003679764,0.0022481678],"domain_scores_gemma":[0.9987449,0.000011731432,0.0005139157,0.00048435116,0.0001027322,0.00014237722],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0018493175,0.0005364303,0.0003578991,0.00020758009,0.00024065204,0.00027130425,0.00064398523,0.0006729064,0.000027551469],"category_scores_gemma":[0.0001266566,0.0004595329,0.00039008257,0.00013625539,0.00008114561,0.000005666802,0.0010150538,0.0077942815,0.00008353931],"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":[0.0003427466,0.00019697397,0.0017141905,0.0013854533,0.004169184,0.000021095266,0.000834665,0.0031409694,0.9299773,0.0029444895,0.022557065,0.032715846],"study_design_scores_gemma":[0.005144289,0.0051605487,0.00014929417,0.004270579,0.0012269074,0.0040002246,0.007166612,0.03296169,0.3044389,0.15409012,0.4726968,0.008694028],"about_ca_topic_score_codex":0.000027211254,"about_ca_topic_score_gemma":0.000087596585,"teacher_disagreement_score":0.6255384,"about_ca_system_score_codex":0.00072991016,"about_ca_system_score_gemma":0.0030190195,"threshold_uncertainty_score":0.99978566},"labels":[],"label_agreement":null},{"id":"W4403507122","doi":"10.1101/2024.10.14.617627","title":"Benchmarking Bayesian colocalization methods in validating Mendelian randomization-based target discoveries from circulating proteins for cardiometabolic diseases","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University and Génome Québec Innovation Centre; McGill University; Montreal Heart Institute","funders":"","keywords":"Mendelian randomization; Colocalization; Benchmarking; Bayesian probability; Computational biology; Computer science; Bioinformatics; Biology; Genetics; Artificial intelligence; Gene; Neuroscience; Genetic variants; Business; Genotype","score_opus":0.009160324374207036,"score_gpt":0.27430073430714497,"score_spread":0.2651404099329379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403507122","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":[0.15705363,0.0015630696,0.83712894,0.000092774826,0.0008916825,0.0020325272,0.0010734239,0.00015155655,0.000012403727],"genre_scores_gemma":[0.68814206,0.000036151592,0.3100264,0.000104196595,0.0006433218,0.0008124933,0.00009442341,0.00013917568,0.0000017835783],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967147,0.00050874654,0.000958036,0.0009987465,0.00031339488,0.00050637295],"domain_scores_gemma":[0.99786764,0.00017525781,0.00061796326,0.00088556844,0.0002919931,0.00016156727],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011808833,0.00060649536,0.0007695139,0.0003774811,0.0002029942,0.00042625,0.00041264217,0.0005638421,0.000017505865],"category_scores_gemma":[0.0019081696,0.00065038353,0.00031266615,0.0005413492,0.000094134244,0.000019664118,0.00054091576,0.00047986204,0.000001948394],"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":[0.00025160683,0.00012119016,0.038986713,0.0025455852,0.00058600114,0.0000102743525,0.00006393642,0.20095542,0.75579,0.00050155167,0.000116656156,0.00007105626],"study_design_scores_gemma":[0.002695026,0.00009967128,0.0073975213,0.0009690056,0.00045484083,1.750316e-8,0.000018748686,0.65704715,0.32693872,0.000055459062,0.0029091006,0.0014147233],"about_ca_topic_score_codex":0.00011697554,"about_ca_topic_score_gemma":0.00001201536,"teacher_disagreement_score":0.5310884,"about_ca_system_score_codex":0.00016343627,"about_ca_system_score_gemma":0.0008440973,"threshold_uncertainty_score":0.99959475},"labels":[],"label_agreement":null},{"id":"W4403714974","doi":"10.1101/2024.10.21.619432","title":"ConvNTC: Convolutional neural tensor completion for predicting the disease-related miRNA pairs and cell-related drug pairs","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Convolutional neural network; microRNA; Tensor (intrinsic definition); Drug; Artificial intelligence; Computer science; Computational biology; Disease; Pattern recognition (psychology); Medicine; Mathematics; Internal medicine; Biology; Pharmacology; Genetics; Pure mathematics","score_opus":0.006968281432690615,"score_gpt":0.20928687427740364,"score_spread":0.202318592844713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403714974","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9884176,0.004971466,0.00058176735,0.0015217284,0.0015829726,0.0016036127,0.0009961723,0.00029362942,0.000031007265],"genre_scores_gemma":[0.997199,0.00018248009,0.0014850347,0.00024848455,0.00036968655,0.00026214658,0.000035557066,0.00013950773,0.0000780755],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997336,0.00020697298,0.000756494,0.0008532824,0.00032638194,0.0005208909],"domain_scores_gemma":[0.9979061,0.0001209334,0.00050417415,0.00082278816,0.00038129473,0.000264701],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008766763,0.0005762468,0.00039357907,0.00011968088,0.00038398858,0.0002265983,0.00045725927,0.00051188224,0.00002313505],"category_scores_gemma":[0.00044576122,0.00049779547,0.00026641972,0.0001875253,0.00034974233,0.000010489063,0.00084816007,0.0010177512,0.000021331347],"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":[0.0007127034,0.00046239866,0.11631982,0.00917135,0.0025218166,0.0000728089,0.0003243529,0.012260144,0.82177967,0.0041934373,0.032156516,0.000024979796],"study_design_scores_gemma":[0.0035238068,0.0003692807,0.19508809,0.0011889675,0.0015545291,9.314397e-7,0.00008547751,0.732599,0.032697484,0.00009977108,0.02995003,0.0028426345],"about_ca_topic_score_codex":0.000024669062,"about_ca_topic_score_gemma":0.0000017466998,"teacher_disagreement_score":0.78908217,"about_ca_system_score_codex":0.000082117476,"about_ca_system_score_gemma":0.00037890035,"threshold_uncertainty_score":0.9997474},"labels":[],"label_agreement":null},{"id":"W4403781424","doi":"10.18488/76.v11i3.3949","title":"Locust-based genetic classifier for abnormality identification in brain","year":2024,"lang":"en","type":"article","venue":"Review of Computer Engineering Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Abnormality; Locust; Classifier (UML); Artificial intelligence; Identification (biology); Pattern recognition (psychology); Computer science; Biology; Psychology; Botany; Psychiatry","score_opus":0.023779739347931834,"score_gpt":0.3735178047716922,"score_spread":0.3497380654237604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403781424","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":[0.035867173,0.050962247,0.9104951,0.0012481613,0.00026650852,0.0010002698,0.000017355718,0.00003634331,0.0001068368],"genre_scores_gemma":[0.8754051,0.009902132,0.112600975,0.00042629207,0.0006527874,0.00021134624,0.00036126346,0.00008339127,0.0003567353],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998931,0.00008061784,0.00037774045,0.00018481756,0.00021515557,0.00021069872],"domain_scores_gemma":[0.9993201,0.00015483932,0.000030478404,0.00031834742,0.00013729268,0.000038954564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019493586,0.00008794811,0.00014835932,0.000120519915,0.00001611645,0.000033820026,0.00022802422,0.00006711412,0.0000074169884],"category_scores_gemma":[0.00027293267,0.000082804836,0.00008595398,0.00028298204,0.00002877402,0.0000045688384,0.00007228292,0.00018512941,0.000008187222],"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":[0.00005950751,0.00021004942,0.0019111182,0.31915438,0.00018996144,0.000021647187,0.00016109568,0.2835474,0.07988709,0.0034139287,0.079646125,0.2317977],"study_design_scores_gemma":[0.00015702013,0.00013424276,0.0030877197,0.0046495846,0.0000059864765,0.000007183558,9.235526e-7,0.8341727,0.004695043,0.000016372564,0.15294598,0.00012719697],"about_ca_topic_score_codex":0.0000033478957,"about_ca_topic_score_gemma":8.396089e-7,"teacher_disagreement_score":0.8395379,"about_ca_system_score_codex":0.000027200913,"about_ca_system_score_gemma":0.00009560063,"threshold_uncertainty_score":0.33766833},"labels":[],"label_agreement":null},{"id":"W4403793040","doi":"10.1101/2024.10.25.620288","title":"Preprocessing homologous regions in annotated protein sequences concerning machine-learning applications","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Homologous chromosome; Computer science; Protein superfamily; Artificial intelligence; Computational biology; Biology; Genetics; Gene","score_opus":0.010604180399952801,"score_gpt":0.24113385562011186,"score_spread":0.23052967522015905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403793040","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9782414,0.007962459,0.009897856,0.00037441682,0.00035981074,0.0020921123,0.00018150575,0.00063554983,0.00025491405],"genre_scores_gemma":[0.98695284,0.00024448024,0.011031624,0.00010432241,0.00035384973,0.001052045,0.000011659095,0.00015916867,0.00009003833],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99689794,0.00024349373,0.00076965935,0.001174101,0.00030603234,0.00060875644],"domain_scores_gemma":[0.9978671,0.000031317515,0.0005726354,0.0010526609,0.00030042895,0.00017583552],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00078924367,0.0006080645,0.00047715488,0.00033317725,0.00025016846,0.00032861935,0.000735656,0.00078673655,0.000015888738],"category_scores_gemma":[0.00048061355,0.0006550823,0.00015165754,0.0006226037,0.00024009054,0.000014712828,0.0012261502,0.002065722,0.00006362448],"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":[0.000041651307,0.00010953742,0.009791714,0.0020087862,0.000193224,0.00006961237,0.00007652839,0.008072714,0.978765,0.00071468734,0.00012993552,0.000026596525],"study_design_scores_gemma":[0.0018067865,0.00058811234,0.00900348,0.00541982,0.0004046325,0.0000018484056,0.00008833801,0.07515173,0.8014185,0.00016599068,0.10071087,0.0052399402],"about_ca_topic_score_codex":0.00012586644,"about_ca_topic_score_gemma":0.000017750419,"teacher_disagreement_score":0.17734656,"about_ca_system_score_codex":0.0001601952,"about_ca_system_score_gemma":0.0008390757,"threshold_uncertainty_score":0.99959004},"labels":[],"label_agreement":null},{"id":"W4403850121","doi":"10.1016/j.compbiomed.2024.109281","title":"An Integrated Multi-Model Framework Utilizing Convolutional Neural Networks Coupled with Feature Extraction for Identification of 4mC Sites in DNA Sequences","year":2024,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Manitoba","funders":"","keywords":"Computer science; Convolutional neural network; Context (archaeology); Identification (biology); Representation (politics); Sequence (biology); Embedding; Artificial intelligence; Data mining; Machine learning; Biology","score_opus":0.017028107617053877,"score_gpt":0.3479974172249105,"score_spread":0.33096930960785664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403850121","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44282,0.0011962559,0.55540264,0.0002600683,0.00017341205,0.00012982365,0.0000053628655,0.000009255099,0.0000031905774],"genre_scores_gemma":[0.9689081,0.00016609674,0.029991433,0.00015098827,0.000096729906,0.000013652204,0.0006565095,0.0000061251585,0.000010372395],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993672,0.00004838922,0.00022743037,0.00020444999,0.000034186764,0.0001183498],"domain_scores_gemma":[0.99964195,0.00010197498,0.00008002721,0.00009888001,0.000049972623,0.000027220018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034272266,0.00010101584,0.00015011869,0.00009548038,0.00003117358,0.0000073363694,0.000082213286,0.00021681708,0.0000012103277],"category_scores_gemma":[0.00009770262,0.00007287472,0.0000146337925,0.000118579985,0.00024181267,0.000009773319,0.00001652565,0.00021673342,4.949055e-8],"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":[0.0011669978,0.00017852186,0.14686227,0.0005904761,0.00015871602,0.0000091342845,0.0020795388,0.33406165,0.47983763,0.010732646,0.0005549859,0.023767443],"study_design_scores_gemma":[0.00046221568,0.00038496443,0.009339504,0.0001712108,0.0000114452705,0.00001897277,0.00015297496,0.988613,0.00037515574,0.00030006972,0.00009405512,0.00007644933],"about_ca_topic_score_codex":0.000014627136,"about_ca_topic_score_gemma":0.000059933165,"teacher_disagreement_score":0.6545513,"about_ca_system_score_codex":0.000012507875,"about_ca_system_score_gemma":0.00003092394,"threshold_uncertainty_score":0.29717448},"labels":[],"label_agreement":null},{"id":"W4403884711","doi":"10.48550/arxiv.2410.03632","title":"BLAST: Beyond Limber Angular power Spectra Toolkit. A fast and efficient algorithm for 3x2 pt analysis","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Space Agency; Ministry of Colleges and Universities; Innovation, Science and Economic Development Canada; Institut Périmètre de physique théorique; Alliance de recherche numérique du Canada; Government of Canada; U.S. Department of Energy","keywords":"Algorithm; Spectral line; Power analysis; Computer science; Physics; Quantum mechanics","score_opus":0.012132820874269163,"score_gpt":0.1886571273214563,"score_spread":0.17652430644718714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403884711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6309177,0.00042260854,0.3632159,0.000063111715,0.00032310138,0.00047799328,0.00035706515,0.000060407976,0.0041621216],"genre_scores_gemma":[0.9847507,0.00013278524,0.00918682,0.000110242654,0.00016035026,0.0000033892516,0.00054698327,0.00004787858,0.005060837],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836224,0.000052564184,0.0002453542,0.00089438754,0.0000876007,0.00035787252],"domain_scores_gemma":[0.9987623,0.000030740397,0.00018264422,0.0007358033,0.00013272795,0.00015577729],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024130695,0.00038776261,0.000390037,0.00031353813,0.000109878594,0.000108474895,0.00037644219,0.0004552985,0.000056829074],"category_scores_gemma":[0.00004347737,0.00041400053,0.00048050424,0.0003998121,0.00014601169,0.000003785991,0.0013126736,0.00045893865,0.000024256735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028698926,0.00042175694,0.0040182984,0.0009605334,0.0093693435,0.0002669838,0.001187374,0.95916414,0.0027697813,0.011660378,0.003812983,0.0060814307],"study_design_scores_gemma":[0.00059991155,0.00026842588,0.0007303515,0.000047249567,0.0019919423,0.000012639584,0.00025973402,0.98611253,0.0012577742,0.001372385,0.0066186883,0.0007283336],"about_ca_topic_score_codex":0.00002818042,"about_ca_topic_score_gemma":0.00002902284,"teacher_disagreement_score":0.35402906,"about_ca_system_score_codex":0.000060673217,"about_ca_system_score_gemma":0.00010458296,"threshold_uncertainty_score":0.9998312},"labels":[],"label_agreement":null},{"id":"W4404010966","doi":"10.1101/2024.11.02.621677","title":"Membrane mimetic thermal proteome profiling (MM-TPP) towards mapping membrane protein-ligand dynamic interactions","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina; University of British Columbia","funders":"","keywords":"Proteome; Profiling (computer programming); Membrane; Chemistry; Membrane protein; Computational biology; Biophysics; Cell biology; Biology; Computer science; Biochemistry","score_opus":0.009100101414967084,"score_gpt":0.23779603881892689,"score_spread":0.2286959374039598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404010966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99122053,0.0009615197,0.0021934458,0.00044597982,0.0015372129,0.0027202321,0.00025620547,0.0004509288,0.00021391506],"genre_scores_gemma":[0.9704752,0.000104832245,0.027109135,0.00015278478,0.0007511621,0.0009252624,0.0000123844475,0.0002958084,0.00017343368],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9960149,0.00021191472,0.0010300205,0.0013444473,0.0005396652,0.00085908483],"domain_scores_gemma":[0.9968409,0.000023261216,0.00062183733,0.0017657911,0.00044829072,0.00029993695],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009077667,0.0009831864,0.00072473014,0.00043797123,0.00025756125,0.00047521733,0.0009371448,0.00085695984,0.00005513669],"category_scores_gemma":[0.0004654996,0.000993983,0.0003834205,0.0004933377,0.00019432722,0.000024354338,0.0017907628,0.0021085732,0.000176104],"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":[0.00005807452,0.00009763047,0.0001892839,0.0031263032,0.0004714888,0.00003673564,0.00003078225,0.00067948934,0.9951762,0.00007539009,0.000042835185,0.000015788926],"study_design_scores_gemma":[0.00046903908,0.00012423503,0.002029193,0.001263505,0.00018250065,4.7959037e-7,0.000011814424,0.01102266,0.978471,0.000003373939,0.0052153696,0.0012068743],"about_ca_topic_score_codex":0.000056761135,"about_ca_topic_score_gemma":0.000006654226,"teacher_disagreement_score":0.02491569,"about_ca_system_score_codex":0.00022709693,"about_ca_system_score_gemma":0.0009787121,"threshold_uncertainty_score":0.99925107},"labels":[],"label_agreement":null},{"id":"W4404551961","doi":"10.1101/2024.11.18.624211","title":"Leveraging AlphaFold 3 for Structural Modeling of Neurological Disorder-Associated Proteins: A Pathway to Precision Medicine","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centennial College","funders":"","keywords":"Druggability; Computational biology; Structural variation; Disease; Brain Structure and Function; Bioinformatics; Computer science; Medicine; Biology; Neuroscience; Genetics; Neuroimaging; Pathology; Gene; Genome","score_opus":0.013736336678932546,"score_gpt":0.2477772528147635,"score_spread":0.23404091613583097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404551961","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9676415,0.0014126995,0.027528845,0.0004055778,0.00080382696,0.0018051903,0.00024536456,0.00014646676,0.000010549283],"genre_scores_gemma":[0.98509884,0.00007668966,0.013672834,0.0002700952,0.00043221825,0.00030393037,0.000007776001,0.00012697777,0.000010647676],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99718225,0.00012723566,0.0008673348,0.00091393583,0.00039981058,0.0005094431],"domain_scores_gemma":[0.9978563,0.000050682036,0.00042465207,0.00094217743,0.00052906456,0.00019711131],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008604253,0.00056092156,0.0006465177,0.00022122389,0.00011912837,0.00007332399,0.00066453073,0.00069136557,0.000010301094],"category_scores_gemma":[0.0019960345,0.00049316307,0.00022014095,0.0002760961,0.000078313264,0.000006668389,0.0013057092,0.00071098184,0.000005352059],"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":[0.00027560772,0.000088691406,0.0021320616,0.0015088746,0.00032883201,0.000008151361,0.00008174685,0.044471983,0.95037794,0.00026562237,0.00041012163,0.000050394865],"study_design_scores_gemma":[0.0020412635,0.0024802797,0.004329063,0.0023653172,0.0003256468,1.18054636e-7,0.000015211516,0.821626,0.1580684,0.000113664486,0.0068098763,0.0018251792],"about_ca_topic_score_codex":0.00004066474,"about_ca_topic_score_gemma":0.0000040631753,"teacher_disagreement_score":0.7923095,"about_ca_system_score_codex":0.000058228095,"about_ca_system_score_gemma":0.00028922933,"threshold_uncertainty_score":0.999752},"labels":[],"label_agreement":null},{"id":"W4404612153","doi":"10.1007/978-1-0716-4196-5_14","title":"Computational Prediction of Linear Interacting Peptides","year":2024,"lang":"en","type":"article","venue":"Methods in molecular biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Michael Smith Health Research BC; Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Computer science; Computational biology; Biological system; Biology","score_opus":0.016682605953480763,"score_gpt":0.40583495289388516,"score_spread":0.3891523469404044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404612153","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":[0.07209374,0.00062125456,0.9252594,0.00007793197,0.00035473562,0.00009520413,0.000022954187,0.000022588645,0.0014521962],"genre_scores_gemma":[0.18453181,0.000023103361,0.8149509,0.00009772691,0.00007040778,0.000010090785,0.00023209228,0.000016613243,0.00006728031],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987812,0.00040789857,0.00037267222,0.00022918945,0.00005718072,0.00015184752],"domain_scores_gemma":[0.99953306,0.00014260152,0.00007467705,0.00017314665,0.00005121963,0.000025301582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091841526,0.00011494918,0.00015224391,0.0001499651,0.000021075168,0.000009769511,0.00013744946,0.0001671474,0.000018842635],"category_scores_gemma":[0.00074891106,0.00010841598,0.000084805106,0.0001603324,0.00008944207,0.000003455364,0.00012051105,0.0002088272,0.0000044163753],"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":[0.00002115657,0.000022119784,0.0042443406,0.00009904862,0.00006291679,0.0000043259984,0.00015637426,0.014653926,0.9599065,0.002620342,0.00008584318,0.01812306],"study_design_scores_gemma":[0.00052413164,0.0007347193,0.0012652634,0.00018971616,0.00003692309,0.00012439548,0.00015515645,0.46775812,0.47450888,0.0067027723,0.04766808,0.00033185384],"about_ca_topic_score_codex":0.000011507734,"about_ca_topic_score_gemma":0.0000015682654,"teacher_disagreement_score":0.48539767,"about_ca_system_score_codex":0.000013673413,"about_ca_system_score_gemma":0.000049967908,"threshold_uncertainty_score":0.44210756},"labels":[],"label_agreement":null},{"id":"W4404622660","doi":"10.1515/jib-2023-0047","title":"Ion channel classification through machine learning and protein language model embeddings","year":2024,"lang":"en","type":"article","venue":"Berichte aus der medizinischen Informatik und Bioinformatik/Journal of integrative bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Machine learning","score_opus":0.013322728363286653,"score_gpt":0.30095299071438236,"score_spread":0.28763026235109573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404622660","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":[0.18803647,0.015888847,0.72422314,0.0013646261,0.0016050898,0.0025090303,0.0003770301,0.00045610432,0.06553965],"genre_scores_gemma":[0.7205423,0.004091951,0.2693254,0.0014695647,0.0006607104,0.00009108893,0.0012748275,0.0001626665,0.0023814572],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99498147,0.00010259859,0.002921396,0.000236081,0.0010372113,0.0007212699],"domain_scores_gemma":[0.9962938,0.00012830885,0.0019333465,0.0004341985,0.0008514701,0.00035888408],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015922347,0.00086142286,0.00081054034,0.0006401846,0.00027503335,0.0006820305,0.0007098459,0.00053028483,0.00003757952],"category_scores_gemma":[0.0011046046,0.00059881055,0.00035165696,0.00075951737,0.0004215278,0.0010970329,0.0004063266,0.0015008482,0.00009189846],"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":[0.0024690055,0.0006034647,0.0010951142,0.0143414335,0.0077981222,0.000098405115,0.6442199,0.013374998,0.060978066,0.03256116,0.048796777,0.17366356],"study_design_scores_gemma":[0.0012831097,0.0014676185,0.000040668157,0.0010006238,0.00026179702,0.00079371384,0.020389542,0.83013517,0.01592075,0.0002409924,0.12755853,0.0009074928],"about_ca_topic_score_codex":0.000013737987,"about_ca_topic_score_gemma":0.000009669803,"teacher_disagreement_score":0.8167602,"about_ca_system_score_codex":0.00013384412,"about_ca_system_score_gemma":0.00059848937,"threshold_uncertainty_score":0.9996463},"labels":[],"label_agreement":null},{"id":"W4404801560","doi":"10.1016/j.procs.2024.09.613","title":"Using Auto-Encoders to Create Encodings for Three-Dimensional Protein Structure Information","year":2024,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Encoder; Theoretical computer science; Artificial intelligence; Algorithm; Computer vision; Operating system","score_opus":0.011499858014108008,"score_gpt":0.2739601485216951,"score_spread":0.26246029050758707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404801560","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":[0.3121456,0.000021413654,0.68666625,0.00021944461,0.00035504912,0.0004653244,0.000014649724,0.00004642283,0.0000658525],"genre_scores_gemma":[0.6081043,3.0588888e-7,0.39110982,0.00048764242,0.00022088183,0.00002062165,0.000025422338,0.000008089159,0.00002294791],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989887,0.0000056046497,0.00019985146,0.00025982424,0.00027030238,0.00027570955],"domain_scores_gemma":[0.99945974,0.00001141752,0.00005383856,0.0001717096,0.0001991055,0.00010416069],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003463531,0.00013056897,0.00008008393,0.00014612828,0.00019203195,0.00030281115,0.00034404217,0.0000645953,0.000004359034],"category_scores_gemma":[0.0001497839,0.00011148033,0.000038254675,0.0003462804,0.000102055215,0.0000786277,0.0002541287,0.00009199289,0.000010266636],"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":[0.00007878927,0.00001973953,0.00070399034,0.0008122305,0.000037181424,0.000001591604,0.0018472326,0.10682701,0.7782932,0.0034344336,0.0040127253,0.1039319],"study_design_scores_gemma":[0.000100136924,0.0001721564,0.00016498702,0.00007232195,0.00000495608,0.00002762325,0.0000043896043,0.95160604,0.036889065,0.00036013767,0.010427502,0.00017069126],"about_ca_topic_score_codex":0.0000066219714,"about_ca_topic_score_gemma":0.0000046799755,"teacher_disagreement_score":0.844779,"about_ca_system_score_codex":0.000035754456,"about_ca_system_score_gemma":0.00037446807,"threshold_uncertainty_score":0.4546036},"labels":[],"label_agreement":null},{"id":"W4404802881","doi":"10.1016/j.foodres.2024.115417","title":"How peptide migration and fraction bioactivity are modulated by applied electrical current conditions during electromembrane process separation: A comprehensive machine learning-based peptidomic approach","year":2024,"lang":"en","type":"article","venue":"Food Research International","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Université Laval","keywords":"Process (computing); Peptide; Current (fluid); Fraction (chemistry); Electrical current; Biochemical engineering; Computer science; Chemistry; Biological system; Nanotechnology; Materials science; Chromatography; Biology; Engineering; Biochemistry","score_opus":0.021607441099761312,"score_gpt":0.3422873704200988,"score_spread":0.3206799293203375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404802881","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9824723,0.00084197393,0.014749584,0.0008276903,0.00009719563,0.0004652698,0.00012834716,0.000079754194,0.00033789466],"genre_scores_gemma":[0.9947369,0.00016084258,0.00022066038,0.000019201196,0.00024319167,0.00017372779,0.0040123104,0.00002842384,0.000404739],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828297,0.00016620848,0.00020408342,0.00044448968,0.0005947168,0.0003075213],"domain_scores_gemma":[0.9992534,0.00006142789,0.00010147138,0.00014153036,0.0003418801,0.00010027904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026332025,0.0001883326,0.00014135071,0.00030682786,0.00028876544,0.00036256923,0.000173272,0.00014373871,0.00001878731],"category_scores_gemma":[0.00019144443,0.00018288037,0.00006127385,0.00030074734,0.00012248967,0.000040444545,0.000069164365,0.00084598165,0.000008419466],"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":[0.00048799702,0.0003224319,0.0035502203,0.00041611787,0.00026939006,0.0000025624822,0.00013326893,0.009469836,0.9816216,0.0002904328,0.0025712089,0.0008649382],"study_design_scores_gemma":[0.0011198255,0.0006126801,0.0063135833,0.000061104605,0.000020176782,0.000058391422,0.00011146659,0.81258357,0.15597445,0.000118944554,0.022694925,0.00033088803],"about_ca_topic_score_codex":0.000010872429,"about_ca_topic_score_gemma":0.000018331608,"teacher_disagreement_score":0.8256471,"about_ca_system_score_codex":0.00012645446,"about_ca_system_score_gemma":0.00012286866,"threshold_uncertainty_score":0.74576443},"labels":[],"label_agreement":null},{"id":"W4404909541","doi":"10.1016/j.seppur.2024.130877","title":"Application of machine learning tools to study the synergistic impact of physicochemical properties of peptides and filtration membranes on peptide migration during electrodialysis with filtration membranes","year":2024,"lang":"en","type":"article","venue":"Separation and Purification Technology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; Université Laval","keywords":"Electrodialysis; Membrane; Filtration (mathematics); Chemistry; Peptide; Chromatography; Chemical engineering; Biochemistry; Engineering; Mathematics","score_opus":0.008662403433438595,"score_gpt":0.2644751632585206,"score_spread":0.255812759825082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404909541","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9933476,0.00043700825,0.0052830363,0.00028052527,0.000008164137,0.0005701524,0.000007835265,0.000031800195,0.00003389762],"genre_scores_gemma":[0.99918973,0.00014759957,0.00029567865,0.000005823604,0.000024267936,0.00014248151,0.00014372739,0.000011504983,0.00003915303],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99911535,0.00007464139,0.00036054262,0.00022568692,0.00013824213,0.00008551365],"domain_scores_gemma":[0.9993248,0.000036267327,0.00023180559,0.00023783401,0.00015005957,0.000019252215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020736692,0.00013376796,0.0001757445,0.00019177109,0.00008627348,0.000031004496,0.0000886644,0.00009846254,0.000002687205],"category_scores_gemma":[0.00017708853,0.00009139864,0.000036965084,0.00035087168,0.0001196376,0.000024701989,0.000020172412,0.00011748816,7.767652e-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":[0.00021623986,0.00007185005,0.003657443,0.00019784455,0.0001012912,5.8784586e-8,0.0016484191,0.004925741,0.98595047,0.00040315688,0.0000049869295,0.0028224832],"study_design_scores_gemma":[0.00022297648,0.0011481994,0.0066779084,0.000038032213,0.00007335774,0.000007817318,0.0008390934,0.024829447,0.9659673,0.000035033943,0.00005751092,0.000103346356],"about_ca_topic_score_codex":0.00005105953,"about_ca_topic_score_gemma":0.000049169765,"teacher_disagreement_score":0.01998321,"about_ca_system_score_codex":0.0000118467005,"about_ca_system_score_gemma":0.000035435758,"threshold_uncertainty_score":0.37271285},"labels":[],"label_agreement":null},{"id":"W4404969095","doi":"10.52711/0974-360x.2024.00663","title":"Bio-inspired Approaches for G-protein coupled receptors identification using Chou’s PseAAC","year":2024,"lang":"en","type":"article","venue":"Research Journal of Pharmacy and Technology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Collège Boréal","funders":"","keywords":"Artificial intelligence; Classifier (UML); Particle swarm optimization; G protein-coupled receptor; Computer science; Machine learning; Swarm behaviour; Identification (biology); Function (biology); Computational biology; Biology; Receptor","score_opus":0.08986630017924732,"score_gpt":0.40751391712057783,"score_spread":0.3176476169413305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404969095","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9710976,0.0064071305,0.01952444,0.0023118998,0.00020505718,0.00036353193,0.000007837351,0.000025451878,0.00005707838],"genre_scores_gemma":[0.993634,0.0006337291,0.005202805,0.00001086496,0.00024612286,0.000018886165,0.000014270812,0.0000209602,0.00021836278],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99887294,0.00008520973,0.0003781405,0.00017375752,0.00021668426,0.00027326358],"domain_scores_gemma":[0.9992944,0.00003559121,0.00013085578,0.00015538189,0.0003117383,0.00007203092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019256518,0.00010136927,0.00014134552,0.000574,0.00016044603,0.00008671863,0.0002810778,0.00014217998,0.0000119903925],"category_scores_gemma":[0.0006053447,0.00008641731,0.00006383047,0.00040923356,0.00027825515,0.000019614363,0.00012416462,0.0004958223,0.0000030556112],"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":[0.00014597861,0.000039790873,0.00061484915,0.00029229265,0.0001229879,0.0000063188095,0.00005538307,0.00005256181,0.9475935,0.0021169367,0.0008415245,0.048117876],"study_design_scores_gemma":[0.0012584196,0.0005658955,0.000030956755,0.00013602426,0.000045830675,0.00032456632,0.000343664,0.15652806,0.69221556,0.002619938,0.14574392,0.00018717063],"about_ca_topic_score_codex":0.000004840662,"about_ca_topic_score_gemma":0.0000012981367,"teacher_disagreement_score":0.25537795,"about_ca_system_score_codex":0.00003405534,"about_ca_system_score_gemma":0.0001939273,"threshold_uncertainty_score":0.35239956},"labels":[],"label_agreement":null},{"id":"W4405181201","doi":"10.1158/1538-8514.cancerchem24-a015","title":"Abstract A015: Design and deciphering of precision peptide inhibitors for cancer stemness using generative deep learning and molecular dynamics simulations","year":2024,"lang":"en","type":"article","venue":"Molecular Cancer Therapeutics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computational biology; Peptide; Molecular dynamics; Notch signaling pathway; Molecular mechanics; Amino acid; Biology; Deep learning; Chemistry; Artificial intelligence; Biochemistry; Computer science; Receptor","score_opus":0.020815070898189177,"score_gpt":0.32440934917473274,"score_spread":0.30359427827654356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405181201","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5031623,0.012453738,0.4838155,0.00006165666,0.000106639505,0.00033852254,0.000027575914,0.000015656493,0.000018398398],"genre_scores_gemma":[0.9599445,0.0010321053,0.03861128,0.00012188662,0.000070677685,0.000049700655,0.000048949358,0.00007761383,0.00004330598],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879915,0.000082592924,0.0003487404,0.000343389,0.00017971382,0.00024641282],"domain_scores_gemma":[0.9993804,0.00008283096,0.00014811024,0.00016680078,0.00015551264,0.00006633213],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002323978,0.0002521532,0.00022249084,0.00008420611,0.0001336119,0.00009472901,0.000100278645,0.00018614548,0.000007289771],"category_scores_gemma":[0.00003987951,0.00024923033,0.000081620536,0.00013990026,0.00010293866,0.000016232763,0.00009818631,0.00019044714,1.3170919e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005388627,0.000010777228,0.0008124106,0.00022546425,0.00023637888,0.0000026045632,0.0004267264,0.3544144,0.6125041,0.000112145935,0.0000017319882,0.031199384],"study_design_scores_gemma":[0.00035348636,0.00013669129,0.00015361121,0.00019800596,0.00016727603,0.0000069088255,0.00012387443,0.7858411,0.20980583,0.00018496557,0.0027477783,0.00028046005],"about_ca_topic_score_codex":0.000044040942,"about_ca_topic_score_gemma":0.000056559664,"teacher_disagreement_score":0.45678216,"about_ca_system_score_codex":0.00007482694,"about_ca_system_score_gemma":0.00015683136,"threshold_uncertainty_score":0.999996},"labels":[],"label_agreement":null},{"id":"W4405975816","doi":"10.1101/2024.12.18.629275","title":"Probabilistic Annotations of Protein Sequences for Intrinsically Disordered Features","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"","keywords":"Probabilistic logic; Intrinsically disordered proteins; Computational biology; Computer science; Statistical physics; Artificial intelligence; Biology; Physics; Biophysics","score_opus":0.007785331848800327,"score_gpt":0.23894589586946088,"score_spread":0.23116056402066057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405975816","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98895955,0.0020120458,0.004059582,0.000572621,0.0005952999,0.0025959804,0.0010012956,0.00015644029,0.00004716914],"genre_scores_gemma":[0.9674559,0.00005735591,0.031228153,0.00006400059,0.000333041,0.00072176603,0.000007881325,0.00009162383,0.000040278166],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981487,0.000076635166,0.00057511876,0.0006272396,0.00023677286,0.00033553733],"domain_scores_gemma":[0.99800026,0.00003847143,0.0004105906,0.0008727344,0.0005677457,0.00011021842],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003996326,0.00040540987,0.00039265782,0.00014645666,0.00008815214,0.00012313628,0.0005122895,0.0005329795,0.000006475221],"category_scores_gemma":[0.0012582984,0.0003903489,0.0002069868,0.00022105016,0.00020310801,0.0000053169842,0.0006136902,0.0005225252,0.0000080476975],"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":[0.00008122273,0.0001216936,0.00031559958,0.0042121564,0.00028950896,0.0000030767653,0.000026858233,0.0010771878,0.9871581,0.0057343473,0.0009660641,0.000014184463],"study_design_scores_gemma":[0.0011075418,0.00095507887,0.011364388,0.0017077401,0.00046120447,9.300197e-8,0.000018274746,0.004797935,0.9513524,0.00045882948,0.025844544,0.0019319252],"about_ca_topic_score_codex":0.000020378913,"about_ca_topic_score_gemma":0.0000088231845,"teacher_disagreement_score":0.035805654,"about_ca_system_score_codex":0.00004680468,"about_ca_system_score_gemma":0.00075927365,"threshold_uncertainty_score":0.99985486},"labels":[],"label_agreement":null},{"id":"W4406016843","doi":"10.1038/s41467-024-55021-3","title":"π-PrimeNovo: an accurate and efficient non-autoregressive deep learning model for de novo peptide sequencing","year":2025,"lang":"en","type":"article","venue":"Nature Communications","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada; Fudan University; National Natural Science Foundation of China; Canada Research Chairs","keywords":"Autoregressive model; Computational biology; Deep learning; Computer science; Artificial intelligence; Machine learning; Biology; Econometrics; Mathematics","score_opus":0.013264334734050144,"score_gpt":0.33279472804214205,"score_spread":0.3195303933080919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406016843","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5835537,0.004543308,0.40214887,0.0013875193,0.00009450272,0.00065266236,0.000030721072,0.00007479849,0.00751393],"genre_scores_gemma":[0.88930756,0.00018327706,0.10901924,0.0005365694,0.000022776792,0.000055726672,0.0002698489,0.000014291194,0.00059072475],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993266,0.00007176017,0.00018195732,0.00016985375,0.000059539925,0.00019029836],"domain_scores_gemma":[0.9986975,0.00008665796,0.00011469612,0.0008719701,0.00017369568,0.00005548885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031172475,0.00012524035,0.00010741061,0.00006390658,0.00044589007,0.000053813306,0.0005802813,0.0002799511,8.006745e-7],"category_scores_gemma":[0.00054338673,0.00012359656,0.00004370071,0.00008267502,0.000098763536,0.0000067402,0.0004029948,0.00059979566,7.43198e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012852163,0.00017828574,0.008112419,0.00020291226,0.00023015,7.5520046e-7,0.0052503226,0.6901769,0.26621598,0.018430617,0.0014113524,0.009661766],"study_design_scores_gemma":[0.00034007762,0.00005131718,0.0008077222,0.00003262314,0.000030954863,0.000006834039,0.00029500743,0.98705536,0.003773555,0.00013109508,0.0073421407,0.00013332823],"about_ca_topic_score_codex":0.0000068853515,"about_ca_topic_score_gemma":0.0001301669,"teacher_disagreement_score":0.30575386,"about_ca_system_score_codex":0.000052881576,"about_ca_system_score_gemma":0.0001714671,"threshold_uncertainty_score":0.5040121},"labels":[],"label_agreement":null},{"id":"W4406259803","doi":"10.1109/bibm62325.2024.10822432","title":"Gene function prediction using an AnnoTree-based genomic language model","year":2024,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Wilfrid Laurier University; University of Waterloo","funders":"","keywords":"Computer science; Function (biology); Language model; Artificial intelligence; Natural language processing; Computational biology; Biology; Genetics","score_opus":0.012513419494518558,"score_gpt":0.2651069880560296,"score_spread":0.25259356856151105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406259803","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5849841,0.00016879704,0.41345367,0.000017358547,0.0001235916,0.000061436265,0.000022394763,0.00007485997,0.0010937782],"genre_scores_gemma":[0.97847784,0.000006175685,0.01966145,0.00028638466,0.0002668909,0.0000043574273,0.00060272514,0.000024994406,0.00066920253],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99943376,0.000022961725,0.00014115711,0.00018846453,0.000083042585,0.00013063065],"domain_scores_gemma":[0.99966604,0.0000028857667,0.000024344,0.00023758081,0.000020643793,0.00004849285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013740736,0.00010204111,0.000055655193,0.000053737407,0.000054685734,0.00005587189,0.00007312852,0.000109449305,0.000043595894],"category_scores_gemma":[0.000010799124,0.00009272217,0.000046952173,0.00005814146,0.000018997327,0.000008447889,0.00003187427,0.00008598401,0.00001590878],"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":[0.000024456214,0.0000160552,0.00028145855,0.000029855939,0.000017977605,9.693026e-7,0.000057134137,0.30012044,0.6971544,0.000034554625,0.00035929133,0.0019033845],"study_design_scores_gemma":[0.00013219887,0.00014489217,0.00025256554,0.0000064507144,0.000025071919,0.000009651855,0.00003439078,0.9409277,0.05696528,0.000017498458,0.0013834153,0.000100909354],"about_ca_topic_score_codex":0.000024811941,"about_ca_topic_score_gemma":0.0000141767205,"teacher_disagreement_score":0.6408072,"about_ca_system_score_codex":0.000023402368,"about_ca_system_score_gemma":0.000081981125,"threshold_uncertainty_score":0.37811002},"labels":[],"label_agreement":null},{"id":"W4406565630","doi":"10.1016/j.endend.2011.08.044","title":"10.1016/j.endend.2011.08.044","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Beta sheet; Computational biology; Computer science; Protein structure; Chemistry; Biology; Biochemistry","score_opus":0.003051698868559565,"score_gpt":0.18232043257603642,"score_spread":0.17926873370747684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406565630","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":[0.0038118502,0.00006529932,0.000014384349,0.00016860903,0.000002608621,0.00011986322,0.000016911434,0.00004657983,0.9957539],"genre_scores_gemma":[0.000770367,0.0000010173491,0.00086738385,0.00013524137,0.00020086982,0.000010551825,0.00013411135,0.000026359598,0.9978541],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99919236,0.00003353087,0.00018691119,0.00019763614,0.00013295865,0.00025661552],"domain_scores_gemma":[0.9993748,0.00000852721,0.00003838485,0.0004179105,0.000036541347,0.00012382884],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001293935,0.000150425,0.00011682285,0.00003594781,0.00006518586,0.000029629113,0.00026495126,0.0001191745,0.9862634],"category_scores_gemma":[0.000045407553,0.00014612889,0.00006489716,0.000055429893,0.00003296877,0.0000035779146,0.000085618216,0.00010918127,0.9841026],"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":[0.000115408286,0.000046084842,0.0000019577449,0.000015013345,0.000040037794,0.0000026810856,0.000020900297,0.00050232594,0.0029303138,0.0000012339119,0.5633386,0.43298542],"study_design_scores_gemma":[0.00022442757,0.0002598955,0.000046545527,0.000005272839,0.000009932612,0.000024709823,8.6944533e-7,0.00039310535,0.0019664546,0.0000021268265,0.99686867,0.00019796233],"about_ca_topic_score_codex":0.00000661195,"about_ca_topic_score_gemma":2.1987329e-7,"teacher_disagreement_score":0.4335301,"about_ca_system_score_codex":0.000009970252,"about_ca_system_score_gemma":0.000028627557,"threshold_uncertainty_score":0.59589636},"labels":[],"label_agreement":null},{"id":"W4406577567","doi":"10.1016/s1544-8800(10)70065-8","title":"10.1016/s1544-8800(10)70065-8","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Framingham Risk Score; Calcium; Algorithm; Computer science; Medicine; Internal medicine","score_opus":0.0027221982438970244,"score_gpt":0.1803409691307968,"score_spread":0.17761877088689978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406577567","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":[0.0033876651,0.000059473336,0.000012710576,0.00016514168,0.0000020644795,0.00014185187,0.000017059157,0.000050604594,0.9961634],"genre_scores_gemma":[0.0004057693,8.116396e-7,0.0010243229,0.00012982675,0.00020884792,0.00001252054,0.00017512997,0.000029508228,0.99801326],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99912214,0.000037399404,0.00020951752,0.0002123975,0.00014003017,0.00027851373],"domain_scores_gemma":[0.99931735,0.000010519518,0.000044318567,0.0004485306,0.00004722341,0.00013206466],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001393701,0.0001673119,0.0001321198,0.000037730726,0.00007375988,0.000036504756,0.0002829267,0.00013164213,0.98668164],"category_scores_gemma":[0.00008571035,0.00016277345,0.000073559466,0.000095296,0.000038087983,0.00000393711,0.000096904776,0.00010841793,0.9804465],"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":[0.00012730055,0.00003844992,8.577375e-7,0.000014091256,0.00003155903,0.0000017089543,0.000014310169,0.0005880795,0.00213504,7.048554e-7,0.66763425,0.32941365],"study_design_scores_gemma":[0.00023807959,0.00031134638,0.000041877825,0.000007943632,0.000011388244,0.000015906331,8.398768e-7,0.0006881686,0.0022007686,0.0000017416378,0.99626225,0.00021970556],"about_ca_topic_score_codex":0.000009853256,"about_ca_topic_score_gemma":2.8566043e-7,"teacher_disagreement_score":0.32919395,"about_ca_system_score_codex":0.000011693298,"about_ca_system_score_gemma":0.000033177406,"threshold_uncertainty_score":0.66377085},"labels":[],"label_agreement":null},{"id":"W4406665480","doi":"10.7554/elife.102274.2.sa3","title":"eLife Assessment: Alzheimer-mutant γ-secretase complexes stall amyloid β-peptide production","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Institutes of Health; Brigham and Women's Hospital","keywords":"Amyloid precursor protein; Mutant; P3 peptide; Amyloid (mycology); Peptide; β amyloid; Chemistry; Amyloid precursor protein secretase; Neuroscience; Alzheimer's disease; Biochemistry; Biology; Medicine; Internal medicine; Gene; Disease","score_opus":0.022747949609090882,"score_gpt":0.33928083704532463,"score_spread":0.31653288743623376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406665480","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":[0.001988778,0.18797494,0.02204353,0.094533816,0.016227003,0.009916465,0.005523037,0.00082064484,0.66097176],"genre_scores_gemma":[0.0023812796,0.07143179,0.04657765,0.02348657,0.003302482,0.0004129359,0.09982289,0.00023875097,0.7523456],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99687326,0.00021080913,0.0009691199,0.00082306005,0.0006254505,0.00049832003],"domain_scores_gemma":[0.99729455,0.000029231183,0.00060930673,0.001418907,0.00049501786,0.00015299952],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00077942543,0.00067956216,0.0007802961,0.00014333718,0.00015451697,0.00008797914,0.00068366085,0.0005028645,0.0006573176],"category_scores_gemma":[0.00056741777,0.00060165767,0.0003550038,0.00021812177,0.00013307371,0.0000075862245,0.00058855745,0.00078970206,0.00007864603],"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":[0.000016283915,0.000073390205,0.000042107276,0.002560551,0.0005719829,0.0000025880179,0.000007157775,0.00008605197,0.009062833,0.00011486995,0.98378533,0.0036768408],"study_design_scores_gemma":[0.0002387995,0.00018808433,0.000053283704,0.0011727113,0.00055711356,0.000036399302,0.000016195807,0.00028843738,0.0070633357,0.000017796312,0.98971677,0.00065110205],"about_ca_topic_score_codex":0.00012022364,"about_ca_topic_score_gemma":0.00015086278,"teacher_disagreement_score":0.11654315,"about_ca_system_score_codex":0.000055479813,"about_ca_system_score_gemma":0.0006946405,"threshold_uncertainty_score":0.9996435},"labels":[],"label_agreement":null},{"id":"W4406715995","doi":"10.1101/2025.01.20.633936","title":"PDP-Miner: an AI/ML tool to detect prophage tail proteins with depolymerase domains across thousands of bacterial genomes","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université Laval","funders":"Canadian Institutes of Health Research; Ontario Genomics; Genome Canada","keywords":"Prophage; Bacterial genome size; Genome; Computational biology; Biology; Genetics; Bacteriophage; Gene; Escherichia coli","score_opus":0.005373435462376582,"score_gpt":0.2371197319489669,"score_spread":0.23174629648659031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406715995","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9834135,0.00040567006,0.012694226,0.00006357516,0.0004053106,0.0017751121,0.0010775196,0.00014469003,0.00002036532],"genre_scores_gemma":[0.950296,0.00007305865,0.048093233,0.00030300787,0.0005863132,0.00046823508,0.000012249846,0.00012669474,0.00004124774],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9968516,0.00017936414,0.0007933271,0.0010324501,0.0004119565,0.0007312757],"domain_scores_gemma":[0.99648124,0.000016357497,0.0005804438,0.002124222,0.00049788266,0.00029984585],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005821307,0.000758822,0.0007209262,0.00018344058,0.00020338438,0.00023117114,0.00096499186,0.0007470889,0.000025125353],"category_scores_gemma":[0.0002595694,0.00070168736,0.00017588193,0.0003882196,0.00018834413,0.000022983902,0.0011191387,0.0006356598,0.000007751466],"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":[0.0005476494,0.0001305953,0.0035475753,0.0008900667,0.00022417272,0.000023673363,0.000053508113,0.0004855024,0.99391574,0.000028416393,0.0000996719,0.000053430518],"study_design_scores_gemma":[0.0011221652,0.0008846301,0.008339648,0.00028597945,0.00010872931,1.4281417e-7,0.000007091242,0.0002244799,0.97864246,4.0106144e-7,0.009424537,0.00095975853],"about_ca_topic_score_codex":0.0000623247,"about_ca_topic_score_gemma":0.000042307187,"teacher_disagreement_score":0.03539901,"about_ca_system_score_codex":0.00008494717,"about_ca_system_score_gemma":0.0010962196,"threshold_uncertainty_score":0.9995434},"labels":[],"label_agreement":null},{"id":"W4406865084","doi":"10.1021/acssensors.4c02682","title":"Comparative Analysis of Machine Learning Algorithms Used for Translating Aptamer-Antigen Binding Kinetic Profiles to Diagnostic Decisions","year":2025,"lang":"en","type":"article","venue":"ACS Sensors","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Canada Research Chairs","keywords":"Aptamer; Computer science; Algorithm; Kinetic energy; Artificial intelligence; Machine learning; Computational biology; Chemistry; Biological system; Biology; Molecular biology; Physics","score_opus":0.020980937193793205,"score_gpt":0.3235792637401617,"score_spread":0.30259832654636853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406865084","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94472235,0.00015973613,0.053695653,0.00016384551,0.00006918591,0.0005191065,0.000106946725,0.000022615557,0.00054056384],"genre_scores_gemma":[0.96769863,0.000040601833,0.03110871,0.00006828933,0.000027857248,0.00003857636,0.0004989527,0.000014786833,0.00050357095],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986915,0.000101074904,0.00048300062,0.00029261416,0.00016035119,0.00027143068],"domain_scores_gemma":[0.99854136,0.00076738757,0.00018957756,0.0002844816,0.0001479353,0.000069259615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029726012,0.00019947118,0.0004536389,0.00041726156,0.00016481009,0.000027504131,0.00021972344,0.00011376856,0.000013750249],"category_scores_gemma":[0.0019535676,0.00018761518,0.00020618226,0.0008738974,0.000056930672,0.000004691589,0.00008568163,0.00014914692,0.0000050031304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013547197,0.00012913476,0.15162638,0.0001159315,0.003071757,0.0000020571288,0.0045243665,0.42326167,0.4084562,0.00031974062,0.00042908938,0.007928198],"study_design_scores_gemma":[0.0014155012,0.0007813909,0.034710992,0.00022459215,0.0016368387,0.0000030608276,0.0019419398,0.51040626,0.43187293,0.00004180476,0.016269539,0.00069514505],"about_ca_topic_score_codex":0.000049300495,"about_ca_topic_score_gemma":0.00010099762,"teacher_disagreement_score":0.11691539,"about_ca_system_score_codex":0.000011113266,"about_ca_system_score_gemma":0.00004167802,"threshold_uncertainty_score":0.76507246},"labels":[],"label_agreement":null},{"id":"W4407220000","doi":"10.1101/2025.01.31.635962","title":"Predicting molecular recognition features in protein sequences with MoRFchibi 2.0","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Computational biology; Pattern recognition (psychology); Artificial intelligence; Biology","score_opus":0.006238984681612775,"score_gpt":0.21812618979209675,"score_spread":0.21188720511048398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407220000","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9950694,0.0006878479,0.002004011,0.00011817568,0.00015887569,0.0011028912,0.00012872145,0.00015425235,0.00057586224],"genre_scores_gemma":[0.9711417,0.00007649044,0.027952185,0.00017629444,0.00015537193,0.0003184482,0.0000049275272,0.00009305288,0.000081517705],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980108,0.00015453993,0.0004154477,0.0007351327,0.00027068437,0.0004133951],"domain_scores_gemma":[0.99844533,0.000012437272,0.00038193903,0.0008447165,0.00020599423,0.00010958925],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041237095,0.0004696976,0.00034575362,0.00025458744,0.00007274615,0.00011972125,0.00044185008,0.0006161953,0.00001645463],"category_scores_gemma":[0.00036332826,0.0004633785,0.00008435777,0.0003134513,0.00010626586,0.000009754352,0.00042942018,0.00078270206,0.0000108201475],"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":[0.00009860893,0.00009024013,0.02798774,0.00090583967,0.00018027255,0.000052360658,0.000013056895,0.0014851954,0.9689012,0.00014447598,0.00012210847,0.000018858536],"study_design_scores_gemma":[0.0007582671,0.00021001007,0.024474371,0.0019604142,0.00007565937,1.0352167e-7,0.000007998686,0.000931226,0.96890825,0.0000056295753,0.0017300192,0.0009380782],"about_ca_topic_score_codex":0.000114004906,"about_ca_topic_score_gemma":0.000034547655,"teacher_disagreement_score":0.025948174,"about_ca_system_score_codex":0.00007215424,"about_ca_system_score_gemma":0.0005021866,"threshold_uncertainty_score":0.9997818},"labels":[],"label_agreement":null},{"id":"W4407305029","doi":"10.70251/hyjr2348.316273","title":"AlphaFold: A Comprehensive Guide to the Revolutionary AI Tool and Its Methodology","year":2025,"lang":"en","type":"article","venue":"American journal of student research.","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Brantford Energy (Canada)","funders":"California Institute of Technology","keywords":"Computer science; Engineering","score_opus":0.06765478966592033,"score_gpt":0.47715431973868616,"score_spread":0.40949953007276585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407305029","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96231055,0.0036346982,0.012637758,0.019747904,0.00016769176,0.00031321295,0.000005279608,0.000004001857,0.0011788774],"genre_scores_gemma":[0.97188914,0.0021993173,0.01706374,0.006120293,0.0002991086,0.000015549433,0.000004096558,0.0000136644585,0.0023951153],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99801797,0.00081759924,0.00037243858,0.000134394,0.00039728993,0.00026031965],"domain_scores_gemma":[0.9984518,0.00031571285,0.00015375999,0.00023670259,0.0007537525,0.00008825435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020293694,0.00009538517,0.00021711439,0.00018544438,0.00017043517,0.000026046035,0.0005314239,0.00003546007,0.000009270016],"category_scores_gemma":[0.0009922821,0.00006440945,0.000066265704,0.00033776733,0.00026309973,0.000005530361,0.00063229504,0.00043186583,0.000007855903],"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":[0.0015014419,0.00029299513,0.049475275,0.00012727547,0.0016034652,0.00007030778,0.0028460866,0.0029112468,0.166051,0.006896253,0.64078224,0.1274424],"study_design_scores_gemma":[0.00067915785,0.0030555143,0.13524644,0.00008659579,0.000039610146,0.000260492,0.004328723,0.00028741753,0.0028431686,0.0001411244,0.8528711,0.00016063449],"about_ca_topic_score_codex":0.000028782866,"about_ca_topic_score_gemma":0.000009018505,"teacher_disagreement_score":0.21208887,"about_ca_system_score_codex":0.00003617639,"about_ca_system_score_gemma":0.00018657399,"threshold_uncertainty_score":0.2626541},"labels":[],"label_agreement":null},{"id":"W4407362158","doi":"10.7554/elife.102274.3.sa0","title":"eLife Assessment: Alzheimer-mutant γ-secretase complexes stall amyloid β-peptide production","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Mutant; Amyloid precursor protein; Amyloid precursor protein secretase; Amyloid (mycology); Peptide; β amyloid; P3 peptide; Chemistry; Alzheimer's disease; Biochemistry; Medicine; Internal medicine; Gene; Disease","score_opus":0.022747949609090882,"score_gpt":0.33928083704532463,"score_spread":0.31653288743623376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407362158","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":[0.001988778,0.18797494,0.02204353,0.094533816,0.016227003,0.009916465,0.005523037,0.00082064484,0.66097176],"genre_scores_gemma":[0.0023812796,0.07143179,0.04657765,0.02348657,0.003302482,0.0004129359,0.09982289,0.00023875097,0.7523456],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99687326,0.00021080913,0.0009691199,0.00082306005,0.0006254505,0.00049832003],"domain_scores_gemma":[0.99729455,0.000029231183,0.00060930673,0.001418907,0.00049501786,0.00015299952],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00077942543,0.00067956216,0.0007802961,0.00014333718,0.00015451697,0.00008797914,0.00068366085,0.0005028645,0.0006573176],"category_scores_gemma":[0.00056741777,0.00060165767,0.0003550038,0.00021812177,0.00013307371,0.0000075862245,0.00058855745,0.00078970206,0.00007864603],"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":[0.000016283915,0.000073390205,0.000042107276,0.002560551,0.0005719829,0.0000025880179,0.000007157775,0.00008605197,0.009062833,0.00011486995,0.98378533,0.0036768408],"study_design_scores_gemma":[0.0002387995,0.00018808433,0.000053283704,0.0011727113,0.00055711356,0.000036399302,0.000016195807,0.00028843738,0.0070633357,0.000017796312,0.98971677,0.00065110205],"about_ca_topic_score_codex":0.00012022364,"about_ca_topic_score_gemma":0.00015086278,"teacher_disagreement_score":0.11654315,"about_ca_system_score_codex":0.000055479813,"about_ca_system_score_gemma":0.0006946405,"threshold_uncertainty_score":0.9996435},"labels":[],"label_agreement":null},{"id":"W4408107786","doi":"10.1007/978-3-031-82481-4_5","title":"Protein Sequence Generation Using Denoising Probabilistic Diffusion Model","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"National Research Council Canada; University of Ottawa","funders":"","keywords":"Computer science; Probabilistic logic; Sequence (biology); Diffusion; Noise reduction; Artificial intelligence; Algorithm; Chemistry","score_opus":0.02435756534585107,"score_gpt":0.2743289694942021,"score_spread":0.24997140414835103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408107786","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":[0.020829657,0.0001328651,0.9772374,0.00006877588,0.00024667569,0.00049414596,0.000007610473,0.000020986521,0.0009619083],"genre_scores_gemma":[0.35361296,0.00002001825,0.6436355,0.0006939043,0.00053216756,0.000010613558,0.000101423815,0.000037746428,0.0013556458],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998276,0.000023279625,0.00036061337,0.00066874054,0.00036644685,0.0003049338],"domain_scores_gemma":[0.99891543,0.000020515505,0.00020880126,0.0006194275,0.00017707687,0.000058744463],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038442775,0.00031796144,0.00022345464,0.00021957049,0.0002178434,0.00015127085,0.00058822636,0.00034307907,0.000003985755],"category_scores_gemma":[0.00024587274,0.00029853208,0.00006468601,0.00013284446,0.00032421944,0.000014027587,0.00059310236,0.0004036598,0.0000020921204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000064577257,0.000009134437,0.000026887112,0.00009531129,0.0000049135365,0.0000030180797,0.00008164339,0.74305207,0.20811133,0.00082054065,0.000006896097,0.0477818],"study_design_scores_gemma":[0.0001041182,0.00006935945,0.000003001366,0.00032459878,0.000009091762,0.000017269002,5.533024e-8,0.9792505,0.014965094,0.004780445,0.00016421171,0.00031224496],"about_ca_topic_score_codex":0.000012658186,"about_ca_topic_score_gemma":0.00004553755,"teacher_disagreement_score":0.33360186,"about_ca_system_score_codex":0.00016653408,"about_ca_system_score_gemma":0.00067203963,"threshold_uncertainty_score":0.99994665},"labels":[],"label_agreement":null},{"id":"W4408146489","doi":"10.1109/icmla61862.2024.00112","title":"Deep Few-Shot Network for Protein Family Classification: Bridging the Gap Between Limited Data and High Performance","year":2024,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; Concordia University","funders":"","keywords":"Bridging (networking); Computer science; Artificial intelligence; One shot; Shot (pellet); Computer network; Engineering; Materials science","score_opus":0.05003641067872572,"score_gpt":0.29468542969586864,"score_spread":0.24464901901714292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408146489","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7061398,0.0018542452,0.28372005,0.0033399598,0.00023265705,0.0010797229,0.000094435905,0.00010869282,0.0034304606],"genre_scores_gemma":[0.9810084,0.00013736844,0.014815141,0.00037457948,0.0009903602,0.0000535821,0.0014912704,0.000023746363,0.0011055695],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915534,0.000031488064,0.00021806915,0.00027976814,0.00009820787,0.00021709867],"domain_scores_gemma":[0.99918133,0.000050370603,0.000054146774,0.00063408207,0.00003945684,0.000040599658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048375744,0.00012862349,0.00009643734,0.000018790606,0.0001885789,0.0001408049,0.00039181762,0.00009756766,0.000007117808],"category_scores_gemma":[0.00009411362,0.000088328234,0.000023990426,0.00010507674,0.0000696548,0.0000121855755,0.00028469352,0.00014392023,0.0000090145995],"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":[0.00024019075,0.00005706153,0.036856126,0.0021680456,0.0008904582,0.0000025422478,0.0005253311,0.0043142904,0.113548644,0.012264655,0.17706163,0.652071],"study_design_scores_gemma":[0.00018981849,0.00014840359,0.015791273,0.000057144538,0.000046381632,0.000007116713,0.000059174832,0.73714983,0.0021275221,0.000074024574,0.24414629,0.00020303529],"about_ca_topic_score_codex":0.000007831361,"about_ca_topic_score_gemma":0.0000065075637,"teacher_disagreement_score":0.73283553,"about_ca_system_score_codex":0.000006578635,"about_ca_system_score_gemma":0.000041421954,"threshold_uncertainty_score":0.3601921},"labels":[],"label_agreement":null},{"id":"W4408159463","doi":"10.1016/j.compbiomed.2025.109958","title":"StackTHP: A stacking ensemble model for accurate prediction of tumor-homing peptides in cancer therapy","year":2025,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; King Saud University","keywords":"Homing (biology); Stacking; Cancer therapy; Computer science; Artificial intelligence; Cancer; Computational biology; Cancer research; Medicine; Internal medicine; Chemistry; Biology","score_opus":0.025505766641454507,"score_gpt":0.35444010443666163,"score_spread":0.32893433779520714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408159463","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8059295,0.0021266618,0.19084531,0.00035568018,0.00023324144,0.0002667536,0.0000124640255,0.0000063090206,0.0002241174],"genre_scores_gemma":[0.9921669,0.0014091298,0.0055486485,0.0006580888,0.0000621824,0.000034064782,0.000060326052,0.000005062415,0.000055630873],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934006,0.000038462902,0.00028768764,0.0001647288,0.000025222798,0.00014382054],"domain_scores_gemma":[0.9996689,0.000067472705,0.00009452111,0.00011125144,0.00003973851,0.00001810166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033706563,0.00009483975,0.00020163418,0.00012619227,0.000028960945,0.0000022071324,0.00009113135,0.00009640738,9.928567e-7],"category_scores_gemma":[0.00009929415,0.0000771275,0.000018566594,0.000084516156,0.00012812768,0.0000037567693,0.000054783806,0.0000941544,2.6566505e-8],"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":[0.0012884017,0.0001288569,0.46290854,0.00062048016,0.0001628703,0.0000018909838,0.0032640966,0.027786013,0.3727085,0.005179126,0.0032861994,0.122665025],"study_design_scores_gemma":[0.0054584406,0.0008694048,0.028395545,0.0006898887,0.00001619736,0.0000046583127,0.00028788528,0.94592315,0.010566516,0.003468296,0.004148464,0.00017155806],"about_ca_topic_score_codex":0.00004644712,"about_ca_topic_score_gemma":0.000078655714,"teacher_disagreement_score":0.91813713,"about_ca_system_score_codex":0.000014221121,"about_ca_system_score_gemma":0.000054568565,"threshold_uncertainty_score":0.3145168},"labels":[],"label_agreement":null},{"id":"W4408177377","doi":"10.1016/j.sbi.2025.103027","title":"Language models for protein design","year":2025,"lang":"en","type":"review","venue":"Current Opinion in Structural Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Protein design; Computational biology; Computer science; Linguistics; Biology; Protein structure; Biochemistry; Philosophy","score_opus":0.06558631815449587,"score_gpt":0.4139570759980702,"score_spread":0.3483707578435743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408177377","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":[0.000007575473,0.9720386,0.022575857,0.00001046461,0.0026095898,0.002270844,0.0003660885,0.000021924423,0.00009905073],"genre_scores_gemma":[0.000025025962,0.9851339,0.0063285325,0.0000101979995,0.00059083593,0.0006782938,0.0070549557,0.000029321605,0.00014896817],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99810696,0.0002980412,0.0006682959,0.00048897753,0.0000581988,0.0003795555],"domain_scores_gemma":[0.9990486,0.00008016739,0.00034011455,0.00042947519,0.000052134794,0.000049514423],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025161487,0.00043366657,0.0008517458,0.00019649505,0.00005710827,0.000020758556,0.000506621,0.0005939313,0.000010257088],"category_scores_gemma":[0.00032588182,0.00033599642,0.00030629637,0.00015665646,0.00008218018,0.0000042302813,0.00024565254,0.00037378143,0.000004454383],"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":[0.000026704756,0.0000084103895,0.000003291228,0.022831708,0.000046931782,6.3477195e-8,0.00003257694,0.00009938092,0.000035334848,0.0023781287,0.0011633813,0.97337407],"study_design_scores_gemma":[0.00035937148,0.00017604308,6.1413556e-7,0.0045954576,0.000036013043,0.000008794206,0.0000070435694,0.0012451366,0.000018644523,0.0009140366,0.9922235,0.0004153649],"about_ca_topic_score_codex":0.000003884063,"about_ca_topic_score_gemma":9.4037205e-7,"teacher_disagreement_score":0.9910601,"about_ca_system_score_codex":0.000043862034,"about_ca_system_score_gemma":0.00029824185,"threshold_uncertainty_score":0.9999092},"labels":[],"label_agreement":null},{"id":"W4408203656","doi":"10.1051/bioconf/202516301001","title":"TooT-SS: Transfer Learning using ProtBERT-BFD Language Model for Predicting Specific Substrates of Transport Proteins","year":2025,"lang":"en","type":"article","venue":"BIO Web of Conferences","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University; Genome Canada","keywords":"Transfer of learning; Computer science; Artificial intelligence","score_opus":0.020483100541744646,"score_gpt":0.2767272163877422,"score_spread":0.2562441158459976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408203656","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.904919,0.00038171283,0.089484,0.00003729053,0.0000607689,0.0007012157,0.00004698603,0.000017733535,0.0043512746],"genre_scores_gemma":[0.9931704,0.00006527344,0.005996945,0.000011600196,0.000037658236,0.00004091866,0.0001069162,0.00001130117,0.0005589888],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988506,0.00005203502,0.0005831545,0.00019517135,0.00013321015,0.0001858747],"domain_scores_gemma":[0.9994115,0.000040481424,0.0001778661,0.00017500298,0.00016474923,0.000030361023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005151231,0.00016125024,0.00033367556,0.00008960309,0.00006386245,0.000014477342,0.00021306581,0.00015895157,0.00001952986],"category_scores_gemma":[0.00013016307,0.00013873671,0.00015176166,0.00009991202,0.00012341094,0.000008340126,0.000019241312,0.0001231003,1.6537236e-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":[0.00023648291,0.00008764413,0.1470998,0.0010552452,0.00017581879,3.7285847e-7,0.0011333717,0.012506173,0.8307863,0.0035022327,0.00003429236,0.0033822837],"study_design_scores_gemma":[0.00074815215,0.00031942636,0.003439975,0.0003194752,0.00008242706,0.0000015891657,0.00120149,0.28373545,0.70679706,0.00008045241,0.003049278,0.00022521976],"about_ca_topic_score_codex":0.00003255582,"about_ca_topic_score_gemma":0.00006142749,"teacher_disagreement_score":0.27122927,"about_ca_system_score_codex":0.000005319215,"about_ca_system_score_gemma":0.00061965466,"threshold_uncertainty_score":0.56575185},"labels":[],"label_agreement":null},{"id":"W4408339030","doi":"10.1101/2025.03.05.641584","title":"Zero-shot segmentation using embeddings from a protein language model identifies functional regions in the human proteome","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Hospital for Sick Children; University of Toronto","funders":"","keywords":"Proteome; Computational biology; Human proteome project; Segmentation; Zero (linguistics); Computer science; Shot (pellet); Artificial intelligence; Natural language processing; Biology; Chemistry; Proteomics; Bioinformatics; Linguistics; Genetics; Gene","score_opus":0.021754238914010775,"score_gpt":0.2732539982848037,"score_spread":0.2514997593707929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408339030","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95895547,0.000219078,0.038838893,0.0001162522,0.00018191645,0.0013223282,0.00026962857,0.00006458664,0.000031826945],"genre_scores_gemma":[0.9824851,0.0000142629015,0.016382013,0.0002741218,0.00024421734,0.0004633597,0.000024833778,0.000045714653,0.000066380744],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99801445,0.00018173552,0.0005194752,0.0006100436,0.0003507626,0.00032352886],"domain_scores_gemma":[0.9983374,0.000017935472,0.00041084,0.0009955524,0.00017897945,0.00005928326],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005724518,0.00039440533,0.0002794741,0.00019537967,0.00023477197,0.00023562224,0.00056863605,0.00046670748,0.000013215578],"category_scores_gemma":[0.00019343726,0.00037157576,0.000132694,0.00024140478,0.00009750352,0.00002010698,0.0005104331,0.00070789835,0.0000054920274],"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":[0.000022088085,0.00006613459,0.001239698,0.00022044666,0.00007962567,0.000005273788,0.00013242422,0.008547935,0.9891348,0.00026949178,0.00028167534,4.1537606e-7],"study_design_scores_gemma":[0.0011054097,0.00006848634,0.014705936,0.0010075766,0.00018664106,7.17911e-8,0.000120031575,0.05478633,0.9263162,0.0000713706,0.00046780694,0.0011641192],"about_ca_topic_score_codex":0.00025525148,"about_ca_topic_score_gemma":0.000022177202,"teacher_disagreement_score":0.06281857,"about_ca_system_score_codex":0.000122045516,"about_ca_system_score_gemma":0.0003951103,"threshold_uncertainty_score":0.99987364},"labels":[],"label_agreement":null},{"id":"W4408454493","doi":"10.1101/2025.03.09.642228","title":"<i>ProteoSync</i> , a program for ortholog selection, automated sequence alignment and conservation projection onto protein atomic coordinates","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Sinai Health System; Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"","keywords":"Selection (genetic algorithm); Projection (relational algebra); Sequence (biology); Computational biology; Computer science; Conserved sequence; Sequence alignment; Biology; Algorithm; Genetics; Artificial intelligence; Peptide sequence; Gene","score_opus":0.009620870331512902,"score_gpt":0.2600677491958133,"score_spread":0.25044687886430045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408454493","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9808165,0.00026888042,0.010306714,0.00043161228,0.00031629726,0.00666115,0.00025859784,0.00092485244,0.000015399859],"genre_scores_gemma":[0.9210656,0.0000788408,0.07353826,0.00027861347,0.00016761091,0.004725215,0.000017275477,0.00006683101,0.00006173587],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.997863,0.00014450781,0.0005610923,0.0008228685,0.00018717011,0.00042139037],"domain_scores_gemma":[0.99808496,0.000019213225,0.0005432945,0.00055520586,0.00069033104,0.000106972344],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006421821,0.00048444513,0.00037453996,0.00016019915,0.00025159802,0.00019821986,0.00026555496,0.00072036387,0.000003313643],"category_scores_gemma":[0.00043497328,0.0005224276,0.00010195148,0.00027217224,0.00012999,0.000017553417,0.000338339,0.00038120153,0.0000025798358],"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":[0.00013982075,0.00014629832,0.011411298,0.001799856,0.00021873422,0.0000014261425,0.000011215876,0.00015906162,0.98361725,0.00034780608,0.0021197265,0.000027487313],"study_design_scores_gemma":[0.0011794795,0.00063319295,0.008056336,0.0006405776,0.00016446867,2.3614433e-7,0.0000064625524,0.07706593,0.8845934,0.0000078203275,0.026657341,0.0009947352],"about_ca_topic_score_codex":0.00011957896,"about_ca_topic_score_gemma":0.000021842085,"teacher_disagreement_score":0.09902385,"about_ca_system_score_codex":0.0001260653,"about_ca_system_score_gemma":0.00079081854,"threshold_uncertainty_score":0.9997227},"labels":[],"label_agreement":null},{"id":"W4408556965","doi":"10.1016/j.xpro.2025.103681","title":"Protocol for assessing distances in pathway space for classifier feature sets from machine learning methods","year":2025,"lang":"en","type":"article","venue":"STAR Protocols","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Canada's Michael Smith Genome Sciences Centre","funders":"Fundação Araucária; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; National Cancer Institute; National Institutes of Health; Fundacion Araucaria","keywords":"Computer science; Classifier (UML); Artificial intelligence; Protocol (science); Machine learning; Feature vector; Pattern recognition (psychology); Medicine","score_opus":0.035988771274633624,"score_gpt":0.4423363084063617,"score_spread":0.40634753713172805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408556965","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":[0.00055464415,0.000018293977,0.28850192,0.00045985123,0.00005070195,0.708072,0.00011259631,0.00004179533,0.0021882039],"genre_scores_gemma":[0.000387148,2.4842285e-7,0.31982315,0.00013179203,0.00007247601,0.67779297,0.00022267971,0.000026344745,0.0015432243],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99842846,0.00026482582,0.00038479955,0.00042712453,0.00011933939,0.0003754702],"domain_scores_gemma":[0.999002,0.00019052395,0.0002686832,0.00036452248,0.00012155666,0.000052744097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009713758,0.00027070832,0.00031297372,0.00007947169,0.00019016124,0.00015661785,0.00029454168,0.00029669382,0.000014944677],"category_scores_gemma":[0.0009729923,0.00023293284,0.0001358527,0.00015539594,0.000057019024,0.000017751683,0.00013105824,0.00034843435,8.5852497e-7],"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":[0.006890264,0.0007206059,0.072352074,0.008340811,0.00044753877,0.000005730092,0.0011060365,0.0018550475,0.5518442,0.0047442084,0.023676401,0.3280171],"study_design_scores_gemma":[0.0034737184,0.00034336734,0.0012951484,0.0004016286,0.000009147591,6.091585e-7,0.000112111185,0.022410106,0.073654026,0.0018566945,0.89614946,0.00029397884],"about_ca_topic_score_codex":0.000018545237,"about_ca_topic_score_gemma":0.000090377864,"teacher_disagreement_score":0.87247306,"about_ca_system_score_codex":0.00004952324,"about_ca_system_score_gemma":0.00023456532,"threshold_uncertainty_score":0.94987255},"labels":[],"label_agreement":null},{"id":"W4408693799","doi":"10.1186/s13321-025-00979-5","title":"An interpretable deep geometric learning model to predict the effects of mutations on protein–protein interactions using large-scale protein language model","year":2025,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Children’s Health Research Institute; Lawson Health Research Institute; University of Manitoba; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Scale (ratio); Artificial intelligence; Machine learning","score_opus":0.004592795866963382,"score_gpt":0.28068493732233607,"score_spread":0.2760921414553727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408693799","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60549605,0.000039239505,0.39256844,0.00003938149,0.000035818113,0.00042344816,0.0000067019923,0.000007678932,0.0013832196],"genre_scores_gemma":[0.9419887,0.000003115225,0.056825586,0.00015349315,0.000046167777,0.0000299861,0.000019540113,0.000017982098,0.0009154473],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984952,0.000037157875,0.0008037224,0.00009088867,0.00032444438,0.00024857323],"domain_scores_gemma":[0.99847156,0.000049123515,0.0007020334,0.0003655113,0.00031102897,0.000100763384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056915253,0.00018958637,0.00027051094,0.00035235166,0.00015477298,0.000063195905,0.0004382721,0.000119126256,0.000005052233],"category_scores_gemma":[0.001374512,0.00014360122,0.00014572365,0.00040545387,0.000043165688,0.00006540283,0.00014405652,0.0005619621,0.0000020099285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000099808734,0.0001256433,0.000060173265,0.0004717925,0.00008713307,6.2223603e-7,0.0040553617,0.5207611,0.4722017,0.00004938801,0.00010810461,0.0019791685],"study_design_scores_gemma":[0.00035639692,0.0003187895,0.000010738018,0.0004149175,0.000044780274,0.000009449468,0.0008511692,0.6234721,0.37425002,0.00005640056,0.0001238337,0.00009138699],"about_ca_topic_score_codex":0.000003918121,"about_ca_topic_score_gemma":0.0000035115477,"teacher_disagreement_score":0.3364926,"about_ca_system_score_codex":0.00006539605,"about_ca_system_score_gemma":0.00019228761,"threshold_uncertainty_score":0.58558875},"labels":[],"label_agreement":null},{"id":"W4408701827","doi":"10.1002/minf.70029","title":"The Use of DeepQSAR Models for the Discovery of Peptides With Enhanced Antimicrobial and Antibiofilm Potential","year":2025,"lang":"en","type":"preprint","venue":"Molecular Informatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"British Columbia Knowledge Development Fund; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canada Foundation for Innovation","keywords":"Antimicrobial; Antimicrobial peptides; Chemistry; Biochemical engineering; Nanotechnology; Computational biology; Microbiology; Biology; Materials science; Engineering","score_opus":0.010574617349845829,"score_gpt":0.2379863335103369,"score_spread":0.22741171616049108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408701827","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36419138,0.00024997274,0.6340546,0.000075302814,0.000120312914,0.00080857397,0.00031423548,0.00000659554,0.00017902978],"genre_scores_gemma":[0.9296734,0.0011533361,0.06820277,0.0002684279,0.000033339373,0.000032862557,0.0003722411,0.000025871514,0.00023778448],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985258,0.000047038146,0.0007915526,0.0001484961,0.00023722545,0.00024988543],"domain_scores_gemma":[0.99780715,0.000118808275,0.0008362742,0.00088894134,0.0003197023,0.00002911761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002977226,0.00030092726,0.00034554725,0.000059918533,0.00015731693,0.00017007552,0.0005451588,0.00027740485,2.4031687e-7],"category_scores_gemma":[0.00019705344,0.0001795879,0.00020334874,0.00007436312,0.00041246685,0.00002481087,0.0009339858,0.00028838884,1.2090344e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006611763,0.000057738882,0.000089779285,0.0033405053,0.0011281121,8.807418e-7,0.001097437,0.88967067,0.09721723,0.0017125926,0.0012707625,0.0037531236],"study_design_scores_gemma":[0.0010547846,0.00033527522,0.00008182585,0.00052685314,0.00048679975,0.000022085964,0.0003959559,0.40154782,0.591944,0.00026140577,0.0028581151,0.0004851189],"about_ca_topic_score_codex":0.000027086175,"about_ca_topic_score_gemma":0.000013982539,"teacher_disagreement_score":0.5658518,"about_ca_system_score_codex":0.0000089155865,"about_ca_system_score_gemma":0.00023757678,"threshold_uncertainty_score":0.73233825},"labels":[],"label_agreement":null},{"id":"W4409323406","doi":"10.1016/j.jhazmat.2025.138240","title":"The role of machine learning in predicting titanium dioxide nanoparticles induced pulmonary pathology using transcriptomic biomarkers","year":2025,"lang":"en","type":"article","venue":"Journal of Hazardous Materials","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Health Canada","funders":"Horizon 2020; Health Canada; Narodowe Centrum Nauki","keywords":"Transcriptome; Titanium dioxide; Nanoparticle; Pathology; Chemistry; Environmental chemistry; Materials science; Medicine; Nanotechnology; Biochemistry; Metallurgy; Gene expression; Gene","score_opus":0.006150515901647446,"score_gpt":0.24373859547675392,"score_spread":0.23758807957510647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409323406","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9976928,0.0012954317,0.00016229738,0.000121455756,0.00040032543,0.00010162271,0.000008594001,0.000005387214,0.00021208516],"genre_scores_gemma":[0.9987344,0.0001706124,0.0009413355,0.000032322143,0.000077233024,0.0000018114944,0.0000046906666,0.000014134234,0.000023425064],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99846655,0.00026046706,0.00083522365,0.00009762665,0.00012735146,0.00021275986],"domain_scores_gemma":[0.99908376,0.00005364927,0.00057691656,0.00015274629,0.00010113587,0.000031766373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014032391,0.0001254856,0.0002812574,0.00012236997,0.000094568735,0.000033358356,0.00024610313,0.00012806055,0.000006202186],"category_scores_gemma":[0.00045802695,0.000092800314,0.00008234641,0.00010815282,0.00006982489,0.000011415751,0.00008366493,0.00017780681,4.93755e-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":[0.00041014142,0.000030940002,0.021946052,0.000047948193,0.0000808924,0.0000126507075,0.00009686,0.0005023239,0.9753379,0.000031889023,0.000009176541,0.0014932007],"study_design_scores_gemma":[0.00044988963,0.00019520505,0.0055922554,0.000103326296,0.00004648866,0.0002152824,0.00036980322,0.0014345922,0.99067146,0.000136647,0.00070368516,0.00008138983],"about_ca_topic_score_codex":0.000037426358,"about_ca_topic_score_gemma":0.000019118737,"teacher_disagreement_score":0.016353795,"about_ca_system_score_codex":0.000031350377,"about_ca_system_score_gemma":0.00013215873,"threshold_uncertainty_score":0.3784287},"labels":[],"label_agreement":null},{"id":"W4409795125","doi":"10.61091/jcmcc127b-394","title":"Research on Structural Variation Detection Methods of Wheat Genome Based on Deep Learning","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Variation (astronomy); Structural variation; Genome; Artificial intelligence; Computational biology; Biology; Computer science; Evolutionary biology; Genetics; Gene; Physics","score_opus":0.014290187179429053,"score_gpt":0.3456524033010899,"score_spread":0.3313622161216609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409795125","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8788871,0.0001290408,0.11220879,0.00007124127,0.0055943457,0.00027899648,9.1296147e-7,0.000013829629,0.0028156987],"genre_scores_gemma":[0.98397326,0.000014141631,0.015395182,0.000024815512,0.00055446837,0.0000015669881,0.0000037600778,0.00002087931,0.000011915878],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974885,0.00061601464,0.0008857333,0.0001866348,0.00056784804,0.0002552954],"domain_scores_gemma":[0.997286,0.00081908226,0.0007848755,0.00026005317,0.00076863973,0.00008129914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004207207,0.00020583594,0.00044871116,0.0004251241,0.00032180062,0.000095194344,0.00030614267,0.00024402702,0.000003908672],"category_scores_gemma":[0.0019036161,0.00018320272,0.00014291453,0.00038026844,0.00008473071,0.000012003292,0.00015779228,0.00082833733,6.4511113e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029823375,0.0011713271,0.00086743286,0.0017351176,0.0006282843,0.000008893918,0.002162707,0.083787486,0.27576482,0.5893896,0.000080839585,0.04142112],"study_design_scores_gemma":[0.011934687,0.014307399,0.0044972473,0.0011355666,0.00021873646,0.00004457538,0.000989277,0.64467335,0.10976545,0.20889843,0.002790057,0.0007452461],"about_ca_topic_score_codex":0.0000054221236,"about_ca_topic_score_gemma":2.815903e-7,"teacher_disagreement_score":0.56088585,"about_ca_system_score_codex":0.00007890031,"about_ca_system_score_gemma":0.0001236746,"threshold_uncertainty_score":0.747079},"labels":[],"label_agreement":null},{"id":"W4410087515","doi":"10.1109/wi-iat62293.2024.00126","title":"Protein Sequence Prediction Based on Feature Combination and Attention Mechanism","year":2024,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Mechanism (biology); Sequence (biology); Feature (linguistics); Artificial intelligence; Protein sequencing; Computational biology; Pattern recognition (psychology); Peptide sequence; Chemistry; Biology; Biochemistry; Gene","score_opus":0.006211221312361955,"score_gpt":0.2416613159760459,"score_spread":0.23545009466368394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410087515","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8557847,0.000092752634,0.12931997,0.0026666673,0.0003182462,0.0006383436,0.00003249201,0.0001855836,0.010961254],"genre_scores_gemma":[0.993242,0.0000074590835,0.003002071,0.00019497891,0.000048443228,0.000021022983,0.0002675884,0.000009323033,0.0032071015],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99958795,0.000021219988,0.000071859555,0.00014673702,0.00010001086,0.00007222406],"domain_scores_gemma":[0.99981576,0.000003819132,0.000019825477,0.000110373745,0.00002557045,0.000024648152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013853784,0.000073932206,0.000036929523,0.00004156322,0.000044975626,0.000052551008,0.000036744063,0.00010604066,0.000013557209],"category_scores_gemma":[0.00003370868,0.00006191877,0.000022100412,0.000050449966,0.000016287011,0.000004948064,0.000019363033,0.0000987542,0.000010441268],"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":[0.000028273966,0.000028981784,0.00039228107,0.00019451488,0.00001638723,0.0000015447862,0.00002497202,0.00014482386,0.9705983,0.020741692,0.0021322095,0.005696044],"study_design_scores_gemma":[0.0004995935,0.0011334213,0.002542936,0.00017830111,0.000019361738,0.0000217036,0.000031523003,0.8155994,0.16334641,0.0013836329,0.015029903,0.00021381458],"about_ca_topic_score_codex":0.0000027460899,"about_ca_topic_score_gemma":0.0000016834832,"teacher_disagreement_score":0.8154546,"about_ca_system_score_codex":0.000011809793,"about_ca_system_score_gemma":0.00001953398,"threshold_uncertainty_score":0.2524974},"labels":[],"label_agreement":null},{"id":"W4410393925","doi":"10.1109/tai.2025.3567434","title":"Deep3BPP: Identification of Blood–Brain Barrier Penetrating Peptides Using Word Embedding Feature Extraction Method and CNN-LSTM","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Identification (biology); Computer science; Artificial intelligence; Word embedding; Feature extraction; Extraction (chemistry); Feature (linguistics); Embedding; Pattern recognition (psychology); Chemistry; Chromatography; Biology; Philosophy; Botany","score_opus":0.0210132262035905,"score_gpt":0.358332301106191,"score_spread":0.3373190749026005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410393925","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2518279,0.000080728634,0.74737144,0.000116761454,0.00026804308,0.00015850007,0.000011422098,0.00001832788,0.00014684677],"genre_scores_gemma":[0.9596847,0.000043486853,0.039503805,0.00009686462,0.000049140093,0.000013167042,0.000008417993,0.000015276199,0.0005851294],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987242,0.00012614876,0.0005145877,0.00030645382,0.00014697512,0.00018161083],"domain_scores_gemma":[0.9991825,0.0001361153,0.0002186328,0.0002826185,0.00012969543,0.000050402527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005527594,0.00017231518,0.00015611766,0.00018609896,0.00027683526,0.00007480951,0.0001384006,0.00019706502,0.000024662751],"category_scores_gemma":[0.00015660882,0.00018518846,0.00009139731,0.00027856213,0.00010252576,0.000024872028,0.0000049303667,0.00028972936,0.0000033911629],"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":[0.000060796898,0.00005956836,0.00004081022,0.000060855204,0.00006058294,4.627291e-7,0.00024133985,0.08733995,0.83551264,0.00020767683,0.000016957114,0.07639833],"study_design_scores_gemma":[0.00003531678,0.00006703188,0.000076819524,0.00006336933,0.000083348765,0.000012973867,0.00048015325,0.15887398,0.83962715,0.00042317226,0.00011894205,0.00013775882],"about_ca_topic_score_codex":0.000040060608,"about_ca_topic_score_gemma":0.00009068651,"teacher_disagreement_score":0.7078677,"about_ca_system_score_codex":0.000018355486,"about_ca_system_score_gemma":0.00006380486,"threshold_uncertainty_score":0.7551766},"labels":[],"label_agreement":null},{"id":"W4410716781","doi":"10.1101/2025.05.19.654848","title":"upsAI: A high-accuracy machine learning classifier for predicting <i>Plasmodium falciparum var</i> gene upstream groups","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"Région Occitanie Pyrénées-Méditerranée; Agence Nationale de la Recherche; Université de Montpellier; Wellcome Trust","keywords":"Plasmodium falciparum; Classifier (UML); Upstream (networking); Artificial intelligence; Computer science; Machine learning; Computational biology; Biology; Malaria; Immunology; Computer network","score_opus":0.00967620302088911,"score_gpt":0.2321083804290883,"score_spread":0.22243217740819918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410716781","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91134745,0.00196473,0.076621935,0.0004938415,0.003420728,0.0026291579,0.0026243955,0.0007194552,0.00017833935],"genre_scores_gemma":[0.95634127,0.00058875495,0.039882984,0.000546513,0.0013861525,0.0007013269,0.00007665518,0.0002345159,0.00024183896],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99558276,0.00025896594,0.0011297597,0.001484391,0.00044963023,0.0010944866],"domain_scores_gemma":[0.9959449,0.00018166828,0.00110916,0.0018042347,0.00062394526,0.00033607887],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0010687343,0.00107486,0.000894052,0.000307099,0.00052410597,0.0003169928,0.0011433996,0.0013884695,0.00002678898],"category_scores_gemma":[0.0018664242,0.0011694921,0.00044440114,0.00034686818,0.00015979524,0.000026129312,0.0016770007,0.0016219261,0.000022417235],"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":[0.0005717764,0.00040790686,0.05498481,0.0029713688,0.0014733226,0.00002263077,0.00005832196,0.012888101,0.92221284,0.0010528822,0.0033051104,0.00005093577],"study_design_scores_gemma":[0.0032259333,0.0006961065,0.008928268,0.0008001664,0.00067049,3.2105294e-7,0.000015084838,0.05229317,0.7716461,0.000011718343,0.15893316,0.002779523],"about_ca_topic_score_codex":0.00010487001,"about_ca_topic_score_gemma":0.000009835553,"teacher_disagreement_score":0.15562806,"about_ca_system_score_codex":0.00017367507,"about_ca_system_score_gemma":0.0007887048,"threshold_uncertainty_score":0.9999079},"labels":[],"label_agreement":null},{"id":"W4410811958","doi":"10.1093/biomethods/bpaf041","title":"KD_MultiSucc: incorporating multi-teacher knowledge distillation and word embeddings for cross-species prediction of protein succinylation sites","year":2025,"lang":"en","type":"article","venue":"Biology Methods and Protocols","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Succinylation; Computer science; Computational biology; Embedding; Artificial intelligence; Biological system; Chemistry; Lysine; Biology; Biochemistry","score_opus":0.05279280048849869,"score_gpt":0.4607313964467801,"score_spread":0.4079385959582814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410811958","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":[0.37527087,0.0003203226,0.60080224,0.00004930142,0.000049748618,0.02290389,0.00006126416,0.000026051252,0.0005162949],"genre_scores_gemma":[0.3487027,0.000010724733,0.63400406,0.000019700325,0.00010535663,0.015667858,0.00024948755,0.000014095311,0.0012260216],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99898386,0.00024951453,0.00037322074,0.00024396554,0.000025066736,0.00012436572],"domain_scores_gemma":[0.9993132,0.00010131448,0.0002579893,0.00014475467,0.00015434621,0.000028420032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011647831,0.00013669254,0.00019858305,0.000068287474,0.00013953485,0.00003239309,0.00006573911,0.00026346094,0.000003559683],"category_scores_gemma":[0.001068841,0.000117019525,0.000039178154,0.00007795179,0.00018359536,0.000010709639,0.00010636693,0.00008835276,1.2577787e-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":[0.0001838186,0.00003554934,0.32358772,0.00045288564,0.000035515768,1.5082517e-8,0.00013271552,0.000013292355,0.6155585,0.0019056373,0.000030593987,0.05806376],"study_design_scores_gemma":[0.0038679945,0.0013241783,0.4792921,0.00031803554,0.00004719602,0.000004556028,0.00011560542,0.08060689,0.34634733,0.0029851792,0.08469513,0.00039581239],"about_ca_topic_score_codex":0.00000600058,"about_ca_topic_score_gemma":0.000007918194,"teacher_disagreement_score":0.26921117,"about_ca_system_score_codex":0.000009289007,"about_ca_system_score_gemma":0.000036765792,"threshold_uncertainty_score":0.47719178},"labels":[],"label_agreement":null},{"id":"W4411219854","doi":"10.1021/acsptsci.5c00694","title":"Identifying Antibiotic Effects of Investigational Drugs on Commensal Bacteria with Machine Learning","year":2025,"lang":"en","type":"preprint","venue":"ACS Pharmacology & Translational Science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; McMaster University; Yale University; Duke Endowment","keywords":"Investigational Drugs; Antibiotics; Bacteria; Microbiology; Medicine; Biology; Internal medicine; Clinical trial; Genetics","score_opus":0.01050145496549598,"score_gpt":0.30322653228663665,"score_spread":0.29272507732114067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411219854","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9921344,0.00022038052,0.003520839,0.0008037365,0.0007730255,0.00052369846,0.000078753226,0.00003104087,0.0019141255],"genre_scores_gemma":[0.9885052,0.0000653858,0.009673334,0.00084953377,0.000119564545,0.000017906726,0.00056819053,0.000014159581,0.00018676346],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980683,0.00017683046,0.0003920751,0.0005274985,0.0005255031,0.0003098379],"domain_scores_gemma":[0.9988874,0.00019699143,0.0003504921,0.00022656041,0.00023540907,0.00010313871],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000626989,0.00028799183,0.00027886863,0.00024864805,0.00028562194,0.000043495646,0.0006656983,0.00021748914,0.000029123039],"category_scores_gemma":[0.00011113581,0.00026623023,0.00007596825,0.000308184,0.0009349488,0.000016523045,0.00032802165,0.00073864555,0.0000042931283],"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":[0.00027974113,0.00015918782,0.02574292,0.00095011457,0.00025936516,0.0000048031425,0.0007232263,0.052680183,0.91624576,0.0011135782,0.00028638754,0.001554717],"study_design_scores_gemma":[0.0022220714,0.0006052459,0.040618643,0.0005216459,0.00026841206,0.000016486132,0.0000209167,0.024466865,0.9279768,0.0004514235,0.0022046405,0.0006268584],"about_ca_topic_score_codex":0.00001816641,"about_ca_topic_score_gemma":0.000005534927,"teacher_disagreement_score":0.02821332,"about_ca_system_score_codex":0.00003377483,"about_ca_system_score_gemma":0.0008537213,"threshold_uncertainty_score":0.999979},"labels":[],"label_agreement":null},{"id":"W4411407631","doi":"10.1016/j.compbiomed.2025.110528","title":"BitterEN: A novel ensemble model for the identification of bitter peptide","year":2025,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; King Saud University","keywords":"Identification (biology); Peptide; Computer science; Ensemble forecasting; Computational biology; Artificial intelligence; Chemistry; Biology; Biochemistry; Botany","score_opus":0.014213001584991369,"score_gpt":0.32411421954649683,"score_spread":0.30990121796150544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411407631","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.098793246,0.000580461,0.8972032,0.002718525,0.00024562527,0.00015194323,0.0000048952743,0.0000037795521,0.00029829724],"genre_scores_gemma":[0.9892364,0.00017354786,0.007978055,0.0019547674,0.0000714284,0.00002114531,0.00006104811,0.000003521593,0.00050005055],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994672,0.000016963619,0.0002721945,0.00012737,0.000021801878,0.000094462775],"domain_scores_gemma":[0.99957263,0.00010160953,0.00009146225,0.00018308542,0.000038855,0.000012362936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000358331,0.00007054159,0.00012184305,0.0000652046,0.000041530115,0.0000022956062,0.00013558332,0.0000894525,6.641333e-7],"category_scores_gemma":[0.00014490118,0.000045619436,0.000021564952,0.000058988215,0.00021019687,0.000001428101,0.00007387623,0.000065005086,1.471073e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026499308,0.00008157214,0.020135015,0.00035321095,0.00016892681,1.8517665e-7,0.0010735659,0.0047005285,0.8859405,0.02507935,0.018485218,0.043716963],"study_design_scores_gemma":[0.0024365755,0.00031371767,0.011722076,0.00013688645,0.000045161712,0.00000807364,0.00011602146,0.9573269,0.010054328,0.0033470306,0.0143602295,0.00013302636],"about_ca_topic_score_codex":0.00000768149,"about_ca_topic_score_gemma":0.000010522114,"teacher_disagreement_score":0.95262635,"about_ca_system_score_codex":0.000003828675,"about_ca_system_score_gemma":0.000020707872,"threshold_uncertainty_score":0.18603066},"labels":[],"label_agreement":null},{"id":"W4411410602","doi":"10.1371/journal.pone.0321761","title":"Machine learning driven dashboard for chronic myeloid leukemia prediction using protein sequences","year":2025,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Artificial Intelligence in Medicine (Canada)","funders":"Princess Nourah Bint Abdulrahman University","keywords":"Support vector machine; Artificial intelligence; Computer science; Machine learning; Random forest; Dashboard; Decision tree; Data mining; Medicine; Database","score_opus":0.01942231184426383,"score_gpt":0.25020784891151115,"score_spread":0.23078553706724733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411410602","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9786138,0.0005085358,0.017867876,0.00018937752,0.000061305676,0.0008496931,0.00003799139,0.00008229327,0.0017891173],"genre_scores_gemma":[0.9556065,0.00011377583,0.03864854,0.00013361494,0.0003324377,0.00013288938,0.0004613621,0.000029808474,0.00454107],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990526,0.000054104523,0.00025839673,0.00023964391,0.00015243929,0.00024280851],"domain_scores_gemma":[0.9994826,0.000015223889,0.0001326833,0.00022913044,0.00009966053,0.00004075764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001967036,0.00015143672,0.00017194352,0.000069471644,0.00020329522,0.000039280578,0.00018046389,0.00015974512,0.00001692826],"category_scores_gemma":[0.00031848394,0.00015224876,0.00006456365,0.00010699275,0.000060779126,0.000008733169,0.00011376063,0.00021931675,0.0000050941126],"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":[0.000058818456,0.00006691007,0.0071088593,0.0004955333,0.00022669624,3.1738128e-7,0.000044297267,0.008857379,0.9820219,0.00011575332,0.00007181797,0.0009316989],"study_design_scores_gemma":[0.0007879348,0.00057873654,0.00032721783,0.00037466426,0.00012819574,0.0000021110775,0.000024262823,0.52644,0.4622551,0.00008663811,0.008785774,0.00020934631],"about_ca_topic_score_codex":0.000027985092,"about_ca_topic_score_gemma":0.000020640618,"teacher_disagreement_score":0.5197668,"about_ca_system_score_codex":0.00015404525,"about_ca_system_score_gemma":0.00026739773,"threshold_uncertainty_score":0.6208524},"labels":[],"label_agreement":null},{"id":"W4411509101","doi":"10.1007/978-981-96-8197-6_18","title":"The Use of Large Language Models to Cluster Genomic Data","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Windsor","funders":"","keywords":"Computer science; Cluster (spacecraft); Natural language processing; Theoretical computer science; Programming language; Artificial intelligence","score_opus":0.024406329382784992,"score_gpt":0.2802765917107655,"score_spread":0.25587026232798055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411509101","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":[0.0008440235,0.00037193057,0.9964485,0.00033078028,0.00034851677,0.00027851984,0.00011317211,0.000008862529,0.0012557027],"genre_scores_gemma":[0.15210065,0.00037047558,0.8184546,0.015202746,0.00095055456,0.000012055322,0.0007392278,0.00009263357,0.012077027],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986581,0.000022173237,0.00030464068,0.00048561598,0.00024992693,0.00027953836],"domain_scores_gemma":[0.99772966,0.00014537331,0.00014167064,0.0018446454,0.00008861548,0.000050027116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054168055,0.00020481354,0.00018685331,0.00012532489,0.00011345488,0.00011277907,0.0019667773,0.00018209469,0.0000038126789],"category_scores_gemma":[0.0002029625,0.0001501636,0.00004637468,0.000095715084,0.0002049268,0.000013206748,0.003426453,0.00028487825,0.000004746468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008764305,0.000030855488,0.00011251662,0.0001613014,0.000076699725,0.0000072717726,0.0013437826,0.56738424,0.004952693,0.0032852655,0.004971719,0.417586],"study_design_scores_gemma":[0.00018363443,0.00010053294,0.00002709745,0.00013945476,0.00001269154,0.0000087874905,5.7136896e-7,0.8950064,0.0014974223,0.0010891458,0.10164222,0.00029202865],"about_ca_topic_score_codex":0.00001997195,"about_ca_topic_score_gemma":0.00026525266,"teacher_disagreement_score":0.41729397,"about_ca_system_score_codex":0.000027181586,"about_ca_system_score_gemma":0.00022723591,"threshold_uncertainty_score":0.6123494},"labels":[],"label_agreement":null},{"id":"W4411950667","doi":"10.1109/forge66646.2025.00011","title":"Automated Codebase Reconciliation using Large Language Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Advanced Micro Devices (Canada); University of Toronto","funders":"","keywords":"Codebase; Computer science; Programming language; Software","score_opus":0.009332571674709807,"score_gpt":0.3005197324523237,"score_spread":0.2911871607776139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411950667","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74001914,0.00015379027,0.21773024,0.00011004985,0.00013087141,0.00014209059,0.000018594748,0.00018447495,0.041510746],"genre_scores_gemma":[0.97858876,0.000010200226,0.015707407,0.0011089391,0.000030820807,0.0000036558038,0.0002011823,0.000008599144,0.004340428],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994828,0.00003162879,0.00016008205,0.000120325836,0.00005996701,0.00014517899],"domain_scores_gemma":[0.999642,0.0000066225784,0.000047508656,0.00022813893,0.000050597595,0.000025110483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017482908,0.0000822672,0.00007310208,0.000043823016,0.00006239797,0.00002049032,0.00009145692,0.000100915975,0.000041627864],"category_scores_gemma":[0.00009073571,0.00007632452,0.00003647992,0.00008838224,0.000012287312,0.000004675406,0.00007840501,0.000058164707,0.000009583903],"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":[0.00016472336,0.00024171504,0.009437289,0.00034546354,0.00028865342,0.000007114808,0.0010972436,0.10357692,0.80422306,0.014478639,0.05930004,0.0068391445],"study_design_scores_gemma":[0.00036659464,0.000020521864,0.00015090927,0.0000120963,0.0000103637185,0.0000026110683,0.00013322616,0.96351135,0.030797642,0.000053007356,0.0048468704,0.00009478503],"about_ca_topic_score_codex":0.000041763793,"about_ca_topic_score_gemma":0.00004127964,"teacher_disagreement_score":0.85993445,"about_ca_system_score_codex":0.000017320557,"about_ca_system_score_gemma":0.00006390377,"threshold_uncertainty_score":0.31124234},"labels":[],"label_agreement":null},{"id":"W4412459700","doi":"10.1053/j.gastro.2025.07.008","title":"Novel Insights Into the Progression of α1-Antitrypsin Deficiency–Associated Liver Disease Using Artificial Intelligence–Driven Deep Visual Proteomics","year":2025,"lang":"en","type":"article","venue":"Gastroenterology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Health Network; Western University","funders":"","keywords":"Disease; Proteomics; Artificial intelligence; Computational biology; Medicine; Biology; Computer science; Pathology; Genetics; Gene","score_opus":0.01147762930206839,"score_gpt":0.29243375004621613,"score_spread":0.2809561207441477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412459700","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74643135,0.00014712223,0.25274676,0.00014536764,0.00016216893,0.00029864218,0.0000037650527,0.000010735275,0.000054104592],"genre_scores_gemma":[0.9879137,0.000029540812,0.011604104,0.0002908908,0.000050037357,0.000019916102,0.00006491838,0.000012391634,0.000014450752],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872214,0.00014850705,0.00043637693,0.0002522225,0.0001433015,0.0002974696],"domain_scores_gemma":[0.9992295,0.000018492205,0.0002723955,0.00028631376,0.00013587852,0.000057436733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001918383,0.00017372608,0.00018972589,0.00009703792,0.00016404115,0.000021645961,0.00034171564,0.00014238979,0.000007376708],"category_scores_gemma":[0.0003105103,0.0001315148,0.00010274607,0.00015118349,0.00032955044,0.0000069564067,0.0003547628,0.00019688884,0.0000027735202],"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":[0.0029417558,0.0015280697,0.22631575,0.00029792188,0.000334265,0.000011359502,0.0015981472,0.030101916,0.7217007,0.004390619,0.00013300603,0.010646464],"study_design_scores_gemma":[0.00086827733,0.002350865,0.06840925,0.00021766846,0.00025982916,0.000021354877,0.0004159537,0.8600617,0.065578915,0.0009621019,0.0004905415,0.0003635112],"about_ca_topic_score_codex":0.000033684555,"about_ca_topic_score_gemma":0.00019631031,"teacher_disagreement_score":0.8299598,"about_ca_system_score_codex":0.000025618574,"about_ca_system_score_gemma":0.00009806755,"threshold_uncertainty_score":0.5363018},"labels":[],"label_agreement":null},{"id":"W4412784157","doi":"10.1007/s13721-025-00576-4","title":"A novel multi-modal dual pathway network with hierarchical channel-spatial attention and adaptive feature fusion for viral genomic variant classification","year":2025,"lang":"en","type":"article","venue":"Network Modeling Analysis in Health Informatics and Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Windsor","funders":"","keywords":"Feature (linguistics); Dual (grammatical number); Channel (broadcasting); Computational biology; Computer science; Artificial intelligence; Biology; Computer network","score_opus":0.01706702782042996,"score_gpt":0.27097553300810423,"score_spread":0.25390850518767427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412784157","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":[0.06606811,0.00034345215,0.93202984,0.00032569526,0.00012346511,0.0008993227,0.00006470088,0.000029141902,0.000116281684],"genre_scores_gemma":[0.5188114,0.0007041805,0.47800526,0.001008337,0.00019390981,0.00007647804,0.0011236544,0.00002054557,0.000056228302],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99710405,0.000073345356,0.0016151426,0.00025753776,0.00026038018,0.00068957254],"domain_scores_gemma":[0.99837375,0.00007486713,0.00078595727,0.00038751503,0.00019880015,0.00017910739],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018073558,0.00038444158,0.00061865494,0.0003445279,0.0005470433,0.00015403714,0.00017382132,0.00038123401,6.4993804e-7],"category_scores_gemma":[0.00007243495,0.0003210804,0.00013457223,0.00063785934,0.00010650185,0.000052116055,0.00023407917,0.000470863,5.232231e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042791283,0.0000617495,0.002320753,0.0006608151,0.0003826521,2.7294277e-7,0.0010318685,0.97793376,0.000025260408,0.001236178,0.00016438442,0.015754389],"study_design_scores_gemma":[0.0018488225,0.0004947691,0.0022973225,0.00024377403,0.00018241085,0.000016379176,0.0007233925,0.993137,0.0000020055168,0.00012435108,0.0005929681,0.00033680786],"about_ca_topic_score_codex":0.0001008815,"about_ca_topic_score_gemma":0.00052063755,"teacher_disagreement_score":0.45402458,"about_ca_system_score_codex":0.0000829428,"about_ca_system_score_gemma":0.0002780135,"threshold_uncertainty_score":0.9999241},"labels":[],"label_agreement":null},{"id":"W4412796409","doi":"10.1101/2025.07.26.666948","title":"C3PI: Component Puzzle Protein-Protein Interaction Prediction","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Computer science; Source code; Conditional random field; Code (set theory); Key (lock); Machine learning; Data mining; Web server; Artificial intelligence; Field (mathematics); Deep learning; Component (thermodynamics); The Internet","score_opus":0.008425595960945978,"score_gpt":0.23055226382134128,"score_spread":0.2221266678603953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412796409","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98038757,0.00042919425,0.01433914,0.00026182993,0.001612214,0.0019179345,0.00046886,0.00032478824,0.00025849318],"genre_scores_gemma":[0.9877176,0.000075642776,0.010609065,0.00015443869,0.0007065625,0.00050973805,0.000014018548,0.000078638295,0.00013426774],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974312,0.0001982918,0.0007077994,0.0008429574,0.00036028886,0.00045944264],"domain_scores_gemma":[0.99734116,0.000012108516,0.00058524136,0.0014668247,0.00041759477,0.00017709163],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00051690347,0.00057433086,0.00041168727,0.00023566827,0.00022193704,0.00019037451,0.0006053867,0.00083173043,0.00003712872],"category_scores_gemma":[0.00035991822,0.00063748774,0.00020964979,0.00021773079,0.00009245579,0.000017605977,0.00096537976,0.001056406,0.00005276566],"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":[0.00008302828,0.00013358255,0.0011589149,0.00074581103,0.00019657654,0.000004984361,0.000006506141,0.00070882635,0.99575025,0.00026636728,0.00093783956,0.000007306041],"study_design_scores_gemma":[0.00061528705,0.00016959438,0.0076193023,0.00092700415,0.00008559111,4.5756984e-8,0.0000046838713,0.0047581005,0.9070052,0.000002135458,0.078082435,0.00073061784],"about_ca_topic_score_codex":0.00005179505,"about_ca_topic_score_gemma":0.00000433673,"teacher_disagreement_score":0.08874506,"about_ca_system_score_codex":0.00019782393,"about_ca_system_score_gemma":0.00038839574,"threshold_uncertainty_score":0.9996076},"labels":[],"label_agreement":null},{"id":"W4412801920","doi":"10.1007/978-3-031-36886-8_34","title":"Correction to: Incorporating Natural Language-Based and Sequence-Based Features to Predict Protein Sumoylation Sites","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"SUMO protein; Sequence (biology); Computer science; Computational biology; Natural language processing; Natural (archaeology); Artificial intelligence; Biology; Genetics; Gene; Paleontology","score_opus":0.006461017573161055,"score_gpt":0.23966375604431706,"score_spread":0.233202738471156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412801920","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08673641,0.040336575,0.8298346,0.0014838554,0.007043796,0.010526092,0.0002468642,0.0003332425,0.02345857],"genre_scores_gemma":[0.9899025,0.000011699397,0.0020074968,0.00058909575,0.0005983525,0.000057733803,0.00085859635,0.00003511524,0.005939436],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882555,0.0000697724,0.0003473552,0.000394439,0.00015993686,0.00020292902],"domain_scores_gemma":[0.99923295,0.00012995482,0.00021278686,0.00025869015,0.0000857217,0.00007991616],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028396706,0.00033412164,0.00032095233,0.00016996959,0.000100415615,0.00013296507,0.000106848194,0.0005002778,0.0000021109659],"category_scores_gemma":[0.00039612196,0.0002938494,0.000049305952,0.00008539546,0.000041747564,0.000004295516,0.000075593605,0.0005422155,5.723677e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030313578,0.000012093886,0.005527812,0.0008391713,0.00006903228,0.000012968295,0.00019935549,0.94047093,0.01038146,0.00022472299,0.0025961534,0.03936315],"study_design_scores_gemma":[0.0005747164,0.00059897685,0.00061133236,0.0034230803,0.000044961147,0.000022901035,0.000015544188,0.9856163,0.0015299239,0.000056696466,0.006776356,0.0007292099],"about_ca_topic_score_codex":0.00014401341,"about_ca_topic_score_gemma":0.0010559646,"teacher_disagreement_score":0.90316606,"about_ca_system_score_codex":0.000048361082,"about_ca_system_score_gemma":0.00008269737,"threshold_uncertainty_score":0.99995136},"labels":[],"label_agreement":null},{"id":"W4412807080","doi":"10.1007/978-981-95-0695-8_33","title":"Automated Prediction of Protein Pair Distances Based on Deep Learning: A Novel Approach to Protein Structure Prediction in SCOP","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Thompson Rivers University","funders":"","keywords":"Computer science; Protein structure prediction; Artificial intelligence; Deep learning; Machine learning; Pattern recognition (psychology); Protein structure; Chemistry","score_opus":0.006670504615950539,"score_gpt":0.22438481692959705,"score_spread":0.21771431231364652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412807080","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":[0.009139772,0.000055963308,0.98538685,0.00009187294,0.00021173258,0.0016092475,0.000092185546,0.0001066437,0.0033057516],"genre_scores_gemma":[0.8141507,0.0000015827893,0.18461765,0.00018842744,0.00014981783,0.00006109212,0.00029221678,0.000030388408,0.0005081163],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99766153,0.000054706445,0.0005592451,0.00080951344,0.00057808857,0.00033691715],"domain_scores_gemma":[0.9988235,0.000036847683,0.00031977604,0.00057456427,0.00016914197,0.000076157325],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005030609,0.0003951662,0.00035827057,0.0005938729,0.00010255966,0.00006818588,0.0006441379,0.00050276954,0.000005928187],"category_scores_gemma":[0.00040240362,0.00035831466,0.00007411708,0.0004662034,0.00026440088,0.000014679507,0.00024269504,0.00075610616,9.936241e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014085988,0.000089847825,0.00077005354,0.00049808284,0.000014978059,0.0000013617221,0.0002274689,0.9339968,0.03748874,0.00025744934,0.000024073079,0.026490312],"study_design_scores_gemma":[0.00051031134,0.00081226305,0.000767404,0.001130398,0.0000073317474,0.000003724269,8.379423e-7,0.97425747,0.020876803,0.00027958356,0.0010744425,0.00027944762],"about_ca_topic_score_codex":0.00001503741,"about_ca_topic_score_gemma":0.000043072345,"teacher_disagreement_score":0.8050109,"about_ca_system_score_codex":0.00014433943,"about_ca_system_score_gemma":0.00035199497,"threshold_uncertainty_score":0.9998869},"labels":[],"label_agreement":null},{"id":"W4413011538","doi":"10.1016/j.ab.2025.115952","title":"K-SNOpred: Identification of protein S-nitrosylation sites through word embedding features and machine learning","year":2025,"lang":"en","type":"article","venue":"Analytical Biochemistry","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; King Saud University","keywords":"Identification (biology); Computer science; Computational biology; Word embedding; Word (group theory); S-Nitrosylation; Artificial intelligence; Embedding; Chemistry; Natural language processing; Biology; Biochemistry; Botany; Cysteine; Linguistics; Philosophy","score_opus":0.0072632339828861605,"score_gpt":0.28217800572695717,"score_spread":0.27491477174407103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413011538","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.986733,0.00117708,0.007436137,0.00037006612,0.000022614755,0.00014489109,0.000014451122,0.000027183078,0.004074574],"genre_scores_gemma":[0.99126625,0.000065933426,0.0022858249,0.00006860327,0.000047770325,0.000008272901,0.00034389368,0.000010304518,0.0059031295],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990361,0.000035756864,0.00036240078,0.00026915898,0.00013515812,0.00016144286],"domain_scores_gemma":[0.99939215,0.00002883336,0.00017097643,0.00027064307,0.00009779233,0.00003960893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021532226,0.00015097045,0.00016595445,0.000041840765,0.00009553265,0.000044371176,0.00014108243,0.0002030133,0.00001815902],"category_scores_gemma":[0.0008576437,0.00014653034,0.000068041336,0.00017254124,0.00013910962,0.000008592144,0.00014764056,0.00022323859,0.0000020762955],"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":[0.00005466242,0.000032431646,0.00891794,0.0002660511,0.00007678763,4.193852e-7,0.000039519797,0.00023433518,0.98767394,0.00050938723,0.00039981585,0.0017947304],"study_design_scores_gemma":[0.00028535808,0.00004608708,0.0021376356,0.000065415144,0.000054811157,0.000006243199,0.0000905671,0.019482054,0.97534764,0.00031927213,0.0020033147,0.00016157805],"about_ca_topic_score_codex":0.000012170284,"about_ca_topic_score_gemma":0.0000022343202,"teacher_disagreement_score":0.019247718,"about_ca_system_score_codex":0.000013705254,"about_ca_system_score_gemma":0.000037579593,"threshold_uncertainty_score":0.59753335},"labels":[],"label_agreement":null},{"id":"W4413028238","doi":"10.1101/2025.08.05.668745","title":"Higher eQTL power reveals signals that boost GWAS colocalization","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Common Fund; National Institute on Drug Abuse; National Institute of Diabetes and Digestive and Kidney Diseases; NIH Office of the Director; National Heart, Lung, and Blood Institute; National Cancer Institute; National Institutes of Health; National Institute of Neurological Disorders and Stroke; National Institute of Mental Health; National Human Genome Research Institute; University of Toronto","keywords":"Expression quantitative trait loci; Genome-wide association study; Colocalization; Biology; Computational biology; Quantitative trait locus; Genetics; Gene; Single-nucleotide polymorphism; Neuroscience; Genotype","score_opus":0.010691296298045678,"score_gpt":0.23967441932889996,"score_spread":0.22898312303085427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413028238","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94789153,0.0050633303,0.032150563,0.0012045138,0.0059977015,0.0031207392,0.0014246998,0.00078708027,0.0023598303],"genre_scores_gemma":[0.99118334,0.00031922394,0.0056025274,0.0017364969,0.00042371269,0.00015457858,0.0000119091665,0.00010932549,0.00045890405],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99712074,0.00024184049,0.0006858405,0.0009264825,0.00042992792,0.0005951552],"domain_scores_gemma":[0.996854,0.000043359163,0.00065632636,0.0016953596,0.00052709784,0.00022387892],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007039497,0.00068138033,0.00057774974,0.00021479063,0.0001848963,0.00022581473,0.0008291268,0.0012259737,0.00018801834],"category_scores_gemma":[0.0003932075,0.000731731,0.00023325963,0.00030741183,0.00013925569,0.000013996021,0.0011184122,0.00070120953,0.000074615295],"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":[0.0001105458,0.00018495774,0.02501302,0.0010734572,0.00052457745,0.000018753684,0.000016003007,0.0020418286,0.94136554,0.0014111634,0.028237322,0.000002843283],"study_design_scores_gemma":[0.0010545567,0.000243201,0.052309446,0.00087330607,0.00025758354,4.612294e-8,0.0000044079243,0.0009713405,0.657355,0.000009425913,0.28498647,0.0019351892],"about_ca_topic_score_codex":0.000019835585,"about_ca_topic_score_gemma":0.000001517113,"teacher_disagreement_score":0.2840105,"about_ca_system_score_codex":0.00012963332,"about_ca_system_score_gemma":0.00059901143,"threshold_uncertainty_score":0.9995134},"labels":[],"label_agreement":null},{"id":"W4413105633","doi":"10.1101/2025.08.10.669533","title":"Multi-Modal Protein Representation Learning with CLASP","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Research in Immunology and Cancer; McGill University; Genome Canada; Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Representation (politics); Modal; Computer science; Artificial intelligence; Political science; Materials science","score_opus":0.009713097066967363,"score_gpt":0.2443413976580875,"score_spread":0.23462830059112014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413105633","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95673287,0.00037493353,0.040470276,0.00016464974,0.00037721512,0.0013580298,0.00008906484,0.00029232205,0.00014064091],"genre_scores_gemma":[0.9272939,0.00007224316,0.071439214,0.00014348827,0.00032119313,0.00030871015,0.000007417305,0.00009308659,0.00032074182],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975337,0.00022494754,0.0005057566,0.00091642234,0.00034282682,0.00047634117],"domain_scores_gemma":[0.99755865,0.00001908435,0.0005396529,0.0012590155,0.00046393657,0.00015967981],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004366236,0.0005496855,0.00041310902,0.00018949492,0.00020659932,0.00018331963,0.0005581636,0.0007107312,0.000017075594],"category_scores_gemma":[0.00054706744,0.0005502962,0.00013950402,0.00029634734,0.00013028414,0.000012850283,0.00077514426,0.0011589875,0.000026619862],"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":[0.00014156208,0.000118992444,0.025996262,0.000683844,0.00028949822,0.000015643947,0.000018793311,0.006952452,0.96540195,0.00010617427,0.00026724313,0.0000075890575],"study_design_scores_gemma":[0.0018293883,0.0003807614,0.0573631,0.0009175513,0.0001794758,7.8939685e-8,0.000016497881,0.017088642,0.8952782,7.1965127e-7,0.025345776,0.0015997842],"about_ca_topic_score_codex":0.00005391199,"about_ca_topic_score_gemma":0.0000069073517,"teacher_disagreement_score":0.07012372,"about_ca_system_score_codex":0.00008711053,"about_ca_system_score_gemma":0.0006508558,"threshold_uncertainty_score":0.9996949},"labels":[],"label_agreement":null},{"id":"W4413312092","doi":"10.1073/pnas.2506316122","title":"Sparse autoencoders uncover biologically interpretable features in protein language model representations","year":2025,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"National Institute of General Medical Sciences; National Cancer Institute; Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology; National Institutes of Health; Massachusetts Institute of Technology","keywords":"Computer science; Artificial intelligence; Natural language processing; Pattern recognition (psychology)","score_opus":0.015405832498503049,"score_gpt":0.3230372084270323,"score_spread":0.3076313759285293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413312092","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96051264,0.00008679647,0.00008834035,0.0016848921,0.000008439686,0.00020550455,0.000010144222,0.000005423725,0.0373978],"genre_scores_gemma":[0.98699427,0.000009083942,0.011046406,0.00039642517,0.000010348729,0.000012723071,6.946573e-7,0.0000015277901,0.0015285513],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992814,0.0000069700714,0.00021418676,0.00014728679,0.0002551557,0.00009501402],"domain_scores_gemma":[0.9996976,0.000019078047,0.00017308531,0.000011315999,0.00008795793,0.000010912467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005932061,0.00006104749,0.00008023609,0.000100279,0.000060854265,0.000014364057,0.0005014774,0.00008582924,0.000003460843],"category_scores_gemma":[0.0010528697,0.000040254068,0.00004351229,0.0003597408,0.00032912652,0.000019502695,0.00019748803,0.00012606084,2.667073e-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":[0.000025124486,0.000031014286,0.009507165,0.000051936706,0.00001154244,2.6173876e-9,0.00019392658,0.025485478,0.93893576,0.024113864,0.0014994347,0.00014478233],"study_design_scores_gemma":[0.00033254325,0.00007264909,0.043023232,0.00019204852,0.000008836798,0.0000029023056,0.00059493835,0.110906884,0.8120158,0.032465845,0.00024986817,0.00013449813],"about_ca_topic_score_codex":0.000010845456,"about_ca_topic_score_gemma":6.8144817e-7,"teacher_disagreement_score":0.12691997,"about_ca_system_score_codex":0.000012283807,"about_ca_system_score_gemma":0.00004829631,"threshold_uncertainty_score":0.16415133},"labels":[],"label_agreement":null},{"id":"W4413376900","doi":"10.1021/acsomega.5c05484","title":"Integrating ESM-2 and Graph Neural Networks with AlphaFold-2 Structures for Enhanced Protein Function Prediction","year":2025,"lang":"en","type":"article","venue":"ACS Omega","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Science and Technology Council","keywords":"Artificial neural network; Computer science; Graph; Protein function prediction; Protein function; Artificial intelligence; Theoretical computer science; Chemistry","score_opus":0.0032486857553476697,"score_gpt":0.2253501991170538,"score_spread":0.22210151336170614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413376900","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.673275,0.00016915792,0.32551047,0.00006874309,0.00011484077,0.00037073533,0.000005443969,0.000025021116,0.00046060607],"genre_scores_gemma":[0.9941139,0.0000102650165,0.004864939,0.00023135138,0.00011589096,0.000093130075,0.00016552243,0.000011421648,0.00039356103],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994389,0.000022368815,0.0001516118,0.00017973156,0.000057264355,0.0001501413],"domain_scores_gemma":[0.9996489,0.000014483183,0.00008213477,0.00015926438,0.000068796064,0.000026380025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009689095,0.00012348489,0.00009311322,0.000045817254,0.00013041428,0.00004326282,0.00007204817,0.00011988078,7.722259e-7],"category_scores_gemma":[0.000088887035,0.000096506956,0.000027050659,0.00009691307,0.000048632002,0.000008617312,0.00004409561,0.00012451864,9.484521e-8],"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":[0.0023040269,0.000061533414,0.015668062,0.0005102867,0.00051485107,7.6049184e-7,0.00030343383,0.030991303,0.81061673,0.0076716947,0.004001329,0.127356],"study_design_scores_gemma":[0.008821502,0.008051311,0.04595599,0.00042311742,0.00044647284,0.000047354457,0.0010779725,0.304448,0.5948259,0.0074156728,0.027040046,0.0014466027],"about_ca_topic_score_codex":0.000007793901,"about_ca_topic_score_gemma":0.00002941905,"teacher_disagreement_score":0.32083893,"about_ca_system_score_codex":0.0000064635274,"about_ca_system_score_gemma":0.00001839418,"threshold_uncertainty_score":0.39354396},"labels":[],"label_agreement":null},{"id":"W4413396779","doi":"10.1093/bioinformatics/btaf460","title":"PDP-Miner: an AI/ML tool to detect prophage tail proteins with depolymerase domains across thousands of bacterial genomes","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Prophage; Genome; Bacteriophage; Bacterial genome size; Source code; Computational biology; Computer science; Biology; Software; Gene; Genetics; Programming language; Escherichia coli","score_opus":0.00454705534616463,"score_gpt":0.2597397804878549,"score_spread":0.2551927251416903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413396779","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93185997,0.00010311653,0.0646424,0.00008107727,0.00015822583,0.0010629846,0.00017439814,0.00006242612,0.001855427],"genre_scores_gemma":[0.83023316,0.000045731398,0.16702443,0.0009974455,0.00019406619,0.0001276074,0.00043974418,0.000049106297,0.00088873756],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99818873,0.000046357713,0.0007591648,0.0002239009,0.00028654945,0.00049527566],"domain_scores_gemma":[0.9984945,0.000014861605,0.00030425758,0.0008646052,0.0001731546,0.00014861983],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003462696,0.00034249388,0.0003531526,0.00012089617,0.0001868465,0.00012880903,0.0004931689,0.00023495813,0.00002280038],"category_scores_gemma":[0.00015980031,0.0002698565,0.00009755426,0.0003243437,0.00014938125,0.000041676172,0.0003183056,0.00018298127,0.00001428889],"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":[0.003400485,0.00045355665,0.009106941,0.0035123373,0.0005887993,0.000018468972,0.007914715,0.0026164167,0.79746145,0.0005328058,0.0040853573,0.17030866],"study_design_scores_gemma":[0.003997643,0.004278224,0.0026832127,0.00023434458,0.00011407132,0.00007271528,0.0011451432,0.0086757485,0.9077847,0.00003159653,0.06985818,0.0011244472],"about_ca_topic_score_codex":0.000020230222,"about_ca_topic_score_gemma":0.000100349,"teacher_disagreement_score":0.16918422,"about_ca_system_score_codex":0.000029896817,"about_ca_system_score_gemma":0.00029087407,"threshold_uncertainty_score":0.9999754},"labels":[],"label_agreement":null},{"id":"W4413469574","doi":"10.1016/j.imed.2025.03.003","title":"A novel stacking-based classifier for identifying antifreeze protein using latent semantic analysis","year":2025,"lang":"en","type":"article","venue":"Intelligent Medicine","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Stacking; Latent semantic analysis; Computer science; Classifier (UML); Antifreeze; Probabilistic latent semantic analysis; Artificial intelligence; Identification (biology); Antifreeze protein; Pattern recognition (psychology); Computational biology; Machine learning; Chemistry; Biology; Biochemistry","score_opus":0.054640104164757244,"score_gpt":0.36262393535679227,"score_spread":0.30798383119203504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413469574","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19122878,0.0003008422,0.80675864,0.0005693336,0.0002358281,0.0005425927,0.000011193902,0.000023030274,0.00032973412],"genre_scores_gemma":[0.9806766,0.00001511534,0.016727518,0.000769487,0.00016350279,0.00004053151,0.0002653205,0.000022078277,0.0013198587],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853975,0.000037264934,0.000555167,0.00033448962,0.00022828401,0.00030502933],"domain_scores_gemma":[0.99896467,0.00004687871,0.00021518675,0.0004760164,0.00022540746,0.00007185126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005913666,0.00021801324,0.00034045576,0.00038440552,0.00012410227,0.000032542746,0.00026429477,0.00014963835,0.000060582563],"category_scores_gemma":[0.0005920931,0.00018095548,0.00020569548,0.00056936644,0.00012264418,0.00000425769,0.00009163072,0.00014580629,0.0000032587593],"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":[0.00017919831,0.00013728163,0.011998682,0.00064802566,0.0013307513,0.0000028405345,0.0001605024,0.024898984,0.95597774,0.0005010941,0.0009831828,0.0031817246],"study_design_scores_gemma":[0.0014786473,0.000366786,0.002127215,0.00064641895,0.0013603892,0.0000049230525,0.00020999859,0.6805404,0.2959221,0.00012238666,0.016827527,0.00039323763],"about_ca_topic_score_codex":0.00011002142,"about_ca_topic_score_gemma":0.000083093226,"teacher_disagreement_score":0.79003114,"about_ca_system_score_codex":0.00004799591,"about_ca_system_score_gemma":0.00010776944,"threshold_uncertainty_score":0.73791504},"labels":[],"label_agreement":null},{"id":"W4413513119","doi":"10.47611/jsrhs.v13i3.7703","title":"Assessing AlphaFold AI’s Protease Enzyme Structure Prediction Accuracy","year":2024,"lang":"en","type":"article","venue":"Journal of Student Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Conestoga College","funders":"","keywords":"Protease; Computer science; Computational biology; Artificial intelligence; Enzyme; Chemistry; Biology; Biochemistry","score_opus":0.062120363048611356,"score_gpt":0.46686590471968237,"score_spread":0.404745541671071,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413513119","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99298644,0.0019061803,0.0023627828,0.001246972,0.00047012817,0.0002500533,0.000010123279,0.0000116064975,0.0007557255],"genre_scores_gemma":[0.9970469,0.000173458,0.0009929643,0.00007794461,0.0012174803,0.000004452807,0.00001676313,0.00001912099,0.000450906],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99794215,0.00020652347,0.00042247944,0.00014711157,0.001008411,0.00027330272],"domain_scores_gemma":[0.9989878,0.0000712343,0.00011861352,0.00021447995,0.0004826741,0.000125224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016792347,0.00010972849,0.0001280672,0.00023720789,0.00017243897,0.0007764102,0.0003997087,0.00012821345,0.00007453594],"category_scores_gemma":[0.00055644335,0.00008122664,0.00009973125,0.00022426035,0.00008636194,0.000050375726,0.00023255755,0.0010758601,0.000010487002],"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":[0.00017423813,0.0002352244,0.035266954,0.0006130211,0.00054041226,0.00021225754,0.0015687994,0.0017401561,0.8479707,0.00032908013,0.078774616,0.032574512],"study_design_scores_gemma":[0.0022138394,0.004086632,0.11962893,0.0013006853,0.00014525172,0.0019496755,0.0028855565,0.010624378,0.23037924,0.00090725033,0.62526655,0.0006120197],"about_ca_topic_score_codex":0.0000049666387,"about_ca_topic_score_gemma":0.000002012873,"teacher_disagreement_score":0.6175915,"about_ca_system_score_codex":0.000074032374,"about_ca_system_score_gemma":0.0004491685,"threshold_uncertainty_score":0.7486942},"labels":[],"label_agreement":null},{"id":"W4414090146","doi":"10.1101/2025.09.08.674958","title":"A novel Vector-Symbolic Architecture for graph encoding and its application to viral pangenome-based species classification","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"ENCODE; Representation (politics); Encoding (memory); Graph; Genome; Pattern recognition (psychology); Sequence (biology); Architecture","score_opus":0.01340911375852166,"score_gpt":0.23934496611340864,"score_spread":0.22593585235488697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414090146","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.520548,0.00056755194,0.47388527,0.0010090275,0.00039306475,0.00242717,0.0009787136,0.00015038322,0.000040819043],"genre_scores_gemma":[0.9740208,0.00006491171,0.02411139,0.0005035456,0.0003569299,0.00084428047,0.000015538966,0.00005764951,0.000024990451],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982078,0.000048240552,0.00041609185,0.0007765639,0.00018445145,0.0003668319],"domain_scores_gemma":[0.9983491,0.000038146074,0.00032176863,0.00083615136,0.00029018687,0.00016465846],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036120985,0.000429687,0.00034758577,0.0002824235,0.00017657132,0.00012228273,0.00044485633,0.0005078695,0.00000256605],"category_scores_gemma":[0.00032607408,0.00047213712,0.00012993878,0.00023896633,0.000055286542,0.0000061505134,0.0003349973,0.00035069245,0.000004091502],"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":[0.000063675114,0.000048757094,0.0011753327,0.0007327493,0.000073100644,1.5694856e-7,0.00001453674,0.0012271797,0.99475604,0.0018172751,0.000076494456,0.000014709104],"study_design_scores_gemma":[0.0010626531,0.00021434273,0.110664174,0.00030420098,0.00016165384,3.3235704e-8,0.0000055893966,0.01499312,0.80212355,0.0000072523226,0.06926531,0.0011981372],"about_ca_topic_score_codex":0.00000938971,"about_ca_topic_score_gemma":0.0000058872038,"teacher_disagreement_score":0.45347276,"about_ca_system_score_codex":0.00007992807,"about_ca_system_score_gemma":0.0003029113,"threshold_uncertainty_score":0.999773},"labels":[],"label_agreement":null},{"id":"W4414273071","doi":"10.1101/2025.09.16.676570","title":"Transcriptomic profiles from stereo-EEGs reveal the local cell microenvironment in human epilepsy","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Novo Nordisk; Royal College of Surgeons in Ireland; Higher Education Authority; National Research Foundation; Danmarks Grundforskningsfond; Queen's University Belfast; Queen's University; European Commission","keywords":"Transcriptome; Epilepsy; Gene; Gene expression; Cell type; Stereoelectroencephalography; Human brain; Gene expression profiling","score_opus":0.006025908613297319,"score_gpt":0.2095458470871882,"score_spread":0.20351993847389088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414273071","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99147916,0.0018130868,0.0040161326,0.00025869158,0.0005652086,0.0010195496,0.00066087523,0.000062361076,0.00012495181],"genre_scores_gemma":[0.99481416,0.00023246981,0.0036611455,0.0005848122,0.0003268823,0.00020703772,0.000014783524,0.00007530576,0.00008339363],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9972455,0.00028818194,0.00076913106,0.00088460883,0.000277068,0.0005355184],"domain_scores_gemma":[0.99770635,0.000030972587,0.0003839816,0.0016847834,0.000069079724,0.00012483003],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005177847,0.00060729595,0.00048457726,0.0001304993,0.00016166287,0.00012032995,0.0010960754,0.00073806365,0.00005590056],"category_scores_gemma":[0.00004351859,0.0005529733,0.00020964611,0.0001464731,0.00025216944,0.000007826077,0.00076034537,0.0011448491,0.000028331746],"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":[0.000053492942,0.00015078552,0.024047842,0.00041251947,0.000112019625,0.000009884805,0.00003942343,0.00059279386,0.9727981,0.000039896047,0.0017339461,0.000009302742],"study_design_scores_gemma":[0.0010044143,0.00010556257,0.15103717,0.000407909,0.000119452154,1.5872427e-8,0.000020407266,0.00055621593,0.82635003,0.000003141359,0.019556386,0.00083928165],"about_ca_topic_score_codex":0.00022575766,"about_ca_topic_score_gemma":0.000027773658,"teacher_disagreement_score":0.14644806,"about_ca_system_score_codex":0.00017941926,"about_ca_system_score_gemma":0.00031197065,"threshold_uncertainty_score":0.9996922},"labels":[],"label_agreement":null},{"id":"W4414382693","doi":"10.1016/j.ab.2025.115981","title":"StackAPP: Advancing autophagy protein identification with ensemble learning","year":2025,"lang":"en","type":"article","venue":"Analytical Biochemistry","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; King Saud University","keywords":"Pseudo amino acid composition; Autophagy; Amino acid; Fusion protein; Amphiphile; ULK1; Stacking","score_opus":0.002632280040962944,"score_gpt":0.25047496026720656,"score_spread":0.24784268022624362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414382693","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92824256,0.00017535812,0.04443826,0.00041118433,0.000037095055,0.00020389436,0.0000039965425,0.00007462774,0.026412992],"genre_scores_gemma":[0.9658734,0.000011868,0.0030035565,0.00018907597,0.0000758701,0.000024890176,0.00018560444,0.00001744247,0.030618254],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987694,0.000036075806,0.00031493825,0.00037413195,0.00018600891,0.0003194391],"domain_scores_gemma":[0.99918216,0.000019956275,0.00012055671,0.00044707576,0.00013625556,0.00009398227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002659216,0.00019222137,0.00016164237,0.00004936657,0.00014099572,0.00006798393,0.00023134948,0.0001905661,0.000034324217],"category_scores_gemma":[0.00056784466,0.00017470549,0.000071834256,0.000245409,0.00011395164,0.0000066701846,0.00012677268,0.00029533077,0.000026091422],"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":[0.00008842484,0.00005503321,0.0029586724,0.00018952253,0.00010668061,0.000004043889,0.000015459618,0.0006782981,0.99075073,0.00057435926,0.0018680268,0.0027107296],"study_design_scores_gemma":[0.00040966552,0.00010307802,0.0005257029,0.00007781977,0.00004697304,0.00001046051,0.00011652633,0.008468993,0.9725891,0.00007359242,0.017338743,0.0002393539],"about_ca_topic_score_codex":0.000005743605,"about_ca_topic_score_gemma":0.0000033290444,"teacher_disagreement_score":0.041434705,"about_ca_system_score_codex":0.00004036465,"about_ca_system_score_gemma":0.00016794539,"threshold_uncertainty_score":0.71242833},"labels":[],"label_agreement":null},{"id":"W4414426256","doi":"10.3389/fbinf.2025.1645785","title":"Extracting a COVID-19 signature from a multi-omic dataset","year":2025,"lang":"en","type":"article","venue":"Frontiers in Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; Engineering Link (Canada); Mila - Quebec Artificial Intelligence Institute; Université Laval","funders":"Canadian Institutes of Health Research; Ministère de la Santé et des Services sociaux; Ministère de la Santé; Génome Québec; Public Health Agency; Public Health Agency of Canada","keywords":"Signature (topology); Pattern recognition (psychology); Path (computing); Biomarker; Feature extraction; Work (physics)","score_opus":0.010564276815481556,"score_gpt":0.29788201329463926,"score_spread":0.2873177364791577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414426256","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":[0.022872299,0.0015738119,0.96584326,0.0010737256,0.0017954941,0.00076623354,0.0024138428,0.000092205766,0.0035691448],"genre_scores_gemma":[0.04750222,0.00043402423,0.9182331,0.014913176,0.0001623473,0.000054616747,0.017569171,0.000043454915,0.0010878994],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983794,0.00006946901,0.00071274064,0.00025098887,0.00018419976,0.0004031693],"domain_scores_gemma":[0.9987521,0.000055667308,0.00028238748,0.0007145773,0.000036914775,0.00015835096],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045248205,0.00028594476,0.0002992108,0.00027046938,0.00014968136,0.000091236034,0.00060206756,0.00040711486,0.00002932178],"category_scores_gemma":[0.0012954132,0.000282155,0.000084364285,0.0003065573,0.00011762318,0.00003059277,0.00032503097,0.0004946005,0.000022241158],"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":[0.0002079863,0.0001289779,0.062050767,0.00041765205,0.00019780728,0.000010025771,0.0013583902,0.005038873,0.0014032933,0.00008877812,0.91708475,0.012012697],"study_design_scores_gemma":[0.002591157,0.00006454378,0.001580917,0.000087248765,0.00004699572,0.000009601172,0.0023137822,0.2909913,0.0014221672,0.0002359768,0.70014256,0.0005137381],"about_ca_topic_score_codex":0.00009450567,"about_ca_topic_score_gemma":0.00007987032,"teacher_disagreement_score":0.28595245,"about_ca_system_score_codex":0.0001236293,"about_ca_system_score_gemma":0.00032455678,"threshold_uncertainty_score":0.99996305},"labels":[],"label_agreement":null},{"id":"W4414458008","doi":"10.1093/bioinformatics/btaf531","title":"SPAED: harnessing AlphaFold output for accurate segmentation of phage endolysin domains","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Vlaamse regering; Universiteit Gent; Alliance de recherche numérique du Canada; European Society of Clinical Microbiology and Infectious Diseases; Mitacs; Fonds de Recherche du Québec - Santé; Fonds Wetenschappelijk Onderzoek","keywords":"Lysin; Segmentation; Bacteriophage; Software; Pattern recognition (psychology)","score_opus":0.012178475071931668,"score_gpt":0.2942372479139277,"score_spread":0.28205877284199604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414458008","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":[0.19707598,0.0002405769,0.7869764,0.00020318445,0.0005391098,0.0009418999,0.00013626358,0.000051881558,0.013834719],"genre_scores_gemma":[0.7434788,0.000108540036,0.25115547,0.0008945844,0.00012668292,0.00006457092,0.00094460143,0.000029501742,0.0031972546],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998763,0.000026335998,0.0006791012,0.00012131074,0.00015596786,0.00025428584],"domain_scores_gemma":[0.9989631,0.000054314813,0.000417838,0.0003728671,0.000144582,0.000047261856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003582448,0.00019104026,0.00022501641,0.00013578417,0.000123436,0.0000572559,0.00025678775,0.00015363262,0.000008049338],"category_scores_gemma":[0.0003003656,0.00017853359,0.00013814196,0.0001691216,0.0000776851,0.000026348685,0.00012886706,0.000084774154,0.000008031569],"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":[0.0010727489,0.0005862501,0.010890628,0.008863434,0.001439639,0.0000024581218,0.005618055,0.012319235,0.54090834,0.012474406,0.08449164,0.32133314],"study_design_scores_gemma":[0.0047098724,0.000509448,0.0015959896,0.00024628796,0.00022564677,0.000013966046,0.0019221489,0.170625,0.70488065,0.00038235288,0.11423173,0.0006569094],"about_ca_topic_score_codex":0.0000049181467,"about_ca_topic_score_gemma":0.0000047740086,"teacher_disagreement_score":0.5464028,"about_ca_system_score_codex":0.00002548291,"about_ca_system_score_gemma":0.00012474596,"threshold_uncertainty_score":0.7280389},"labels":[],"label_agreement":null},{"id":"W4414540666","doi":"10.1021/acs.jcim.5c01489","title":"DeepMaT: Prediction of Target Peptide Classification and Cleavage Site by Combining Mamba2 and Multiple Attention Mechanisms","year":2025,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Fundo para o Desenvolvimento das Ciências e da Tecnologia; Ministry of Science and Technology of the People's Republic of China; National Natural Science Foundation of China","keywords":"Cleavage (geology); Peptide; Focus (optics); Cleavage factor; Deep learning; End-to-end principle","score_opus":0.00870271070868965,"score_gpt":0.23774746663785046,"score_spread":0.22904475592916082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414540666","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7161293,0.000133826,0.28336933,0.00009433561,0.000031247633,0.00004993034,0.000011271221,0.0000034602674,0.00017730611],"genre_scores_gemma":[0.98810476,0.00025706913,0.011341622,0.00014115653,0.000013608413,8.5872756e-7,0.0001267637,0.0000030009176,0.000011158088],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926764,0.000014944144,0.0005012495,0.000049278246,0.00009980985,0.000067053705],"domain_scores_gemma":[0.99944544,0.0000141719465,0.0003107856,0.000055347737,0.00012849817,0.00004578093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002967018,0.0000717077,0.000114822695,0.00007274764,0.000042171672,0.000034601326,0.00003673892,0.000103473,7.7487675e-7],"category_scores_gemma":[0.00014923378,0.00006614627,0.000027110009,0.000036946294,0.000029794663,0.00006954288,0.00004671335,0.00011994593,1.5649996e-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":[0.00011638882,0.000018221186,0.0030812272,0.00019729049,0.000035249075,5.0502223e-8,0.0003033914,0.001253219,0.99106956,0.00035640612,0.000606545,0.0029624286],"study_design_scores_gemma":[0.0010249718,0.000094089046,0.0004289111,0.00009737901,0.000029988203,0.00002513474,0.0004541753,0.9186906,0.07800901,0.0002952209,0.00078274944,0.00006772381],"about_ca_topic_score_codex":0.0000026926268,"about_ca_topic_score_gemma":1.4536906e-7,"teacher_disagreement_score":0.91743743,"about_ca_system_score_codex":0.000008653561,"about_ca_system_score_gemma":0.000016954556,"threshold_uncertainty_score":0.26973665},"labels":[],"label_agreement":null},{"id":"W4414683622","doi":"10.1093/bioadv/vbaf222","title":"An overview of computational methods for gene prediction in eukaryotes: strengths, limitations, and future directions","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Benchmark (surveying); Gene prediction; Scripting language; Gene; Sequence (biology); DNA sequencing","score_opus":0.02498786159813313,"score_gpt":0.3762993471727817,"score_spread":0.35131148557464853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414683622","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":[0.07315348,0.18411379,0.73698175,0.0005388521,0.0014315034,0.0012626009,0.00081704295,0.0001505475,0.0015504297],"genre_scores_gemma":[0.019390294,0.025429266,0.9536635,0.00007892338,0.00022198465,0.000055880428,0.0011091662,0.000017392485,0.00003356517],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992088,0.000042038744,0.00042647257,0.000119275624,0.000087476226,0.00011590061],"domain_scores_gemma":[0.99948055,0.00014891534,0.00010826241,0.0001414705,0.000078010984,0.000042804073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036746048,0.00011670084,0.00013139252,0.00013132064,0.00006193014,0.00004269175,0.00008472797,0.00008826439,0.0000042428724],"category_scores_gemma":[0.00014370451,0.00010633293,0.000046819427,0.00017035226,0.000053392683,0.00006329678,0.000027547849,0.00007690553,9.434279e-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":[0.000028886605,0.000053061696,0.00058389414,0.0011359095,0.000062834166,1.3225791e-7,0.001274788,0.0113996025,0.0010428918,0.0048033376,0.00021359684,0.97940105],"study_design_scores_gemma":[0.00032071772,0.00040651765,0.0023170547,0.00008364588,0.000033429482,0.000016711507,0.00069078215,0.59502023,0.0017923866,0.0018317999,0.3973203,0.00016640221],"about_ca_topic_score_codex":0.0000022428683,"about_ca_topic_score_gemma":0.000012224162,"teacher_disagreement_score":0.97923464,"about_ca_system_score_codex":0.00001261343,"about_ca_system_score_gemma":0.000062507286,"threshold_uncertainty_score":0.43361312},"labels":[],"label_agreement":null},{"id":"W4414717304","doi":"10.1101/2025.09.30.679566","title":"Identification and characterization of bacterial repeat-in-toxin adhesins using long-read genome analysis","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Queen's University","funders":"Canadian Glycomics Network; Natural Sciences and Engineering Research Council of Canada","keywords":"Bacterial adhesin; Genome; Bacteria; Bacterial genetics; DNA; Function (biology); Escherichia coli; Host (biology)","score_opus":0.00826467601069353,"score_gpt":0.2341864144382199,"score_spread":0.22592173842752636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414717304","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9816816,0.0001679527,0.016983869,0.000023182974,0.00029846825,0.00038995966,0.00042193983,0.000028620585,0.000004398541],"genre_scores_gemma":[0.9969383,0.0002993127,0.002443624,0.00003165787,0.00016912258,0.000026367166,0.00004211267,0.000032224616,0.00001730535],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.998052,0.00014473428,0.0007767179,0.00060735614,0.00017701325,0.00024216538],"domain_scores_gemma":[0.9978761,0.000011967618,0.0007838257,0.00096746226,0.00028458415,0.00007606076],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005409158,0.00032030762,0.00048628545,0.00050959626,0.00006249067,0.00010600111,0.0003044884,0.00051061966,0.000017216458],"category_scores_gemma":[0.00018196685,0.0003806343,0.00013543938,0.00055650034,0.00008287091,0.000015473783,0.00043200343,0.00025846882,0.0000013727174],"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":[0.00003162543,0.000050007784,0.034535035,0.00040927174,0.00030632145,0.0000019905126,0.0000137573625,0.00044834055,0.964181,0.00001819444,0.0000012163524,0.0000032139844],"study_design_scores_gemma":[0.0002808904,0.000028289687,0.5429594,0.0001222585,0.00042818428,1.3460548e-8,0.0000015475827,0.004687522,0.45081207,1.988737e-7,0.0003143254,0.00036526518],"about_ca_topic_score_codex":0.000038956412,"about_ca_topic_score_gemma":0.000012160284,"teacher_disagreement_score":0.51336896,"about_ca_system_score_codex":0.00007843121,"about_ca_system_score_gemma":0.0002778242,"threshold_uncertainty_score":0.9998646},"labels":[],"label_agreement":null},{"id":"W4414969529","doi":"10.1101/2025.10.08.681198","title":"Uncovering distinct protein conformations using coevolutionary information and AlphaFold","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Benchmark (surveying); Set (abstract data type); Markov chain; Sampling (signal processing); Sequence (biology); Key (lock); Conformational ensembles; Variation (astronomy)","score_opus":0.007236109952496665,"score_gpt":0.22601556042749552,"score_spread":0.21877945047499886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414969529","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96311253,0.00058111356,0.03356544,0.00010356992,0.00050780486,0.0010769798,0.00066344347,0.0001580186,0.00023108891],"genre_scores_gemma":[0.9803123,0.000093937175,0.019015536,0.00021393252,0.00018651065,0.000111825924,0.000015875034,0.000030988867,0.000019086996],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982818,0.00007670924,0.0006774949,0.0003449717,0.00025979584,0.00035926694],"domain_scores_gemma":[0.99812967,0.000017528784,0.0005440757,0.00077866996,0.00038475567,0.00014531342],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042458178,0.00042987926,0.00031373405,0.00022800977,0.0002757391,0.00022294279,0.00034867192,0.00053796987,0.000010145657],"category_scores_gemma":[0.00043936886,0.0004856426,0.00009715147,0.00020751095,0.00012241935,0.00006347917,0.0010230972,0.0005192789,0.000012644144],"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":[0.00023059903,0.00019986593,0.032337084,0.0075668106,0.0009012132,0.000009315882,0.000113030845,0.023214996,0.92868364,0.0041584596,0.002530567,0.00005440345],"study_design_scores_gemma":[0.0041694157,0.00046733706,0.14831175,0.004036373,0.0006909142,8.5441775e-7,0.000059912447,0.17786802,0.43630698,0.000041051542,0.22245504,0.005592371],"about_ca_topic_score_codex":0.00006725278,"about_ca_topic_score_gemma":0.0000028708175,"teacher_disagreement_score":0.4923767,"about_ca_system_score_codex":0.00013069708,"about_ca_system_score_gemma":0.0007199477,"threshold_uncertainty_score":0.9997595},"labels":[],"label_agreement":null},{"id":"W4415447705","doi":"10.1016/j.cmpb.2025.109127","title":"A deep learning model leveraging semantic features fusion for DNase I hypersensitive sites identification in the human genome","year":2025,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Manitoba","funders":"King Faisal University; Deanship of Scientific Research, King Khalid University","keywords":"Feature (linguistics); Deep learning; Code (set theory); Identification (biology); Feature learning; Source code; Representation (politics); Pattern recognition (psychology); Semantic feature","score_opus":0.02989842743848736,"score_gpt":0.36372290575101957,"score_spread":0.3338244783125322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415447705","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35446846,0.0006390035,0.6440083,0.0003444922,0.000056648194,0.0004081877,5.701673e-7,0.000010348147,0.00006400673],"genre_scores_gemma":[0.7129913,0.00007982403,0.28593007,0.00047065568,0.000096138436,0.00004456803,0.00028943343,0.0000083558925,0.000089638444],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989374,0.00026184856,0.0002853959,0.000253737,0.00007511779,0.00018646858],"domain_scores_gemma":[0.9995561,0.000094740906,0.0000888935,0.00018517522,0.000051360432,0.000023718638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018023876,0.00013319046,0.00017372292,0.00017182111,0.00013609769,0.000056996716,0.00014445212,0.00010017804,4.8679084e-7],"category_scores_gemma":[0.000098742916,0.0000972281,0.000039569124,0.00024170161,0.00010071874,0.000005375013,0.000116718315,0.00019949702,1.5780093e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060107068,0.00011254453,0.008734448,0.0003913555,0.000045416364,0.000004331005,0.0063396394,0.003909383,0.27666846,0.0005119549,0.00006117844,0.7031612],"study_design_scores_gemma":[0.0013876217,0.00041644997,0.045072865,0.0001673069,0.000042371797,0.000026352329,0.0012286913,0.94395983,0.0016098854,0.00149025,0.0043753833,0.00022298069],"about_ca_topic_score_codex":0.000017576425,"about_ca_topic_score_gemma":0.00001741472,"teacher_disagreement_score":0.9400505,"about_ca_system_score_codex":0.000012263294,"about_ca_system_score_gemma":0.000012408102,"threshold_uncertainty_score":0.39648467},"labels":[],"label_agreement":null},{"id":"W4415506496","doi":"10.1038/s41587-025-02859-7","title":"Democratizing protein language model training, sharing and collaboration","year":2025,"lang":"en","type":"article","venue":"Nature Biotechnology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"","keywords":"Language model; Training (meteorology); Language barrier; Training set; Deep learning","score_opus":0.003583905128090461,"score_gpt":0.2719175898338231,"score_spread":0.2683336847057326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415506496","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9752035,0.0017609033,0.014884634,0.0034823625,0.00008372529,0.00028837103,0.000007432876,0.00011127709,0.004177809],"genre_scores_gemma":[0.9777456,0.000039409995,0.020005016,0.00056463096,0.00003406931,0.000019447049,0.00004588539,0.000010748788,0.0015352293],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999351,0.0000133094345,0.00014898105,0.00025960398,0.000056308498,0.00017075788],"domain_scores_gemma":[0.99956614,0.0000040502364,0.00006608695,0.00030273758,0.000039868446,0.00002113158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001454552,0.000119786906,0.00011360544,0.0001275281,0.00009273305,0.00003027304,0.00019029656,0.0010680903,0.0000021922594],"category_scores_gemma":[0.0003849879,0.00011609752,0.000020471829,0.00019961348,0.00007944402,0.000004783761,0.00020376666,0.00050700246,0.0000013046223],"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":[0.00002854213,0.000011720293,0.000540852,0.00006081198,0.000035930647,0.0000019462675,0.00027713273,0.00023238336,0.95093864,0.035855256,0.0009124941,0.011104284],"study_design_scores_gemma":[0.00093852606,0.00019986584,0.00019735399,0.000091894944,0.000029072711,0.000030131885,0.0012939207,0.15473638,0.8081143,0.0034007423,0.030563343,0.00040450267],"about_ca_topic_score_codex":0.0000023603532,"about_ca_topic_score_gemma":0.00003966624,"teacher_disagreement_score":0.154504,"about_ca_system_score_codex":0.000014583751,"about_ca_system_score_gemma":0.00006933165,"threshold_uncertainty_score":0.823809},"labels":[],"label_agreement":null},{"id":"W4415550892","doi":"10.1101/2025.10.24.684331","title":"Improving conformational ensembles of folded proteins in GōMartini","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Max-Planck-Gesellschaft; Deutsche Forschungsgemeinschaft","keywords":"Force field (fiction); Molecular dynamics; Conformational ensembles; Energy landscape; Benchmark (surveying); Protein structure; Space (punctuation); Work (physics)","score_opus":0.0069444235014090964,"score_gpt":0.22391462505459406,"score_spread":0.21697020155318497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415550892","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9892117,0.0004445947,0.00825347,0.00009815683,0.00043046026,0.0010008388,0.00030823585,0.00006807576,0.00018448631],"genre_scores_gemma":[0.97901034,0.00006334779,0.020423444,0.00014575398,0.00014379573,0.00015099849,0.000004827401,0.0000352514,0.000022230774],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99797523,0.000101318365,0.0008471764,0.00044007078,0.0002735935,0.0003625956],"domain_scores_gemma":[0.9979035,0.000029946328,0.0006921518,0.000914516,0.00037103152,0.000088820474],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006478271,0.00037597297,0.00042646387,0.00026644292,0.00005884282,0.000058941623,0.0005244469,0.0005961462,0.000015765798],"category_scores_gemma":[0.0007133122,0.00041509417,0.000141144,0.00022821085,0.00009554415,0.000012096421,0.0007709461,0.0005294472,0.0000066807384],"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":[0.00007389541,0.00010829128,0.013623852,0.0018308131,0.000110433015,0.0000032682365,0.0000226431,0.0010800387,0.9820392,0.0008323855,0.0002613922,0.000013788272],"study_design_scores_gemma":[0.00094157626,0.00011602774,0.031986713,0.00059628946,0.00004812497,2.0721895e-8,0.000007726107,0.0072613973,0.95345294,0.0000028128325,0.004927556,0.0006587877],"about_ca_topic_score_codex":0.000083301136,"about_ca_topic_score_gemma":0.000010349139,"teacher_disagreement_score":0.028586231,"about_ca_system_score_codex":0.000066127126,"about_ca_system_score_gemma":0.00093172514,"threshold_uncertainty_score":0.99983007},"labels":[],"label_agreement":null},{"id":"W4415633432","doi":"10.1139/cjm-2024-0208","title":"Machine learning methods to identify markers and predict antimicrobial resistance in <i>Escherichia coli</i>","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Microbiology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada; Lethbridge College; Public Health Agency of Canada; University of Lethbridge; University of Manitoba; Genome Canada; Canadian Food Inspection Agency","funders":"Ministero dello Sviluppo Economico; Agriculture and Agri-Food Canada; Government of Canada; Public Health Agency; Public Health Agency of Canada","keywords":"Support vector machine; Identification (biology); Genome; In silico; Artificial neural network; Genomics; Antibiotic resistance; Feature (linguistics)","score_opus":0.005357339667588123,"score_gpt":0.2728747164874293,"score_spread":0.26751737681984117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415633432","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9856816,0.003108911,0.006835671,0.0014535548,0.0005291878,0.00016247109,0.00003972757,0.0000036035738,0.0021853072],"genre_scores_gemma":[0.93868315,0.00020133634,0.056308657,0.003076009,0.0000822095,0.000002577455,0.00005220359,0.000020838022,0.0015730147],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99870783,0.00034136453,0.0004466604,0.00016751137,0.00002118388,0.00031546934],"domain_scores_gemma":[0.9993413,0.000044878125,0.00017543885,0.0001411438,0.00009882153,0.00019839832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009654924,0.0001429656,0.00026057553,0.00032525914,0.00008981233,0.00003360829,0.00027009973,0.00019408611,0.000018759061],"category_scores_gemma":[0.0006593287,0.0001440643,0.000059105765,0.00021169128,0.00012973919,0.0000057687816,0.00006316392,0.00040850166,0.0000020320601],"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":[0.00016769649,0.000006823126,0.036005028,0.000060535334,0.00007273429,0.000020890131,0.00017248622,0.00025962444,0.9486147,0.000060619863,0.013536084,0.0010227353],"study_design_scores_gemma":[0.001417991,0.00033932447,0.024117336,0.0002503939,0.00004364405,0.0002137189,0.00012180286,0.00008290993,0.0588237,0.00007339507,0.91419804,0.00031773833],"about_ca_topic_score_codex":0.00042209617,"about_ca_topic_score_gemma":0.018423965,"teacher_disagreement_score":0.90066195,"about_ca_system_score_codex":0.00005919404,"about_ca_system_score_gemma":0.0005847201,"threshold_uncertainty_score":0.9994872},"labels":[],"label_agreement":null},{"id":"W4415933323","doi":"10.1021/acsomega.5c07055","title":"Half-Space Proximal Networks (HSPNs): A Proxy for Multi-Query Similarity Searching Models Predicting Tumor-Homing Peptides","year":2025,"lang":"en","type":"article","venue":"ACS Omega","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Universidad San Francisco de Quito; Universitat de València","keywords":"Leverage (statistics); Similarity (geometry); Centrality; Pairwise comparison; Benchmarking; Pattern recognition (psychology); Artificial neural network; Proxy (statistics)","score_opus":0.017765659202204024,"score_gpt":0.2960223005562391,"score_spread":0.2782566413540351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415933323","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53370005,0.00043455738,0.4613036,0.00045203324,0.00020742632,0.0012973278,0.00002143743,0.00010827801,0.0024753083],"genre_scores_gemma":[0.9193583,0.000030197956,0.07811469,0.00054661,0.00024772313,0.00018567688,0.00013109171,0.000042563763,0.0013431226],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983055,0.00009191125,0.00041857825,0.00043409594,0.00016780637,0.0005821282],"domain_scores_gemma":[0.9989794,0.00010705253,0.00018509802,0.0004721619,0.00016770794,0.000088573775],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008608748,0.0002740521,0.00026187222,0.00009786644,0.00038012117,0.00014192924,0.0004031409,0.00021128113,6.0659386e-7],"category_scores_gemma":[0.00086311426,0.00026906992,0.0001348314,0.0001710755,0.00009314944,0.000030707208,0.00046200017,0.00045581418,0.0000012766335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018474059,0.00092204456,0.206688,0.0039543905,0.0013325673,0.000028937444,0.0034501867,0.5876225,0.14213541,0.012887876,0.014921799,0.024208872],"study_design_scores_gemma":[0.0010797175,0.00016704724,0.0007571514,0.00016939412,0.000040383755,0.000011609443,0.00023348702,0.97875464,0.012528372,0.00024174315,0.0057044188,0.00031203544],"about_ca_topic_score_codex":0.000053677966,"about_ca_topic_score_gemma":0.000052722655,"teacher_disagreement_score":0.39113212,"about_ca_system_score_codex":0.000042949938,"about_ca_system_score_gemma":0.00017081633,"threshold_uncertainty_score":0.99997616},"labels":[],"label_agreement":null},{"id":"W4415937939","doi":"10.1101/2025.11.04.686393","title":"Harnessing Interpretable Deep Learning to Predict Resistance in <i>Klebsiella pneumoniae</i>","year":2025,"lang":"","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"FPInnovations","funders":"Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Deep learning; Meropenem; Antibiotic resistance; Inference; Profiling (computer programming); ORFS; False positive paradox; Mechanism (biology)","score_opus":0.004704489044187024,"score_gpt":0.21941770165089075,"score_spread":0.21471321260670373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415937939","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9295451,0.010408547,0.047615547,0.0010589018,0.0042493627,0.0035461856,0.00037147413,0.0004984394,0.0027064427],"genre_scores_gemma":[0.9725117,0.0016715209,0.023202332,0.00088728464,0.00054025307,0.00035392056,0.0000043226114,0.00022461462,0.0006040365],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99197584,0.0007899283,0.0021562052,0.0024936604,0.0007481445,0.0018362118],"domain_scores_gemma":[0.994461,0.0001592198,0.0011492039,0.0027726504,0.000792941,0.0006649937],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.0021883694,0.0015766806,0.0015051796,0.0007827983,0.0005230063,0.0007156648,0.002062377,0.0017950035,0.00006433684],"category_scores_gemma":[0.0025332659,0.0019514173,0.00041541283,0.0015776206,0.00026377194,0.00005431204,0.0029671714,0.003140702,0.000121033605],"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":[0.00061580254,0.000404304,0.07230928,0.0042036986,0.00052621716,0.000095821975,0.00033348848,0.024600578,0.89567626,0.0003169035,0.00085004035,0.00006763546],"study_design_scores_gemma":[0.0034682471,0.0007565049,0.057572693,0.013579554,0.000539658,2.279858e-7,0.00011382387,0.039429735,0.38147014,0.000005489697,0.49657652,0.0064873975],"about_ca_topic_score_codex":0.0000675069,"about_ca_topic_score_gemma":0.00009052121,"teacher_disagreement_score":0.5142061,"about_ca_system_score_codex":0.0006097898,"about_ca_system_score_gemma":0.0014048722,"threshold_uncertainty_score":0.9996981},"labels":[],"label_agreement":null},{"id":"W4416113856","doi":"10.1371/journal.pcbi.1012929","title":"Zero-shot segmentation using embeddings from a protein language model identifies functional regions in the human proteome","year":2025,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Hospital for Sick Children; University of Toronto","funders":"Canadian Institutes of Health Research; Canada Foundation for Innovation; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"UniProt; Human proteome project; Proteome; Categorization; Protein function prediction; Protein domain; Proteomics; Protein family; Annotation; Function (biology)","score_opus":0.030587635920844774,"score_gpt":0.32111751825544865,"score_spread":0.29052988233460386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416113856","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8355407,0.00005306994,0.16312467,0.00034827917,0.00003627436,0.00041441573,0.000045668527,0.000015066131,0.00042186212],"genre_scores_gemma":[0.97908866,0.0000010763622,0.017494591,0.0006694857,0.00006395522,0.00010563668,0.0023345673,0.000008077036,0.00023396313],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991034,0.00013255513,0.000277484,0.0002255724,0.00011489842,0.0001460562],"domain_scores_gemma":[0.9995873,0.00004938361,0.000117747746,0.00015656406,0.00007298302,0.000016039756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017363652,0.00012311128,0.00011164486,0.000107750246,0.00016587562,0.000037555656,0.000187442,0.000117937394,0.000015521664],"category_scores_gemma":[0.00010281787,0.000102177786,0.000048714694,0.00013338364,0.00009574603,0.000009284433,0.00009432871,0.0001577858,0.000005507135],"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":[0.00003421585,0.00008324216,0.0033618838,0.000026674617,0.000067765715,8.9601076e-7,0.00063462276,0.11203528,0.87627256,0.007038772,0.0003747952,0.000069315225],"study_design_scores_gemma":[0.0016735105,0.00017239414,0.011996993,0.00012628315,0.00006328914,0.000013391463,0.0009595542,0.8576242,0.041774236,0.08486998,0.00027854755,0.00044763702],"about_ca_topic_score_codex":0.0000730254,"about_ca_topic_score_gemma":0.000029856057,"teacher_disagreement_score":0.8344983,"about_ca_system_score_codex":0.000029991821,"about_ca_system_score_gemma":0.000089320005,"threshold_uncertainty_score":0.41666892},"labels":[],"label_agreement":null},{"id":"W4416140500","doi":"10.1093/neuonc/noaf201.0960","title":"PATH-08. Establishing the utility of deep-learning for H&amp;E-based meningioma molecular classification and outcome prediction","year":2025,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Deep learning; Classifier (UML); Leverage (statistics); Precision medicine; Correlation; Predictive modelling; Neuroimaging; Genomics","score_opus":0.01880609155948536,"score_gpt":0.30846736329931845,"score_spread":0.2896612717398331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416140500","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73412645,0.00024187911,0.2587568,0.0015700875,0.00036717864,0.0006442752,0.000016676171,0.000042745545,0.004233907],"genre_scores_gemma":[0.9929569,0.000020005593,0.005977605,0.0007303224,0.000045192297,0.000071337345,0.00014862345,0.000012951518,0.000037060632],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987068,0.0002891319,0.00043179246,0.00026874407,0.00010698326,0.00019651113],"domain_scores_gemma":[0.9988286,0.00038069338,0.0002707151,0.00033982474,0.00014085748,0.00003931147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007273948,0.00013695599,0.00019677749,0.00007182972,0.00016431931,0.0000286771,0.00020362738,0.00023829282,0.0000070812803],"category_scores_gemma":[0.002403054,0.0001155484,0.000085532425,0.00013127459,0.00014727048,0.000007583086,0.00011304071,0.00025896778,7.7698627e-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":[0.00024941258,0.00006660677,0.1041862,0.00021405063,0.00004780843,9.56697e-7,0.00018075856,0.0010355811,0.8605977,0.0006630512,0.00082149525,0.031936374],"study_design_scores_gemma":[0.0025471968,0.001343906,0.061481997,0.000030808234,0.00020557143,0.000025621202,0.0003922833,0.37576705,0.07818911,0.00031217327,0.4794292,0.00027511225],"about_ca_topic_score_codex":0.000007715309,"about_ca_topic_score_gemma":0.000012371715,"teacher_disagreement_score":0.7824086,"about_ca_system_score_codex":0.000023832165,"about_ca_system_score_gemma":0.000101118334,"threshold_uncertainty_score":0.4711927},"labels":[],"label_agreement":null},{"id":"W4416294149","doi":"10.1101/2025.11.16.688401","title":"BioPrediction-PPI: Simplifying the Prediction of Protein-Protein actions through Artificial Intelligence","year":2025,"lang":"","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"WiLAN (Canada)","funders":"Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Interpretability; Process (computing); Feature (linguistics); Deep learning; Key (lock)","score_opus":0.025568420844397227,"score_gpt":0.2634717243552467,"score_spread":0.23790330351084946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416294149","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5922416,0.001908426,0.39052445,0.0013980485,0.003895526,0.0062678894,0.0030275672,0.00037854823,0.00035794906],"genre_scores_gemma":[0.9807164,0.00084507366,0.01630903,0.00014557093,0.0011016185,0.00070602493,0.000008135003,0.00010744529,0.000060722254],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99426645,0.00048370202,0.002204195,0.0013854066,0.0007682963,0.00089196826],"domain_scores_gemma":[0.9936357,0.000076349446,0.0018131905,0.002955323,0.0013035927,0.00021582184],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0012167619,0.0010460947,0.0008007169,0.0002953149,0.00095685665,0.00028055298,0.0015329705,0.0015397064,0.000094990224],"category_scores_gemma":[0.0013880322,0.000994733,0.00051680394,0.0012228192,0.00078174553,0.00005956282,0.0013721156,0.0019881218,0.000042652096],"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":[0.00016463504,0.0002565364,0.00043515424,0.001411268,0.000641019,0.0000026810308,0.000057558525,0.003718989,0.9863415,0.006770856,0.00012608849,0.00007374225],"study_design_scores_gemma":[0.00022354406,0.0003734539,0.0021306225,0.0013430148,0.00034502105,9.442814e-8,0.00006834786,0.010601328,0.9590334,0.00006231392,0.025031054,0.00078780076],"about_ca_topic_score_codex":0.0001564531,"about_ca_topic_score_gemma":0.0000078476905,"teacher_disagreement_score":0.3884748,"about_ca_system_score_codex":0.00026093522,"about_ca_system_score_gemma":0.0015740872,"threshold_uncertainty_score":0.9997565},"labels":[],"label_agreement":null},{"id":"W4416295244","doi":"10.1101/2025.11.13.688294","title":"TooTranslator: Zero-Shot Classification of Specific Substrates for Transport Proteins by Language Embedding Alignment of Proteins and Chemicals","year":2025,"lang":"","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Canada","keywords":"Embedding; Transmembrane protein; Task (project management); Substrate (aquarium); Substrate specificity; Function (biology); Class (philosophy); Training set","score_opus":0.012350228304203067,"score_gpt":0.2530394296372403,"score_spread":0.24068920133303723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416295244","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9488316,0.0045117605,0.038921032,0.0001202132,0.00021459344,0.00425866,0.0030408152,0.000047744896,0.000053574255],"genre_scores_gemma":[0.9693526,0.0013425284,0.028387403,0.000030911375,0.00012209985,0.000615943,0.000031543936,0.000090233734,0.000026738117],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9958991,0.00012146917,0.001788675,0.0011331683,0.00044706083,0.0006105619],"domain_scores_gemma":[0.99624884,0.00006762153,0.0014573043,0.0014032482,0.00059092167,0.00023206454],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010099766,0.0008135814,0.0010601166,0.00024272496,0.0001367146,0.00006080078,0.0006905888,0.001120779,0.00002246137],"category_scores_gemma":[0.00016476476,0.0009057059,0.00034165807,0.0003702407,0.00041647,0.000024779745,0.0001711051,0.0005204481,0.0000010796422],"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":[0.00026056566,0.00034586265,0.0039831204,0.0059130173,0.00039942216,0.0000010568149,0.00012054075,0.00008545405,0.98818296,0.00056801725,0.00011843678,0.000021555536],"study_design_scores_gemma":[0.0012260625,0.0003276867,0.004212058,0.000970612,0.0002359206,3.2049194e-8,0.000033421056,0.0010848271,0.9843651,0.000001799728,0.006783475,0.000759003],"about_ca_topic_score_codex":0.000031625328,"about_ca_topic_score_gemma":0.0000020536565,"teacher_disagreement_score":0.020520993,"about_ca_system_score_codex":0.00009559473,"about_ca_system_score_gemma":0.00058170117,"threshold_uncertainty_score":0.99933934},"labels":[],"label_agreement":null},{"id":"W4416408018","doi":"10.1101/2025.11.14.688531","title":"Scalable prediction of symmetric protein complex structures","year":2025,"lang":"","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Gilead Sciences (Canada)","funders":"","keywords":"Scalability; Protein structure; Protein structure prediction; Function (biology); Limit (mathematics); Feature (linguistics); Structural biology; CASP; Power (physics)","score_opus":0.011149183225215844,"score_gpt":0.2270414140722054,"score_spread":0.21589223084698955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416408018","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97269505,0.0027805564,0.014150362,0.00018720282,0.001980703,0.003579624,0.0037660818,0.00023004539,0.00063039374],"genre_scores_gemma":[0.96953404,0.0005465207,0.028841011,0.00014406822,0.0005362232,0.00017954451,0.000012265789,0.00011046339,0.000095850904],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9947377,0.0004013701,0.0018212785,0.001382634,0.00075213023,0.0009048988],"domain_scores_gemma":[0.9939107,0.00005395367,0.0016769113,0.0026327786,0.0013852492,0.00034046502],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0010444853,0.0010880328,0.001135367,0.00076839083,0.000321906,0.0001901999,0.0013831996,0.0017052059,0.00015258638],"category_scores_gemma":[0.0012631968,0.0012143627,0.00043367854,0.0014060108,0.0004386814,0.000024649371,0.0015859646,0.0012727948,0.000023601122],"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":[0.00014878674,0.00024432258,0.008949942,0.004110165,0.00068031705,0.000003987248,0.000009430445,0.0012640536,0.9808738,0.002769085,0.0009283122,0.000017750473],"study_design_scores_gemma":[0.0013461161,0.00050032866,0.09061183,0.00093312195,0.00035077197,4.872221e-8,0.0000060448965,0.010962877,0.85778934,0.0000073008646,0.036415532,0.0010766884],"about_ca_topic_score_codex":0.000087026485,"about_ca_topic_score_gemma":0.0000016733021,"teacher_disagreement_score":0.12308451,"about_ca_system_score_codex":0.00021920659,"about_ca_system_score_gemma":0.0014401647,"threshold_uncertainty_score":0.9995908},"labels":[],"label_agreement":null},{"id":"W4416448852","doi":"10.1093/jimmun/vkaf283.374","title":"A machine learning approach to the identification of somatic recombination in immune cells 2462","year":2025,"lang":"en","type":"article","venue":"The Journal of Immunology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Vitalité Health Network; Université de Moncton","funders":"National Institute on Minority Health and Health Disparities; National Institutes of Health","keywords":"IGHV@; Identification (biology); Somatic cell; Biomarker; Chronic lymphocytic leukemia; Immune system","score_opus":0.005028954228380122,"score_gpt":0.23613417791199126,"score_spread":0.23110522368361114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416448852","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9661409,0.002679397,0.027655855,0.0015135829,0.00032787735,0.0002265795,0.0000011112937,0.0000032645746,0.0014513927],"genre_scores_gemma":[0.99818254,0.0004430637,0.00063826266,0.00007693542,0.000017116203,0.0000034217585,0.000008241835,0.0000059909244,0.00062443234],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986412,0.0004084888,0.0007014048,0.00005336853,0.000087360175,0.00010819494],"domain_scores_gemma":[0.9989209,0.00006981001,0.00061269786,0.00026650165,0.00012170421,0.000008377158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019632787,0.00007607174,0.00015932646,0.00014226818,0.000068117675,0.000010271468,0.0004873417,0.0000761214,0.0000036694632],"category_scores_gemma":[0.00050246157,0.00004619975,0.000058134923,0.00021606561,0.00006296019,0.000005521184,0.00012641647,0.00033199796,0.000003969108],"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":[0.00018233694,0.000097373915,0.00071177265,0.000041353647,0.000117990625,1.5147724e-7,0.0012165618,0.022908382,0.9686814,0.00050917355,0.0001450902,0.005388398],"study_design_scores_gemma":[0.0037039446,0.0018694602,0.090424925,0.00023488463,0.0002463267,0.0002944324,0.0047037588,0.06012749,0.8162811,0.0020521134,0.019682843,0.00037874488],"about_ca_topic_score_codex":0.000026406558,"about_ca_topic_score_gemma":0.0000055048918,"teacher_disagreement_score":0.15240033,"about_ca_system_score_codex":0.000021401678,"about_ca_system_score_gemma":0.00004997916,"threshold_uncertainty_score":0.18839712},"labels":[],"label_agreement":null},{"id":"W4416728543","doi":"10.1109/mwscas53549.2025.11244593","title":"Integrating Graph Signal Processing with Graph Convolutional Networks for N - and O-Glycosylation Site Prediction","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Windsor","funders":"","keywords":"Graph; Signal processing; Pattern recognition (psychology); Graph theory; Power graph analysis; Dual graph; Wait-for graph","score_opus":0.003942839405322031,"score_gpt":0.23081518454288105,"score_spread":0.22687234513755902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416728543","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061992556,0.00193059,0.9314576,0.00024298603,0.00014052891,0.0007335276,0.00004964651,0.000038556813,0.0034140146],"genre_scores_gemma":[0.9603188,0.0002031123,0.037115384,0.00035896595,0.00022941602,0.000070662674,0.0009571037,0.00002402187,0.0007225499],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835986,0.00006532003,0.00055949186,0.0004701092,0.00017068867,0.00037454837],"domain_scores_gemma":[0.9989491,0.0000681306,0.0003115073,0.00018343634,0.00039991768,0.00008788309],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045189573,0.00033571164,0.0002414731,0.00017194981,0.00058188225,0.00019767765,0.00011258391,0.00038252442,0.000018352986],"category_scores_gemma":[0.000075505246,0.00028896827,0.00009612233,0.00034410268,0.000255486,0.000031558797,0.00009629138,0.00030563658,4.3765607e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004492132,0.00044808714,0.42564008,0.003851935,0.0014556672,0.0000020274795,0.0011162213,0.14235102,0.03069964,0.024441695,0.0060090097,0.3594925],"study_design_scores_gemma":[0.0017325308,0.0008569564,0.005693228,0.00041987363,0.00020916192,0.000021179956,0.00021761538,0.9827502,0.0013940887,0.0005849729,0.005770737,0.00034946177],"about_ca_topic_score_codex":0.000020822148,"about_ca_topic_score_gemma":0.00007412271,"teacher_disagreement_score":0.8983262,"about_ca_system_score_codex":0.000032205506,"about_ca_system_score_gemma":0.00024729024,"threshold_uncertainty_score":0.99995625},"labels":[],"label_agreement":null},{"id":"W4416888770","doi":"10.1093/bioinformatics/btaf647","title":"PICNIC web server for predicting proteins involved in biomolecular condensates","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Innovation Cluster (Canada)","funders":"H2020 European Research Council; NOMIS Stiftung; Max-Planck-Gesellschaft","keywords":"Picnic; Web server; Software; Clickstream; Server; The Internet","score_opus":0.008964446904368453,"score_gpt":0.26154384707350364,"score_spread":0.2525794001691352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416888770","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9558691,0.00033326255,0.03499274,0.00043896007,0.00034673238,0.001828418,0.00006671776,0.00009176402,0.0060323016],"genre_scores_gemma":[0.9515028,0.000044098466,0.04577348,0.0011266393,0.00007344478,0.00016764083,0.00039709377,0.00002736181,0.0008874253],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985893,0.000032703545,0.00066878047,0.00017429235,0.00015123883,0.0003837054],"domain_scores_gemma":[0.9991309,0.000031034073,0.00020184819,0.00046435956,0.00011163442,0.00006024723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004844511,0.00022794135,0.00022306963,0.00019258259,0.00010362918,0.00006961711,0.0003334228,0.00025375778,0.000008027497],"category_scores_gemma":[0.0005986646,0.00021826001,0.000116061456,0.0002735308,0.00007579953,0.000018074566,0.00020925797,0.000160462,0.000013970246],"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":[0.0010257174,0.0007822521,0.35218087,0.010929072,0.0011207836,0.000010969993,0.0036522362,0.0054210536,0.5473537,0.011916121,0.039130278,0.026476942],"study_design_scores_gemma":[0.0071827834,0.00089355884,0.0059902836,0.0006226445,0.000106021405,0.000014966624,0.0018012547,0.6838063,0.17423072,0.0009078525,0.12326452,0.0011791056],"about_ca_topic_score_codex":0.000010997557,"about_ca_topic_score_gemma":0.00009025547,"teacher_disagreement_score":0.6783852,"about_ca_system_score_codex":0.000041154624,"about_ca_system_score_gemma":0.0002365388,"threshold_uncertainty_score":0.8900385},"labels":[],"label_agreement":null},{"id":"W4417017350","doi":"10.5376/cmb.2025.15.0014","title":"Pretrained Language Models for Biological Sequence Understanding","year":2025,"lang":"","type":"article","venue":"Computational Molecular Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interpretability; Sequence (biology); Field (mathematics); Biological data; Biological database; Function (biology); Computational model; Language model","score_opus":0.04331735219292956,"score_gpt":0.3521607780462377,"score_spread":0.30884342585330815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417017350","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":[0.016897365,0.0023398641,0.9708333,0.0013322034,0.00054396864,0.0009308524,0.00040115416,0.00004651136,0.0066747754],"genre_scores_gemma":[0.9249498,0.00005616987,0.06863124,0.0023945877,0.00011538002,0.00008083262,0.003507009,0.000030759944,0.00023420411],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974326,0.00030385295,0.00071071,0.0007926825,0.00013203852,0.00062814483],"domain_scores_gemma":[0.99863523,0.00028224548,0.00028060997,0.00042871365,0.00025247876,0.00012071278],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00049689313,0.00045436312,0.00044550127,0.00022173893,0.000289875,0.00007575684,0.0005725512,0.0007788863,0.000024769255],"category_scores_gemma":[0.0006694919,0.00045845105,0.00033088014,0.00030370912,0.0005469004,0.000009762827,0.00037668733,0.00030545806,0.000007722557],"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":[0.00027635513,0.000103245366,0.0004275365,0.00021277304,0.0004794007,0.000006393257,0.0001916141,0.12563613,0.08696824,0.781348,0.000642385,0.003707958],"study_design_scores_gemma":[0.0015988341,0.0006945307,0.000043390744,0.00007985068,0.000072302675,0.00002382888,0.0002758597,0.4751679,0.0018777851,0.5173649,0.002282186,0.00051859615],"about_ca_topic_score_codex":0.000006545049,"about_ca_topic_score_gemma":0.000002746082,"teacher_disagreement_score":0.90805244,"about_ca_system_score_codex":0.00017101028,"about_ca_system_score_gemma":0.00052271504,"threshold_uncertainty_score":0.99978673},"labels":[],"label_agreement":null},{"id":"W4417122478","doi":"10.1021/acs.jcim.5c02196","title":"AcidProNet: Acidophilic Protein Classification via DCGAN-GP-Based Data Augmentation and Parameter-Shared Mixture-of-Experts Transformer","year":2025,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Fundo para o Desenvolvimento das Ciências e da Tecnologia; Hainan Provincial Department of Science and Technology; Natural Science Foundation of Hainan Province; National Natural Science Foundation of China","keywords":"Scalability; Identification (biology); Embedding; Key (lock); Transformer; Stability (learning theory); Generative grammar; Exploit","score_opus":0.02609890357100594,"score_gpt":0.3021179786139657,"score_spread":0.2760190750429598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417122478","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6070506,0.00015736953,0.3921114,0.00037710497,0.000029497669,0.00014102529,0.000010671126,0.000003541417,0.000118835706],"genre_scores_gemma":[0.98126674,0.00005914504,0.0179853,0.0003158365,0.000025996602,0.0000045932015,0.00033285125,0.000004040688,0.000005479917],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902725,0.000019600137,0.0006415337,0.000075234624,0.00014756937,0.00008879334],"domain_scores_gemma":[0.9992666,0.0000148569825,0.00032746114,0.00016829654,0.00017111178,0.000051644176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002965049,0.00009956773,0.00014414443,0.000099624645,0.00003544181,0.00004478299,0.00014683529,0.000127869,0.000003459726],"category_scores_gemma":[0.00018690221,0.00008473183,0.000035731486,0.00006544619,0.000040470823,0.00011465906,0.000034701952,0.00012425918,2.3798307e-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":[0.00030154295,0.00003531222,0.00015339947,0.0003142027,0.000051397954,1.0891623e-7,0.00037036,0.0019994364,0.95514596,0.000051619452,0.0001965191,0.04138016],"study_design_scores_gemma":[0.001016555,0.00008661788,0.000044385502,0.00011061116,0.000032694414,0.000012246999,0.00014748325,0.7608306,0.2361595,0.00011240952,0.0013503575,0.00009657247],"about_ca_topic_score_codex":0.0000029192379,"about_ca_topic_score_gemma":4.657879e-7,"teacher_disagreement_score":0.75883114,"about_ca_system_score_codex":0.000012609129,"about_ca_system_score_gemma":0.00007382494,"threshold_uncertainty_score":0.34552637},"labels":[],"label_agreement":null},{"id":"W4417520771","doi":"10.64898/2025.12.18.694875","title":"Enigma: An Efficient Model for Deciphering Regulatory Genomics","year":2025,"lang":"","type":"article","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Set (abstract data type); Computational model; Genomics; Training set; Genome; Scale (ratio)","score_opus":0.007570151171111024,"score_gpt":0.22982715985984037,"score_spread":0.22225700868872936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417520771","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7152722,0.0017345832,0.28052065,0.00012659816,0.0009435807,0.0010451414,0.00018096424,0.000115472736,0.00006082937],"genre_scores_gemma":[0.93598366,0.00022267751,0.062261794,0.0006715513,0.00043365118,0.00015927419,0.0000018744058,0.00017052657,0.00009501338],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961381,0.0001335489,0.0010865903,0.0012069846,0.00032134366,0.0011134305],"domain_scores_gemma":[0.9961292,0.00005788236,0.0005022744,0.0021999192,0.0006843483,0.00042634722],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012248352,0.0007925702,0.00061898405,0.00025422723,0.0006209306,0.00028930197,0.000991857,0.0008853083,0.000012424929],"category_scores_gemma":[0.0005346171,0.00095281744,0.00032291262,0.00047077806,0.00027159826,0.000029252016,0.000478429,0.0004652893,0.000016789978],"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":[0.00024289277,0.00032643732,0.0013600196,0.0006808338,0.00030019754,0.0000029427333,0.00004100559,0.13062577,0.86239547,0.0035080274,0.0004882236,0.000028169783],"study_design_scores_gemma":[0.0013512261,0.000186023,0.0026185138,0.00014779315,0.00018978617,2.2014042e-8,0.000010720524,0.7091724,0.26405263,0.0000020494742,0.021408413,0.0008603931],"about_ca_topic_score_codex":0.000006006473,"about_ca_topic_score_gemma":0.0000039604724,"teacher_disagreement_score":0.59834284,"about_ca_system_score_codex":0.00037590583,"about_ca_system_score_gemma":0.0016201882,"threshold_uncertainty_score":0.99929225},"labels":[],"label_agreement":null},{"id":"W5984741","doi":"","title":"A refined multisite fungal protein localizer","year":2008,"lang":"en","type":"article","venue":"International conference on Artificial intelligence and applications","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Subcellular localization; Classifier (UML); Protein subcellular localization prediction; Computer science; Artificial intelligence; Computational biology; Pattern recognition (psychology); Data mining; Biology; Cytoplasm; Biochemistry; Gene","score_opus":0.06156228484602595,"score_gpt":0.3292272926304756,"score_spread":0.2676650077844497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W5984741","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38466334,0.00006914449,0.54121125,0.0041271145,0.000174831,0.001068887,0.00009781431,0.00009414693,0.06849346],"genre_scores_gemma":[0.9951153,0.00013185057,0.0025052081,0.00040259596,0.00021592082,0.00019232712,0.00013776594,0.000009788436,0.0012892619],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999196,0.000019610376,0.0002532638,0.00024105875,0.00016273512,0.00012734854],"domain_scores_gemma":[0.99945325,0.000011224251,0.00008640265,0.00020993817,0.00017257752,0.000066592795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008297441,0.00011713072,0.00007751596,0.00005593099,0.00016193833,0.00004190506,0.00022587064,0.00007924822,0.00014324852],"category_scores_gemma":[0.000063919484,0.00011226108,0.00003754792,0.00007051861,0.00016391213,0.000009848046,0.00007208593,0.00012775153,0.00016883084],"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":[0.00017473976,0.0002647723,0.0010457608,0.000013803936,0.00005743551,0.0000048333045,0.00020586837,0.0005602824,0.11650241,0.77199334,0.0005133163,0.10866347],"study_design_scores_gemma":[0.00028374142,0.0008306942,0.0023994737,0.00010235064,0.00002277683,0.00018184575,0.0007416127,0.07771805,0.5407725,0.027991533,0.34783003,0.0011253902],"about_ca_topic_score_codex":0.000020945557,"about_ca_topic_score_gemma":0.000029830044,"teacher_disagreement_score":0.7440018,"about_ca_system_score_codex":0.0000102468575,"about_ca_system_score_gemma":0.00003953212,"threshold_uncertainty_score":0.4577874},"labels":[],"label_agreement":null},{"id":"W6893158151","doi":"10.5281/zenodo.14825943","title":"SPOT: A machine learning model that predicts specific substrates for transport proteins","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Deutsche Forschungsgemeinschaft","keywords":"Python (programming language); Function (biology); Web server; Transporter; Membrane transport protein; Set (abstract data type); Training set; Protein function prediction","score_opus":0.02885701052006852,"score_gpt":0.24266829989273347,"score_spread":0.21381128937266497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6893158151","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33006266,0.0025102869,0.5525967,0.0014770926,0.00036037102,0.0033316503,0.0017531972,0.0024976856,0.105410345],"genre_scores_gemma":[0.9837796,0.00031329982,0.0035602995,0.00005906844,0.00021487888,4.220937e-7,0.0076576862,0.0010696824,0.0033450732],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.998694,0.00008594093,0.00023599903,0.00039527463,0.00024295358,0.00034583034],"domain_scores_gemma":[0.99930316,0.000011103281,0.000065280685,0.0003092106,0.00018774562,0.00012349273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005904446,0.0001795263,0.00012520798,0.00012759201,0.0008799045,0.00040524142,0.00053572096,0.00011216715,0.0008418403],"category_scores_gemma":[0.00018007129,0.00017734154,0.00009543894,0.00019254709,0.00010074427,0.000027372618,0.00024610202,0.0003170568,0.00045889302],"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":[0.0012512617,0.00050955446,0.0002829168,0.0029773272,0.0006265499,0.000059945534,0.0067647216,0.055223074,0.5292396,0.01576044,0.19375817,0.19354647],"study_design_scores_gemma":[0.00037247853,0.0003918044,0.000113124675,0.00004841157,0.000016782966,0.00007463396,0.000068421024,0.09512058,0.009774438,0.00010627947,0.8937049,0.00020816263],"about_ca_topic_score_codex":0.000004299566,"about_ca_topic_score_gemma":6.476932e-7,"teacher_disagreement_score":0.6999467,"about_ca_system_score_codex":0.000037718397,"about_ca_system_score_gemma":0.000009556385,"threshold_uncertainty_score":0.9217561},"labels":[],"label_agreement":null},{"id":"W6893965887","doi":"10.5281/zenodo.6583296","title":"The Influence of Emotional Wellness on Student Success Pre-Pandemic","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Windsor","funders":"","keywords":"Student engagement; Context (archaeology); Higher education; Emotional health; Emotional intelligence; Sample (material); Academic achievement","score_opus":0.01153860994687944,"score_gpt":0.26472428262587455,"score_spread":0.2531856726789951,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6893965887","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.986134,0.000035988447,0.00033480217,0.0002515294,0.000061399274,0.00022545528,0.000085182284,0.000061502054,0.012810155],"genre_scores_gemma":[0.9981707,0.000040850136,0.00002751473,0.00014073841,0.00004711473,1.1268428e-7,0.0005933808,0.00021693714,0.00076268666],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987657,0.000303324,0.00020045381,0.00017257356,0.00038751718,0.00017042644],"domain_scores_gemma":[0.9992554,0.000019707044,0.00013168022,0.00036674034,0.0001789098,0.000047518926],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00071045785,0.000078097924,0.00006381651,0.000050887516,0.002026051,0.000118701544,0.0010269271,0.000027161315,0.00092851504],"category_scores_gemma":[0.0003560145,0.0000680858,0.00003482819,0.00017226377,0.00012679717,0.0000071408235,0.001508585,0.00022432987,0.00014483152],"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":[0.0015821371,0.0014143015,0.005263687,0.00030099618,0.00050743326,0.000010847306,0.006553568,0.41688764,0.1256865,0.02725613,0.21906795,0.19546881],"study_design_scores_gemma":[0.00032692423,0.00067788333,0.0334424,0.000007996992,0.000005302255,0.000050091905,0.0002295822,0.000362093,0.0011757425,0.000041632866,0.9635762,0.00010417494],"about_ca_topic_score_codex":0.0000049891537,"about_ca_topic_score_gemma":2.1177514e-7,"teacher_disagreement_score":0.7445082,"about_ca_system_score_codex":0.000043696517,"about_ca_system_score_gemma":0.0000057194684,"threshold_uncertainty_score":0.9999848},"labels":[],"label_agreement":null},{"id":"W6901814734","doi":"10.60692/7r1eb-5qw49","title":"TranCEP: Predicting the substrate class of transmembrane transport proteins using compositional, evolutionary, and positional information","year":2020,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Transmembrane protein; Membrane; Membrane transport; Transmembrane domain; Proteome; Membrane transport protein; Substrate (aquarium); Sequence (biology)","score_opus":0.017394529771918674,"score_gpt":0.2051392104797007,"score_spread":0.18774468070778205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901814734","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89668167,0.000011657476,0.1010286,0.00030406454,0.000058862188,0.0005400815,0.00044226367,0.0000402543,0.00089255796],"genre_scores_gemma":[0.99693024,7.918575e-7,0.0021143837,0.00035477598,0.00008383361,0.000025590396,0.00048008567,0.0000071287013,0.0000031876582],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866015,0.000054179316,0.0007236449,0.000092294846,0.0003142927,0.00015541461],"domain_scores_gemma":[0.999188,0.0000047108892,0.0003841709,0.00014953862,0.00019677775,0.00007682356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021362993,0.00016205812,0.00016367639,0.0000629306,0.00019692855,0.00004734941,0.00014582773,0.00012228123,0.000008071862],"category_scores_gemma":[0.0000131763845,0.00012814709,0.00007832997,0.00013493231,0.000095657415,0.0001383857,0.00002267692,0.00012822203,0.000009759225],"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":[0.0028417925,0.000029470195,0.548349,0.010999659,0.0008107696,0.0000031860357,0.251119,0.16625082,0.014800141,0.0037877436,0.00031176902,0.00069665414],"study_design_scores_gemma":[0.0048346296,0.00074233447,0.37657043,0.00049284473,0.00021373942,0.00050042634,0.01676511,0.5729949,0.023328513,0.0000036193737,0.0027435643,0.0008098963],"about_ca_topic_score_codex":0.000007089627,"about_ca_topic_score_gemma":1.6959243e-7,"teacher_disagreement_score":0.40674406,"about_ca_system_score_codex":0.00002007284,"about_ca_system_score_gemma":0.00007656289,"threshold_uncertainty_score":0.5225687},"labels":[],"label_agreement":null},{"id":"W6901822532","doi":"10.6084/m9.figshare.13468119.v1","title":"Additional file 1 of Integrative approach for detecting membrane proteins","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Membrane protein; Protein–protein interaction; Protein methods; Protein detection","score_opus":0.021320783514906558,"score_gpt":0.24180710373682066,"score_spread":0.2204863202219141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901822532","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011293763,0.000007945105,0.00045503344,0.000019136787,0.0000025927186,0.00029436988,0.9920867,0.000013014868,0.0071098898],"genre_scores_gemma":[0.0020412186,9.685434e-8,0.051352553,0.00018708948,0.00014908334,0.00108973,0.9448987,0.00001237148,0.0002691402],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995688,0.00001408127,0.00012801973,0.00012459449,0.00006985662,0.00009461572],"domain_scores_gemma":[0.99950254,0.00012519276,0.00012801874,0.000090887064,0.00011137391,0.000041992473],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000012358646,0.00008714269,0.00009124957,0.000011111976,0.000038340793,0.000008572332,0.00012993481,0.00007572729,0.83651245],"category_scores_gemma":[0.009301605,0.000073767755,0.00007606242,0.000055266788,0.0000067330225,0.0000028783115,0.00007322597,0.000084650484,0.000067943874],"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":[0.000018526343,0.000008818792,2.5814302e-7,0.0002347774,0.000017563978,8.2933965e-8,0.00006615792,0.00009656699,0.0022442692,0.0000011304669,0.9964685,0.00084333384],"study_design_scores_gemma":[0.00013279366,0.00024179302,0.00001405638,0.00019470711,0.00000249353,0.0000026186688,0.00009951944,0.016862137,0.041834496,0.0000016980556,0.9405107,0.00010301123],"about_ca_topic_score_codex":3.1495927e-7,"about_ca_topic_score_gemma":7.0090476e-7,"teacher_disagreement_score":0.83644456,"about_ca_system_score_codex":0.0000034515356,"about_ca_system_score_gemma":0.000056514575,"threshold_uncertainty_score":0.99904346},"labels":[],"label_agreement":null},{"id":"W6902048758","doi":"10.6084/m9.figshare.13468123","title":"Additional file 2 of Integrative approach for detecting membrane proteins","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Membrane protein; Protein–protein interaction; Protein detection; Protein methods","score_opus":0.020502350756592996,"score_gpt":0.24123325854319705,"score_spread":0.22073090778660406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902048758","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001121196,0.000008081248,0.00044455903,0.000019030476,0.0000026089003,0.00029380436,0.9919253,0.000013011328,0.007282364],"genre_scores_gemma":[0.002007603,9.968874e-8,0.050251115,0.00018727033,0.0001515902,0.0010683279,0.9460513,0.000012364136,0.00027033789],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99956894,0.000014076148,0.00012808126,0.00012449428,0.000069837864,0.0000945783],"domain_scores_gemma":[0.9995047,0.0001232959,0.00012821077,0.000090699825,0.00011110822,0.00004198584],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000012286292,0.00008711297,0.00009127353,0.000011104174,0.000038343805,0.000008592289,0.00012985726,0.00007572776,0.833703],"category_scores_gemma":[0.009182343,0.00007374189,0.000076046636,0.00005522071,0.0000067329224,0.0000028804272,0.00007321493,0.00008462959,0.00006716672],"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":[0.000018416957,0.000008815122,2.4935656e-7,0.00023704425,0.00001756299,8.536519e-8,0.000066213404,0.0000970584,0.0021610605,0.0000011517412,0.9965238,0.0008685633],"study_design_scores_gemma":[0.00013284503,0.0002401656,0.00001371832,0.00019080444,0.0000024666845,0.0000026067648,0.0000977503,0.016626839,0.04127525,0.0000017007276,0.9413138,0.00010206922],"about_ca_topic_score_codex":3.1836484e-7,"about_ca_topic_score_gemma":7.053551e-7,"teacher_disagreement_score":0.8336358,"about_ca_system_score_codex":0.000003452596,"about_ca_system_score_gemma":0.00005624487,"threshold_uncertainty_score":0.99916375},"labels":[],"label_agreement":null},{"id":"W6902190148","doi":"10.6084/m9.figshare.28396632.v1","title":"Additional file 2 of A hybrid machine learning framework for functional annotation of mitochondrial glutathione transport and metabolism proteins in cancers","year":2025,"lang":"en","type":"article","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"","keywords":"Annotation; Supervised learning; Metabolism; Mitochondrion; Support vector machine","score_opus":0.008491494647390456,"score_gpt":0.2372374522927996,"score_spread":0.22874595764540914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902190148","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00096134207,0.0001270801,0.0012329298,0.000022942457,0.000028011254,0.00028907196,0.997032,0.00000538318,0.00030125753],"genre_scores_gemma":[0.016832357,0.0000031494833,0.021333104,0.00005050933,0.00007942065,0.0007446439,0.9606472,0.00000843986,0.00030113434],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99946547,0.000019039699,0.00021702156,0.00012359669,0.000087919936,0.00008694781],"domain_scores_gemma":[0.9994557,0.00018705128,0.0001542522,0.00007445617,0.00011041298,0.000018138928],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00002385815,0.0000805638,0.00012598748,0.00006602944,0.00003345813,0.0000036569493,0.000055316752,0.00007306315,0.24093269],"category_scores_gemma":[0.0026615623,0.000083752144,0.000053943004,0.00008885739,0.000014167418,0.0000055771147,0.000023028015,0.00012418968,0.0000022987113],"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":[0.0002934625,0.000037399397,0.00008544379,0.00059920107,0.00006647491,5.70808e-7,0.0000714527,0.0030023006,0.0019977516,0.000098110424,0.99154204,0.0022057882],"study_design_scores_gemma":[0.00079239596,0.00013448062,0.007359429,0.0013785302,0.000014454786,0.000003142235,0.00003222177,0.008235191,0.00601429,0.0002326796,0.9756615,0.00014166078],"about_ca_topic_score_codex":0.000009091268,"about_ca_topic_score_gemma":0.000023953637,"teacher_disagreement_score":0.24093038,"about_ca_system_score_codex":0.000009431302,"about_ca_system_score_gemma":0.00017253078,"threshold_uncertainty_score":0.7597612},"labels":[],"label_agreement":null},{"id":"W6907947199","doi":"10.25545/6dgf1v/cueqbf","title":"3_DSLR.JPG","year":2024,"lang":"en","type":"dataset","venue":"UNB Dataverse","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 New Brunswick","funders":"","keywords":"Identification (biology); Natural (archaeology); Product (mathematics); Work (physics)","score_opus":0.005661468393171776,"score_gpt":0.2597627303322914,"score_spread":0.25410126193911964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6907947199","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000045325938,0.000104042905,0.000042548974,0.000034857287,0.0010141442,0.00015680694,0.9968374,0.000030559677,0.0017343195],"genre_scores_gemma":[0.000009467005,0.00057870033,0.00061351206,0.0006615753,0.0007738837,0.000011272388,0.9942415,0.000033029977,0.0030771052],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998716,0.00003577598,0.00029990944,0.00043052406,0.00022404747,0.00029374397],"domain_scores_gemma":[0.99820787,0.000011656354,0.0001316073,0.0015078585,0.00003884673,0.00010213582],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00019774197,0.00033244418,0.00021443609,0.000113980925,0.000058607566,0.00009341865,0.0007378801,0.00049468694,0.001624007],"category_scores_gemma":[0.0002410096,0.00030487645,0.00012427453,0.000101233134,0.00008930325,0.0000038660255,0.00090676756,0.0005390535,0.029544018],"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":[0.0000149321695,0.000021890597,0.0000052352707,0.0002352015,0.000098992365,0.000030217314,0.000006284666,0.000016148659,0.00012801438,0.000008616071,0.9991717,0.00026279615],"study_design_scores_gemma":[0.00016004579,0.000120708806,0.0000026246373,0.000060146533,0.00010915845,0.0000473478,0.00001881553,0.000073491705,0.00014232367,0.00001229691,0.9988989,0.00035410482],"about_ca_topic_score_codex":0.00006899343,"about_ca_topic_score_gemma":0.0001201119,"teacher_disagreement_score":0.027920011,"about_ca_system_score_codex":0.000020883055,"about_ca_system_score_gemma":0.0001386972,"threshold_uncertainty_score":0.99994034},"labels":[],"label_agreement":null},{"id":"W6908512496","doi":"10.26181/21980069","title":"Paramedic transition into an academic role in universities: A demographic and qualification survey of paramedic academics in Australia and New Zealand","year":2016,"lang":"en","type":"article","venue":"La Trobe University","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Normative; Survey instrument; Demographic profile; Professional development; Demographics; Postgraduate research; The Internet; Distance education","score_opus":0.017042799701512484,"score_gpt":0.27054355229690935,"score_spread":0.25350075259539684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6908512496","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9982083,0.000060910737,0.0013940801,0.00019603645,0.000010091515,0.0000814977,0.000020735068,0.000005817708,0.000022526196],"genre_scores_gemma":[0.99849725,0.0007527615,0.0004522146,0.000023942144,0.000008925624,1.5637778e-7,0.000070154885,0.000004298306,0.00019027243],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992332,0.00025170538,0.0001470992,0.00016887742,0.00007549225,0.00012361593],"domain_scores_gemma":[0.99961954,0.000069507616,0.00008878441,0.000109624634,0.000020510386,0.00009201648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045343756,0.0000886463,0.00012583332,0.00015237016,0.000022542483,0.0000032671908,0.00011520769,0.00030591074,0.000004110813],"category_scores_gemma":[0.00005149991,0.0000846719,0.000014588037,0.00016028495,0.00018580804,0.000028564658,0.000038099875,0.00019602198,3.1859437e-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":[0.0003765259,0.000028913882,0.96660525,0.00004254708,0.000018342917,0.000003049515,0.0042481623,0.000097475044,0.024689075,0.00042241075,0.000100481404,0.0033677896],"study_design_scores_gemma":[0.002156212,0.00019016146,0.99195695,0.000088499655,0.000018814226,0.000008663979,0.0019663332,0.0008801519,0.0005316952,0.0003349452,0.001697039,0.00017054939],"about_ca_topic_score_codex":0.004620718,"about_ca_topic_score_gemma":0.0021564062,"teacher_disagreement_score":0.025351707,"about_ca_system_score_codex":0.000030828145,"about_ca_system_score_gemma":0.00006459619,"threshold_uncertainty_score":0.6985174},"labels":[],"label_agreement":null},{"id":"W6912536821","doi":"10.5281/zenodo.4026261","title":"DeepTFactor: a deep learning-based tool for the prediction of transcription factors","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Genome; Transcription factor; Transcription (linguistics); Human genome; Genomics; ENCODE","score_opus":0.025676533657383576,"score_gpt":0.23101099834610797,"score_spread":0.2053344646887244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6912536821","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24546938,0.00015827903,0.7470709,0.001275135,0.00013785307,0.0012258069,0.0004796954,0.00039006685,0.0037929055],"genre_scores_gemma":[0.99607277,0.00003496382,0.0004359974,0.0001529116,0.0001110772,1.18320784e-7,0.0027814072,0.00033903224,0.00007173972],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990823,0.00014001713,0.00022460589,0.00019319866,0.00018766876,0.00017216876],"domain_scores_gemma":[0.99929744,0.00002473556,0.00012389007,0.00020818219,0.0002777473,0.0000679911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027093088,0.000105720996,0.00009209415,0.000040495786,0.0007457875,0.00011616392,0.00043785505,0.00007614927,0.0007021826],"category_scores_gemma":[0.0010846993,0.000088552806,0.00008648167,0.00015040411,0.00009301637,0.000012768845,0.0001404172,0.00017145966,0.000074916046],"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":[0.0013455291,0.0002655925,0.0010515038,0.0009014556,0.00037690945,9.0758203e-7,0.0078050727,0.05566786,0.7606573,0.00097617006,0.06362631,0.1073254],"study_design_scores_gemma":[0.00068781595,0.0010185314,0.0020555602,0.000008664147,0.000031127176,0.000003877037,0.00033862444,0.044144724,0.018510384,0.0000059640515,0.933086,0.000108748616],"about_ca_topic_score_codex":0.000002695213,"about_ca_topic_score_gemma":1.7276432e-7,"teacher_disagreement_score":0.8694597,"about_ca_system_score_codex":0.000019441268,"about_ca_system_score_gemma":0.0000041413095,"threshold_uncertainty_score":0.7688407},"labels":[],"label_agreement":null},{"id":"W6920769586","doi":"10.6084/m9.figshare.23590429.v1","title":"Additional file 2 of ExplaiNN: interpretable and transparent neural networks for genomics","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"BC Children's Hospital","funders":"","keywords":"Artificial neural network; Genomics; Feature (linguistics); File format; Pattern recognition (psychology)","score_opus":0.019771287049590722,"score_gpt":0.24915967458582586,"score_spread":0.22938838753623514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920769586","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001988491,0.00003412538,0.000068060814,0.000013983069,0.000016322543,0.00011753649,0.9990277,0.000014176812,0.0005092017],"genre_scores_gemma":[0.008999109,0.0000032409262,0.00083291496,0.00009209913,0.00009900233,0.00040743625,0.98907584,0.000012508599,0.00047784456],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996103,0.000008112725,0.00011945174,0.0000983662,0.00004087413,0.00012291376],"domain_scores_gemma":[0.9996011,0.00016503794,0.00006331094,0.00009873558,0.000039673254,0.000032144162],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00001581413,0.0000693583,0.000073801224,0.000019904599,0.000036622947,0.00001077846,0.00008699978,0.00006851734,0.6269666],"category_scores_gemma":[0.00061414094,0.00006933572,0.00004672098,0.000042437656,0.000007299238,0.0000028388502,0.00006442114,0.000047546833,0.00003587141],"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":[0.000013144273,0.0000034428958,0.0000022924514,0.0000794882,0.000011685511,2.2429414e-7,0.000021641645,0.0031982607,0.00007194235,7.7571605e-7,0.9947349,0.0018621888],"study_design_scores_gemma":[0.0000910596,0.00007785466,0.0002864406,0.00012289928,0.0000021195333,0.0000033531649,0.000017060958,0.21272406,0.00018907947,0.0000035222156,0.78641397,0.00006856964],"about_ca_topic_score_codex":2.6857222e-7,"about_ca_topic_score_gemma":0.0000027223336,"teacher_disagreement_score":0.6269307,"about_ca_system_score_codex":0.0000033455542,"about_ca_system_score_gemma":0.000018638888,"threshold_uncertainty_score":0.3733744},"labels":[],"label_agreement":null},{"id":"W6920828410","doi":"10.6084/m9.figshare.13468119","title":"Additional file 1 of Integrative approach for detecting membrane proteins","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Membrane protein; Protein–protein interaction; Protein methods; Protein detection","score_opus":0.021320783514906558,"score_gpt":0.24180710373682066,"score_spread":0.2204863202219141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920828410","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011293763,0.000007945105,0.00045503344,0.000019136787,0.0000025927186,0.00029436988,0.9920867,0.000013014868,0.0071098898],"genre_scores_gemma":[0.0020412186,9.685434e-8,0.051352553,0.00018708948,0.00014908334,0.00108973,0.9448987,0.00001237148,0.0002691402],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995688,0.00001408127,0.00012801973,0.00012459449,0.00006985662,0.00009461572],"domain_scores_gemma":[0.99950254,0.00012519276,0.00012801874,0.000090887064,0.00011137391,0.000041992473],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000012358646,0.00008714269,0.00009124957,0.000011111976,0.000038340793,0.000008572332,0.00012993481,0.00007572729,0.83651245],"category_scores_gemma":[0.009301605,0.000073767755,0.00007606242,0.000055266788,0.0000067330225,0.0000028783115,0.00007322597,0.000084650484,0.000067943874],"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":[0.000018526343,0.000008818792,2.5814302e-7,0.0002347774,0.000017563978,8.2933965e-8,0.00006615792,0.00009656699,0.0022442692,0.0000011304669,0.9964685,0.00084333384],"study_design_scores_gemma":[0.00013279366,0.00024179302,0.00001405638,0.00019470711,0.00000249353,0.0000026186688,0.00009951944,0.016862137,0.041834496,0.0000016980556,0.9405107,0.00010301123],"about_ca_topic_score_codex":3.1495927e-7,"about_ca_topic_score_gemma":7.0090476e-7,"teacher_disagreement_score":0.83644456,"about_ca_system_score_codex":0.0000034515356,"about_ca_system_score_gemma":0.000056514575,"threshold_uncertainty_score":0.99904346},"labels":[],"label_agreement":null},{"id":"W6925233830","doi":"10.18429/jacow-ipac2023-wepm132","title":"Conceptual design of a super bend dipole magnet as a high-field radiation source for the ILSF storage ring","year":2023,"lang":"en","type":"article","venue":"JACOW","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Light Source (Canada)","funders":"","keywords":"Storage ring; Magnet; Dipole; Conceptual design; Dipole magnet; Field (mathematics); Magnetic dipole; Thermal emittance","score_opus":0.012211588664712671,"score_gpt":0.2591849229717339,"score_spread":0.24697333430702123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6925233830","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7728661,0.00041744264,0.22450636,0.00074239424,0.00025312023,0.0005615495,0.000029128043,0.00004253517,0.0005813988],"genre_scores_gemma":[0.9940364,0.00006100188,0.00258184,0.00030205422,0.00020423501,0.000047538793,0.00008183245,0.000017983675,0.0026671614],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.999434,0.00004236937,0.00015380315,0.00011076655,0.00009893287,0.00016014828],"domain_scores_gemma":[0.9994482,0.0001895383,0.00007875507,0.00021938297,0.000036325946,0.00002784273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028453246,0.000084644176,0.000089033514,0.000027829888,0.00008252154,0.000016682292,0.00015799531,0.00009833315,0.000058508325],"category_scores_gemma":[0.00043546344,0.00006617355,0.000052415828,0.00007530663,0.000049296454,0.000003824457,0.000069326685,0.00007627634,0.000027138049],"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":[0.0006133015,0.00008909642,0.003083243,0.000213206,0.00035917346,0.0000028789425,0.00583579,0.12050336,0.67162156,0.005252943,0.13482438,0.057601076],"study_design_scores_gemma":[0.0027150435,0.0024559365,0.005134245,0.00003835002,0.00012891178,0.000013057026,0.002595437,0.19922775,0.38539878,0.00031347375,0.4014462,0.0005328305],"about_ca_topic_score_codex":0.000054878343,"about_ca_topic_score_gemma":0.00000420443,"teacher_disagreement_score":0.2862228,"about_ca_system_score_codex":0.000005976993,"about_ca_system_score_gemma":0.000036737038,"threshold_uncertainty_score":0.26984787},"labels":[],"label_agreement":null},{"id":"W6925934292","doi":"10.21227/nsjq-k919","title":"ExoNet Database: Wearable Camera Images of Human Locomotion Environments","year":2020,"lang":"en","type":"dataset","venue":"IEEE DataPort","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Wearable computer; Exoskeleton; Robotics; RGB color model; Drone; Wearable technology; Humanoid robot","score_opus":0.013267604843145736,"score_gpt":0.2763571578649286,"score_spread":0.26308955302178283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6925934292","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004454588,0.00012445962,0.00069396326,0.000023272303,0.00024516252,0.0002724992,0.9980103,0.0000094509915,0.00017543434],"genre_scores_gemma":[0.00044849145,0.0009333659,0.00083982025,0.00023105255,0.00035753127,0.000018349521,0.99665165,0.000033743472,0.0004859794],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982046,0.000071678354,0.00058729365,0.00048705275,0.0003790444,0.00027034778],"domain_scores_gemma":[0.9976884,0.00000815891,0.00059875817,0.0015630503,0.000022477465,0.00011912309],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025429306,0.0003536856,0.00038792656,0.00006871031,0.000082451006,0.000027787148,0.000803838,0.00032141368,0.00022393328],"category_scores_gemma":[0.0000817677,0.00036715713,0.000097096796,0.00006944422,0.00015870122,0.000012973537,0.0004791329,0.00043634427,0.0003550375],"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":[0.000017470245,0.000084744504,0.00007396892,0.00031674484,0.000096156255,0.000013633855,0.000004596882,0.000036073186,0.074100904,4.890894e-7,0.9251501,0.000105111634],"study_design_scores_gemma":[0.0002981625,0.0002568072,0.000102014536,0.0000731355,0.00009903832,0.000018522673,0.000009044758,0.000016452408,0.038401946,0.0000012935132,0.9603934,0.00033014617],"about_ca_topic_score_codex":0.0001943215,"about_ca_topic_score_gemma":0.000021471224,"teacher_disagreement_score":0.035698954,"about_ca_system_score_codex":0.000017494542,"about_ca_system_score_gemma":0.00007434772,"threshold_uncertainty_score":0.99987805},"labels":[],"label_agreement":null},{"id":"W6926283738","doi":"10.2307/1571493","title":"The Making of the Mosaic: A History of Canadian Immigration Policy","year":2000,"lang":"en","type":"article","venue":"The American Historical Review","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Liquation; Dysgeusia; Diafiltration; Emperipolesis; Triacetin; Demotion","score_opus":0.010427142302775446,"score_gpt":0.2600657872489586,"score_spread":0.24963864494618318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6926283738","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023748532,0.7630158,0.0002016484,0.076771796,0.0007518311,0.0016803625,0.000040820418,0.0000279147,0.1337613],"genre_scores_gemma":[0.5578752,0.37777126,0.00083448034,0.027332548,0.0004928981,0.00008219149,0.000031075877,0.000065193075,0.03551512],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990782,0.0001968318,0.00032425366,0.00008789938,0.0001565058,0.00015627372],"domain_scores_gemma":[0.9988696,0.000032271426,0.00037398492,0.00063969934,0.000051911204,0.000032548673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037474153,0.00009062258,0.00019619953,0.000031405307,0.00009355116,0.0000022078639,0.00051025517,0.000022803046,0.000042895354],"category_scores_gemma":[0.0004358501,0.000044846078,0.00014634004,0.00040279434,0.0002898622,0.0000017294041,0.000039934974,0.00012147199,0.000010132201],"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":[0.000028813685,0.000018790388,0.000411998,0.0002429468,0.000043545588,2.2134246e-7,0.0004253316,0.000040654042,0.0016767802,0.0007521871,0.6974931,0.29886568],"study_design_scores_gemma":[0.000024558633,0.00005336349,0.00047522885,0.00009329246,0.00002741865,0.0000058081905,0.000011504401,0.000046381043,0.000030401618,0.000010327468,0.9991682,0.000053474294],"about_ca_topic_score_codex":0.06358795,"about_ca_topic_score_gemma":0.005915689,"teacher_disagreement_score":0.5341267,"about_ca_system_score_codex":0.00048752013,"about_ca_system_score_gemma":0.00046737472,"threshold_uncertainty_score":0.9426477},"labels":[],"label_agreement":null},{"id":"W6926409621","doi":"10.22008/fk2/cs5lka/lnf4xv","title":"chrisz10.gsf","year":2022,"lang":"hu","type":"dataset","venue":"Geological Survey of Denmark and Greenland (GEUS)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Apotex Pharmachem (Canada)","funders":"","keywords":"Process (computing); Identification (biology); Product (mathematics)","score_opus":0.01715127517586906,"score_gpt":0.26141898794439467,"score_spread":0.2442677127685256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6926409621","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30568352,0.009238476,0.00033141885,0.0002656462,0.00089563476,0.00079780817,0.68119377,0.00002082434,0.0015729015],"genre_scores_gemma":[0.11541248,0.012094305,0.0004271102,0.0006287069,0.00029417206,0.00003900798,0.86912334,0.000044524608,0.00193635],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948721,0.0016577144,0.0011476427,0.0009488796,0.00059432624,0.00077934796],"domain_scores_gemma":[0.99690336,0.00056969014,0.0008752649,0.0011003604,0.00021593629,0.00033539638],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029798883,0.0007722556,0.0011853217,0.00014115218,0.00039806077,0.00006337043,0.0010406055,0.001203432,0.024683893],"category_scores_gemma":[0.0021240432,0.00063707045,0.00026558712,0.00030668068,0.0006807804,0.000008318626,0.0022090205,0.0012330533,0.000097645934],"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":[0.0011444397,0.00039901873,0.2954515,0.0006595855,0.000511192,0.000054073556,0.000043030515,0.0001957018,0.000108696644,0.000011147717,0.69449943,0.0069221505],"study_design_scores_gemma":[0.0010954957,0.0021204303,0.346558,0.000035379093,0.0001350449,0.000108425134,0.000028371958,0.00017216518,0.000033462013,0.000046013625,0.64889985,0.0007673402],"about_ca_topic_score_codex":0.0024564802,"about_ca_topic_score_gemma":0.0012546021,"teacher_disagreement_score":0.19027105,"about_ca_system_score_codex":0.000020485555,"about_ca_system_score_gemma":0.00016387996,"threshold_uncertainty_score":0.99960804},"labels":[],"label_agreement":null},{"id":"W6928942248","doi":"10.48448/mfka-vc24","title":"DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Text generation; Fluency; Generalization; Space (punctuation); Process (computing); Construct (python library); Language model; Dual (grammatical number)","score_opus":0.021991968296399923,"score_gpt":0.28268443320529113,"score_spread":0.2606924649088912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6928942248","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":[0.0127164135,0.0018833185,0.0608619,0.0013973394,0.0041872743,0.004561359,0.0010491973,0.0007268876,0.9126163],"genre_scores_gemma":[0.11037257,0.0003397854,0.23290342,0.0050866543,0.007083861,0.00055422104,0.009136017,0.0010371836,0.6334863],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981242,0.000048325775,0.00033653263,0.0005578635,0.00044933637,0.00048375083],"domain_scores_gemma":[0.99893486,0.00002446923,0.0002775823,0.0005312931,0.00011245423,0.00011936192],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00084445404,0.00029262438,0.0002785136,0.00024017318,0.00040639593,0.00012561298,0.00053718855,0.00024363217,0.0010481703],"category_scores_gemma":[0.00031540878,0.00028250192,0.000090625974,0.00027037127,0.00022981106,0.000009753868,0.00024273066,0.00022323562,0.000024212055],"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":[0.000057718175,0.00019180158,0.0002102569,0.00024000207,0.00024006284,0.0000062239715,0.0011308056,0.007099842,0.24225895,0.0020242431,0.7285412,0.017998917],"study_design_scores_gemma":[0.0009289955,0.00031974487,0.0000039367765,0.000010797959,0.000036527334,0.000019029067,0.00020081017,0.17244186,0.001586807,0.000016139338,0.8240933,0.00034208075],"about_ca_topic_score_codex":0.00002548805,"about_ca_topic_score_gemma":0.00010839777,"teacher_disagreement_score":0.27913,"about_ca_system_score_codex":0.00007264513,"about_ca_system_score_gemma":0.0007525442,"threshold_uncertainty_score":0.9999627},"labels":[],"label_agreement":null},{"id":"W6929035192","doi":"10.48448/fmh0-vp28","title":"Welcoming and Opening Session “The Intersectionality of Art in Inuit Nunangat”","year":2021,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Intersectionality; Session (web analytics); Race (biology); Representation (politics); Reflexivity; Context (archaeology)","score_opus":0.01079441191634832,"score_gpt":0.295259506761528,"score_spread":0.2844650948451797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929035192","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27519143,0.0036973224,0.015710307,0.0019024278,0.0023948585,0.0014370698,0.00012335145,0.000077175864,0.69946605],"genre_scores_gemma":[0.9003839,0.00020479801,0.018163653,0.00044760818,0.00028122737,0.000010253177,0.00013869963,0.000093577495,0.08027631],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991494,0.000048839614,0.00021686337,0.00023835043,0.00020135373,0.00014519315],"domain_scores_gemma":[0.999436,0.000018238692,0.00018907675,0.00027807872,0.000044053028,0.000034556735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006549495,0.00011495251,0.00014067948,0.00012831968,0.000063841035,0.00003517717,0.00029726565,0.00012177995,0.0002001289],"category_scores_gemma":[0.00025822595,0.00008658729,0.000024315113,0.00022593116,0.00045459074,0.0000040157433,0.00043486664,0.00019906767,0.0000021293636],"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":[0.00014258469,0.0004937939,0.083789095,0.0023194447,0.00029126345,0.0000366306,0.006148723,0.0024537807,0.5835847,0.005879542,0.16543612,0.14942428],"study_design_scores_gemma":[0.0018393814,0.0004821036,0.014836404,0.003054928,0.00005845056,0.0002779579,0.003820779,0.035554692,0.03253253,0.0005324424,0.9056005,0.0014098465],"about_ca_topic_score_codex":0.00014598298,"about_ca_topic_score_gemma":0.0013402529,"teacher_disagreement_score":0.74016434,"about_ca_system_score_codex":0.000024460174,"about_ca_system_score_gemma":0.00024115366,"threshold_uncertainty_score":0.35309273},"labels":[],"label_agreement":null},{"id":"W6929050356","doi":"10.48550/arxiv.0709.3754","title":"Numerical simulations of type III planetary migration: II. Inward migration of massive planets","year":2007,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"The Scarborough Hospital","funders":"","keywords":"Planet; Planetary migration; Eccentricity (behavior); Type (biology); RADIUS; Limit (mathematics); Boundary (topology)","score_opus":0.01190979729330824,"score_gpt":0.2763329359026132,"score_spread":0.26442313860930494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929050356","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9725381,0.00030960597,0.020069458,0.00026206183,0.00034965106,0.0004277548,0.00020903358,0.000025286174,0.0058090417],"genre_scores_gemma":[0.9761136,0.00010632428,0.012932848,0.00012222401,0.00015766929,0.0000028008687,0.010020807,0.000016266602,0.0005274686],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868864,0.00004761041,0.0006453364,0.00023115623,0.00023928042,0.0001480001],"domain_scores_gemma":[0.9986841,0.000041658484,0.00051533885,0.00046820473,0.00023500755,0.000055687546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014082331,0.00021735152,0.00030405167,0.00010984017,0.00004442453,0.000008582784,0.00022347395,0.00050830405,0.00018191441],"category_scores_gemma":[0.00011827973,0.00020350046,0.00009560401,0.000092991235,0.000070694245,0.0000032676005,0.00025615894,0.00027924703,0.0000048157544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048037554,0.00023255982,0.03275142,0.0006120509,0.00043151662,0.000002797753,0.0009238576,0.92149174,0.022848297,0.0002820595,0.018668156,0.0012751853],"study_design_scores_gemma":[0.0016829267,0.0023052061,0.022525385,0.00028301013,0.00030945387,0.00003246118,0.00026686257,0.73502505,0.14275105,0.00035833093,0.093095176,0.0013651047],"about_ca_topic_score_codex":0.00049466104,"about_ca_topic_score_gemma":0.00028678268,"teacher_disagreement_score":0.1864667,"about_ca_system_score_codex":0.000011967597,"about_ca_system_score_gemma":0.00014830714,"threshold_uncertainty_score":0.82985073},"labels":[],"label_agreement":null},{"id":"W6929112566","doi":"10.4224/8895063","title":"The design of a podded propeller base model geometry and predictions of its hydrodynamics","year":2006,"lang":"en","type":"report","venue":"NPARC","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Research Council Canada; Memorial University of Newfoundland","keywords":"Propeller; Base (topology); Software; 3d model; Variation (astronomy)","score_opus":0.017112661576657355,"score_gpt":0.2578484346851528,"score_spread":0.24073577310849542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929112566","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08439323,0.0054278295,0.5392553,0.00026246175,0.0006620819,0.0028150433,0.0012808568,0.000060542,0.3658426],"genre_scores_gemma":[0.92293197,0.012187169,0.033014484,0.000030127294,0.00027483926,0.000066935056,0.00085343624,0.000104935534,0.03053608],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874246,0.00005649293,0.000493444,0.00018571211,0.0003540253,0.00016786502],"domain_scores_gemma":[0.9986047,0.000040114355,0.00049258175,0.00046089906,0.00036094515,0.000040719362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006148439,0.00018568714,0.00024925038,0.00007226343,0.00007506605,0.000011934958,0.00021255575,0.00032595603,0.000007889182],"category_scores_gemma":[0.0004884461,0.00013390504,0.000089181325,0.00008481536,0.00015032834,0.0000022944178,0.00017094161,0.00023489268,6.354895e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028332495,0.00035410174,0.0012390397,0.0033258784,0.0009088996,0.0000040051277,0.00015730233,0.581394,0.26769093,0.00040278092,0.1331946,0.011045159],"study_design_scores_gemma":[0.00029603526,0.0002641557,0.00019787268,0.00010476499,0.0001422578,0.000041572166,0.000011125642,0.97724265,0.005603012,0.00020307,0.015667295,0.00022617402],"about_ca_topic_score_codex":0.000012589482,"about_ca_topic_score_gemma":0.0000074551344,"teacher_disagreement_score":0.83853877,"about_ca_system_score_codex":0.000019115003,"about_ca_system_score_gemma":0.0005366283,"threshold_uncertainty_score":0.5460489},"labels":[],"label_agreement":null},{"id":"W6929329809","doi":"10.4224/20329062","title":"User's Guide: NBC 2005: Application and Intent Statements","year":2005,"lang":"en","type":"standard","venue":"NPARC","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Audit; Set (abstract data type); Subject (documents); Work (physics)","score_opus":0.006545324567407902,"score_gpt":0.30834966194465074,"score_spread":0.3018043373772428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929329809","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":[0.01668455,0.0065039187,0.17320587,0.00568561,0.0027400183,0.0042933268,0.0036935525,0.00026142524,0.78693175],"genre_scores_gemma":[0.05268613,0.049114242,0.18587871,0.008371307,0.009147003,0.000763577,0.0431126,0.00064155046,0.6502849],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986931,0.0000369918,0.0003992862,0.00033009626,0.0002565105,0.00028401686],"domain_scores_gemma":[0.9990381,0.000008612495,0.0002562762,0.0004807803,0.0001111845,0.000105033214],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002886167,0.0002583312,0.00022075318,0.0000594924,0.0000759705,0.000049602808,0.00025032376,0.00033741203,0.00020254443],"category_scores_gemma":[0.00009600726,0.00024645167,0.000063859094,0.000034603203,0.00007911753,0.0000046156283,0.0002653801,0.0002718595,0.000043355092],"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":[0.000040478244,0.000028236054,0.00026801837,0.00018735252,0.00011648581,8.9014316e-7,0.000051567444,0.00003801323,0.012520786,0.0001776707,0.93425995,0.052310552],"study_design_scores_gemma":[0.0003868467,0.000109398716,0.000080764876,0.00003922231,0.000034566296,0.000009370477,0.000025987378,0.00050234084,0.0015332046,0.0000920145,0.9969273,0.00025897296],"about_ca_topic_score_codex":0.0000140355505,"about_ca_topic_score_gemma":0.000061942395,"teacher_disagreement_score":0.13664685,"about_ca_system_score_codex":0.000055091023,"about_ca_system_score_gemma":0.00011215108,"threshold_uncertainty_score":0.99999875},"labels":[],"label_agreement":null},{"id":"W6929647291","doi":"10.5061/dryad.q2bvq83n0","title":"The environmental drivers of tree cover and forest-savanna mosaics in Southeast Asia","year":2022,"lang":"en","type":"dataset","venue":"DRYAD","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Vegetation (pathology); Fire regime; Fragmentation (computing); Threatened species; Distribution (mathematics); Fire ecology; Precipitation; Tree (set theory); Disturbance (geology)","score_opus":0.003260524693815899,"score_gpt":0.20979905720245795,"score_spread":0.20653853250864204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929647291","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016620634,0.00061902,0.000010352382,0.000059434537,0.00014923417,0.00023532975,0.9817398,0.0000028694717,0.000563284],"genre_scores_gemma":[0.00947829,0.0012747642,0.00006404175,0.00006263693,0.00005045603,0.000018178258,0.98855555,0.000017209682,0.00047888717],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991589,0.00006573492,0.00024209164,0.00017588257,0.00018665378,0.00017070766],"domain_scores_gemma":[0.99930316,0.000026868938,0.00019411033,0.00043528143,0.0000043923087,0.00003616989],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018488603,0.00016794422,0.00015485566,0.000039021954,0.00008681638,0.00001566983,0.00031736432,0.00017083886,0.00034540836],"category_scores_gemma":[0.00006031242,0.0001380131,0.000059332768,0.000034064855,0.00017583376,0.0000019708953,0.00042601,0.00030249608,0.000010723352],"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":[0.00006409739,0.00003644646,0.0028370037,0.000050375682,0.000047110643,0.00000357491,0.000049513226,0.00023857334,0.000283226,0.0000134643005,0.9955523,0.0008243292],"study_design_scores_gemma":[0.00033259267,0.00018041547,0.0018911132,0.0000068575955,0.000021456102,0.000008451444,0.00032024964,0.00017147914,0.00007312825,0.000008043051,0.9968424,0.000143823],"about_ca_topic_score_codex":0.000043614036,"about_ca_topic_score_gemma":0.00015698686,"teacher_disagreement_score":0.007142344,"about_ca_system_score_codex":0.000019610909,"about_ca_system_score_gemma":0.00003747661,"threshold_uncertainty_score":0.56280106},"labels":[],"label_agreement":null},{"id":"W6929720774","doi":"10.5066/p9cwyqgu","title":"Alaska Science Center Data Sheets from Intracoelomic Transmitter Implant and Liver Biopsy Surgeries in Birds, 1993-2012","year":2022,"lang":"en","type":"dataset","venue":"USGS DOI Tool Production Environment","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Implant; Tracking (education); Data quality; Center (category theory); Field (mathematics); Patient data; Needle biopsy","score_opus":0.009640688032212437,"score_gpt":0.22760471525127415,"score_spread":0.21796402721906172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929720774","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20989166,0.0009587388,0.00007621553,0.0005600877,0.0019207892,0.00060486153,0.78596234,0.000016233782,0.000009085521],"genre_scores_gemma":[0.008353341,0.0053854412,0.0008914359,0.0002576694,0.00044494687,0.00005364346,0.9843702,0.000034021446,0.00020931156],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974143,0.0001160295,0.00048576397,0.0011378248,0.0004514179,0.00039469494],"domain_scores_gemma":[0.99795413,0.00001536199,0.00024277467,0.0016968064,0.000008352795,0.00008256234],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007647974,0.0003676839,0.0002774025,0.000182839,0.00019535243,0.00008675999,0.0007486121,0.0001935143,0.004119796],"category_scores_gemma":[0.00008512443,0.0003572603,0.000043153574,0.000097699754,0.00047192877,0.000056625777,0.0012626582,0.00050858036,0.000045574096],"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":[0.00009531252,0.00019331295,0.0014324929,0.000101269354,0.000058749978,0.000015013551,0.00012576662,0.00027208263,0.012060581,4.2304552e-7,0.9826523,0.0029926812],"study_design_scores_gemma":[0.00028259165,0.00008039085,0.005193575,0.000020467805,0.00004357657,0.00016073647,0.00004989012,0.000079162346,0.0016521564,0.0000022566724,0.9920073,0.00042786926],"about_ca_topic_score_codex":0.00024072046,"about_ca_topic_score_gemma":0.00003156835,"teacher_disagreement_score":0.20153831,"about_ca_system_score_codex":0.00010172198,"about_ca_system_score_gemma":0.000077820994,"threshold_uncertainty_score":0.99988794},"labels":[],"label_agreement":null},{"id":"W6929732211","doi":"10.5281/zenodo.11734337","title":"Hoodoo pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Folklore; Syncretism (linguistics); Subject (documents); Power (physics); Key (lock); Spirituality","score_opus":0.012633695485659534,"score_gpt":0.2441904511397656,"score_spread":0.23155675565410605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929732211","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":[0.000034549787,0.00058582163,0.0016197882,0.00017804894,0.00021758935,0.0002684407,0.00024322659,0.0005232009,0.9963293],"genre_scores_gemma":[0.0012840121,0.00032226485,0.00073564466,0.00019980624,0.0007597483,3.5222655e-8,0.007139681,0.009157108,0.9804017],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987776,0.00012753802,0.00018953074,0.00039095694,0.00023581088,0.00027851117],"domain_scores_gemma":[0.9990605,0.0000022988058,0.000116531184,0.0005973681,0.000107741835,0.00011555258],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00028274232,0.00020730429,0.00014417496,0.00020770924,0.00029421507,0.00042010905,0.00081693596,0.00024401836,0.061823837],"category_scores_gemma":[0.00030918806,0.00021304659,0.00007894364,0.00018399075,0.000112185844,0.0000035627797,0.0012861756,0.0003394299,0.14092721],"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":[0.000009875801,0.000023359837,3.1742715e-7,0.0002076055,0.00008644388,0.000005204873,0.00007030344,0.0000051679067,0.00123432,0.00042161025,0.98736686,0.010568943],"study_design_scores_gemma":[0.0001664389,0.00017088489,0.0000052845226,0.0000801719,0.000022594068,0.000085655935,0.000038190676,0.00006221811,0.00019957095,0.000034547218,0.99890083,0.00023362812],"about_ca_topic_score_codex":0.000008576819,"about_ca_topic_score_gemma":5.0975484e-7,"teacher_disagreement_score":0.07910337,"about_ca_system_score_codex":0.000030145666,"about_ca_system_score_gemma":0.000004020626,"threshold_uncertainty_score":0.9390338},"labels":[],"label_agreement":null},{"id":"W6929790288","doi":"10.5061/dryad.7qs70","title":"Data from:Physiological effects of increased foraging effort in a small passerine","year":2017,"lang":"en","type":"dataset","venue":"Data Archiving and Networked Services (DANS)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Foraging; Passerine; Homeothermy; Zebra finch; Thermoregulation; Gizzard; Body weight","score_opus":0.020701728388104326,"score_gpt":0.29020276815444995,"score_spread":0.26950103976634565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929790288","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27140066,0.00058352185,0.00018367718,0.000009734948,0.00016409982,0.00027235513,0.7273342,0.000013263555,0.000038471568],"genre_scores_gemma":[0.027924683,0.0018134573,0.0019564922,0.00014821795,0.00046900788,0.000014794614,0.9676332,0.000030314879,0.000009840513],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99764913,0.00021892121,0.00055658544,0.00097039074,0.00016498133,0.00043997765],"domain_scores_gemma":[0.9936244,0.00021926752,0.0006325328,0.0053699245,0.00002081131,0.0001330784],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00065003097,0.000471171,0.00068581634,0.00008414433,0.00015540072,0.00010032837,0.0052168043,0.00033583815,0.0000058408673],"category_scores_gemma":[0.00021223282,0.0003997968,0.000050267845,0.00006633847,0.00015822558,0.000028236878,0.008963571,0.00058373436,0.0000061519104],"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":[0.00080164976,0.00044740096,0.047020566,0.010701979,0.0008832875,0.00013964137,0.00019415666,0.0005374966,0.010589062,0.0000025224085,0.92352533,0.0051569007],"study_design_scores_gemma":[0.0019305907,0.00042116275,0.13387175,0.0032662957,0.00041042294,0.000026873318,0.0000591711,0.1406039,0.00019060822,0.000082000144,0.71795315,0.0011840876],"about_ca_topic_score_codex":0.0052446756,"about_ca_topic_score_gemma":0.016143143,"teacher_disagreement_score":0.24347596,"about_ca_system_score_codex":0.0000071110967,"about_ca_system_score_gemma":0.00006604674,"threshold_uncertainty_score":0.9998454},"labels":[],"label_agreement":null},{"id":"W6929990955","doi":"10.5281/zenodo.11625998","title":"+27640409447'',,./[][)* THE 3 IN 1 SSD CHEMICAL SOLUTIONS AND ACTIVATION POWDER FOR CLEANING OF BLACK NOTES","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Chemical industry; Chemical products; Chemical laboratory; Chemical safety; Organic chemicals; Euros","score_opus":0.023654188389071348,"score_gpt":0.26119301825140945,"score_spread":0.2375388298623381,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929990955","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01206734,0.0012124624,0.023599986,0.0029465451,0.0002554484,0.002716891,0.0010413545,0.0005610731,0.9555989],"genre_scores_gemma":[0.8425811,0.0010591331,0.005445894,0.000577317,0.0015194097,0.0000011726694,0.012925969,0.014512463,0.121377565],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991272,0.00008280398,0.00020515449,0.0002497021,0.00013421311,0.00020094145],"domain_scores_gemma":[0.99941057,0.000020501162,0.000131754,0.00029030556,0.00010694601,0.00003989489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039777966,0.0001330356,0.00012566119,0.00014304544,0.00018062447,0.00012785241,0.00036161023,0.0001678161,0.0007268764],"category_scores_gemma":[0.00080053246,0.00011633371,0.000045637917,0.000159791,0.00020331635,0.0000058603105,0.0006676918,0.00023020917,0.00023511186],"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":[0.000065017615,0.000058405607,0.000004143028,0.0006625301,0.00011328523,5.359233e-7,0.0008580199,0.00006814008,0.05116771,0.00311668,0.92788726,0.015998257],"study_design_scores_gemma":[0.00026501497,0.00010689179,0.000030561816,0.00013064012,0.00001882618,0.000011493007,0.0001604587,0.00090903364,0.0025364642,0.00010942406,0.9955875,0.0001336684],"about_ca_topic_score_codex":0.000016822698,"about_ca_topic_score_gemma":0.0000013604267,"teacher_disagreement_score":0.83422136,"about_ca_system_score_codex":0.000024846066,"about_ca_system_score_gemma":0.000004970164,"threshold_uncertainty_score":0.79587865},"labels":[],"label_agreement":null},{"id":"W6930026354","doi":"10.5281/zenodo.10094805","title":"FIGURE 161 in Revision of the metallic species of Lasioglossum (Dialictus) in Canada (Hymenoptera, Halictidae, Halictini) 2591","year":2010,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Metal; Scale (ratio); Proterozoic; Dorsum","score_opus":0.011507581337532394,"score_gpt":0.2215658761530058,"score_spread":0.2100582948154734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930026354","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0483055,0.0004573663,0.000074674346,0.0002882049,0.00027484776,0.0008119421,0.0005385541,0.000050728948,0.9491982],"genre_scores_gemma":[0.764139,0.001250856,0.00087518984,0.0003197988,0.00041384104,1.7404179e-7,0.0042540343,0.0048515494,0.22389558],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99844533,0.00027572035,0.0004299052,0.00026386915,0.00034773408,0.00023742182],"domain_scores_gemma":[0.9986769,0.000013482511,0.0003993688,0.00071237254,0.00014116493,0.00005668562],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038990003,0.00018788764,0.00027382193,0.00019785456,0.00012575384,0.00005055687,0.0010625747,0.00020062148,0.008600958],"category_scores_gemma":[0.0007915486,0.00016101656,0.000063311796,0.00035207928,0.00013658273,0.000005945248,0.0009053653,0.0004462899,0.000083107225],"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":[0.000079167,0.00014008602,0.00083426293,0.0007074919,0.000113594244,0.0000061331198,0.00058613525,0.00015710421,0.032548327,0.00094051915,0.9482217,0.015665485],"study_design_scores_gemma":[0.00031581317,0.00007290698,0.0014641839,0.00020241764,0.000009801075,0.000008505632,0.000086341344,0.00004827244,0.0038255805,0.0000039624074,0.9938179,0.0001442635],"about_ca_topic_score_codex":0.046095375,"about_ca_topic_score_gemma":0.02559475,"teacher_disagreement_score":0.7253026,"about_ca_system_score_codex":0.000078771845,"about_ca_system_score_gemma":0.000044941156,"threshold_uncertainty_score":0.99230534},"labels":[],"label_agreement":null},{"id":"W6930094572","doi":"10.5281/zenodo.11649609","title":"Pay After Job Is Done +27789734524 Love Spell Caster - Traditional Healers – Powerful Sangoma in Koffiefontein, Koppies, Kroonstad, Ladybrand, FreeState, Parys, Phuthaditjhaba, Reitz, Sasolburg, Senekal, Springfontein, Thaba'Nchu, Theunissen, Viljoenskroon, Virginia, Vrede, Vredefort, Wesselsbron, Winburg","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Spell; Champion; Happiness; Reading (process); Miracle; Face (sociological concept); Ridiculous; Economic shortage; Government (linguistics)","score_opus":0.014249530195798481,"score_gpt":0.22884343261203485,"score_spread":0.21459390241623638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930094572","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":[0.0047639147,0.0048861713,0.0007789985,0.0018077757,0.00081838097,0.0014997972,0.0048634266,0.0004679135,0.9801136],"genre_scores_gemma":[0.040353224,0.005646699,0.0015268482,0.002635548,0.002316475,5.999218e-7,0.015504654,0.013034622,0.9189813],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954112,0.00044833162,0.00094687333,0.001317635,0.0008402917,0.0010356802],"domain_scores_gemma":[0.9973447,0.00002761233,0.0004550715,0.0014468012,0.0003042506,0.0004215656],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007967977,0.00086789223,0.00067210733,0.00080040056,0.00022543003,0.000779068,0.0013896169,0.0006836971,0.050809093],"category_scores_gemma":[0.00023848246,0.0008112107,0.00030484571,0.00062200916,0.00050418125,0.000057523524,0.001292914,0.0012844556,0.027790997],"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":[0.00039646556,0.00019877747,0.00006375342,0.0005461287,0.00040150774,0.00024850163,0.0009873082,0.000037055677,0.0020168144,0.0001152481,0.9933054,0.0016830381],"study_design_scores_gemma":[0.0012226984,0.00064622826,0.00030141172,0.0005981263,0.00008928297,0.00055304443,0.0004154434,0.00014961581,0.000460575,0.000070864175,0.9945484,0.0009443507],"about_ca_topic_score_codex":0.00028735492,"about_ca_topic_score_gemma":0.00014886323,"teacher_disagreement_score":0.061132293,"about_ca_system_score_codex":0.00020019973,"about_ca_system_score_gemma":0.00004934053,"threshold_uncertainty_score":0.9994339},"labels":[],"label_agreement":null},{"id":"W6930160664","doi":"10.5281/zenodo.10511585","title":"ANDROID-BASED CONTEXTUALIZED ELECTRONIC STRATEGIC INTERVENTION MATERIALS (ACE-SIMS) ON THE SELECTED TOPICS IN EARTH SCIENCE","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Intervention (counseling); Electronic learning; Quarter (Canadian coin); Earth (classical element); Earth observation satellite","score_opus":0.025617613742631096,"score_gpt":0.2718970307217436,"score_spread":0.2462794169791125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930160664","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98886794,0.000012925889,0.00043851064,0.0007320698,0.000057020367,0.0003623263,0.000037513768,0.00017920886,0.009312482],"genre_scores_gemma":[0.9977588,0.000028581528,0.00003684521,0.00014124093,0.000051667677,1.5353798e-7,0.0011013515,0.00019363515,0.0006877003],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99862057,0.00032304783,0.0002154758,0.00024352162,0.00024303238,0.0003543271],"domain_scores_gemma":[0.9992623,0.000014136069,0.000090567846,0.0003319189,0.00025155387,0.0000495771],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013798306,0.00010087389,0.00008668638,0.00018143351,0.00069163,0.00039494707,0.00066209276,0.000053638374,0.0012620369],"category_scores_gemma":[0.00092773605,0.000085147876,0.000027829708,0.0008572998,0.00016672382,0.000012937945,0.00035530812,0.00018265887,0.0009076581],"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":[0.0003821095,0.00016951124,0.000032533768,0.00010120281,0.00003760278,0.000006063152,0.0005068899,0.0014955496,0.95432734,0.018765315,0.014973811,0.009202038],"study_design_scores_gemma":[0.0024107567,0.0019523671,0.003991946,0.00010060482,0.00001206283,0.000036222096,0.0006140385,0.01425113,0.2536303,0.00040707085,0.7221703,0.00042318183],"about_ca_topic_score_codex":0.000009043761,"about_ca_topic_score_gemma":0.0000025130087,"teacher_disagreement_score":0.70719653,"about_ca_system_score_codex":0.000053094198,"about_ca_system_score_gemma":0.000018105933,"threshold_uncertainty_score":0.99987024},"labels":[],"label_agreement":null},{"id":"W6930224333","doi":"10.5281/zenodo.11650036","title":"Pay After Job Is Done +27789734524 Love Spell Caster - Traditional Healers – Powerful Sangoma in Tshaneni, Abercorn, Mliba, Madlangampisi, Luyengo, Lomati Store, Lomati, Kobolondo, Heights, Horo, Ngonini, Herefords, Nkanni, Nomahasha, Piggs Peak, Lesotho, Maseru, Teyateyaneng, Berea, Mafeteng, Hlotse, Leribe, Mohale's Hoek","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Spell; Champion; Happiness; Reading (process); Miracle; Face (sociological concept); Ridiculous; Economic shortage; Government (linguistics); Notice; Apprenticeship","score_opus":0.01718179072595172,"score_gpt":0.23412605191185634,"score_spread":0.21694426118590462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930224333","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":[0.018718012,0.0051559834,0.00053797505,0.0013463886,0.00071594445,0.0020328672,0.006430112,0.0005802419,0.9644825],"genre_scores_gemma":[0.025525603,0.0018443685,0.002638764,0.0014559394,0.0018560415,0.0000012062158,0.024341743,0.010571089,0.93176526],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949676,0.00051428966,0.0010625067,0.0014196247,0.00091042847,0.0011255572],"domain_scores_gemma":[0.9971422,0.00002863049,0.00052274845,0.00152435,0.00029556337,0.00048649134],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00071042735,0.0010014226,0.0007907113,0.0008457296,0.00022861148,0.0008554542,0.0015624494,0.00086523785,0.059981905],"category_scores_gemma":[0.00017857882,0.0009254647,0.0003295494,0.0006585054,0.00048189017,0.00007008552,0.0013389861,0.001368622,0.032624263],"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":[0.00023914583,0.0002622083,0.00014239966,0.0010011583,0.00034282362,0.00022064017,0.0010604302,0.000032179974,0.0010137171,0.000148005,0.9935563,0.0019809958],"study_design_scores_gemma":[0.0013290949,0.0007184062,0.0017409769,0.00057634845,0.00008507955,0.0006683811,0.00026582478,0.00020736024,0.0003456011,0.00008318034,0.992879,0.0011007808],"about_ca_topic_score_codex":0.00024636663,"about_ca_topic_score_gemma":0.0000626399,"teacher_disagreement_score":0.03271723,"about_ca_system_score_codex":0.0003007106,"about_ca_system_score_gemma":0.000047769707,"threshold_uncertainty_score":0.9993196},"labels":[],"label_agreement":null},{"id":"W6930290649","doi":"10.5281/zenodo.11700566","title":"Steven pinker der sprachinstinkt pdf","year":2024,"lang":"de","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Circumstantial evidence; Gloom; Subject (documents); Staring; Ridiculous","score_opus":0.01480209502436162,"score_gpt":0.2493258613217246,"score_spread":0.234523766297363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930290649","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":[0.00036335702,0.002581833,0.0042966856,0.0007677166,0.0007563068,0.0007842451,0.00057554495,0.0004691578,0.98940516],"genre_scores_gemma":[0.01669766,0.0014167908,0.0023489483,0.0008015504,0.002895277,1.669165e-7,0.022419462,0.015010526,0.9384096],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966758,0.00053618156,0.0006043549,0.000918541,0.00056176883,0.00070338877],"domain_scores_gemma":[0.9977129,0.000012605172,0.0003638235,0.0011862136,0.00040767892,0.00031678975],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00091865985,0.00053591013,0.0003673573,0.00037227853,0.0011219264,0.0013738269,0.0017153797,0.0005893906,0.14939953],"category_scores_gemma":[0.0010809442,0.0005584936,0.00021200605,0.00042326315,0.0003326502,0.000018579167,0.0024176415,0.0011110521,0.43644193],"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":[0.00006199573,0.000117933014,0.0000026202163,0.0007179667,0.0005087799,0.000029837658,0.0004760337,0.000059430906,0.0031671275,0.00080983585,0.96173453,0.032313883],"study_design_scores_gemma":[0.00048315743,0.00045103524,0.000030405294,0.00025296462,0.00015206118,0.00022323671,0.0001268559,0.00052255625,0.00031660098,0.00006389768,0.9967756,0.0006016295],"about_ca_topic_score_codex":0.00001273329,"about_ca_topic_score_gemma":9.606571e-7,"teacher_disagreement_score":0.28704238,"about_ca_system_score_codex":0.0001263762,"about_ca_system_score_gemma":0.000018107748,"threshold_uncertainty_score":0.99968666},"labels":[],"label_agreement":null},{"id":"W6930344010","doi":"10.5281/zenodo.11759309","title":"marketing strategy of adidas pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nike; Core (optical fiber); Strategic management; Plan (archaeology); Marketing strategy; Strategic planning; Brand strategy; Management strategy","score_opus":0.013890453655071756,"score_gpt":0.2495882560685853,"score_spread":0.23569780241351357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930344010","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":[0.00018601329,0.00080786,0.000412275,0.000048716905,0.000100800054,0.00022967582,0.00023144459,0.00021870703,0.9977645],"genre_scores_gemma":[0.008834779,0.0006425415,0.0009312926,0.00006282309,0.000531066,4.0709534e-8,0.005470202,0.007986971,0.9755403],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987819,0.00021631601,0.00024611174,0.0003085354,0.00022027716,0.00022685171],"domain_scores_gemma":[0.9991112,0.000005450927,0.00019113121,0.00047134465,0.000140251,0.00008062124],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005576509,0.000174516,0.00015923964,0.00019666726,0.00017434018,0.00019356431,0.00066094345,0.00020570027,0.04403428],"category_scores_gemma":[0.0005010152,0.00018087128,0.00007320791,0.00017835136,0.00012410004,0.000003432533,0.0009036706,0.00027100698,0.01643297],"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":[0.000026885382,0.000024544446,6.801461e-7,0.00054215203,0.00009714739,0.0000032415383,0.00005412347,0.000012681438,0.0036364712,0.00020072843,0.9632143,0.032187082],"study_design_scores_gemma":[0.00015055273,0.00013102783,0.000025782329,0.00015803141,0.00002200309,0.00004625279,0.000064468906,0.00008200434,0.00036483744,0.000016083739,0.998765,0.00017398174],"about_ca_topic_score_codex":0.0000105520085,"about_ca_topic_score_gemma":5.4434145e-7,"teacher_disagreement_score":0.03555071,"about_ca_system_score_codex":0.000020125495,"about_ca_system_score_gemma":0.0000055460264,"threshold_uncertainty_score":0.98433286},"labels":[],"label_agreement":null},{"id":"W6930483775","doi":"10.5281/zenodo.12140701","title":"Iso 22745 pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Automation; Terminology; Scope (computer science); Identification (biology); Data exchange; Open architecture; XML; Task (project management); Information system","score_opus":0.012735683694753606,"score_gpt":0.24663884663119484,"score_spread":0.23390316293644123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930483775","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":[0.00003694137,0.0006185106,0.0018098202,0.0001974684,0.00022752515,0.00028104914,0.00025008497,0.0005277766,0.99605083],"genre_scores_gemma":[0.0011361593,0.00035027092,0.0007633224,0.00022430519,0.0007733866,4.328248e-8,0.006975955,0.008817544,0.980959],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99870634,0.00013679077,0.00020495852,0.00041074888,0.00024636462,0.00029479046],"domain_scores_gemma":[0.9990091,0.0000026504933,0.0001241745,0.00062678015,0.000117656935,0.000119641205],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00030117473,0.0002188519,0.00015240081,0.00021876887,0.00032643584,0.0004375298,0.00085479085,0.00026257575,0.06979248],"category_scores_gemma":[0.00032268907,0.00022481414,0.000083079,0.00019563027,0.00012615554,0.000004004225,0.0013418042,0.00036593885,0.13676852],"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":[0.000011309926,0.00002501984,3.569211e-7,0.00022248426,0.00008835192,0.0000055498267,0.000079735946,0.000006036114,0.0014090344,0.00046908084,0.98718566,0.010497356],"study_design_scores_gemma":[0.00017382187,0.00017545637,0.000004859168,0.00008304794,0.000023237832,0.00008600107,0.00004078438,0.00008648628,0.00020509344,0.000036708243,0.9988391,0.00024544066],"about_ca_topic_score_codex":0.000010835289,"about_ca_topic_score_gemma":6.516665e-7,"teacher_disagreement_score":0.06697605,"about_ca_system_score_codex":0.00003413559,"about_ca_system_score_gemma":0.000004581324,"threshold_uncertainty_score":0.9310579},"labels":[],"label_agreement":null},{"id":"W6930523793","doi":"10.5281/zenodo.12095896","title":"Aho heft 19 pdf download","year":2024,"lang":"de","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; Point (geometry); Stuttgart","score_opus":0.013527917503333719,"score_gpt":0.2471743401337761,"score_spread":0.23364642263044239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930523793","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":[0.00022519834,0.003265325,0.0021359448,0.00087142043,0.00073753967,0.0007637588,0.0012590222,0.0006000619,0.99014175],"genre_scores_gemma":[0.010868495,0.0039534243,0.0012925338,0.0011317683,0.0027822198,1.9764119e-7,0.049546752,0.013337204,0.9170874],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996732,0.00048075293,0.0005736931,0.0009387233,0.0005523427,0.00072251103],"domain_scores_gemma":[0.9976353,0.0000125263305,0.0003287926,0.0012417284,0.00038093128,0.00040071504],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00084352127,0.0005322422,0.00037080926,0.00040735066,0.0011294169,0.0014094893,0.0018230082,0.0005893081,0.1688533],"category_scores_gemma":[0.0011244847,0.0005574681,0.00022438973,0.00047034494,0.000367337,0.000014123072,0.003168047,0.0009991549,0.50608605],"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":[0.00006153496,0.000097484146,0.0000015995998,0.0007850633,0.0003608193,0.000028454935,0.00044344238,0.000049274695,0.003250762,0.0006119156,0.96963453,0.024675125],"study_design_scores_gemma":[0.0004978131,0.00050876336,0.000011019542,0.00018610596,0.000109213666,0.00021453029,0.00015538816,0.00030704998,0.00034893912,0.00005632412,0.99700904,0.00059579493],"about_ca_topic_score_codex":0.000018371598,"about_ca_topic_score_gemma":7.388454e-7,"teacher_disagreement_score":0.33723277,"about_ca_system_score_codex":0.00014730547,"about_ca_system_score_gemma":0.000019352172,"threshold_uncertainty_score":0.9996877},"labels":[],"label_agreement":null},{"id":"W6930577413","doi":"10.5281/zenodo.15272301","title":"JSOSuite.jl: One stop solutions for all things optimization","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Polytechnique Montréal","funders":"","keywords":"Documentation; Set (abstract data type); Section (typography); Test set; Key (lock)","score_opus":0.023591497285733537,"score_gpt":0.2564279688987664,"score_spread":0.23283647161303286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930577413","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":[0.000006199163,0.00028296086,0.3507028,0.0005689989,0.00015699043,0.0008506988,0.00069387053,0.0005373701,0.6462001],"genre_scores_gemma":[0.0011888496,0.0016151386,0.05157877,0.0018529753,0.0012260019,0.0000010547112,0.07655494,0.011447012,0.8545353],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984682,0.00016057592,0.00028110383,0.0004293258,0.00023309216,0.00042770887],"domain_scores_gemma":[0.9986421,0.000012566285,0.00024443248,0.00060746877,0.00038511178,0.00010834779],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00052437687,0.00023091023,0.00019891604,0.0002798246,0.00092754606,0.00034060722,0.00087771984,0.00032295624,0.0070483866],"category_scores_gemma":[0.0010453151,0.00026540135,0.00010016307,0.00020255569,0.00011541591,0.000012878372,0.0011877128,0.00026223468,0.00077087054],"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":[0.000053154705,0.000080288286,2.428706e-7,0.0002371211,0.00016362978,4.6022168e-7,0.00012693276,0.0016972303,0.00097062223,0.0025816336,0.9836356,0.010453088],"study_design_scores_gemma":[0.0005290787,0.00021420157,0.0000041075546,0.00008636771,0.000055292436,0.000011316393,0.00004370657,0.0049244775,0.00012850345,0.000038177564,0.9937012,0.00026354028],"about_ca_topic_score_codex":0.000019919265,"about_ca_topic_score_gemma":7.7530547e-7,"teacher_disagreement_score":0.29912403,"about_ca_system_score_codex":0.00006371189,"about_ca_system_score_gemma":0.000015073879,"threshold_uncertainty_score":0.9999798},"labels":[],"label_agreement":null},{"id":"W6930732525","doi":"10.5281/zenodo.14597148","title":"Erdosiella acarensis Soyka 1956","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Natural Resources Canada","funders":"","keywords":"Holotype; Term (time); Class (philosophy)","score_opus":0.015899777380526333,"score_gpt":0.2529161726543527,"score_spread":0.23701639527382634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930732525","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15249644,0.0018506146,0.035748072,0.0031482659,0.0008440629,0.0008578722,0.00047419601,0.0022295136,0.80235094],"genre_scores_gemma":[0.9891563,0.00023328482,0.001000127,0.0003463151,0.00042745544,3.967743e-8,0.003306003,0.0011720973,0.0043583764],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989243,0.00012502221,0.00018353618,0.00029875722,0.0002059144,0.00026247159],"domain_scores_gemma":[0.99927044,0.00000874313,0.000038222544,0.00038766838,0.00018731898,0.000107609216],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003920846,0.000123318,0.0000834753,0.00011388698,0.00070256816,0.00061034586,0.00054805435,0.00009349031,0.0032565733],"category_scores_gemma":[0.00038767324,0.00012375918,0.000065342254,0.00025465456,0.0001003017,0.000013154669,0.00083073456,0.00022823873,0.005558667],"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":[0.00004604591,0.000048905873,0.00000945165,0.00020888468,0.000116212774,0.000015793292,0.00078703807,0.00022566917,0.07196914,0.0037907055,0.73944074,0.18334141],"study_design_scores_gemma":[0.00013521762,0.00018388977,0.00011001596,0.000025290752,0.000011615918,0.0001329164,0.00009577174,0.0017475537,0.004344547,0.00005135865,0.99301326,0.00014856351],"about_ca_topic_score_codex":0.0000045932757,"about_ca_topic_score_gemma":1.7296159e-7,"teacher_disagreement_score":0.83665985,"about_ca_system_score_codex":0.000034500154,"about_ca_system_score_gemma":0.0000049541236,"threshold_uncertainty_score":0.99765456},"labels":[],"label_agreement":null},{"id":"W6930940673","doi":"10.5281/zenodo.3990008","title":"Ouranosinc/xclim: v0.19.0","year":2020,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Ouranos","funders":"","keywords":"Code refactoring; Class (philosophy); Metadata; Object (grammar); Key (lock); Variable (mathematics); Order (exchange); Set (abstract data type); Relation (database); Dimension (graph theory)","score_opus":0.018739987960386884,"score_gpt":0.2475643197285177,"score_spread":0.2288243317681308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930940673","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":[0.00004931886,0.00043340292,0.0036019587,0.0008661017,0.00015396917,0.0004130404,0.00045618403,0.0007040238,0.993322],"genre_scores_gemma":[0.009159976,0.0020024597,0.005492762,0.0028564436,0.0030745878,1.794596e-7,0.045707267,0.030085078,0.9016212],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984757,0.00021623806,0.00023983936,0.00044207388,0.00030043375,0.00032573217],"domain_scores_gemma":[0.99880004,0.000004746656,0.00021514061,0.000619995,0.00012736228,0.00023272658],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002381804,0.00025228306,0.00020036972,0.00015769112,0.00059254584,0.00033394157,0.0011205495,0.00027427138,0.023081008],"category_scores_gemma":[0.00075543264,0.00026773955,0.000088777175,0.00021566334,0.00013860592,0.000005181523,0.0014192141,0.00037124602,0.011081242],"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":[0.000028905204,0.00003291273,0.0000018269334,0.00014809791,0.00008135897,0.0000061191095,0.00011662986,0.000011766617,0.0036214523,0.00040401987,0.9850427,0.010504203],"study_design_scores_gemma":[0.00036598582,0.00025506664,0.00001850846,0.00003886489,0.000020841322,0.000070511676,0.00005106038,0.00008981064,0.000375893,0.000012014945,0.9984119,0.00028956428],"about_ca_topic_score_codex":0.000016671624,"about_ca_topic_score_gemma":6.8612957e-7,"teacher_disagreement_score":0.091700755,"about_ca_system_score_codex":0.00003549457,"about_ca_system_score_gemma":0.0000074995487,"threshold_uncertainty_score":0.99997747},"labels":[],"label_agreement":null},{"id":"W6930979102","doi":"10.5281/zenodo.3541313","title":"NPA_ref7626","year":2019,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Context (archaeology); Metabolite; Component (thermodynamics); Atlas (anatomy)","score_opus":0.011267871365293256,"score_gpt":0.2321559619478285,"score_spread":0.22088809058253525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930979102","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4356452,0.00011676278,0.005556519,0.0005764635,0.00024924107,0.00060179597,0.00015054544,0.00039930438,0.55670416],"genre_scores_gemma":[0.99055976,0.000020789212,0.00059867,0.00033164426,0.0001199596,2.3660894e-8,0.002313065,0.0006934909,0.005362604],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990324,0.00014369043,0.00014626833,0.00022386565,0.00020404655,0.00024977062],"domain_scores_gemma":[0.9992424,0.0000035804383,0.00007298191,0.00042613022,0.00017844912,0.00007643727],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00041830997,0.00009018662,0.00007548202,0.00007092171,0.000822197,0.00018179807,0.0006477431,0.00005082572,0.004071174],"category_scores_gemma":[0.00018188854,0.00009542509,0.00004222219,0.00015030464,0.000049465496,0.000007437097,0.0013448723,0.00017901031,0.008096715],"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":[0.0002362641,0.00020772191,0.00017964112,0.00017618784,0.00012737859,0.000005457909,0.0008524913,0.002319374,0.2917083,0.006501637,0.586494,0.111191556],"study_design_scores_gemma":[0.0003423659,0.00034053624,0.00034762154,0.0000052865767,0.0000035380301,0.00009430673,0.00011933527,0.0007898893,0.0021245037,0.000030173414,0.9956781,0.00012430019],"about_ca_topic_score_codex":0.0000021910082,"about_ca_topic_score_gemma":4.291948e-8,"teacher_disagreement_score":0.55491453,"about_ca_system_score_codex":0.000030092564,"about_ca_system_score_gemma":0.000002800548,"threshold_uncertainty_score":0.9968392},"labels":[],"label_agreement":null},{"id":"W6931189786","doi":"10.5281/zenodo.4670374","title":"ArtinWedderburn","year":2021,"lang":"en","type":"other","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Perimeter Institute","funders":"","keywords":"","score_opus":0.014402779641241783,"score_gpt":0.26636908378864566,"score_spread":0.2519663041474039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931189786","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.4182795e-7,0.002596354,0.0000052363603,0.000020497691,0.00007444952,0.00010349304,0.05847784,0.000047399157,0.9386739],"genre_scores_gemma":[0.000012477255,0.000016376438,0.0006765913,0.00026668236,0.0005401981,0.000031235442,0.40718815,0.00018552439,0.59108275],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99942285,0.000020627289,0.00010763287,0.00019352826,0.0000996703,0.00015569388],"domain_scores_gemma":[0.9993565,0.0000042484007,0.00013135787,0.00042820524,0.000028711307,0.000050961095],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000013788666,0.00016704132,0.00012577056,0.000034625264,0.000017903465,0.000026897666,0.00019354386,0.00036369628,0.6262703],"category_scores_gemma":[0.0005066233,0.00016735785,0.00008425615,0.000043308744,0.0000040224672,2.9806495e-7,0.00020180682,0.0001465042,0.0020389971],"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":[7.205269e-7,0.00000623218,0.00000582128,0.00024819977,0.0000324399,0.000004736451,0.000003396686,0.0000034300076,0.00015044265,0.0000013210773,0.9985721,0.0009711516],"study_design_scores_gemma":[0.000078769786,0.00002120112,0.000019245275,0.00091263273,0.0000041604867,0.00001258552,0.0000035924563,0.000030135054,0.00073833065,6.8623933e-7,0.99797857,0.00020011832],"about_ca_topic_score_codex":0.000002822377,"about_ca_topic_score_gemma":0.000023468689,"teacher_disagreement_score":0.6242313,"about_ca_system_score_codex":0.0000037273567,"about_ca_system_score_gemma":0.0000681359,"threshold_uncertainty_score":0.99873805},"labels":[],"label_agreement":null},{"id":"W6931296112","doi":"10.5281/zenodo.3741998","title":"Chinese version of \"Ten quick tips for machine learning in computational biology\"","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Krembil Foundation","funders":"","keywords":"Computational learning theory; Machine translation; Training set; Feature (linguistics); Computational model","score_opus":0.015699542434593816,"score_gpt":0.25963897109636713,"score_spread":0.24393942866177332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931296112","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8295811,0.00035772892,0.13391045,0.0047477162,0.00013617697,0.001301717,0.0009250041,0.00041874437,0.028621402],"genre_scores_gemma":[0.9890738,0.000029269222,0.002938188,0.00021604483,0.00008155868,5.041831e-8,0.007294032,0.00027416213,0.00009289588],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99909973,0.00015371757,0.00024049862,0.0002164332,0.000115781724,0.00017386429],"domain_scores_gemma":[0.99941933,0.000021952721,0.00012407622,0.00013087518,0.00022588194,0.00007785808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035552125,0.00010013179,0.00012467158,0.00008383057,0.00033624607,0.000050111244,0.00039992484,0.000073634175,0.0005549087],"category_scores_gemma":[0.0013605006,0.0000994957,0.000048550453,0.0002219391,0.00008009879,0.000010840114,0.00052204536,0.00017502728,0.00020415604],"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":[0.004529445,0.00089149614,0.025008362,0.0020541397,0.0004963029,0.000010839417,0.009437995,0.14671598,0.42590794,0.009124063,0.18679617,0.18902726],"study_design_scores_gemma":[0.0017434392,0.0012386091,0.0034735142,0.000018439603,0.0000085795255,0.000022802704,0.00013861676,0.08816908,0.0012162966,0.0001434472,0.9036243,0.00020287688],"about_ca_topic_score_codex":0.0000065525314,"about_ca_topic_score_gemma":3.1487968e-7,"teacher_disagreement_score":0.7168281,"about_ca_system_score_codex":0.00001898066,"about_ca_system_score_gemma":0.000005179876,"threshold_uncertainty_score":0.6075861},"labels":[],"label_agreement":null},{"id":"W6931360076","doi":"10.5281/zenodo.5095115","title":"Phylogeography of cavity-nesting honeybees (Apis)","year":2023,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Phylogenetic tree; Phylogeography; Lineage (genetic); Mainland; Clade; Population; Phylogenetics; Endemism","score_opus":0.015531201082932752,"score_gpt":0.2448464288247179,"score_spread":0.22931522774178514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931360076","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":[0.0017150026,0.0003724773,0.0018632564,0.00010943183,0.00023597285,0.0005139018,0.000728021,0.001345093,0.99311686],"genre_scores_gemma":[0.19024171,0.004949907,0.011783591,0.0006221791,0.004106288,5.8898956e-7,0.040521976,0.10823343,0.6395403],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99871516,0.00016485564,0.00025650157,0.00031974883,0.00026897228,0.00027475102],"domain_scores_gemma":[0.99884486,0.000010579166,0.00029256352,0.0005600378,0.00020078164,0.0000911464],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004060109,0.00019244246,0.00019670813,0.00031782183,0.0003871459,0.00012119047,0.0008076954,0.00021477623,0.003075416],"category_scores_gemma":[0.0008228895,0.00020586036,0.000095780764,0.00037236587,0.00019036539,0.0000046486116,0.0010532897,0.0002449758,0.0016625441],"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":[0.000021807522,0.0000566061,0.000041745072,0.0003271858,0.00014889943,0.0000039835895,0.00016051813,0.000048705224,0.010178118,0.00035948257,0.95777184,0.030881137],"study_design_scores_gemma":[0.00023239257,0.00018904185,0.0001843373,0.00010028112,0.000018589715,0.00002539501,0.000062760904,0.00006647577,0.0008399181,0.000013654629,0.9980612,0.00020599569],"about_ca_topic_score_codex":0.000057590474,"about_ca_topic_score_gemma":0.0000030747656,"teacher_disagreement_score":0.3535765,"about_ca_system_score_codex":0.000016148066,"about_ca_system_score_gemma":0.0000041515787,"threshold_uncertainty_score":0.99911475},"labels":[],"label_agreement":null},{"id":"W6931388679","doi":"10.5281/zenodo.3672057","title":"BOLD &amp; mBRAVE: Purpose-Built Research Data Platforms in the Biodiversity Domain","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Barcode; Domain (mathematical analysis); Research data; Biodiversity; Key (lock)","score_opus":0.29174486563723173,"score_gpt":0.3894434346760084,"score_spread":0.09769856903877666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931388679","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3214753,0.0011502206,0.00010572799,0.015778344,0.00012633314,0.0023620566,0.6287364,0.0001187846,0.030146843],"genre_scores_gemma":[0.2834783,0.000032594242,0.0013432793,0.004715384,0.00040039685,0.000044015076,0.7097662,0.000020218024,0.00019964612],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988351,0.00008319222,0.0001593939,0.00029540577,0.00032916552,0.00029776202],"domain_scores_gemma":[0.9988291,0.00005892971,0.000055266704,0.0009120712,0.0000634111,0.000081202175],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004154058,0.00011373035,0.00009391935,0.000037153117,0.00014774167,0.00008393735,0.0017335818,0.00014607189,0.0074999197],"category_scores_gemma":[0.0022363502,0.00008389047,0.0000353847,0.00026294065,0.000024773712,0.0000134561515,0.0015890534,0.0004740908,0.0021305035],"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":[0.000032409294,0.000020194639,0.0010433138,0.00009499711,0.000009956507,0.000008447997,0.000598232,0.000025392515,0.0009847097,0.000011685109,0.9965698,0.00060087466],"study_design_scores_gemma":[0.00027989288,0.00009210417,0.0019795098,0.00005000193,0.0000019384977,0.000008381356,0.00030483707,0.00031874783,0.00063726475,0.000037323363,0.99615836,0.00013164783],"about_ca_topic_score_codex":0.000022977181,"about_ca_topic_score_gemma":0.00011655679,"teacher_disagreement_score":0.0810298,"about_ca_system_score_codex":0.000009871752,"about_ca_system_score_gemma":0.000073967545,"threshold_uncertainty_score":0.99864644},"labels":[],"label_agreement":null},{"id":"W6931424955","doi":"10.5281/zenodo.4368205","title":"Uvularia sessilifolia Linnaeus 1753","year":2007,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Column (typography); Identification (biology); Key (lock)","score_opus":0.015247843499696536,"score_gpt":0.260095428621647,"score_spread":0.24484758512195043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931424955","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37192726,0.00024970708,0.08638523,0.0005653817,0.00039588127,0.0006490613,0.00014409138,0.0007994598,0.5388839],"genre_scores_gemma":[0.9907679,0.000049151557,0.0026879832,0.00040468486,0.00039855606,1.6999214e-8,0.0024872415,0.00088570017,0.002318799],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987689,0.00011439522,0.0002514903,0.00026759016,0.00023716068,0.0003604137],"domain_scores_gemma":[0.99894303,0.0000085746115,0.00010261004,0.00047609914,0.00031309001,0.00015661528],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00096265925,0.00012993347,0.00009588386,0.00010933777,0.00094728486,0.0002586853,0.0006802751,0.00011788444,0.0024545758],"category_scores_gemma":[0.0007496656,0.00013592555,0.000053059273,0.0002319402,0.0001083537,0.000012615096,0.0008264189,0.00023218029,0.0027653202],"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":[0.00037276713,0.0003013144,0.0002551042,0.00017550845,0.00018051799,0.000033497683,0.0011289368,0.0004984245,0.29834935,0.0075830244,0.47098526,0.22013628],"study_design_scores_gemma":[0.00037178327,0.00023898581,0.0019642226,0.000009649986,0.000008035895,0.00011264633,0.000112403344,0.00032276227,0.009300606,0.000040247432,0.98734754,0.00017112934],"about_ca_topic_score_codex":0.0000075709954,"about_ca_topic_score_gemma":4.4065771e-7,"teacher_disagreement_score":0.6188406,"about_ca_system_score_codex":0.000040633793,"about_ca_system_score_gemma":0.0000043047953,"threshold_uncertainty_score":0.9984573},"labels":[],"label_agreement":null},{"id":"W6931608490","doi":"10.5281/zenodo.6217772","title":"Sarcophaga (Heteronychia) gallica Whitmore, Richet, Pape & Blackith, 2009, sp. nov.","year":2009,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Holotype; Paratype; Dorsum; Cultivar","score_opus":0.013977891689540478,"score_gpt":0.24306452801344267,"score_spread":0.2290866363239022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931608490","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26066968,0.0007574946,0.01739073,0.0034295705,0.0003250226,0.001258885,0.0003531853,0.0012273021,0.7145881],"genre_scores_gemma":[0.98869485,0.00026008632,0.0026699142,0.0014242674,0.00041761764,5.639708e-8,0.0032538648,0.0008559857,0.0024233563],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982681,0.00019541456,0.00032347732,0.00041635835,0.00033307876,0.00046355277],"domain_scores_gemma":[0.99861455,0.000006692468,0.00014851986,0.0006973424,0.00032622894,0.00020668985],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00046451474,0.00021525582,0.00015997188,0.00011655054,0.00097529386,0.00039623422,0.0009877025,0.00013824545,0.0030182754],"category_scores_gemma":[0.00046604147,0.000223151,0.00008503977,0.00030688825,0.00012943654,0.000024099494,0.00063251087,0.00031744724,0.0036481188],"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":[0.00025776823,0.00039613826,0.00007401612,0.000090936985,0.00010919949,0.000016723841,0.00068614754,0.00055099063,0.15844613,0.0017674535,0.683346,0.15425855],"study_design_scores_gemma":[0.0006003854,0.0007241051,0.002977843,0.000016893113,0.000013741274,0.0001303456,0.00005394837,0.00060042646,0.0045796116,0.00008272488,0.9899376,0.00028239875],"about_ca_topic_score_codex":0.0000037664397,"about_ca_topic_score_gemma":2.757405e-7,"teacher_disagreement_score":0.7280252,"about_ca_system_score_codex":0.000043205117,"about_ca_system_score_gemma":0.0000061273377,"threshold_uncertainty_score":0.9978931},"labels":[],"label_agreement":null},{"id":"W6931690553","doi":"10.5683/sp3/m510ci","title":"Cape Duncan Ontario. 1:50,000. Map Sheet 043A10, ed. 1, 1994","year":2021,"lang":"en","type":"dataset","venue":"Borealis","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Georeference; General partnership; Cape; Natural (archaeology); Raster graphics; Aerial photography; Digital mapping; Topographic map (neuroanatomy); Orthophoto","score_opus":0.0066774348333565586,"score_gpt":0.24036336954928686,"score_spread":0.2336859347159303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931690553","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010426209,0.0007915469,0.000050383842,0.0001492009,0.00058431906,0.00024071072,0.99428713,0.000027157103,0.0037653153],"genre_scores_gemma":[0.00001396644,0.00068142056,0.0010968007,0.0014737168,0.0009480555,0.000044921206,0.9926341,0.00005534671,0.0030516698],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99775517,0.0001125585,0.00056722376,0.00060303306,0.0004141561,0.0005478688],"domain_scores_gemma":[0.9974385,0.00002236474,0.0003606548,0.001851105,0.00010385836,0.00022355592],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002617101,0.00056384853,0.00050216133,0.00009307954,0.00014123815,0.00013729627,0.00082558714,0.0009030645,0.0010563986],"category_scores_gemma":[0.00018356727,0.0005560471,0.0002676957,0.000072965304,0.000112867594,0.000004911241,0.0005992515,0.00074283354,0.000056436827],"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":[0.00003180145,0.00006156119,0.0001560864,0.0002115599,0.00017896947,0.000042696578,0.000037905174,0.000051096085,0.00011695455,0.0000061068167,0.99883735,0.00026792643],"study_design_scores_gemma":[0.00033880258,0.00017035207,0.0003195661,0.00007770356,0.00012997861,0.00006836442,0.000029255913,0.000014083226,0.00023914348,0.000007503004,0.99795026,0.0006550041],"about_ca_topic_score_codex":0.28660017,"about_ca_topic_score_gemma":0.4895552,"teacher_disagreement_score":0.20295504,"about_ca_system_score_codex":0.000109340916,"about_ca_system_score_gemma":0.00060543953,"threshold_uncertainty_score":0.99985677},"labels":[],"label_agreement":null},{"id":"W6931702093","doi":"10.5683/sp3/ew5shn","title":"Search strategy for ketamine therapy in the treatment for substance use disorders","year":2024,"lang":"fr","type":"dataset","venue":"Borealis","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"PsycINFO; CINAHL; MEDLINE; Ketamine; Substance use","score_opus":0.03769402302962196,"score_gpt":0.32744087938579614,"score_spread":0.2897468563561742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931702093","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043963934,0.0051356684,0.00097202713,0.0013233948,0.00020400982,0.0028747169,0.9849163,0.000009937315,0.00016752312],"genre_scores_gemma":[0.0014346536,0.029188974,0.00087445567,0.00038722256,0.00047696527,0.0010696207,0.9657472,0.00006251752,0.0007583937],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981111,0.00015218132,0.00047446217,0.0004939953,0.00019642552,0.0005718052],"domain_scores_gemma":[0.9984349,0.0003391633,0.00013451758,0.00093339814,0.00009085249,0.000067165005],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00048600076,0.00049284624,0.00035728337,0.00008796955,0.00013243084,0.00022630938,0.0005951241,0.00048170588,0.00001175106],"category_scores_gemma":[0.00009824314,0.00033609386,0.0003364534,0.00013692681,0.00016351524,0.000009072462,0.000031027866,0.00026316685,0.000013108631],"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":[0.00044389238,0.00041286714,0.0002220686,0.00049349794,0.00028465368,0.0000039430392,0.0006532569,0.001008753,0.0000854308,0.00040005366,0.9665497,0.02944187],"study_design_scores_gemma":[0.0015470223,0.0038610215,0.00029976404,0.00006732794,0.000098181146,0.000006746923,0.00034849462,0.0025347527,0.00036083595,0.00012253512,0.99038714,0.0003661486],"about_ca_topic_score_codex":0.0045621023,"about_ca_topic_score_gemma":0.073243506,"teacher_disagreement_score":0.06868141,"about_ca_system_score_codex":0.00008519899,"about_ca_system_score_gemma":0.00018465317,"threshold_uncertainty_score":0.9999091},"labels":[],"label_agreement":null},{"id":"W6931823525","doi":"10.5281/zenodo.7687982","title":"Berjaya Food Berhad: An Investment and Financial Decision-Making Insight","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Investment (military); Profitability index; Franchise; Attractiveness; Quarter (Canadian coin); Venture capital; Cash; Debt","score_opus":0.017932802439020405,"score_gpt":0.25868370215897785,"score_spread":0.24075089971995745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931823525","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94117165,0.00013313495,0.0064788554,0.00031732218,0.00014624686,0.0004311342,0.00013550167,0.00050405686,0.05068213],"genre_scores_gemma":[0.99461913,0.00011212045,0.0019620922,0.00068671716,0.0001810475,7.269214e-8,0.0016667973,0.00053835474,0.00023363739],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99894106,0.00012572756,0.00018909112,0.00028470386,0.00020828449,0.0002511584],"domain_scores_gemma":[0.99927944,0.000014106819,0.000068519446,0.0003564447,0.00015779595,0.00012367281],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042348244,0.00011573877,0.00008947399,0.00014298428,0.0010143104,0.00029652557,0.00042727115,0.00008506595,0.00049234834],"category_scores_gemma":[0.0011248019,0.00011876266,0.00002775453,0.00029852608,0.00009678751,0.000021366852,0.0011342146,0.00014926562,0.00073526904],"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":[0.00036086162,0.00022799474,0.00014563825,0.000182436,0.0001067817,0.000025573667,0.005529905,0.001204485,0.0231265,0.012262361,0.32844663,0.62838084],"study_design_scores_gemma":[0.00033133602,0.00069810543,0.002302189,0.000024403256,0.000006567716,0.00005945532,0.00012553691,0.0015374235,0.0006979703,0.00044192735,0.9936119,0.00016319139],"about_ca_topic_score_codex":0.0000018099453,"about_ca_topic_score_gemma":8.6955805e-7,"teacher_disagreement_score":0.66516525,"about_ca_system_score_codex":0.000022946668,"about_ca_system_score_gemma":0.0000053761955,"threshold_uncertainty_score":0.94506407},"labels":[],"label_agreement":null},{"id":"W6931851033","doi":"10.5683/sp3/lnjf0n","title":"Rolphton Ontario. 1:50,000. Map Sheet 031K04, ed. 6, 1996","year":2021,"lang":"en","type":"dataset","venue":"Borealis","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Georeference; General partnership; Raster graphics; Natural (archaeology); Aerial photography; Digital mapping; Government (linguistics); Viewshed analysis","score_opus":0.006902676327158872,"score_gpt":0.24524419942564435,"score_spread":0.23834152309848547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931851033","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007263015,0.00090043875,0.000061985054,0.00013922772,0.00049884827,0.00028976976,0.9947901,0.000026583464,0.0032204657],"genre_scores_gemma":[0.000011919407,0.00068747,0.0011027723,0.0014012541,0.00091355783,0.00007478357,0.99359626,0.00005195445,0.0021600344],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99784034,0.00010610473,0.00055422075,0.000590706,0.00039753597,0.0005111171],"domain_scores_gemma":[0.9974984,0.000020853056,0.0003542726,0.0018021526,0.00013142441,0.00019288497],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002800278,0.0005400585,0.00048192553,0.00009077652,0.00012329365,0.00013072141,0.000787847,0.00097464886,0.0007768409],"category_scores_gemma":[0.00019051944,0.0005314953,0.00026841473,0.00006881844,0.000093398754,0.0000051025922,0.000599479,0.00075050426,0.000077034994],"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":[0.000043463635,0.00006603472,0.00015142093,0.00020581513,0.00016259427,0.000033805893,0.00002514174,0.000061329185,0.00012373265,0.0000044933117,0.9987204,0.00040178697],"study_design_scores_gemma":[0.00033376043,0.00020936746,0.00035563236,0.00007874134,0.00012227298,0.000055689226,0.000020376983,0.000017304441,0.00030015197,0.000008139027,0.9978817,0.00061687187],"about_ca_topic_score_codex":0.22261406,"about_ca_topic_score_gemma":0.35686117,"teacher_disagreement_score":0.13424711,"about_ca_system_score_codex":0.000095129595,"about_ca_system_score_gemma":0.00044659572,"threshold_uncertainty_score":0.99971366},"labels":[],"label_agreement":null},{"id":"W6939218847","doi":"10.60692/stgq5-wb469","title":"TranCEP: Predicting the substrate class of transmembrane transport proteins using compositional, evolutionary, and positional information","year":2020,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Transmembrane protein; Membrane; Membrane transport; Transmembrane domain; Proteome; Membrane transport protein; Substrate (aquarium); Sequence (biology)","score_opus":0.017394529771918674,"score_gpt":0.2051392104797007,"score_spread":0.18774468070778205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939218847","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89668167,0.000011657476,0.1010286,0.00030406454,0.000058862188,0.0005400815,0.00044226367,0.0000402543,0.00089255796],"genre_scores_gemma":[0.99693024,7.918575e-7,0.0021143837,0.00035477598,0.00008383361,0.000025590396,0.00048008567,0.0000071287013,0.0000031876582],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866015,0.000054179316,0.0007236449,0.000092294846,0.0003142927,0.00015541461],"domain_scores_gemma":[0.999188,0.0000047108892,0.0003841709,0.00014953862,0.00019677775,0.00007682356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021362993,0.00016205812,0.00016367639,0.0000629306,0.00019692855,0.00004734941,0.00014582773,0.00012228123,0.000008071862],"category_scores_gemma":[0.0000131763845,0.00012814709,0.00007832997,0.00013493231,0.000095657415,0.0001383857,0.00002267692,0.00012822203,0.000009759225],"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":[0.0028417925,0.000029470195,0.548349,0.010999659,0.0008107696,0.0000031860357,0.251119,0.16625082,0.014800141,0.0037877436,0.00031176902,0.00069665414],"study_design_scores_gemma":[0.0048346296,0.00074233447,0.37657043,0.00049284473,0.00021373942,0.00050042634,0.01676511,0.5729949,0.023328513,0.0000036193737,0.0027435643,0.0008098963],"about_ca_topic_score_codex":0.000007089627,"about_ca_topic_score_gemma":1.6959243e-7,"teacher_disagreement_score":0.40674406,"about_ca_system_score_codex":0.00002007284,"about_ca_system_score_gemma":0.00007656289,"threshold_uncertainty_score":0.5225687},"labels":[],"label_agreement":null},{"id":"W6949674789","doi":"10.5281/zenodo.14825942","title":"SPOT: A machine learning model that predicts specific substrates for transport proteins","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Deutsche Forschungsgemeinschaft","keywords":"Python (programming language); Function (biology); Web server; Transporter; Membrane transport protein; Set (abstract data type); Training set; Protein function prediction","score_opus":0.02885701052006852,"score_gpt":0.24266829989273347,"score_spread":0.21381128937266497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6949674789","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33006266,0.0025102869,0.5525967,0.0014770926,0.00036037102,0.0033316503,0.0017531972,0.0024976856,0.105410345],"genre_scores_gemma":[0.9837796,0.00031329982,0.0035602995,0.00005906844,0.00021487888,4.220937e-7,0.0076576862,0.0010696824,0.0033450732],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.998694,0.00008594093,0.00023599903,0.00039527463,0.00024295358,0.00034583034],"domain_scores_gemma":[0.99930316,0.000011103281,0.000065280685,0.0003092106,0.00018774562,0.00012349273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005904446,0.0001795263,0.00012520798,0.00012759201,0.0008799045,0.00040524142,0.00053572096,0.00011216715,0.0008418403],"category_scores_gemma":[0.00018007129,0.00017734154,0.00009543894,0.00019254709,0.00010074427,0.000027372618,0.00024610202,0.0003170568,0.00045889302],"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":[0.0012512617,0.00050955446,0.0002829168,0.0029773272,0.0006265499,0.000059945534,0.0067647216,0.055223074,0.5292396,0.01576044,0.19375817,0.19354647],"study_design_scores_gemma":[0.00037247853,0.0003918044,0.000113124675,0.00004841157,0.000016782966,0.00007463396,0.000068421024,0.09512058,0.009774438,0.00010627947,0.8937049,0.00020816263],"about_ca_topic_score_codex":0.000004299566,"about_ca_topic_score_gemma":6.476932e-7,"teacher_disagreement_score":0.6999467,"about_ca_system_score_codex":0.000037718397,"about_ca_system_score_gemma":0.000009556385,"threshold_uncertainty_score":0.9217561},"labels":[],"label_agreement":null},{"id":"W6955106142","doi":"10.58079/oihb","title":"Séminaire québécois en philosophie moderne (Sherbrooke, Québec, 26-28 septembre 2013)","year":2013,"lang":"fr","type":"article","venue":"OpenEdition (OpenEdition)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); Subject (documents); Context (archaeology); Relation (database); Interpretation (philosophy)","score_opus":0.008181515321317792,"score_gpt":0.22851660014983724,"score_spread":0.22033508482851943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6955106142","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058046877,0.034372643,0.015724888,0.67617196,0.009407637,0.004918265,0.0011338904,0.0005631471,0.1996607],"genre_scores_gemma":[0.8092482,0.006570656,0.010037082,0.05656067,0.007611095,0.0012653924,0.00594861,0.0004198305,0.10233848],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99528414,0.00047499576,0.0013068634,0.0010623299,0.00078565197,0.0010859916],"domain_scores_gemma":[0.99640363,0.00013504594,0.0006958419,0.0013897176,0.0007163959,0.00065937365],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005640703,0.00096695195,0.00073004863,0.00021080958,0.000670411,0.00046935797,0.0010946094,0.0011412828,0.013673293],"category_scores_gemma":[0.0003759627,0.0010480055,0.00046772195,0.00033381354,0.000566519,0.0015837608,0.0006521938,0.0009078957,0.016773654],"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":[0.00020177155,0.0010446097,0.00070811226,0.0013665356,0.0007009159,0.000073421776,0.000644862,0.004409473,0.007930432,0.029558262,0.8971566,0.056205016],"study_design_scores_gemma":[0.0019920687,0.00094834174,0.0064135618,0.0005447263,0.00023511045,0.0003543883,0.00036301467,0.009436865,0.00634466,0.0021303287,0.9696654,0.0015715483],"about_ca_topic_score_codex":0.020058915,"about_ca_topic_score_gemma":0.04536506,"teacher_disagreement_score":0.75120133,"about_ca_system_score_codex":0.0003896503,"about_ca_system_score_gemma":0.0008773481,"threshold_uncertainty_score":0.999197},"labels":[],"label_agreement":null},{"id":"W6955331845","doi":"10.58079/oq7w","title":"Mercredi 16 juin : Catherine Ferland et Benoît Grenier, de l'univ. de Sherbrooke","year":2010,"lang":"fr","type":"article","venue":"OpenEdition (OpenEdition)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Theme (computing); Event (particle physics)","score_opus":0.007197924844726568,"score_gpt":0.25138010161929353,"score_spread":0.24418217677456697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6955331845","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59310377,0.0055505414,0.048395563,0.14217131,0.012443876,0.0021046887,0.0022565988,0.0002862617,0.19368742],"genre_scores_gemma":[0.84364885,0.0033759049,0.034131,0.04511059,0.004804346,0.00033403837,0.009883768,0.00023806543,0.058473416],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99676234,0.00037992653,0.00076792494,0.00064735056,0.00045963924,0.0009828082],"domain_scores_gemma":[0.9975851,0.00010204293,0.0004043994,0.0009785392,0.00034585604,0.000584037],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013990965,0.0006058113,0.00046096384,0.00013977198,0.00044394197,0.00036011005,0.00079078093,0.00094699673,0.0068829567],"category_scores_gemma":[0.0005866461,0.0006738545,0.00026525542,0.00025740752,0.00041746374,0.00056085136,0.00040876397,0.0012290695,0.00072202855],"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":[0.0009023481,0.0020115643,0.010020722,0.0014799968,0.000858473,0.00018282485,0.0012027234,0.003148334,0.37107658,0.18799111,0.3590182,0.06210711],"study_design_scores_gemma":[0.002087393,0.0007228178,0.016703052,0.00021234043,0.00017266555,0.00063615286,0.00015787131,0.0026763023,0.039448008,0.0013859633,0.9348559,0.00094156206],"about_ca_topic_score_codex":0.0005682841,"about_ca_topic_score_gemma":0.011631807,"teacher_disagreement_score":0.5758377,"about_ca_system_score_codex":0.00022314975,"about_ca_system_score_gemma":0.00070773007,"threshold_uncertainty_score":0.99957126},"labels":[],"label_agreement":null},{"id":"W6957911493","doi":"10.6068/dp14ba89f7c2634","title":"Most Recent Data (2002). Statistics Canada. CANSIM: Children and Youth - Child Development and Behavior | Country: Canada | Table: Health behaviour in school-aged children 2002, student response to question: How do you feel about yourself? | Variable: 11 years, Agree, Males, I am usually tired when I go to school in the morning | Units: %, 2002. Data-Planet™ Statistical Ready Reference by Conquest Systems, Inc. Dataset-ID: 075-001-024.","year":2015,"lang":"en","type":"other","venue":"Data Planet","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Statistics education; Official statistics; Socioeconomic status; Population; Poverty; Census; Child development; Descriptive statistics; Economic statistics","score_opus":0.014160657876899577,"score_gpt":0.2609139757108519,"score_spread":0.24675331783395232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6957911493","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033922092,0.0035524126,0.000018803572,0.00004299113,0.00020621384,0.001982389,0.9936711,0.000025953992,0.00016086831],"genre_scores_gemma":[0.00007441969,0.00099454,0.0025540139,0.0012402533,0.00017698517,0.00004018622,0.99307793,0.00016257502,0.0016791016],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99472445,0.00095039664,0.0009293608,0.0013946738,0.0011118094,0.0008893151],"domain_scores_gemma":[0.9949413,0.00009283393,0.00058620545,0.0033546041,0.00013273634,0.0008923115],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0025200385,0.000733246,0.00075790094,0.00016251026,0.00019977882,0.00057879504,0.0028991278,0.00041783237,0.00036830126],"category_scores_gemma":[0.00071603956,0.0006909486,2.040938e-7,0.0003948636,0.00009816149,0.000060149963,0.0020947636,0.0011311993,0.000014558811],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001826391,0.00012588236,0.010161211,0.000081395185,0.00011678435,0.000098263656,0.000038336086,0.00003758494,7.616881e-7,0.000005000747,0.9888758,0.0002763568],"study_design_scores_gemma":[0.0012133966,0.00016477512,0.03285158,0.0001567583,0.00017801645,0.00023604059,0.0005031813,0.000077250836,2.2963533e-8,4.107702e-9,0.9638357,0.00078328844],"about_ca_topic_score_codex":0.9924038,"about_ca_topic_score_gemma":0.99505717,"teacher_disagreement_score":0.025040098,"about_ca_system_score_codex":0.0003133964,"about_ca_system_score_gemma":0.016708627,"threshold_uncertainty_score":0.99955416},"labels":[],"label_agreement":null},{"id":"W6958184062","doi":"10.6084/m9.figshare.16620928.v1","title":"Additional file 2 of PathFams: statistical detection of pathogen-associated protein domains","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Wilfrid Laurier University; University of Waterloo","funders":"","keywords":"Domain (mathematical analysis); Statistical analysis; Pattern recognition (psychology); Protein detection; Table (database)","score_opus":0.006946089948129705,"score_gpt":0.2201791178083597,"score_spread":0.21323302786023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958184062","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011049919,0.000017063629,0.000049558847,0.0000033859956,0.0000069414814,0.00008231273,0.9973322,0.0000074416657,0.0013960697],"genre_scores_gemma":[0.030881053,4.087166e-7,0.0029381611,0.000025887446,0.000036441026,0.00016851324,0.965483,0.00001002088,0.00045653404],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99939436,0.000055089455,0.00020037031,0.00010938809,0.00013921467,0.00010155188],"domain_scores_gemma":[0.9992621,0.00013029641,0.0001852621,0.00015173944,0.0002373093,0.00003331652],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000021864487,0.00007304007,0.00010042283,0.000016412945,0.000027487784,0.000005444097,0.000069566006,0.00011825611,0.91218466],"category_scores_gemma":[0.0080438955,0.00007607705,0.000056429282,0.00008081085,0.000011597586,0.0000023508733,0.00008048825,0.00007962085,0.00012964461],"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":[0.0000085089405,0.000048533188,0.0000027742246,0.00010756001,0.000024640758,0.0000035166936,0.000010073827,0.0000075072307,0.065844126,0.0000040518157,0.93286747,0.0010712387],"study_design_scores_gemma":[0.00025891938,0.00021616885,0.00434613,0.00078610406,0.000006754239,0.000013533175,0.000037382608,0.000744068,0.12491861,0.00003590569,0.8684792,0.00015722123],"about_ca_topic_score_codex":6.6515713e-7,"about_ca_topic_score_gemma":0.000012249441,"teacher_disagreement_score":0.912055,"about_ca_system_score_codex":0.000009363638,"about_ca_system_score_gemma":0.00013340455,"threshold_uncertainty_score":0.9629875},"labels":[],"label_agreement":null},{"id":"W6958546491","doi":"10.6084/m9.figshare.29190.v1","title":"The use of D dimer, ventilationâ perfusion scan (VQ), spiral chest computed tomography (CT), and angiography (angio) for the diagnosis of pulmonary embolism, as reported by Canadian Intensive Care Unit Directors","year":2011,"lang":"en","type":"other","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Licensee; Intensive care unit; Spiral computed tomography; Computed tomography; Angiography; Pulmonary angiography; Intensive care; Computed tomographic angiography","score_opus":0.03110943097913488,"score_gpt":0.25271626953748605,"score_spread":0.22160683855835117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958546491","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04761401,0.14213927,0.000021278474,0.0002966728,0.0010058308,0.0074934065,0.77876544,0.00016783243,0.022496263],"genre_scores_gemma":[0.45354122,0.0016952156,0.00045228828,0.0006188379,0.00033937528,0.00073613145,0.5329597,0.00059387676,0.009063368],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990487,0.00004605692,0.0003089254,0.00023810609,0.00013394584,0.00022424418],"domain_scores_gemma":[0.9982135,0.000098055934,0.0005874165,0.00051825144,0.00048221872,0.000100526115],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0000438976,0.000257595,0.00024308903,0.00020109711,0.00015380452,0.00003075685,0.00029609993,0.00020226746,0.0014084865],"category_scores_gemma":[0.00044365058,0.00018249983,0.0003285921,0.00023773944,0.00009163411,0.000004815513,0.00013458189,0.00013307676,0.0000026852958],"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":[0.00003094008,0.000015911015,0.026776135,0.00036583334,0.00046427574,0.000003267111,0.00020708503,0.000009676374,0.000070990165,0.0000022125741,0.9623069,0.009746748],"study_design_scores_gemma":[0.00014969218,0.00010637707,0.025732456,0.00070665363,0.00012666872,0.000011564115,0.00019645812,0.00014828384,0.0011476033,8.8237965e-7,0.97144586,0.00022750214],"about_ca_topic_score_codex":0.016338615,"about_ca_topic_score_gemma":0.012759192,"teacher_disagreement_score":0.4059272,"about_ca_system_score_codex":0.0000073816973,"about_ca_system_score_gemma":0.000091490474,"threshold_uncertainty_score":0.9995044},"labels":[],"label_agreement":null},{"id":"W6958657450","doi":"10.6084/m9.figshare.26719512.v1","title":"Additional file 11 of Combined transcriptomics and proteomics unveil the impact of vitamin C in modulating specific protein abundance in the mouse liver","year":2024,"lang":"en","type":"dataset","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre hospitalier universitaire de Québec; Université Laval","funders":"","keywords":"Transcriptome; Proteomics; Table (database); Vitamin C; Gene; Liver metabolism; Gene expression","score_opus":0.011973869235617302,"score_gpt":0.24183125451521273,"score_spread":0.22985738527959543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958657450","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037564288,0.00010605736,3.6087934e-7,0.000012687991,0.000006560548,0.0008153108,0.9952681,0.000002779372,0.000031722528],"genre_scores_gemma":[0.0016325045,0.000017813747,0.00030451373,0.000021586053,0.000055043605,0.00051905314,0.997385,0.000018092262,0.000046372115],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99898577,0.00009918045,0.00039083287,0.00019749973,0.00016507863,0.00016164637],"domain_scores_gemma":[0.99909145,0.0001406214,0.00028192473,0.00041334715,0.00005300765,0.000019643343],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000114932845,0.00021488716,0.00022333351,0.000074950454,0.000028187662,0.00003441008,0.0004426511,0.00024647577,0.084983505],"category_scores_gemma":[0.0007482909,0.00014042987,0.000110708206,0.00015239438,0.0000434816,0.0000060154985,0.0001345551,0.00046709555,0.000042368516],"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":[0.000030430532,0.000048660113,0.0000031983095,0.00076159666,0.000020043759,0.0000032420253,0.00010128838,0.0002631086,0.00065168843,6.8568437e-7,0.9980559,0.000060165487],"study_design_scores_gemma":[0.00039100123,0.00028624706,0.001058898,0.0027441594,0.0000074246673,0.000015228638,0.00007268765,0.0040985197,0.00089647877,0.000012116164,0.9901639,0.00025332216],"about_ca_topic_score_codex":0.000070382855,"about_ca_topic_score_gemma":0.00021105686,"teacher_disagreement_score":0.084941134,"about_ca_system_score_codex":0.000025360481,"about_ca_system_score_gemma":0.00014219992,"threshold_uncertainty_score":0.91585296},"labels":[],"label_agreement":null},{"id":"W6958966469","doi":"10.6084/m9.figshare.c.7138430","title":"The IMPACT survey: a mixed methods study to understand the experience of children, adolescents and adults with osteogenesis imperfecta and their caregivers","year":2024,"lang":"en","type":"other","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Osteogenesis imperfecta; Health care; Scoliosis; Young adult; Quality of life (healthcare); Affect (linguistics)","score_opus":0.012492969010973123,"score_gpt":0.30859054449167395,"score_spread":0.2960975754807008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958966469","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6763711,0.027612926,0.00009164941,0.0000620748,0.0002274373,0.006726075,0.28081733,0.000099447236,0.007991953],"genre_scores_gemma":[0.988307,0.00012613146,0.00015229602,0.000031955522,0.0000770912,0.000077260825,0.007302222,0.00023556635,0.0036904754],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9989739,0.00027998225,0.00014087139,0.00030901362,0.00011418008,0.00018203733],"domain_scores_gemma":[0.999168,0.000054892906,0.00015092602,0.00050011877,0.000052850806,0.00007323903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019276723,0.0002843394,0.00021333074,0.00004437895,0.0000800694,0.00007765193,0.0003089899,0.000114137416,0.0004363278],"category_scores_gemma":[0.00036113185,0.00013240613,0.00004890629,0.00012210647,0.000050878756,0.0000019136685,0.00040349178,0.00014159497,0.0000065845297],"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":[0.0005378574,0.000100851306,0.012559694,0.0009766221,0.0014412381,0.0000036065596,0.031222738,0.000016816559,0.00036612438,5.5437215e-7,0.93418497,0.018588902],"study_design_scores_gemma":[0.006951369,0.013093069,0.61975855,0.023447048,0.0005362912,0.0003471461,0.20247664,0.0005732033,0.010797797,0.000009178709,0.11738283,0.0046269],"about_ca_topic_score_codex":0.00048668202,"about_ca_topic_score_gemma":0.0012989572,"teacher_disagreement_score":0.81680214,"about_ca_system_score_codex":0.000011018989,"about_ca_system_score_gemma":0.00005226803,"threshold_uncertainty_score":0.53993654},"labels":[],"label_agreement":null},{"id":"W6960729084","doi":"10.1371/journal.pone.0292226.s002","title":"Search strategy.","year":2023,"lang":"en","type":"other","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Odds ratio; Meta-analysis; Pregnancy; Confidence interval; Scopus; Incidence (geometry); Inclusion and exclusion criteria; Subgroup analysis","score_opus":0.028995623643785627,"score_gpt":0.3027106084136111,"score_spread":0.2737149847698255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6960729084","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":[0.0000020473185,0.0003462508,0.0000018813887,0.000011138126,0.000059311038,0.00017144799,0.15124545,0.00025929944,0.8479032],"genre_scores_gemma":[0.000088408815,0.000031607637,0.00010487018,0.000069954775,0.0005860408,0.000048044716,0.24960482,0.0007358984,0.74873036],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993399,0.000020314492,0.000100954785,0.00019531198,0.00014027276,0.00020324677],"domain_scores_gemma":[0.99945205,0.000008252814,0.00007267194,0.00038405508,0.00002583482,0.00005713953],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000027331922,0.00016727282,0.00011158841,0.000063124724,0.000022023938,0.000031538093,0.00026890857,0.00039232493,0.21391198],"category_scores_gemma":[0.00029122076,0.00016160466,0.00006705008,0.00006799163,0.000005678943,6.3183137e-7,0.00019416754,0.00019486135,0.016468316],"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":[0.0000012653674,0.0000037465736,0.000009008016,0.00018470887,0.000030861807,0.0000040241343,0.0000042989004,0.000029710587,0.000032758646,0.0000023801626,0.99777555,0.0019216827],"study_design_scores_gemma":[0.00007980306,0.000049126793,0.000055995006,0.00052850234,0.0000030441195,0.0000038491753,0.000008691286,0.00008535103,0.0003007437,5.9793757e-7,0.99869525,0.00018902219],"about_ca_topic_score_codex":0.000012778738,"about_ca_topic_score_gemma":0.00007319522,"teacher_disagreement_score":0.19744366,"about_ca_system_score_codex":0.000006466079,"about_ca_system_score_gemma":0.00007602114,"threshold_uncertainty_score":0.98429745},"labels":[],"label_agreement":null},{"id":"W6961030997","doi":"10.14288/1.0006056","title":"Cape Island boats with anglers competing in the International Tuna Cup Match at Soldier's Rip off Wedgeport, Nova Scotia","year":2002,"lang":"en","type":"other","venue":"Open Collections","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nova scotia; Cape; Tuna; Fishing; Cape verde","score_opus":0.01125768573903511,"score_gpt":0.25201002805236594,"score_spread":0.24075234231333084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6961030997","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":[0.0006693332,0.00012919032,0.00013504787,0.00024939503,0.0004255491,0.0006541391,0.00012058813,0.000017138607,0.9975996],"genre_scores_gemma":[0.0025550765,0.00013838006,0.0019511917,0.0003650602,0.00029127984,0.00004744318,0.0005608387,0.0001372478,0.99395347],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989126,0.00007077548,0.00026747986,0.0003060832,0.00021571216,0.00022735893],"domain_scores_gemma":[0.9991634,0.000024147012,0.00029231745,0.00042787872,0.000051722458,0.000040539464],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022290848,0.00024328758,0.0002152265,0.00010435215,0.00035722586,0.00044536495,0.00073389115,0.00021400914,0.0061893007],"category_scores_gemma":[0.00005963851,0.0001851588,0.000059272763,0.00030892168,0.0000863852,0.000006158395,0.00034117594,0.0002945017,0.00006634758],"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":[0.00002992989,0.00006583957,0.0015101421,0.000018462464,0.00012224559,0.000009428354,0.00016790854,0.00027845992,0.0000786222,0.0000028048923,0.9976227,0.00009342284],"study_design_scores_gemma":[0.0007551835,0.00011571168,0.00019996201,0.000119063574,0.00003241035,0.00019536554,0.00025094164,0.0008124874,0.00009081901,0.0000033749807,0.9971454,0.00027928324],"about_ca_topic_score_codex":0.0056472407,"about_ca_topic_score_gemma":0.12438888,"teacher_disagreement_score":0.11874164,"about_ca_system_score_codex":0.00006791377,"about_ca_system_score_gemma":0.00010573619,"threshold_uncertainty_score":0.99471915},"labels":[],"label_agreement":null},{"id":"W6961190452","doi":"10.14288/1.0177524","title":"Daily Building Record","year":2016,"lang":"en","type":"article","venue":"Open Collections","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Publishing; Historical record; Project commissioning; Architecture; Record keeping","score_opus":0.010685399386185084,"score_gpt":0.27589903680870087,"score_spread":0.2652136374225158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6961190452","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":[0.018818583,0.000023936253,0.057534527,0.0008610719,0.0005045315,0.00039965467,0.00003163789,0.000037277907,0.92178875],"genre_scores_gemma":[0.092325434,0.00008119938,0.038977135,0.0004051779,0.00024397176,0.00008973023,0.0000156804,0.000027185966,0.8678345],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995025,0.00003157338,0.00013000032,0.00014613493,0.000052716678,0.00013706827],"domain_scores_gemma":[0.99956733,0.000017918785,0.000054281256,0.00026448307,0.00004740631,0.000048555532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012962805,0.00007223467,0.00006770576,0.000020884348,0.0006570909,0.00023878645,0.00028320294,0.000061704835,0.00046329555],"category_scores_gemma":[0.00019808323,0.000053011107,0.000035618756,0.00017727626,0.00002906081,0.0000072417906,0.00025272134,0.000045359753,0.00003047827],"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":[0.000042762935,0.000031245152,0.001044455,0.0000038093388,0.000040367086,5.495987e-7,0.000015298348,0.000019654653,0.07118535,0.00016533211,0.9150133,0.012437834],"study_design_scores_gemma":[0.00045538953,0.00015688935,0.00022658259,0.000014562209,0.0000066969483,0.000019236586,0.000018947314,0.000082990715,0.015454454,0.0002976475,0.9831396,0.00012702453],"about_ca_topic_score_codex":0.00034650924,"about_ca_topic_score_gemma":0.00032685715,"teacher_disagreement_score":0.073506854,"about_ca_system_score_codex":0.000019205138,"about_ca_system_score_gemma":0.00006678004,"threshold_uncertainty_score":0.5072761},"labels":[],"label_agreement":null},{"id":"W6966428059","doi":"10.48350/196575","title":"A deep learning-based approach for efficient detection and classification of local Ca²⁺ release events in Full-Frame confocal imaging","year":2024,"lang":"en","type":"article","venue":"Open Access CRIS of the University of Bern","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Segmentation; Robustness (evolution); Deep learning; Confocal; Labeled data; Pattern recognition (psychology); Annotation","score_opus":0.012256716848352864,"score_gpt":0.28000220184309355,"score_spread":0.26774548499474066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6966428059","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55382055,0.00005842699,0.44546163,0.00010368852,0.000022713191,0.00023849089,0.000006162097,0.0000026073972,0.0002857639],"genre_scores_gemma":[0.99859923,0.000007921739,0.0012706532,0.000010192854,0.0000039631095,7.744173e-7,0.000025263093,0.0000054811508,0.000076545846],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99953496,0.0000589471,0.00012567942,0.00012967292,0.00008172758,0.000068980604],"domain_scores_gemma":[0.9995964,0.000023858294,0.00014297711,0.00014674012,0.00007073096,0.000019291938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023023218,0.00005861673,0.000102562226,0.000056913163,0.00005418459,0.00001688423,0.0004482754,0.000054105873,0.0000039799825],"category_scores_gemma":[0.000066488545,0.00005498472,0.000051798084,0.000094561525,0.0001270684,0.000016166268,0.0003622321,0.00009317238,2.1824752e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018762036,0.00035201345,0.04753728,0.0019747666,0.00012864648,9.702034e-7,0.0011808134,0.7397151,0.15315083,0.00024254517,0.00020795244,0.05363288],"study_design_scores_gemma":[0.0005839476,0.000073261086,0.0130951395,0.00006218098,0.000034579054,0.0000015566105,0.0007276167,0.9655252,0.01921598,0.000011732138,0.0006058145,0.00006300822],"about_ca_topic_score_codex":0.00046720606,"about_ca_topic_score_gemma":0.00012187373,"teacher_disagreement_score":0.44477868,"about_ca_system_score_codex":0.000022632174,"about_ca_system_score_gemma":0.000050537532,"threshold_uncertainty_score":0.22422118},"labels":[],"label_agreement":null},{"id":"W6968119745","doi":"10.5281/zenodo.1292784","title":"research-iobserve/jpetstore-6: Single Archive JPetStore with iObserve instrumentation","year":2018,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Apache (Canada)","funders":"","keywords":"Instrumentation (computer programming); Data acquisition; Key (lock); Component (thermodynamics)","score_opus":0.02723348627373085,"score_gpt":0.2600930621648237,"score_spread":0.23285957589109285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6968119745","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":[0.005231954,0.00016340004,0.003912743,0.00021501191,0.00019315847,0.0009836948,0.00058060145,0.00058983424,0.9881296],"genre_scores_gemma":[0.076591045,0.0008724054,0.025414487,0.0007278283,0.005112766,0.0000021562626,0.099274546,0.03554101,0.75646377],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99693996,0.00065910583,0.0003327417,0.0006992048,0.0007477545,0.0006212549],"domain_scores_gemma":[0.99777734,0.000016769112,0.00032448984,0.0010319782,0.00060825894,0.00024118992],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008472256,0.0003480891,0.0002511217,0.00045395028,0.0012072792,0.00055568735,0.0014147037,0.00030487354,0.0126022855],"category_scores_gemma":[0.00054496096,0.00033655067,0.00007863875,0.00046109883,0.00069675496,0.000020402505,0.0016068828,0.00055720605,0.006566428],"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":[0.00017171884,0.00013438483,0.000017913793,0.00022162659,0.00014499678,0.00000918353,0.00038790194,0.00002092729,0.0053869393,0.0004546781,0.98221093,0.010838818],"study_design_scores_gemma":[0.00068884774,0.0016760834,0.00014471947,0.00019568151,0.000024239653,0.00009607337,0.0003104732,0.00010148997,0.0011371782,0.0000372501,0.9952041,0.0003838453],"about_ca_topic_score_codex":0.000077932884,"about_ca_topic_score_gemma":0.00002298362,"teacher_disagreement_score":0.23166585,"about_ca_system_score_codex":0.00014443116,"about_ca_system_score_gemma":0.000021237893,"threshold_uncertainty_score":0.9999086},"labels":[],"label_agreement":null},{"id":"W6977261316","doi":"10.6084/m9.figshare.26752744","title":"Additional file 2 of A qualitative exploration of the reasons and influencing factors for pregnancy termination among young women in Soweto, South Africa: a Socio-ecological perspective","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Perspective (graphical); Qualitative research; Table (database); Pregnancy; Population; Abortion","score_opus":0.03842470397259103,"score_gpt":0.30626041084590994,"score_spread":0.2678357068733189,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977261316","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054647096,0.000058614853,0.000011202691,0.00001603379,0.000008428301,0.00030251005,0.94418424,0.0000072953653,0.0007645956],"genre_scores_gemma":[0.8235852,5.9252096e-7,0.00028233643,0.0000046792265,0.000015753765,0.00089572306,0.17494532,0.000006576496,0.0002638114],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9994999,0.000063229694,0.00014411872,0.00011559343,0.000078643716,0.000098514254],"domain_scores_gemma":[0.999225,0.00045447543,0.00012776596,0.00006729875,0.00010520281,0.00002024244],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000058563215,0.00006892633,0.000082473816,0.000037425143,0.000038746013,0.000012562446,0.00006384006,0.000087673296,0.067332],"category_scores_gemma":[0.008666762,0.000050828563,0.00004602465,0.00008667536,0.000029990551,0.000019536137,0.0000640905,0.00007498424,0.0000019536812],"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":[0.000025146375,0.000054607994,0.00063587725,0.00076439814,0.00007229974,7.041502e-7,0.33835462,0.00010373183,0.0005556193,0.00012816637,0.6590093,0.00029555862],"study_design_scores_gemma":[0.0010791179,0.0015061402,0.2524682,0.013835418,0.000041149877,0.000006872617,0.67463934,0.010544189,0.0028052458,0.0040753516,0.03818521,0.00081374036],"about_ca_topic_score_codex":0.0000024573817,"about_ca_topic_score_gemma":0.0000122640195,"teacher_disagreement_score":0.7692389,"about_ca_system_score_codex":0.00004912648,"about_ca_system_score_gemma":0.00010286989,"threshold_uncertainty_score":0.9996837},"labels":[],"label_agreement":null},{"id":"W6977261965","doi":"10.6084/m9.figshare.28396632","title":"Additional file 2 of A hybrid machine learning framework for functional annotation of mitochondrial glutathione transport and metabolism proteins in cancers","year":2025,"lang":"en","type":"article","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"","keywords":"Annotation; Supervised learning; Metabolism; Mitochondrion; Support vector machine","score_opus":0.008491494647390456,"score_gpt":0.2372374522927996,"score_spread":0.22874595764540914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977261965","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00096134207,0.0001270801,0.0012329298,0.000022942457,0.000028011254,0.00028907196,0.997032,0.00000538318,0.00030125753],"genre_scores_gemma":[0.016832357,0.0000031494833,0.021333104,0.00005050933,0.00007942065,0.0007446439,0.9606472,0.00000843986,0.00030113434],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99946547,0.000019039699,0.00021702156,0.00012359669,0.000087919936,0.00008694781],"domain_scores_gemma":[0.9994557,0.00018705128,0.0001542522,0.00007445617,0.00011041298,0.000018138928],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00002385815,0.0000805638,0.00012598748,0.00006602944,0.00003345813,0.0000036569493,0.000055316752,0.00007306315,0.24093269],"category_scores_gemma":[0.0026615623,0.000083752144,0.000053943004,0.00008885739,0.000014167418,0.0000055771147,0.000023028015,0.00012418968,0.0000022987113],"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":[0.0002934625,0.000037399397,0.00008544379,0.00059920107,0.00006647491,5.70808e-7,0.0000714527,0.0030023006,0.0019977516,0.000098110424,0.99154204,0.0022057882],"study_design_scores_gemma":[0.00079239596,0.00013448062,0.007359429,0.0013785302,0.000014454786,0.000003142235,0.00003222177,0.008235191,0.00601429,0.0002326796,0.9756615,0.00014166078],"about_ca_topic_score_codex":0.000009091268,"about_ca_topic_score_gemma":0.000023953637,"teacher_disagreement_score":0.24093038,"about_ca_system_score_codex":0.000009431302,"about_ca_system_score_gemma":0.00017253078,"threshold_uncertainty_score":0.7597612},"labels":[],"label_agreement":null},{"id":"W6979757815","doi":"","title":"Addressing the shortcomings of commercial-of-the-shelf model-to-model transformations with open-source tools; from SysML to AUTOSAR","year":2024,"lang":"en","type":"preprint","venue":"MacSphere (McMaster University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Windsor","funders":"","keywords":"AUTOSAR; Traceability; Variety (cybernetics); Automotive industry; TRACE (psycholinguistics); Implementation; Model transformation; Systems Modeling Language","score_opus":0.044907998385703404,"score_gpt":0.2670255011805692,"score_spread":0.2221175027948658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979757815","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28237712,0.00013114704,0.47265652,0.0026207601,0.00025066134,0.0023149594,0.0014056511,0.00005966939,0.23818353],"genre_scores_gemma":[0.90201664,0.000015855441,0.038382344,0.00096924574,0.00006296197,0.000011163002,0.00023335412,0.000085916916,0.058222543],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986415,0.00009696062,0.0003727417,0.000376191,0.00027132835,0.00024130572],"domain_scores_gemma":[0.99857044,0.000038550428,0.0002517344,0.000904469,0.00013256732,0.000102250175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017066677,0.0003219239,0.00037690456,0.0000856229,0.00017477488,0.00014700503,0.0019717568,0.00027655123,0.00029333678],"category_scores_gemma":[0.00003279768,0.00023733739,0.00019269243,0.00029394863,0.00012938706,0.000018032897,0.0037654564,0.0005797031,0.0000062217587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003292684,0.0000581019,0.00050037226,0.00044841145,0.00036394387,0.0000018664139,0.006020788,0.93406665,0.0057789753,0.0006990828,0.0025893054,0.04914322],"study_design_scores_gemma":[0.0015486531,0.0003660708,0.00063543825,0.0026105302,0.0011844776,0.000010532795,0.002871231,0.71637917,0.031111127,0.0005141633,0.24136914,0.0013994875],"about_ca_topic_score_codex":0.00029015073,"about_ca_topic_score_gemma":0.0005164427,"teacher_disagreement_score":0.6196395,"about_ca_system_score_codex":0.000060427752,"about_ca_system_score_gemma":0.00034677237,"threshold_uncertainty_score":0.96783376},"labels":[],"label_agreement":null},{"id":"W6980376867","doi":"","title":"Canada and Alberta invest in infrastructure projects in Central Alberta to strengthen the economy and build resilient communities - Commodities (COMMODIT) News","year":2020,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Economic impact analysis; National economy","score_opus":0.006974593819059278,"score_gpt":0.20466843154246364,"score_spread":0.19769383772340438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6980376867","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26253867,0.0006609433,0.000012052418,0.0077303564,0.00020829655,0.0017323052,0.00025498332,0.00001901228,0.7268434],"genre_scores_gemma":[0.7861862,0.0010282187,0.002216761,0.024987934,0.0005509283,0.000174405,0.0021249983,0.000492468,0.18223804],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989227,0.00014560431,0.0003078186,0.00022180086,0.00008589216,0.00031619525],"domain_scores_gemma":[0.99916,0.00010620784,0.00012827091,0.0004679787,0.000010287789,0.00012723364],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000059912876,0.0003359549,0.00032482855,0.00009283207,0.00005379221,0.00007729001,0.00039705852,0.00023643492,0.00012148436],"category_scores_gemma":[0.00010751433,0.00025595794,0.000019757665,0.00008093426,0.00015218931,0.0000045653187,0.0005391878,0.00045084927,9.0817537e-7],"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":[0.000041945834,0.00001465278,0.1448721,0.00028141425,0.000067880355,0.0000023661642,0.003458544,0.0005347324,0.000009007608,0.000952596,0.8491017,0.0006630224],"study_design_scores_gemma":[0.00042635683,0.00009127327,0.0082610035,0.00011262464,0.000009442369,0.0000097364245,0.0027777993,0.001061003,0.00003180459,0.000024831023,0.98683774,0.0003563883],"about_ca_topic_score_codex":0.9642712,"about_ca_topic_score_gemma":0.99896884,"teacher_disagreement_score":0.5446054,"about_ca_system_score_codex":0.00004724373,"about_ca_system_score_gemma":0.00042673174,"threshold_uncertainty_score":0.9999893},"labels":[],"label_agreement":null},{"id":"W6981573693","doi":"","title":"Enphase Energy (NASDAQ:ENPH) Given New $85.00 Price Target at Royal Bank of Canada","year":2024,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Energy (signal processing); Government (linguistics); Energy policy; Work (physics)","score_opus":0.003160239094939873,"score_gpt":0.20949753567402882,"score_spread":0.20633729657908895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6981573693","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":[0.000043229993,0.003740497,0.002374003,0.00029523516,0.00059372257,0.00012630547,0.00020950174,0.000049921568,0.9925676],"genre_scores_gemma":[0.0010393205,0.00013363124,0.0048555573,0.00058236485,0.00064230314,0.000006683563,0.00074470224,0.00032923254,0.9916662],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985798,0.000037603986,0.0003612006,0.00037820303,0.00029308756,0.00035012857],"domain_scores_gemma":[0.99888337,0.000009907431,0.00026166163,0.0006082815,0.000037386388,0.00019936854],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00007961475,0.00037695726,0.0003471439,0.000085520405,0.000025793483,0.000017565211,0.0003896419,0.0004546284,0.011111003],"category_scores_gemma":[0.00006842327,0.00033153355,0.00013037896,0.000080985534,0.000062990475,8.900965e-7,0.00036352492,0.00017868863,0.000058413432],"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":[0.000020712036,0.000014314132,0.000031586107,0.00024333254,0.00022651676,0.000011378434,0.000016821474,0.00012425987,0.0009820787,0.0002723187,0.9977967,0.0002599419],"study_design_scores_gemma":[0.0002667705,0.000103279024,0.0000048471566,0.00006739965,0.00003019929,0.0000122366355,0.000013610653,0.0004229789,0.00841469,0.000026372156,0.9902697,0.0003678997],"about_ca_topic_score_codex":0.24009952,"about_ca_topic_score_gemma":0.28248343,"teacher_disagreement_score":0.04238392,"about_ca_system_score_codex":0.00006890076,"about_ca_system_score_gemma":0.00093773496,"threshold_uncertainty_score":0.9999137},"labels":[],"label_agreement":null},{"id":"W6981715213","doi":"","title":"An expert looks at Province's new legislation taking aim at telecos","year":2022,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Legislation; Government (linguistics); Public interest; Public sector; Public policy","score_opus":0.005380335605895414,"score_gpt":0.20741368742363905,"score_spread":0.20203335181774365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6981715213","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":[0.00047249388,0.0004981674,0.000008732767,0.00008134816,0.00025236415,0.0005667952,0.00010038425,0.00012258255,0.99789715],"genre_scores_gemma":[0.0009076764,0.0001906957,0.00294932,0.00058447395,0.00037932536,0.00002303155,0.0027891072,0.00018627117,0.9919901],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981416,0.00010470302,0.00064310693,0.00029804927,0.0004668732,0.00034570936],"domain_scores_gemma":[0.9978831,0.000022402593,0.0011555332,0.0007101147,0.00006845563,0.00016042223],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00021131252,0.0004067455,0.00033151644,0.00007847995,0.00017743409,0.00004999342,0.00048849493,0.0004921705,0.4108235],"category_scores_gemma":[0.00013556522,0.00042892937,0.00016037603,0.000007649372,0.00008878988,8.4976286e-8,0.00039813016,0.00027401868,0.0022034992],"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":[0.00014250101,0.00003056762,0.000040691164,0.00016551765,0.00006153296,0.0000053399526,0.00018827348,0.0015874434,0.00005177279,0.000006405119,0.9939786,0.003741343],"study_design_scores_gemma":[0.000574456,0.00042800533,0.000014796964,0.000050344424,0.000028036387,0.00011159484,0.000056632914,0.00025845805,0.00020700849,0.0000010770242,0.99779963,0.00046996004],"about_ca_topic_score_codex":0.002762548,"about_ca_topic_score_gemma":0.0044605676,"teacher_disagreement_score":0.40862,"about_ca_system_score_codex":0.00014798371,"about_ca_system_score_gemma":0.000103154605,"threshold_uncertainty_score":0.99981624},"labels":[],"label_agreement":null},{"id":"W6982306833","doi":"","title":"I giovani LGBT+ senza dimora trovano casa!","year":2020,"lang":"it","type":"other","venue":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Population; Context (archaeology); Family economy","score_opus":0.013753432674814105,"score_gpt":0.2314363790596526,"score_spread":0.2176829463848385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6982306833","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69110936,0.0010566121,0.014033657,0.0009335717,0.00036201332,0.00095170416,0.0013389029,0.00014884956,0.29006532],"genre_scores_gemma":[0.97596174,0.0012646603,0.007898186,0.00025808977,0.00011803573,6.432289e-7,0.0006858546,0.00011420796,0.013698576],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99574155,0.002031933,0.0005998418,0.00053310295,0.00056868914,0.0005248977],"domain_scores_gemma":[0.9964424,0.00031468042,0.0012822998,0.001362846,0.00025600655,0.000341772],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008260045,0.0007401683,0.0014378423,0.00027277178,0.00043636974,0.000027632846,0.0020152908,0.0015556534,0.0016887913],"category_scores_gemma":[0.0005484161,0.00082125503,0.00070852326,0.0004135784,0.002126946,0.000019870706,0.0026914293,0.0021557962,0.00010716891],"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":[0.015193721,0.01652245,0.033511244,0.027797133,0.013338045,0.013302749,0.08468077,0.0052126627,0.20133643,0.064340666,0.22813289,0.29663122],"study_design_scores_gemma":[0.004351124,0.008148073,0.009701736,0.0007577855,0.00069030863,0.00058668025,0.021535495,0.0029099328,0.00091593637,0.00024099789,0.94807917,0.0020827523],"about_ca_topic_score_codex":0.00049708085,"about_ca_topic_score_gemma":0.00022024965,"teacher_disagreement_score":0.71994627,"about_ca_system_score_codex":0.00004783246,"about_ca_system_score_gemma":0.00017347043,"threshold_uncertainty_score":0.99974054},"labels":[],"label_agreement":null},{"id":"W6982402744","doi":"","title":"The Impact of Frailty on Functional Survival in Patients 1-Year Post-Cardiac Surgery","year":2015,"lang":"en","type":"other","venue":"Mspace (University of Manitoba)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Delirium; Cardiac surgery; EuroSCORE; Risk assessment; Adverse effect; Risk factor; Vulnerability (computing); Frailty syndrome; MEDLINE","score_opus":0.012463399920081504,"score_gpt":0.2149515939796824,"score_spread":0.2024881940596009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6982402744","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78047204,0.0001500115,0.000050417766,0.00010700756,0.00064518594,0.0003524794,0.00084315496,0.00002177286,0.2173579],"genre_scores_gemma":[0.80208856,0.00079098984,0.0009349508,0.0000501728,0.0007644269,0.0000012412498,0.0070672086,0.00048173073,0.18782072],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9992206,0.00011909714,0.000095053845,0.00014494186,0.00026723635,0.00015304837],"domain_scores_gemma":[0.9991354,0.00004504491,0.00029237248,0.00034398027,0.00013502785,0.00004820666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026860327,0.00015285378,0.00026674525,0.00013106421,0.00004053345,0.0000051516745,0.00021067854,0.00024572804,0.00003174663],"category_scores_gemma":[0.00012259149,0.00013839865,0.0002140808,0.00009023199,0.00011917005,0.0000030666436,0.00014141937,0.00015953928,0.00002997462],"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":[0.000332963,0.00008128939,0.32544878,0.000032918193,0.00018642224,5.132804e-7,0.000018923876,0.00010510173,0.00004703298,0.000020333233,0.6734257,0.00030002015],"study_design_scores_gemma":[0.0005111449,0.00048871606,0.84655565,0.000063853404,0.000024617024,1.9189777e-7,0.0007567456,0.000023454597,0.000021672786,0.000004913763,0.15134408,0.00020495302],"about_ca_topic_score_codex":0.001700145,"about_ca_topic_score_gemma":0.013991174,"teacher_disagreement_score":0.5220816,"about_ca_system_score_codex":0.00004843081,"about_ca_system_score_gemma":0.0001592824,"threshold_uncertainty_score":0.7807404},"labels":[],"label_agreement":null},{"id":"W6982591182","doi":"","title":"Interview with Ninna Piiksii (Dr. Michael Bruised Head)","year":2023,"lang":"en","type":"article","venue":"Scholar Works  (Boise State University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Interview; Conversation; Colonialism; Space (punctuation); Value (mathematics); Ethnography","score_opus":0.011302613151369502,"score_gpt":0.2293321869972527,"score_spread":0.2180295738458832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6982591182","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9753568,0.0002867228,0.008111245,0.0009957684,0.00020249224,0.00036402742,0.000048268073,0.00023461302,0.014400031],"genre_scores_gemma":[0.88095737,0.0031923847,0.00801889,0.0018588703,0.00022060524,0.0000050910994,0.0012801796,0.00016647972,0.104300134],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987162,0.00016908538,0.00017143588,0.00034480548,0.00018926013,0.00040925323],"domain_scores_gemma":[0.999067,0.0000173208,0.00012266789,0.0004943095,0.00012758271,0.0001711304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003737553,0.00023206967,0.00018910573,0.00026567234,0.00026251777,0.00008725976,0.00046043485,0.00014373286,0.000053925763],"category_scores_gemma":[0.00007515931,0.0002271396,0.00010142245,0.00083996553,0.00011342952,0.000037454,0.00035757825,0.0005094646,0.00022192216],"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":[0.008319981,0.001240326,0.10611047,0.0025536008,0.004823631,0.0037563178,0.009425942,0.061168723,0.15411031,0.0037586,0.27671832,0.36801377],"study_design_scores_gemma":[0.0019922107,0.00043138996,0.0054648537,0.00027140626,0.000056581728,0.000025062045,0.00091117306,0.0012210003,0.0027267516,0.000038399485,0.98630846,0.00055272836],"about_ca_topic_score_codex":0.000014795951,"about_ca_topic_score_gemma":0.000083754225,"teacher_disagreement_score":0.70959014,"about_ca_system_score_codex":0.000038061204,"about_ca_system_score_gemma":0.000092975824,"threshold_uncertainty_score":0.9262484},"labels":[],"label_agreement":null},{"id":"W6984784170","doi":"","title":"Canada goose","year":2006,"lang":"en","type":"other","venue":"Digital Collections (East Carolina University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Goose; Quilt; Natural (archaeology)","score_opus":0.0024355464860695074,"score_gpt":0.1559234974936399,"score_spread":0.1534879510075704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6984784170","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":[0.0001726437,0.00006897944,0.0005854991,0.000038153314,0.00026403327,0.0001635894,0.0009721271,0.00006662064,0.9976683],"genre_scores_gemma":[0.010490647,0.000017279935,0.00013540602,0.000051953706,0.0002579128,8.9433223e-7,0.0010828078,0.00013725666,0.9878259],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992386,0.00001927114,0.00011035099,0.00025431003,0.0001504485,0.00022698958],"domain_scores_gemma":[0.99937546,0.000005028354,0.00013254266,0.00033193742,0.00006057339,0.000094471616],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000014380397,0.00023374129,0.00017578801,0.0003395665,0.00017282074,0.000060148785,0.0002506976,0.0002492132,0.00007089769],"category_scores_gemma":[0.000031791187,0.00028413942,0.00010384116,0.000563185,0.000067445115,0.0000048983507,0.00014349536,0.00016927152,0.000014882742],"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":[0.000015778458,0.000025177484,0.00051365496,0.000025308542,0.00008351348,0.000021564807,0.0000029384432,0.0001585903,0.000010185953,0.00011658983,0.9988585,0.00016821285],"study_design_scores_gemma":[0.00030235696,0.000056523895,0.000054094482,0.000018667335,0.000030426456,0.000028274444,0.00003873982,0.00004927412,0.000020695303,0.0000024558867,0.99910784,0.00029066505],"about_ca_topic_score_codex":0.15020071,"about_ca_topic_score_gemma":0.66968393,"teacher_disagreement_score":0.51948327,"about_ca_system_score_codex":0.00015713889,"about_ca_system_score_gemma":0.0010575252,"threshold_uncertainty_score":0.9999611},"labels":[],"label_agreement":null},{"id":"W6984839853","doi":"","title":"Bearded seal","year":2008,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.004785933268626557,"score_gpt":0.23399224078160671,"score_spread":0.22920630751298016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6984839853","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":[0.000097431366,0.00034035975,0.00074958865,0.00004972975,0.00015270215,0.000107005515,0.00001653903,0.000077569464,0.9984091],"genre_scores_gemma":[0.0002979517,0.0005180267,0.007354976,0.0004025547,0.0005423332,0.0000048660804,0.0004490134,0.0002469989,0.9901833],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99947035,0.00001637161,0.0001052946,0.00015752968,0.00010259575,0.00014787323],"domain_scores_gemma":[0.9994882,0.0000017433367,0.00008099655,0.0003683121,0.000011763129,0.000048988964],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00003079612,0.00015980443,0.00012334724,0.00004781515,0.000020520314,0.000007814905,0.00016852922,0.0003548071,0.0021275452],"category_scores_gemma":[0.000029238496,0.0001395252,0.000068272566,0.000025952326,0.00004746961,2.1918738e-7,0.00009468536,0.00011412624,0.0005000025],"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":[0.0000029497708,0.000007936764,0.00015845113,0.000023032766,0.000040760813,0.0000015586934,0.0000054496936,0.0000037683985,0.00031928314,0.000047532976,0.99904805,0.0003412494],"study_design_scores_gemma":[0.00014867554,0.000053402888,0.000035068282,0.000010121331,0.0000056126237,0.000024541545,0.0000032168596,0.000027275186,0.00062400464,9.76813e-7,0.9988857,0.00018142386],"about_ca_topic_score_codex":0.00003703643,"about_ca_topic_score_gemma":0.00006232453,"teacher_disagreement_score":0.008225795,"about_ca_system_score_codex":0.0000035012288,"about_ca_system_score_gemma":0.000044208085,"threshold_uncertainty_score":0.99878466},"labels":[],"label_agreement":null},{"id":"W6985976592","doi":"","title":"Rodgers, Richard","year":2000,"lang":"en","type":"article","venue":"Sound Ideas (University of Puget Sound)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Natural (archaeology); Work (physics); Context (archaeology); Perspective (graphical); Set (abstract data type)","score_opus":0.005448994054033166,"score_gpt":0.20684852694871736,"score_spread":0.20139953289468418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6985976592","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9614038,0.00016551188,0.0043941215,0.00014804256,0.00007381585,0.000095577954,0.000024163832,0.000032895692,0.033662084],"genre_scores_gemma":[0.9810568,0.00012300465,0.0034755627,0.0001461069,0.00008664194,1.6292526e-7,0.0001384644,0.000014309667,0.014958924],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992113,0.00004925635,0.00012327968,0.00021152594,0.00017406927,0.00023056312],"domain_scores_gemma":[0.99933785,0.000011946237,0.00010074262,0.00038624383,0.000068883404,0.00009431416],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016307205,0.00013590681,0.00015905578,0.000055926983,0.00019096721,0.000018669638,0.0003499261,0.00015103699,0.0013242968],"category_scores_gemma":[0.000037349593,0.00016737136,0.00013999216,0.00012392786,0.00018430715,0.000014157965,0.00009971435,0.00012932609,0.00028361403],"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":[0.0031076681,0.0014910796,0.23289678,0.0011991336,0.002868014,0.00014310774,0.018304057,0.017764602,0.014172104,0.3816568,0.30812216,0.018274508],"study_design_scores_gemma":[0.0026593471,0.0007448972,0.015978089,0.000035024415,0.00015503066,0.000072636125,0.002855066,0.0018645608,0.00012974736,0.67397994,0.30052334,0.0010023392],"about_ca_topic_score_codex":0.000095018564,"about_ca_topic_score_gemma":0.00008825298,"teacher_disagreement_score":0.29232314,"about_ca_system_score_codex":0.000020471696,"about_ca_system_score_gemma":0.00004431151,"threshold_uncertainty_score":0.9995886},"labels":[],"label_agreement":null},{"id":"W6986010806","doi":"","title":"Welcome to Canada","year":2019,"lang":"en","type":"other","venue":"York University Digital Library (York University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.0034951600041638366,"score_gpt":0.1463363160104384,"score_spread":0.14284115600627456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986010806","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":[0.0008203818,0.00006841897,0.00025607698,0.00025111643,0.00049676327,0.00034426173,0.0020692577,0.00019330447,0.99550045],"genre_scores_gemma":[0.0043569794,0.00005061178,0.0008375691,0.0004188972,0.00027736244,4.97935e-8,0.0020011377,0.00021571487,0.9918417],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986658,0.00004600562,0.000119794066,0.0005169054,0.00024256368,0.00040892276],"domain_scores_gemma":[0.99871475,0.000019453539,0.00019058086,0.000716277,0.000017908233,0.0003410208],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000013678273,0.00040295676,0.0003245639,0.00044969335,0.00010401494,0.000105140585,0.001249953,0.0004192865,0.0004427124],"category_scores_gemma":[0.000015052979,0.0005105125,0.00016223123,0.0005619341,0.00008246857,0.000033401782,0.0010329128,0.00027497677,0.00040679198],"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":[0.000103739236,0.000027085545,0.002275397,0.0000706785,0.0001584068,0.00009887303,0.000017606164,0.00009149835,0.000010472042,0.0009790477,0.99563247,0.0005347533],"study_design_scores_gemma":[0.00045084374,0.00012507253,0.000093444265,0.000083910134,0.00003269179,0.0000069785087,0.0005778355,0.00000947332,0.000036302117,0.0000015931565,0.9979754,0.00060647493],"about_ca_topic_score_codex":0.012531285,"about_ca_topic_score_gemma":0.020829964,"teacher_disagreement_score":0.008298679,"about_ca_system_score_codex":0.00010715932,"about_ca_system_score_gemma":0.00094645174,"threshold_uncertainty_score":0.99973464},"labels":[],"label_agreement":null},{"id":"W6986076902","doi":"","title":"Armistice Day","year":2013,"lang":"en","type":"other","venue":"York University Digital Library (York University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.004366926420743741,"score_gpt":0.15407858539479458,"score_spread":0.14971165897405084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986076902","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":[0.00033057912,0.00017100597,0.001420915,0.000077479985,0.00022227704,0.00029281652,0.0011566371,0.00040962396,0.9959187],"genre_scores_gemma":[0.002169807,0.00023663772,0.0018028322,0.00014912682,0.00031612953,8.97351e-8,0.003400785,0.00026309138,0.9916615],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99858934,0.00008663639,0.00014069553,0.00055571954,0.00020731674,0.00042027258],"domain_scores_gemma":[0.99861777,0.000032504046,0.000304657,0.0007212829,0.000022607926,0.00030117916],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000022464412,0.0004659254,0.00033057376,0.0005030161,0.00015350891,0.00019560501,0.0012511964,0.0006733211,0.0019104214],"category_scores_gemma":[0.000029343164,0.00057151425,0.0002456175,0.00049006566,0.00027769178,0.00008416442,0.00094681635,0.00036280724,0.001136297],"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":[0.00006285981,0.00006795359,0.0012971647,0.00008703913,0.00022296631,0.000089932335,0.000027121147,0.000021376913,0.000023958772,0.004057272,0.9929139,0.00112846],"study_design_scores_gemma":[0.0005563291,0.00012147427,0.00006180061,0.000090727546,0.000075585915,0.000010440633,0.0005195934,0.000044174292,0.000044784283,0.00000942636,0.99781406,0.0006516324],"about_ca_topic_score_codex":0.000044272525,"about_ca_topic_score_gemma":0.000010420534,"teacher_disagreement_score":0.004900136,"about_ca_system_score_codex":0.000041232022,"about_ca_system_score_gemma":0.00021480666,"threshold_uncertainty_score":0.9996736},"labels":[],"label_agreement":null},{"id":"W6986111520","doi":"","title":"Orang Kaya Jangan Pakai BPJS","year":2022,"lang":"id","type":"article","venue":"Unika Repositor (Unika)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Labor cost; Java; Work (physics)","score_opus":0.004801269801342744,"score_gpt":0.22003692933513494,"score_spread":0.2152356595337922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986111520","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8849608,0.0055780946,0.0010944275,0.002792199,0.0059608514,0.0012752542,0.00022740036,0.00023869636,0.09787229],"genre_scores_gemma":[0.9065876,0.00021750925,0.0029201938,0.0013614699,0.0012807809,0.000089038156,0.0011196597,0.0001738112,0.08624995],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959073,0.00063068746,0.0008652867,0.00083889696,0.0008319565,0.0009258462],"domain_scores_gemma":[0.9969338,0.00006315585,0.000689968,0.0017388719,0.00021553623,0.0003586604],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0007365486,0.00062668155,0.0005347095,0.0002385406,0.001435622,0.00023528087,0.0011920758,0.00042146828,0.0004828547],"category_scores_gemma":[0.00024573063,0.00071833987,0.00042263567,0.00061029085,0.00021527227,0.000022857206,0.0016737136,0.0011917519,0.00014304428],"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":[0.0007862515,0.0012366262,0.018235138,0.00082124764,0.0013725595,0.00065347925,0.004706899,0.0026866815,0.82869625,0.0030719999,0.1258638,0.011869082],"study_design_scores_gemma":[0.0013975749,0.0015211912,0.0023227525,0.000053821084,0.0002120939,0.0007270972,0.0018454276,0.004003733,0.02837847,0.000022364933,0.95842105,0.0010944173],"about_ca_topic_score_codex":0.00019388959,"about_ca_topic_score_gemma":0.000029565068,"teacher_disagreement_score":0.83255726,"about_ca_system_score_codex":0.0001991969,"about_ca_system_score_gemma":0.00039444474,"threshold_uncertainty_score":0.9998644},"labels":[],"label_agreement":null},{"id":"W6986124642","doi":"","title":"Oklahoma Firefighter (Oklahoma City, Okla.), Vol. 26, No. 10, Ed. 1 Tuesday, December 1, 2009","year":2009,"lang":"en","type":"other","venue":"The Gateway to Oklahoma History","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"State (computer science); Information system; Government (linguistics); Quarter (Canadian coin)","score_opus":0.007588765836207091,"score_gpt":0.22657498337292195,"score_spread":0.21898621753671485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986124642","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":[0.0020790312,0.015924353,0.00024546476,0.0005679083,0.004849087,0.0014710148,0.00019575753,0.00070755224,0.9739598],"genre_scores_gemma":[0.0010509295,0.0007523281,0.0026167496,0.0051551913,0.004386342,0.00013931721,0.0006614693,0.0012094505,0.9840282],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951351,0.0003271729,0.0010223292,0.0012956361,0.0009154927,0.0013042613],"domain_scores_gemma":[0.99494225,0.00006332111,0.0008450159,0.0031821625,0.000417784,0.0005494907],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0006744391,0.0014258232,0.0010643802,0.00043660455,0.00028468418,0.00010078702,0.0021579592,0.0014648933,0.02131191],"category_scores_gemma":[0.00061057514,0.001185642,0.0006357101,0.0002423797,0.0004961862,0.000014811732,0.0008411152,0.001005059,0.013557686],"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":[0.00021734653,0.00016572665,0.000110542984,0.00013604981,0.00023937192,0.000027905438,0.00025672655,0.000029216199,0.00208911,0.000034563294,0.99264824,0.004045192],"study_design_scores_gemma":[0.0008566264,0.000658946,0.0005130342,0.00023473112,0.00017681684,0.00008826921,0.000016024984,0.000097601194,0.0007012449,0.00003275113,0.99508405,0.0015398943],"about_ca_topic_score_codex":0.0004615386,"about_ca_topic_score_gemma":0.00094527757,"teacher_disagreement_score":0.015172025,"about_ca_system_score_codex":0.00049804244,"about_ca_system_score_gemma":0.00046272227,"threshold_uncertainty_score":0.9998492},"labels":[],"label_agreement":null},{"id":"W6986126444","doi":"","title":"The Oklahoma Daily (Norman, Okla.), Vol. 95, No. 34, Ed. 1 Tuesday, October 6, 2009","year":2009,"lang":"en","type":"other","venue":"The Gateway to Oklahoma History","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Newspaper; Government (linguistics); Work (physics); Quarter (Canadian coin)","score_opus":0.004718624718177563,"score_gpt":0.21299690069755564,"score_spread":0.2082782759793781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986126444","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":[0.0006075195,0.04694902,0.00018217773,0.0005923589,0.0054909997,0.0012839746,0.00010727357,0.00032926223,0.9444574],"genre_scores_gemma":[0.00036734022,0.002611811,0.0010168898,0.0059986757,0.0040258197,0.00011105146,0.0003416637,0.000673405,0.9848533],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996443,0.00030844464,0.0007718163,0.0007780197,0.00069039257,0.0010083374],"domain_scores_gemma":[0.9957564,0.000075108605,0.00070772314,0.002857812,0.00028174187,0.00032123647],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00086865475,0.00094567536,0.00061412086,0.00016525654,0.00044567607,0.00009925158,0.0022125905,0.0008514543,0.0019468386],"category_scores_gemma":[0.0005660624,0.000644112,0.0004144502,0.00016148189,0.0005426949,0.000008438363,0.0005733904,0.00093323865,0.005587667],"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":[0.00013631055,0.00006233162,0.000044617063,0.000062424515,0.00016603967,0.000009483204,0.00021272118,0.00003441172,0.0013984131,0.00009250094,0.9918851,0.005895643],"study_design_scores_gemma":[0.0004799539,0.00041676572,0.00032119543,0.00010786468,0.000108232685,0.00004628909,0.00003858651,0.000099563,0.00021294587,0.00002314498,0.9972592,0.00088624255],"about_ca_topic_score_codex":0.00048147823,"about_ca_topic_score_gemma":0.0007840415,"teacher_disagreement_score":0.044337213,"about_ca_system_score_codex":0.00036728175,"about_ca_system_score_gemma":0.00039360407,"threshold_uncertainty_score":0.999601},"labels":[],"label_agreement":null},{"id":"W6986141266","doi":"","title":"Offre de travail endogène et mobilité du capital dans un modèle d'équilibre général calculable birégional","year":2005,"lang":"fr","type":"other","venue":"EspaceINRS (National Institute for Scientific Research (Canada))","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Wage; Context (archaeology); Compensation of employees; Frugality","score_opus":0.019544353836475986,"score_gpt":0.28263270150478087,"score_spread":0.2630883476683049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986141266","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":[0.38853654,0.006918646,0.029529557,0.09954941,0.013156807,0.00874088,0.025573878,0.00016859762,0.4278257],"genre_scores_gemma":[0.33081296,0.00019595545,0.017103555,0.00069562736,0.0022699034,0.00044410359,0.012096822,0.00028740236,0.6360937],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99240834,0.0004965929,0.0008107849,0.0013162552,0.0032993434,0.0016686894],"domain_scores_gemma":[0.9959781,0.00026925167,0.00034350355,0.00090096274,0.0017887633,0.0007194037],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0041015167,0.00065616873,0.0004992322,0.00043444193,0.0013639312,0.0005478289,0.0015847347,0.00064576615,0.002480114],"category_scores_gemma":[0.002482613,0.00069293677,0.0002989827,0.00073600764,0.0020292115,0.00007751149,0.00057069695,0.0010840471,0.00005908852],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029211846,0.0006864203,0.0016722002,0.0008818842,0.0008057362,0.000071391965,0.0008149119,0.16481051,0.026688486,0.14543997,0.6516876,0.006148791],"study_design_scores_gemma":[0.0011411479,0.00018943773,0.0014978959,0.000117085096,0.000030278128,0.00009527624,0.00035219055,0.05107755,0.005780055,0.00025966225,0.93878317,0.00067622575],"about_ca_topic_score_codex":0.28769332,"about_ca_topic_score_gemma":0.9896816,"teacher_disagreement_score":0.7019883,"about_ca_system_score_codex":0.002071916,"about_ca_system_score_gemma":0.02782518,"threshold_uncertainty_score":0.99993616},"labels":[],"label_agreement":null},{"id":"W6986146631","doi":"","title":"Objectif Numérique S01 E34 Adieu, Photos Floues et Sony A58","year":2013,"lang":"fr","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pixel; Reflection (computer programming)","score_opus":0.0035796255253060507,"score_gpt":0.19228421975342855,"score_spread":0.1887045942281225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986146631","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":[0.0018039381,0.001154914,0.000019854264,0.00051482563,0.0007606093,0.0011039494,0.00022360777,0.00009715536,0.99432117],"genre_scores_gemma":[0.0060459836,0.0015802642,0.0058245757,0.0015375977,0.00043928565,0.0000693645,0.0010774069,0.00019013906,0.98323536],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99655133,0.00030048535,0.0014451703,0.00043529595,0.0005274628,0.00074025744],"domain_scores_gemma":[0.99681664,0.00013387186,0.0013470089,0.0009430516,0.00045673392,0.000302699],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005332441,0.0008769622,0.00078076334,0.00010604076,0.00016012581,0.000188385,0.0007736965,0.0014825325,0.45883554],"category_scores_gemma":[0.000633625,0.0008872397,0.0004345134,0.000015709686,0.00037064872,2.0126609e-7,0.00039272165,0.0008619178,0.032121576],"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":[0.00012439599,0.000113552705,0.000042800588,0.0014596874,0.00027871892,0.00000969676,0.0007046589,0.0018644101,0.000063365864,0.00022175608,0.99091613,0.0042008446],"study_design_scores_gemma":[0.00086788886,0.00066437054,0.000052834905,0.00042462038,0.000072041694,0.00026600334,0.00039098403,0.00075777253,0.0007285597,0.00000999243,0.9948477,0.0009171881],"about_ca_topic_score_codex":0.0043416317,"about_ca_topic_score_gemma":0.0023038122,"teacher_disagreement_score":0.42671397,"about_ca_system_score_codex":0.00007888811,"about_ca_system_score_gemma":0.00017007258,"threshold_uncertainty_score":0.99981374},"labels":[],"label_agreement":null},{"id":"W6986170839","doi":"","title":"Optimiser les serres pour augmenter l’autonomie alimentaire du Québec","year":2022,"lang":"fr","type":"other","venue":"Espace ÉTS (ETS)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Quality (philosophy); Work (physics); Sustainability; Adaptability","score_opus":0.006291435327414317,"score_gpt":0.23407556659566242,"score_spread":0.2277841312682481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986170839","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":[0.036272638,0.011944331,0.0017749347,0.04579775,0.002243961,0.0013667503,0.00035615143,0.00018266818,0.90006083],"genre_scores_gemma":[0.033052213,0.0007286585,0.0057031573,0.003401344,0.001334477,0.00012562185,0.0009304966,0.00046504298,0.954259],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99742943,0.00027817299,0.00053071656,0.0007401666,0.00033221598,0.0006893219],"domain_scores_gemma":[0.9980537,0.000055193585,0.00056858454,0.0010233186,0.000059665836,0.00023952537],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00029884014,0.00079502154,0.00053756486,0.00015070516,0.0003717711,0.0001269185,0.0008470698,0.0006381175,0.10919312],"category_scores_gemma":[0.00014436766,0.0008161726,0.000389531,0.00010154693,0.00026110237,0.00001075798,0.0010742901,0.00071281247,0.0015041286],"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":[0.00026531317,0.0004610571,0.03823019,0.0006107806,0.001488825,0.00007814898,0.0011997023,0.009359053,0.0039745555,0.0014767785,0.9269111,0.015944468],"study_design_scores_gemma":[0.0010743585,0.00030917273,0.0009093554,0.00009072452,0.00021430741,0.00008138421,0.00071676535,0.0025624293,0.0017472222,0.000005647587,0.99143034,0.00085830595],"about_ca_topic_score_codex":0.0034686807,"about_ca_topic_score_gemma":0.008056898,"teacher_disagreement_score":0.107688986,"about_ca_system_score_codex":0.0004556229,"about_ca_system_score_gemma":0.0008527507,"threshold_uncertainty_score":0.9994289},"labels":[],"label_agreement":null},{"id":"W6986180806","doi":"","title":"Ontario Bird Records Committee Report for 2002","year":2024,"lang":"en","type":"article","venue":"Digital Commons - University of South Florida (University of South Florida)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.0129414809975284,"score_gpt":0.20180368457665177,"score_spread":0.18886220357912337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986180806","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91056085,0.00011661449,0.05746713,0.00025338074,0.0007479344,0.00046430065,0.0011503565,0.00016483678,0.02907463],"genre_scores_gemma":[0.9714944,0.000012277033,0.004274966,0.000016948716,0.00012727376,1.716056e-7,0.0006229995,0.000042290572,0.023408705],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984422,0.000031690706,0.00029193866,0.00049699616,0.0003493667,0.0003878281],"domain_scores_gemma":[0.9983672,0.0000649592,0.00033062903,0.0007387394,0.00029823082,0.00020024339],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002717629,0.00031040295,0.00045979462,0.0002789094,0.00034833746,0.00006228049,0.00079360494,0.0003084008,0.00019016844],"category_scores_gemma":[0.00008333635,0.00041514495,0.0005254587,0.00031800906,0.00048498446,0.00009736718,0.00056351227,0.000361419,0.00011053803],"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":[0.0063582794,0.00065544347,0.74600273,0.0034352778,0.005104731,0.0013581282,0.10890626,0.0025293045,0.0027193702,0.00494855,0.101988584,0.015993357],"study_design_scores_gemma":[0.003178868,0.0014025507,0.023638131,0.0003645092,0.0005663316,0.00010955914,0.034676306,0.0033928547,0.00043230507,0.00020327802,0.9306617,0.0013736173],"about_ca_topic_score_codex":0.0016852029,"about_ca_topic_score_gemma":0.004387918,"teacher_disagreement_score":0.8286731,"about_ca_system_score_codex":0.00011105707,"about_ca_system_score_gemma":0.0003784911,"threshold_uncertainty_score":0.99983007},"labels":[],"label_agreement":null},{"id":"W6986181180","doi":"","title":"Onomástica y sociedad en la epigrafía antigua de las provincias de Salamanca y Ávila","year":2010,"lang":"es","type":"article","venue":"Gredos (University of Salamanca)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Quarter (Canadian coin); Metropolitan area; Period (music)","score_opus":0.002052915770477187,"score_gpt":0.20366595326452233,"score_spread":0.20161303749404513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986181180","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9787046,0.00014952618,0.004315292,0.0010180308,0.0002136698,0.00028902132,0.00010444447,0.00006393384,0.015141523],"genre_scores_gemma":[0.9705702,0.00045622364,0.02597088,0.00012441492,0.00028279482,7.7256556e-7,0.0001113384,0.00004771902,0.0024356663],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99811184,0.00021477287,0.000278894,0.00045215068,0.00027163103,0.0006707341],"domain_scores_gemma":[0.9983805,0.00012024514,0.0003561383,0.0007088247,0.00016225237,0.0002720499],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007892846,0.00036791497,0.00042247266,0.00014744728,0.00031046238,0.00006708429,0.00086366304,0.00094266824,0.00020588296],"category_scores_gemma":[0.0003126334,0.0004745672,0.0003186072,0.0001861406,0.00069892674,0.000033191478,0.00052674994,0.0009304367,0.000077370656],"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":[0.00055566384,0.0007676171,0.42202064,0.0020607829,0.0009814977,0.0002264596,0.009505141,0.0005355642,0.50452304,0.012595875,0.018455017,0.027772712],"study_design_scores_gemma":[0.0035136333,0.0009413696,0.6551601,0.00032191406,0.00060203247,0.000283882,0.0035028423,0.030637773,0.01480975,0.00039182094,0.2882829,0.001551959],"about_ca_topic_score_codex":0.0002508992,"about_ca_topic_score_gemma":0.00034094419,"teacher_disagreement_score":0.48971325,"about_ca_system_score_codex":0.00007646423,"about_ca_system_score_gemma":0.00070061453,"threshold_uncertainty_score":0.9997706},"labels":[],"label_agreement":null},{"id":"W6986189392","doi":"","title":"Oral History Interview with Alva Hudson, December 26, 2007","year":2007,"lang":"en","type":"article","venue":"The Portal to Texas History (University of North Texas)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Oral history; Navy; Duty; Nova scotia; World War II","score_opus":0.014510049122813664,"score_gpt":0.21314201613780234,"score_spread":0.19863196701498867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986189392","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9073384,0.001398448,0.013280354,0.00028443846,0.00056625257,0.00042163767,0.000015521005,0.00008479126,0.07661019],"genre_scores_gemma":[0.9267596,0.000083932195,0.007621062,0.002209191,0.00014228337,4.1355776e-7,0.00011076083,0.000066490094,0.063006274],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99880356,0.000069989095,0.00023115856,0.00028235198,0.00027779845,0.000335134],"domain_scores_gemma":[0.99871004,0.000019389607,0.0002923414,0.00063716073,0.00015059228,0.0001904622],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005517713,0.00022493358,0.0002500703,0.00011628402,0.00009440146,0.0000031124962,0.0006615479,0.00011033646,0.0011173654],"category_scores_gemma":[0.000034301316,0.0002064541,0.00013985808,0.00011018801,0.00038933154,0.000017214288,0.00024831493,0.0002446286,0.00023402514],"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":[0.00070030004,0.00022183605,0.18885645,0.00015981634,0.0003127977,0.00012861118,0.0015774793,0.00038331596,0.0002628323,0.00026857943,0.79697794,0.010150068],"study_design_scores_gemma":[0.00034882975,0.00032280796,0.19628032,0.00002098629,0.00006657832,0.000036385896,0.000092968316,0.000035799345,0.00004275068,0.0000014549408,0.80251265,0.00023846797],"about_ca_topic_score_codex":0.00029088868,"about_ca_topic_score_gemma":0.008332845,"teacher_disagreement_score":0.019421225,"about_ca_system_score_codex":0.00026660858,"about_ca_system_score_gemma":0.00020114973,"threshold_uncertainty_score":0.99979573},"labels":[],"label_agreement":null},{"id":"W6986190935","doi":"","title":"online love vashikaran specialist +91-9116799099","year":2021,"lang":"en","type":"other","venue":"OSF Preprints (OSF Preprints)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bengali; MAGIC (telescope); Cheating; Kali; Phone","score_opus":0.01026323146235286,"score_gpt":0.2683170457752113,"score_spread":0.25805381431285845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986190935","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":[0.0011312031,0.000033628898,0.0016561962,0.00020196187,0.0007988041,0.0006794024,0.0002100458,0.00010118256,0.9951876],"genre_scores_gemma":[0.0005867628,0.0007685616,0.007343431,0.0004887118,0.0014500119,0.000031039654,0.0023699575,0.0004926884,0.98646885],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955798,0.00046145718,0.00072456815,0.0021680854,0.00048083605,0.00058527157],"domain_scores_gemma":[0.9935505,0.00006346763,0.0006367288,0.0053469,0.00013175477,0.00027066385],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012731277,0.00068633707,0.0006866588,0.00018863178,0.00007455545,0.00013617815,0.001514087,0.0011083598,0.7276562],"category_scores_gemma":[0.002077842,0.00077838765,0.00042592353,0.00018207014,0.00024204263,0.000006104382,0.002335848,0.00085776666,0.4868925],"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":[0.000057544356,0.00045456074,0.002165385,0.00045904992,0.00058255927,0.00004113247,0.00020578034,0.00023741595,0.008284192,0.0002034133,0.9815551,0.0057538464],"study_design_scores_gemma":[0.00057723635,0.000002849649,0.0011053134,0.00024158126,0.00009168479,0.00007023115,0.000068856585,0.0001622284,0.004469664,0.00007532074,0.9923781,0.0007568917],"about_ca_topic_score_codex":0.00027360368,"about_ca_topic_score_gemma":0.00069481565,"teacher_disagreement_score":0.24076371,"about_ca_system_score_codex":0.000098705175,"about_ca_system_score_gemma":0.00032088757,"threshold_uncertainty_score":0.9994667},"labels":[],"label_agreement":null},{"id":"W6986205884","doi":"","title":"Outside the Box [HD video]","year":2015,"lang":"en","type":"other","venue":"Research Output (Edinburgh Napier University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Jazz; Depiction; Portrait; Blues; Studio; Exhibition","score_opus":0.038410729420264134,"score_gpt":0.30709332211340856,"score_spread":0.26868259269314443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986205884","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":[0.00011962079,0.0012135325,0.00064004847,0.0007394672,0.0003350864,0.0005716249,0.00011458808,0.000092356546,0.9961737],"genre_scores_gemma":[0.001199452,0.00093115924,0.00057785027,0.00013346512,0.0011435996,0.0000030870829,0.00033712763,0.00022137498,0.9954529],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99707866,0.00037847355,0.0002026076,0.0005289146,0.0010436057,0.0007677307],"domain_scores_gemma":[0.99780196,0.000081348095,0.00017751672,0.0012288286,0.0003894957,0.000320879],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015711855,0.00034985997,0.00031353248,0.0007463581,0.00025584677,0.000087441884,0.0015484961,0.00069154886,0.0010374554],"category_scores_gemma":[0.0005834562,0.00028633073,0.00016659059,0.0006941781,0.000588537,0.000007603046,0.0012502804,0.0011216198,0.00032947987],"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":[0.00006312804,0.00003103442,0.00015197312,0.000034418823,0.00020305901,0.00004018494,0.00015359765,0.000020216843,0.00017566976,0.00022093342,0.99784315,0.0010626556],"study_design_scores_gemma":[0.0005706956,0.00019899507,0.000012894567,0.00007299718,0.00003557389,0.000011741619,0.00047648602,0.000076260934,0.0001617385,0.00003952545,0.9980175,0.00032562276],"about_ca_topic_score_codex":0.00033478034,"about_ca_topic_score_gemma":0.00026745757,"teacher_disagreement_score":0.0010798313,"about_ca_system_score_codex":0.00014209386,"about_ca_system_score_gemma":0.0007056665,"threshold_uncertainty_score":0.9999589},"labels":[],"label_agreement":null},{"id":"W6986206797","doi":"","title":"The parisien block of flats in \"Pot-bouille\" of Emile Zola and \"Passage de Milan\" of Michel Butor : from the \"chronotope\" to the mythology","year":2008,"lang":"en","type":"other","venue":"OpenGrey (Institut de l'Information Scientifique et Technique)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Block (permutation group theory); Mythology; Quarter (Canadian coin)","score_opus":0.008235149601779072,"score_gpt":0.2612748718276717,"score_spread":0.2530397222258926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986206797","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17595321,0.0042367144,0.12245562,0.007017981,0.0014747507,0.029372947,0.0033020275,0.00020383479,0.6559829],"genre_scores_gemma":[0.73736495,0.011132657,0.14614671,0.008075074,0.00054125313,0.003315508,0.002631006,0.00048841187,0.0903044],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982258,0.00025271781,0.0007653638,0.00019897099,0.00028267127,0.00027446568],"domain_scores_gemma":[0.9979281,0.000121620906,0.00079756876,0.0009330418,0.00016038555,0.000059316702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023163243,0.00023605452,0.00032408288,0.0001616149,0.00013463461,0.000057112382,0.001031281,0.00041651836,0.0000323465],"category_scores_gemma":[0.00085495017,0.00014539677,0.000094049195,0.00027009222,0.0005217902,0.000027859916,0.00048736832,0.00036453237,0.0000072435605],"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":[0.00014415963,0.00007041841,0.0034799178,0.00048419402,0.00014276453,0.000002514033,0.006653204,0.0009639865,0.03664599,0.0011906468,0.93233424,0.017887956],"study_design_scores_gemma":[0.0002997276,0.00006388096,0.0020430028,0.0003270484,0.000019245585,0.00002267713,0.00019928871,0.00052086485,0.054920185,0.000036176305,0.9413619,0.0001860248],"about_ca_topic_score_codex":0.00091790163,"about_ca_topic_score_gemma":0.0013909631,"teacher_disagreement_score":0.56567854,"about_ca_system_score_codex":0.000038766924,"about_ca_system_score_gemma":0.0004092119,"threshold_uncertainty_score":0.5929108},"labels":[],"label_agreement":null},{"id":"W6986211472","doi":"","title":"Pandemic Pals: Vancouver (w/ Charlie Demers + David Harris)","year":2020,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Conversation; Pandemic; Mental illness; Panic; Mental health; Coronavirus disease 2019 (COVID-19)","score_opus":0.005571690912159602,"score_gpt":0.196728470658818,"score_spread":0.1911567797466584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986211472","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":[0.00005524899,0.00048001634,0.00000839642,0.000082949744,0.00046278356,0.00039999085,0.00020163367,0.00013715168,0.9981718],"genre_scores_gemma":[0.00067605067,0.0008639223,0.002626292,0.001095276,0.00035799705,0.000017407263,0.000843424,0.00018700649,0.9933326],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982184,0.000076244265,0.0007121019,0.0002685606,0.0003811719,0.00034349333],"domain_scores_gemma":[0.99840677,0.000028644094,0.0007977988,0.0005008874,0.00008942848,0.00017649357],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00019757255,0.00044327058,0.000439632,0.00005209552,0.000058503156,0.000036923455,0.0004973714,0.0006757779,0.17503205],"category_scores_gemma":[0.00027144185,0.0004415039,0.00021854305,0.000007918985,0.00013691676,3.775751e-8,0.00021568501,0.00038961376,0.006592185],"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":[0.00007798464,0.000020403924,0.000040117782,0.0005187263,0.00014631322,0.0000045387505,0.00008388402,0.00018268722,0.000009866294,0.000003815848,0.99676377,0.0021479195],"study_design_scores_gemma":[0.00058351445,0.0002179704,0.000011166016,0.00012650086,0.00006838051,0.000028149709,0.00007591182,0.00006496188,0.000056518908,0.0000017378587,0.9982984,0.00046677448],"about_ca_topic_score_codex":0.0008727434,"about_ca_topic_score_gemma":0.0012015239,"teacher_disagreement_score":0.16843987,"about_ca_system_score_codex":0.000023714478,"about_ca_system_score_gemma":0.000059033824,"threshold_uncertainty_score":0.99980366},"labels":[],"label_agreement":null},{"id":"W6986232245","doi":"","title":"The oficial web site of The International Olympic Committe - Cartão postal","year":2012,"lang":"pt","type":"other","venue":"Lume (Universidade Federal do Rio Grande do Sul)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Web site; The Internet; Public access; Information system; Quarter (Canadian coin)","score_opus":0.00450199290215498,"score_gpt":0.20953581504033644,"score_spread":0.20503382213818147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986232245","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4302018,0.0046841395,0.0003428853,0.006067232,0.0073441574,0.0015617168,0.001505761,0.00007276386,0.54821956],"genre_scores_gemma":[0.7799382,0.0006383851,0.00010697036,0.00035837898,0.0008942672,0.0000051006346,0.0005277701,0.00015060947,0.21738029],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973576,0.0002863377,0.0005275853,0.00045246672,0.0007002917,0.0006757027],"domain_scores_gemma":[0.997612,0.00007602176,0.0008972191,0.0010531323,0.00018903958,0.00017257911],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00039363536,0.00060137233,0.00048164875,0.00014815731,0.00085172214,0.0003255627,0.0016288228,0.00080778525,0.0018308706],"category_scores_gemma":[0.000108283435,0.0004451078,0.0006609229,0.00021971088,0.0006085698,0.000026500446,0.0010587377,0.0008260897,0.00017816748],"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":[0.0037918005,0.001039495,0.2523787,0.0012923406,0.007814394,0.000058908383,0.012413136,0.0005407878,0.076988384,0.014752634,0.5856989,0.04323048],"study_design_scores_gemma":[0.0025209251,0.00019621791,0.009947741,0.00021216352,0.00022101628,0.00006198532,0.0013507114,0.00081197976,0.00067533203,0.000047825848,0.98325664,0.0006974497],"about_ca_topic_score_codex":0.00035106033,"about_ca_topic_score_gemma":0.0014518991,"teacher_disagreement_score":0.39755774,"about_ca_system_score_codex":0.000112088856,"about_ca_system_score_gemma":0.0002795534,"threshold_uncertainty_score":0.9998001},"labels":[],"label_agreement":null},{"id":"W6986236417","doi":"","title":"Oxygénation des lits capillaires à la papille optique des patients sains et glaucomateux","year":2013,"lang":"fr","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Congenital disease; Central nervous system disease; Medical screening; Computed tomography","score_opus":0.002300692938633739,"score_gpt":0.15004688965729046,"score_spread":0.1477461967186567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986236417","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24131061,0.0018280265,0.00027420282,0.0007777714,0.000212965,0.00035821108,0.0004059731,0.00001043673,0.7548218],"genre_scores_gemma":[0.6773712,0.005683423,0.013105664,0.0015819262,0.00016067667,0.000029142991,0.00039145548,0.00018129885,0.3014952],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977526,0.00024771754,0.00042307738,0.00031450175,0.00086377014,0.00039834777],"domain_scores_gemma":[0.9988912,0.00013860739,0.00038853314,0.00029069572,0.0000033589963,0.00028765626],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000023922708,0.00041073037,0.00033356,0.000033451073,0.00019935332,0.000061180224,0.00031835816,0.0001774928,0.0003488702],"category_scores_gemma":[0.000033410943,0.00039764002,0.00005547579,0.000053224394,0.00034690707,0.000049249753,0.00032771094,0.00022534921,5.044939e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005641444,0.0003683402,0.5349198,0.0061756833,0.0011959431,0.00005889916,0.001546193,0.0007812102,0.032911897,0.20173366,0.034125283,0.18561897],"study_design_scores_gemma":[0.00086157967,0.00037618625,0.2519528,0.00090545026,0.000059040955,0.000015575548,0.000994117,0.0033016338,0.031902723,0.00089805847,0.7078951,0.0008377311],"about_ca_topic_score_codex":0.0072222305,"about_ca_topic_score_gemma":0.11050798,"teacher_disagreement_score":0.67376983,"about_ca_system_score_codex":0.000019504554,"about_ca_system_score_gemma":0.0015546057,"threshold_uncertainty_score":0.99984753},"labels":[],"label_agreement":null},{"id":"W6986270018","doi":"","title":"Patient/user perceptions on the principles of integration","year":2016,"lang":"en","type":"other","venue":"Lume (Universidade Federal do Rio Grande do Sul)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Focus group; Variety (cybernetics); Perception; Health care; Corporate governance; Perspective (graphical); Qualitative property; Population; Qualitative research","score_opus":0.006955931646362689,"score_gpt":0.22499906071827083,"score_spread":0.21804312907190815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986270018","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":[0.0282921,0.00016686266,0.002358248,0.0008050876,0.00034980176,0.00065124565,0.0002531684,0.00006814979,0.9670553],"genre_scores_gemma":[0.22993757,0.00050594565,0.00096201757,0.00032238237,0.00031412224,0.000015706924,0.0005391333,0.00022369764,0.7671794],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99890745,0.000115651834,0.00021552278,0.00028597112,0.00024850635,0.00022688981],"domain_scores_gemma":[0.998932,0.000025942996,0.00034631422,0.0005649464,0.000066715285,0.00006407789],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009629789,0.0002948884,0.00023379589,0.00015736115,0.00017370304,0.00006828504,0.00034221238,0.00041173803,0.0030295379],"category_scores_gemma":[0.000067644396,0.00019732067,0.00020761175,0.000079895864,0.00017394734,0.0000073147435,0.00013935451,0.00026621946,0.00017190655],"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":[0.0003816844,0.00020127819,0.002137708,0.00023226406,0.0005876091,0.0000070967103,0.002042869,0.000077611185,0.021160774,0.02994811,0.92629063,0.016932381],"study_design_scores_gemma":[0.0007059846,0.000320491,0.0010194381,0.00033844818,0.00004112843,0.0000070475126,0.0008957259,0.00004774136,0.0008362521,0.00007634698,0.9953447,0.00036667092],"about_ca_topic_score_codex":0.00009563174,"about_ca_topic_score_gemma":0.00029900396,"teacher_disagreement_score":0.20164546,"about_ca_system_score_codex":0.00003551309,"about_ca_system_score_gemma":0.000053299897,"threshold_uncertainty_score":0.9978818},"labels":[],"label_agreement":null},{"id":"W6986274613","doi":"","title":"Parasitosis intestinal en estudiantes del nivel primario de Huancayo al 2014","year":2014,"lang":"en","type":"article","venue":"Dialnet (Universidad de la Rioja)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Statistical significance; Quarter (Canadian coin); Test (biology); Statistical analysis; Parasitism; Descriptive statistics; Significant difference; Rural area","score_opus":0.003620985680980977,"score_gpt":0.24130065709591622,"score_spread":0.23767967141493523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986274613","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9278142,0.00010505458,0.048758168,0.00074063207,0.00010740879,0.0001328513,0.000012338021,0.00006208829,0.022267286],"genre_scores_gemma":[0.96903276,0.000109952765,0.028562192,0.0010953364,0.00023253508,0.0000061139913,0.00010855787,0.000034089262,0.00081846333],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987027,0.00027855573,0.00016617676,0.00028057533,0.00015426731,0.0004177158],"domain_scores_gemma":[0.99906164,0.0001959244,0.00014188504,0.000361456,0.000066816654,0.00017228693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005584542,0.0002212847,0.00019823315,0.00010063945,0.00016054921,0.000053784104,0.0004183054,0.00024774455,0.0000533122],"category_scores_gemma":[0.00054996414,0.00024401669,0.000118318545,0.00011450982,0.00017129724,0.000014930033,0.00023061938,0.00030846582,0.00007774476],"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":[0.00031045973,0.000245038,0.705176,0.00012605233,0.0002949959,0.000051467105,0.0023836696,0.00221139,0.14865004,0.0076668584,0.10827318,0.024610829],"study_design_scores_gemma":[0.0023661258,0.0007609574,0.62766594,0.000075065356,0.00014944354,0.0002292428,0.0006830287,0.023613568,0.011518067,0.00052007433,0.33146477,0.0009537284],"about_ca_topic_score_codex":0.00027361652,"about_ca_topic_score_gemma":0.00010213218,"teacher_disagreement_score":0.22319159,"about_ca_system_score_codex":0.00007969552,"about_ca_system_score_gemma":0.00018372163,"threshold_uncertainty_score":0.9950712},"labels":[],"label_agreement":null},{"id":"W6986289512","doi":"","title":"Performance measures. 2019: Quarter 4 (2019: Oct. 1 - 2019: Dec. 31)","year":2017,"lang":"en","type":"article","venue":"State Elections Enforcement Commission (State of Connecticut)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Index (typography); Head (geology); Table (database)","score_opus":0.009917048694765526,"score_gpt":0.27130522001923774,"score_spread":0.26138817132447223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986289512","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76436716,0.0006046778,0.043831818,0.0011265237,0.0020364227,0.0015920987,0.00019977723,0.00018583314,0.1860557],"genre_scores_gemma":[0.9537917,0.0010176802,0.0013685772,0.00013165013,0.00011001699,0.000035178964,0.00024586968,0.000053123455,0.043246254],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975904,0.00010253551,0.0007964702,0.00041258993,0.0004862025,0.00061175483],"domain_scores_gemma":[0.9969472,0.000048415077,0.00080417196,0.0014668531,0.00047175522,0.00026155412],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006902962,0.00040319416,0.00037328232,0.00019132315,0.0011218966,0.00017321615,0.00075739546,0.00014386475,0.00025573734],"category_scores_gemma":[0.00042119596,0.0003668817,0.00018213697,0.0001263823,0.00023534744,0.000068961206,0.00024838475,0.00032061202,0.00009285141],"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":[0.0015247292,0.00052278413,0.014936438,0.00033844868,0.000866176,0.0000075860394,0.0013384583,0.018663533,0.14791745,0.0005118751,0.7095652,0.103807285],"study_design_scores_gemma":[0.002466238,0.0021305552,0.00876368,0.00015254934,0.00009683922,0.00006164838,0.00012248092,0.011348873,0.15637502,0.00022126723,0.8173899,0.0008709632],"about_ca_topic_score_codex":0.00032194876,"about_ca_topic_score_gemma":0.000139263,"teacher_disagreement_score":0.1894245,"about_ca_system_score_codex":0.000071361814,"about_ca_system_score_gemma":0.0002922892,"threshold_uncertainty_score":0.9998783},"labels":[],"label_agreement":null},{"id":"W6986322945","doi":"","title":"Paysage I and II (Countryside)","year":2020,"lang":"en","type":"article","venue":"Bryant Digital Repository (Bryant University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Painting; Sculpture; The arts; Center (category theory); Class (philosophy)","score_opus":0.005076326352583133,"score_gpt":0.16795737046858147,"score_spread":0.16288104411599835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986322945","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9056255,0.000129222,0.0013212409,0.00024117192,0.000109325054,0.00014123526,0.000040402127,0.000079920115,0.09231193],"genre_scores_gemma":[0.9901888,0.00005448258,0.0002915537,0.00029340974,0.00016363492,2.8689684e-7,0.000052743762,0.000019174206,0.008935907],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911976,0.000025505804,0.00016477676,0.00031922656,0.00015197693,0.0002187708],"domain_scores_gemma":[0.99937373,0.000013701389,0.00010778627,0.0002268218,0.000056419733,0.00022153338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000028364613,0.00018098528,0.00015019036,0.00005000549,0.0002355893,0.00010555511,0.00023881906,0.000121187324,0.000005833062],"category_scores_gemma":[0.00008976924,0.00018765476,0.00007882973,0.00014136362,0.00012482885,0.00003837414,0.00046662078,0.00013678781,0.000012734757],"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":[0.0017445498,0.0005083323,0.19481942,0.00062698737,0.0008867379,0.001705374,0.0026915767,0.00087879715,0.7354842,0.007636009,0.03614857,0.01686944],"study_design_scores_gemma":[0.0012794671,0.0009822474,0.0058297003,0.00003909146,0.00006579445,0.0002539569,0.00074766966,0.0017035629,0.024976095,0.000019235064,0.96339667,0.0007065319],"about_ca_topic_score_codex":0.000008711488,"about_ca_topic_score_gemma":0.0000019660467,"teacher_disagreement_score":0.92724806,"about_ca_system_score_codex":0.000018622532,"about_ca_system_score_gemma":0.000068847105,"threshold_uncertainty_score":0.76523393},"labels":[],"label_agreement":null},{"id":"W6986338569","doi":"","title":"In permanent transit: discourses and maps of the intercultural experience","year":2012,"lang":"en","type":"book","venue":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"H2020 European Research Council","keywords":"Narrative; Ethnography; Agency (philosophy); Work (physics); Qualitative research; Identity (music); Field (mathematics)","score_opus":0.03502184245117839,"score_gpt":0.3672477875919453,"score_spread":0.3322259451407669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986338569","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79200476,0.026575323,0.00028531757,0.0046449276,0.0011966602,0.0068227053,0.0018198505,0.00009477692,0.16655566],"genre_scores_gemma":[0.87202805,0.0018982047,0.000733403,0.00005297719,0.00015180133,0.00032343186,0.00033935526,0.000031650114,0.12444113],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99774957,0.000039007395,0.00037581354,0.00046574476,0.00080559595,0.0005642629],"domain_scores_gemma":[0.9988928,0.00006767383,0.00018174302,0.0002708544,0.0005120423,0.0000748881],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0018932609,0.00020846886,0.0002194066,0.0008241232,0.00036482405,0.000042124564,0.00078185066,0.00035166912,0.0000064971273],"category_scores_gemma":[0.0009902841,0.00014743042,0.0000543855,0.0006388701,0.0032445474,0.000046533096,0.00055460865,0.00056370173,8.7351765e-7],"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":[0.0006691388,0.0010645727,0.034037404,0.0031692926,0.00039414509,0.000014833439,0.01571439,0.000014128551,0.41128024,0.23074347,0.22337773,0.07952064],"study_design_scores_gemma":[0.0032482368,0.0040186937,0.0073823608,0.0015161168,0.000086968386,0.00078514137,0.005266565,0.0015006461,0.11077443,0.05945285,0.80348766,0.0024803348],"about_ca_topic_score_codex":0.000016485594,"about_ca_topic_score_gemma":0.000025590014,"teacher_disagreement_score":0.58010995,"about_ca_system_score_codex":0.00011520527,"about_ca_system_score_gemma":0.00090356136,"threshold_uncertainty_score":0.999468},"labels":[],"label_agreement":null},{"id":"W6986363188","doi":"","title":"Pianonsoiton diskursiivis-materiaalisia kytkentöjä rakentamassa","year":2012,"lang":"fi","type":"article","venue":"Jyväskylä University Digital Archive (University of Jyväskylä)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Musée de la Civilisation","funders":"","keywords":"Accreditation; Polish","score_opus":0.004936016825154133,"score_gpt":0.17900962986575417,"score_spread":0.17407361304060004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986363188","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83925873,0.0004371071,0.026274538,0.000704815,0.0010652809,0.0008436483,0.004289008,0.00014305091,0.12698384],"genre_scores_gemma":[0.97193074,0.00066068035,0.0045447494,0.00009561183,0.00032340238,1.5479212e-7,0.0022306766,0.00007290275,0.020141087],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99640816,0.00035122936,0.00045154072,0.00077686994,0.00065982196,0.001352381],"domain_scores_gemma":[0.9967659,0.0001497726,0.0008272395,0.0011273527,0.00023151233,0.00089820503],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032680383,0.00076231884,0.00083945965,0.00046712137,0.0006964714,0.00013050798,0.0016053213,0.0005406877,0.00055067084],"category_scores_gemma":[0.00014646554,0.0010229606,0.00082093506,0.00052751997,0.0013671416,0.00042770483,0.0021512022,0.00048945966,0.000532085],"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":[0.014814971,0.009655632,0.51845366,0.004446089,0.0080694305,0.0006855563,0.036653228,0.0011493136,0.13264783,0.035342332,0.15863033,0.07945161],"study_design_scores_gemma":[0.0051920856,0.0011816144,0.05947799,0.00033072932,0.00066068454,0.00012885945,0.01892657,0.0010126352,0.0016335002,0.00019300621,0.90931517,0.0019471562],"about_ca_topic_score_codex":0.0003204384,"about_ca_topic_score_gemma":0.00011631224,"teacher_disagreement_score":0.75068486,"about_ca_system_score_codex":0.00023081884,"about_ca_system_score_gemma":0.00028315934,"threshold_uncertainty_score":0.9992221},"labels":[],"label_agreement":null},{"id":"W6986374827","doi":"","title":"P.K. Page and Pablo Neruda: an intertextual and metapoetical dialogue","year":2009,"lang":"en","type":"article","venue":"Redalyc (Universidad Autónoma del Estado de México)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Intertextuality; Praise; Theme (computing); Poetry; Creativity; Ode","score_opus":0.009133490393398166,"score_gpt":0.2395681379118985,"score_spread":0.23043464751850032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986374827","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98615104,0.00039384124,0.008077193,0.00060378143,0.000048892765,0.00013941451,0.000019399311,0.00005237288,0.0045140595],"genre_scores_gemma":[0.9904687,0.0002081905,0.007889175,0.0007058346,0.000098847646,0.0000016457451,0.00011066993,0.000021213242,0.0004957215],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9987725,0.0001270451,0.00020336676,0.0003813152,0.00013310916,0.0003826831],"domain_scores_gemma":[0.99915004,0.000028502722,0.00009359602,0.00038170558,0.000048738046,0.0002974047],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025625227,0.00025377178,0.00024273583,0.00012544355,0.00016392826,0.000091062146,0.00022891896,0.0002720438,0.000025959302],"category_scores_gemma":[0.000105992636,0.00025416823,0.000069301124,0.00012070494,0.00020695003,0.000036567213,0.00017810344,0.0002503403,0.00000692613],"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":[0.0011487085,0.00083974196,0.06090464,0.00026971332,0.0005790122,0.0005520175,0.007154881,0.0003153016,0.5328323,0.04649235,0.005605274,0.343306],"study_design_scores_gemma":[0.010930521,0.012380721,0.6312063,0.00021971065,0.0007705128,0.003411722,0.01104437,0.20292048,0.026732119,0.0052487464,0.09064776,0.0044870684],"about_ca_topic_score_codex":0.00004524046,"about_ca_topic_score_gemma":0.00004318394,"teacher_disagreement_score":0.57030165,"about_ca_system_score_codex":0.000030298794,"about_ca_system_score_gemma":0.00006899352,"threshold_uncertainty_score":0.99999106},"labels":[],"label_agreement":null},{"id":"W6986387084","doi":"","title":"2,565,000,000,000,000. A photoalbum","year":2018,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"nobody; Agora; Ice caps; Cube (algebra)","score_opus":0.004730326471366858,"score_gpt":0.2015966731005704,"score_spread":0.19686634662920352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986387084","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":[0.00038283595,0.00042705776,0.000009707592,0.000090155685,0.00065464625,0.0007018572,0.0009603812,0.00018502376,0.99658835],"genre_scores_gemma":[0.0013707851,0.0005225171,0.002979582,0.000885487,0.0007743408,0.000040865612,0.001556529,0.0002914118,0.99157846],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99696904,0.00013406207,0.0011441879,0.00043890323,0.0006376426,0.0006761768],"domain_scores_gemma":[0.9970717,0.0000487696,0.001199239,0.001129645,0.00029919122,0.00025147406],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00044458284,0.0007512364,0.0006678522,0.00015030097,0.00013781422,0.00011081429,0.0008969954,0.0012217473,0.3242839],"category_scores_gemma":[0.00037228013,0.00074315304,0.00032811312,0.000020487445,0.00036706508,1.1269418e-7,0.00038732844,0.00046591077,0.013471124],"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":[0.00015472909,0.00006708825,0.00003508119,0.00073374517,0.00018843125,0.000009131003,0.0001165783,0.000108757304,0.000024169549,0.000011849022,0.9970818,0.0014686264],"study_design_scores_gemma":[0.00089460885,0.0005603016,0.00002859867,0.00027261474,0.000098409946,0.00015373745,0.000080037025,0.000120023615,0.00036160857,0.000004877035,0.99662787,0.00079731864],"about_ca_topic_score_codex":0.0031465928,"about_ca_topic_score_gemma":0.00073817105,"teacher_disagreement_score":0.31081277,"about_ca_system_score_codex":0.00004461856,"about_ca_system_score_gemma":0.000059202597,"threshold_uncertainty_score":0.99950194},"labels":[],"label_agreement":null},{"id":"W6986387538","doi":"","title":"Performative production of homes as places for care, narrative experiences of people caring informally for seniors in Kingston, Ontario, Canada","year":2002,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Narrative; Performative utterance; Production (economics); Ethnography; Agency (philosophy); Performativity","score_opus":0.0018908400317586803,"score_gpt":0.15936856469118932,"score_spread":0.15747772465943063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986387538","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77366763,0.0005786827,0.000048022546,0.00015801364,0.0004749938,0.0010618037,0.0004224607,0.0000042361817,0.22358413],"genre_scores_gemma":[0.9323749,0.000097102056,0.0022514742,0.000086727036,0.00005337792,0.00007370052,0.00014251059,0.000051456394,0.06486878],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9986062,0.000024421017,0.00039135094,0.00017993277,0.0005887584,0.00020930315],"domain_scores_gemma":[0.99914104,0.000057435656,0.00057011755,0.00015841417,0.000004138734,0.0000688774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000016393557,0.00021598402,0.0003567502,0.000043952678,0.00007478912,0.0000060629172,0.0001933397,0.00006687544,0.000033649663],"category_scores_gemma":[0.000024474217,0.00020602142,0.000035810175,0.000046364905,0.000075080345,0.000026003874,0.00008185437,0.00010800126,2.2505546e-10],"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":[0.0068161986,0.00020259863,0.17905918,0.02899754,0.0019962403,0.000013755853,0.5316263,0.011277272,0.017106038,0.0038572922,0.20069924,0.018348368],"study_design_scores_gemma":[0.0012822739,0.00088945066,0.0069039688,0.00090233044,0.00005938699,0.000008838677,0.53993136,0.0012542248,0.24107791,0.0000195457,0.206871,0.00079973554],"about_ca_topic_score_codex":0.6858749,"about_ca_topic_score_gemma":0.9914572,"teacher_disagreement_score":0.3055823,"about_ca_system_score_codex":0.000021553482,"about_ca_system_score_gemma":0.003550069,"threshold_uncertainty_score":0.840131},"labels":[],"label_agreement":null},{"id":"W6986395340","doi":"","title":"Plantas e pessoas: um estudo de caso sobre redes sociais a partir da circulação e uso de plantas cultivadas por famílias indígenas Sateré-Mawé na cidade de Manaus","year":2016,"lang":"pt","type":"article","venue":"Americanae (AECID Library)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Statistical analysis; Social impact; Quarter (Canadian coin); Population; Work (physics)","score_opus":0.010082927519878195,"score_gpt":0.24992393899744975,"score_spread":0.23984101147757156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986395340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9841744,0.0014530936,0.004297239,0.004446376,0.00037328273,0.00062549015,0.0010451443,0.00024550347,0.0033395195],"genre_scores_gemma":[0.9778404,0.003540731,0.0064496114,0.0048150998,0.00073915214,0.000103917024,0.00087694294,0.00027171258,0.0053624227],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9942279,0.0007124856,0.0011242168,0.0011202899,0.00057197246,0.0022431589],"domain_scores_gemma":[0.9963766,0.0002481705,0.0010104658,0.0013243555,0.00007366531,0.0009667606],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004642308,0.0010741005,0.0009903186,0.00025468075,0.0005007603,0.00022761352,0.0014571234,0.00082929205,0.00049820315],"category_scores_gemma":[0.00040520486,0.0009292745,0.0005005665,0.0005033949,0.00079969154,0.0001392852,0.0008921108,0.0007588835,0.00021137959],"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":[0.0005053309,0.000327971,0.8290542,0.00033801762,0.0013416221,0.0006800515,0.0036622996,0.00008442109,0.05225887,0.00019168465,0.08293385,0.028621724],"study_design_scores_gemma":[0.005213263,0.0026822214,0.6051466,0.001077199,0.0010304374,0.0019218987,0.005215625,0.0024454156,0.1924129,0.00049575313,0.17768532,0.0046734023],"about_ca_topic_score_codex":0.005501714,"about_ca_topic_score_gemma":0.00013932797,"teacher_disagreement_score":0.22390759,"about_ca_system_score_codex":0.00034086933,"about_ca_system_score_gemma":0.0015063629,"threshold_uncertainty_score":0.9993158},"labels":[],"label_agreement":null},{"id":"W6986424317","doi":"","title":"Physical literacy and physical activity in swedish preschool children – a cross-sectional study","year":2023,"lang":"en","type":"article","venue":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Physical activity; Promotion (chess); Literacy; Health promotion; Early childhood; Public health; Cognition","score_opus":0.011425426350377873,"score_gpt":0.31903915793031273,"score_spread":0.3076137315799349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986424317","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9977251,0.000015086702,0.00027856923,0.0004303217,0.00009358034,0.0005798202,0.00034206035,0.00015416091,0.00038127883],"genre_scores_gemma":[0.9967021,0.000011549701,0.00087080925,0.000029056442,0.00014033595,0.00014354124,0.001859333,0.000016771388,0.00022649979],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99863917,0.000038930957,0.0002930491,0.0005032034,0.0002530729,0.00027255248],"domain_scores_gemma":[0.99876183,0.000014537811,0.00021448235,0.00077507255,0.00016068689,0.00007338391],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003066153,0.0002030856,0.00022517896,0.00041240742,0.00011902672,0.00008574659,0.00047569085,0.00015008677,0.0000070528276],"category_scores_gemma":[0.0009160665,0.00019962607,0.00005653854,0.0007660007,0.0003181147,0.00009559545,0.0008738923,0.00041229153,0.000021325537],"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":[0.00007615257,0.0010849447,0.98315126,0.000053124193,0.000061926476,0.000002672566,0.00008636594,0.00040119237,0.0072172806,0.001133784,0.0013431861,0.005388106],"study_design_scores_gemma":[0.0011911675,0.0002478018,0.9718148,0.00001532546,0.000015381911,0.000009508975,0.000022569067,0.016213888,0.00549635,0.0000711182,0.0046665766,0.00023551585],"about_ca_topic_score_codex":0.000091587106,"about_ca_topic_score_gemma":0.00002151044,"teacher_disagreement_score":0.015812695,"about_ca_system_score_codex":0.000022492575,"about_ca_system_score_gemma":0.00008247796,"threshold_uncertainty_score":0.81405145},"labels":[],"label_agreement":null},{"id":"W6986430593","doi":"","title":"Plan of a portion of the Town of Niagara shewing the lots adjoining Mississaugua Reserve which have been built upon, also the Lots which have been granted but not built upon.","year":2016,"lang":"en","type":"other","venue":"Brock University Digital Repository (Brock University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Plan (archaeology); Ravine; Guard (computer science); Master plan; Section (typography); Port (circuit theory); Point (geometry); Boundary (topology); Excavation; George (robot)","score_opus":0.01179893456516282,"score_gpt":0.21478623787893072,"score_spread":0.2029873033137679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986430593","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":[0.491986,0.000354746,0.0019984143,0.00013454688,0.00053669215,0.0016154054,0.0014024812,0.0001384763,0.5018332],"genre_scores_gemma":[0.43513834,0.000094332885,0.00007549921,0.000022977132,0.00012306619,3.483051e-7,0.00012845232,0.000095901,0.5643211],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973595,0.00031157304,0.0005852899,0.0005782385,0.00070917566,0.0004561796],"domain_scores_gemma":[0.9958063,0.00015856476,0.0017998386,0.0013807467,0.0007054215,0.00014915134],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00004105977,0.00053381146,0.00062357937,0.0003765637,0.00039814334,0.000054000306,0.0021823724,0.00071517687,0.000022239496],"category_scores_gemma":[0.00033683487,0.00038680056,0.00046863846,0.00046495043,0.00033977084,0.00007930146,0.0015744295,0.0005255741,0.0000041618705],"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":[0.0038419827,0.0006183591,0.13064635,0.0014578525,0.004165794,0.00008233537,0.00079619006,0.0017620699,0.36943287,0.00017173066,0.48585963,0.0011648454],"study_design_scores_gemma":[0.004383513,0.0011384616,0.024632785,0.002960406,0.001515649,0.00022284099,0.0155028375,0.00016059118,0.09470101,0.000029632074,0.85288274,0.0018695479],"about_ca_topic_score_codex":0.0010856596,"about_ca_topic_score_gemma":0.004435068,"teacher_disagreement_score":0.36702308,"about_ca_system_score_codex":0.00012698764,"about_ca_system_score_gemma":0.0004542223,"threshold_uncertainty_score":0.9998584},"labels":[],"label_agreement":null},{"id":"W6986438679","doi":"","title":"Positive and negative caregiver appraisal and caregiver health outcomes / by Sarah A. Vernon-Scott.","year":2017,"lang":"en","type":"dissertation","venue":"Knowledge Commons (Lakehead University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Hyporeflexia; Diafiltration; Hyperlactatemia","score_opus":0.01001222544015893,"score_gpt":0.28186035736002774,"score_spread":0.2718481319198688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986438679","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77317643,0.006363902,0.00024077894,0.0005225029,0.0009062054,0.0007478498,0.0010201095,0.000065383734,0.21695682],"genre_scores_gemma":[0.90460664,0.0002080879,0.00006758332,0.000023224318,0.00008720041,0.0000033568801,0.004339513,0.00006977562,0.090594605],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99839556,0.00021450726,0.00024052321,0.0005904958,0.00016338193,0.00039552723],"domain_scores_gemma":[0.998286,0.00013215454,0.000468385,0.00059697067,0.00024233967,0.00027414496],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00012353418,0.00051475974,0.0006032927,0.00023393454,0.00074496184,0.00010332734,0.00049193535,0.000528479,0.000011949567],"category_scores_gemma":[0.0001514395,0.0005614242,0.00013969494,0.00010477477,0.00033176003,0.000030800442,0.0002861897,0.0005336929,0.00001254305],"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":[0.0028917633,0.0011655681,0.2798045,0.0044497233,0.004955923,0.0001996301,0.1348868,0.000019438354,0.004439763,0.009664019,0.42424774,0.13327514],"study_design_scores_gemma":[0.0031644928,0.0007744504,0.1059887,0.00047751813,0.0002553524,0.000025440175,0.005279381,0.00005553578,0.0013136695,0.000020721629,0.88137347,0.0012712433],"about_ca_topic_score_codex":0.00053246575,"about_ca_topic_score_gemma":0.061931826,"teacher_disagreement_score":0.45712575,"about_ca_system_score_codex":0.00010668716,"about_ca_system_score_gemma":0.0003565514,"threshold_uncertainty_score":0.99968374},"labels":[],"label_agreement":null},{"id":"W6986443793","doi":"","title":"PHANGS-JWST First Results:The Influence of Stellar Clusters on Polycyclic Aromatic Hydrocarbons in Nearby Galaxies","year":2023,"lang":"en","type":"article","venue":"UWA Profiles and Research Repository (University of Western Australia)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Galaxy; Galaxy cluster; Cluster (spacecraft); Galaxy groups and clusters; Luminosity","score_opus":0.030868688732898046,"score_gpt":0.295793377258134,"score_spread":0.26492468852523593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986443793","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.998605,0.000033134816,0.0000026345006,0.00056934933,0.00003107001,0.0002764182,0.000009425986,0.00001155559,0.0004614239],"genre_scores_gemma":[0.9948445,0.00017511594,0.00007348005,0.0000055090172,0.000026188629,0.0000013806291,0.000026730242,0.000008997293,0.004838129],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986943,0.00019287817,0.00023051222,0.00022762452,0.00036786354,0.0002867964],"domain_scores_gemma":[0.999235,0.00012061812,0.00015984598,0.0003901106,0.000020099822,0.00007432421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064962835,0.00011192266,0.0001665336,0.0001770192,0.00023878126,0.000025147197,0.00038404914,0.00013873949,7.570391e-7],"category_scores_gemma":[0.000109206085,0.000100268975,0.00005576353,0.00032413533,0.00061527395,0.000016061806,0.0002694943,0.00026974812,0.000009781426],"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":[0.0015235323,0.00024338951,0.7599567,0.0009648731,0.0002368398,0.00013623794,0.010068116,0.0032102885,0.21954976,0.000048988375,0.0035827965,0.00047847835],"study_design_scores_gemma":[0.0010197953,0.0008602482,0.95550454,0.00038099734,0.000016473186,0.000024137142,0.0029570449,0.001300441,0.035617433,0.000022042752,0.0021126063,0.00018424122],"about_ca_topic_score_codex":0.0010173329,"about_ca_topic_score_gemma":0.000112474125,"teacher_disagreement_score":0.19554783,"about_ca_system_score_codex":0.00001899553,"about_ca_system_score_gemma":0.0000453799,"threshold_uncertainty_score":0.408885},"labels":[],"label_agreement":null},{"id":"W6986447327","doi":"","title":"Peter Pan La Película Ver Online Gratis - Chile y Latino","year":2020,"lang":"es","type":"other","venue":"OSF Preprints (OSF Preprints)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Latin Americans; Amazon rainforest","score_opus":0.007108564838366342,"score_gpt":0.2505693360167165,"score_spread":0.24346077117835016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986447327","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":[0.014325523,0.000015149504,0.0012594148,0.00051223533,0.00047851756,0.0012136261,0.00044657587,0.00014456578,0.9816044],"genre_scores_gemma":[0.08078075,0.0012624717,0.01113168,0.0009349737,0.0010866418,0.00012790052,0.0023561546,0.00054997054,0.90176946],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9933319,0.0011170014,0.0011598585,0.0029569704,0.0006556253,0.0007786278],"domain_scores_gemma":[0.99320126,0.00020902985,0.0009912888,0.0050087306,0.00013887667,0.0004508254],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016107254,0.0010923602,0.0009887369,0.00018923439,0.00020245589,0.00030445345,0.0020499625,0.0015111307,0.481795],"category_scores_gemma":[0.0027733375,0.0011690352,0.00064451015,0.00023260454,0.0004326809,0.000021977152,0.0036136308,0.0016273296,0.5779104],"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":[0.0005726421,0.0017267335,0.070748545,0.0027098304,0.0032449325,0.00017631623,0.0027575223,0.0013816946,0.03577584,0.001501298,0.79977125,0.0796334],"study_design_scores_gemma":[0.0009820962,0.000011066468,0.02341278,0.00030639008,0.00024017257,0.00010494224,0.00006259602,0.0012260886,0.003689052,0.000083790634,0.96874475,0.0011362898],"about_ca_topic_score_codex":0.00016101653,"about_ca_topic_score_gemma":0.00009296691,"teacher_disagreement_score":0.16897349,"about_ca_system_score_codex":0.000102293605,"about_ca_system_score_gemma":0.00035792176,"threshold_uncertainty_score":0.9997851},"labels":[],"label_agreement":null},{"id":"W6986462345","doi":"","title":"500 popular roses : for Canadian gardeners","year":2000,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.004080929658815208,"score_gpt":0.1918467447764915,"score_spread":0.1877658151176763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986462345","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":[0.000051843515,0.00039676044,0.0000025242748,0.00011103905,0.00022837163,0.00057871314,0.00063475315,0.000058221765,0.9979378],"genre_scores_gemma":[0.00042025617,0.0003569389,0.0034747652,0.00050823524,0.00026141532,0.00003202507,0.002679482,0.00017527622,0.9920916],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985867,0.000048905647,0.0005242692,0.00020808166,0.00021936948,0.00041268894],"domain_scores_gemma":[0.9988415,0.000015881096,0.0003787361,0.00047191876,0.00007992405,0.00021201227],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00017033414,0.00035997172,0.00033359125,0.00010126593,0.000091598675,0.000047415855,0.00039389383,0.00064896455,0.10040636],"category_scores_gemma":[0.00013019935,0.00037588677,0.00021122342,0.0000056547988,0.00009885763,2.0144453e-8,0.00004971316,0.00017713505,0.0021123048],"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":[0.00004710936,0.000012175776,0.000006855529,0.00033421026,0.00008529279,0.0000022640832,0.000036585432,0.0005195318,0.0000021026228,0.0000100551915,0.9965099,0.0024339347],"study_design_scores_gemma":[0.00045240755,0.0002201361,0.0000047687217,0.000097920856,0.000050106173,0.00004010591,0.000033497407,0.000039453207,0.00004629107,0.0000030988883,0.9986008,0.0004114374],"about_ca_topic_score_codex":0.04720624,"about_ca_topic_score_gemma":0.104688875,"teacher_disagreement_score":0.09829406,"about_ca_system_score_codex":0.000029372442,"about_ca_system_score_gemma":0.000121263896,"threshold_uncertainty_score":0.9998693},"labels":[],"label_agreement":null},{"id":"W6986464041","doi":"","title":"Plus que des histoires de jeunesse : les mineur.e.s devant les tribunaux dans la région du Saguenay―Lac-Saint-Jean entre 1950 et 1977","year":2022,"lang":"fr","type":"dissertation","venue":"Constellation (Université du Québec à Chicoutimi)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Economic Justice; Administration of justice; Context (archaeology); Criminal liability","score_opus":0.006160196964558473,"score_gpt":0.20587059162676552,"score_spread":0.19971039466220705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986464041","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9401397,0.0036758834,0.008190719,0.0037629467,0.0005040843,0.00050738186,0.0001504907,0.00011501121,0.04295379],"genre_scores_gemma":[0.9784101,0.0018468718,0.0010220774,0.00017557919,0.00017860634,0.000009447926,0.0060277903,0.00010748822,0.012222026],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969057,0.0007978221,0.0006522755,0.0006837542,0.00041361593,0.00054685184],"domain_scores_gemma":[0.99750054,0.0004754461,0.0008863306,0.0005420358,0.00033891594,0.00025674346],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00054443494,0.0006942844,0.0005245176,0.0003179914,0.0015156631,0.00013463739,0.0006383371,0.0008177867,0.00609981],"category_scores_gemma":[0.0005732911,0.00085364113,0.00044046383,0.0002991827,0.000752676,0.000053653624,0.00033156207,0.0008267873,0.000021338534],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028645163,0.0008380749,0.3036314,0.003451019,0.0016515887,0.00053452875,0.1290212,0.37150887,0.046056576,0.017659288,0.053052377,0.06973055],"study_design_scores_gemma":[0.0038641868,0.00067301345,0.03835795,0.00057287916,0.0012208079,0.0007190782,0.057603344,0.16947995,0.005610798,0.00009199074,0.7195716,0.0022344117],"about_ca_topic_score_codex":0.06147606,"about_ca_topic_score_gemma":0.19202901,"teacher_disagreement_score":0.6665192,"about_ca_system_score_codex":0.0012813115,"about_ca_system_score_gemma":0.0021654554,"threshold_uncertainty_score":0.99978423},"labels":[],"label_agreement":null},{"id":"W6986496505","doi":"","title":"Power Co. of Canada (TSE:POW) Given New C$22.00 Price Target at CIBC","year":2020,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Power (physics); Production (economics); Work (physics); Measure (data warehouse); Government (linguistics)","score_opus":0.0033834950303716126,"score_gpt":0.21489239691660228,"score_spread":0.21150890188623067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986496505","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":[0.00008525418,0.00070675433,0.0010098679,0.00049517356,0.00023465395,0.00022645922,0.000174838,0.000031606567,0.9970354],"genre_scores_gemma":[0.000892191,0.00009993561,0.005882316,0.0012159429,0.00029376938,0.0000031216457,0.0005960219,0.00022344067,0.9907933],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99879986,0.000033891585,0.00031105973,0.00029192198,0.00028270215,0.00028057856],"domain_scores_gemma":[0.99891245,0.0000102605545,0.00034721964,0.000492644,0.000030643056,0.00020678506],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000059871007,0.00030579756,0.00034071706,0.000041118717,0.000028203023,0.000009396269,0.0004035892,0.0003673948,0.0711002],"category_scores_gemma":[0.00011514863,0.00027563618,0.00009733828,0.00006911337,0.00004570418,9.330392e-7,0.00025119394,0.00018727119,0.0000619748],"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":[0.000019146388,0.000010853484,0.0003448828,0.00012616099,0.00014496592,0.000003933082,0.000028195756,0.000023888879,0.0022965632,0.000036204023,0.99695647,0.000008723531],"study_design_scores_gemma":[0.00028828686,0.000120839344,0.00008133751,0.000027459128,0.000003864771,0.000007075002,0.000019049821,0.0000522381,0.0079456065,0.0000034578286,0.99114114,0.00030963603],"about_ca_topic_score_codex":0.010800895,"about_ca_topic_score_gemma":0.0062152827,"teacher_disagreement_score":0.071038224,"about_ca_system_score_codex":0.000044377866,"about_ca_system_score_gemma":0.00087108085,"threshold_uncertainty_score":0.9999696},"labels":[],"label_agreement":null},{"id":"W6986502063","doi":"","title":"Preamble : The International Committee of Historical Sciences","year":2020,"lang":"en","type":"article","venue":"Érudit documents and data repository (Érudit Consortium, University of Montreal)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Diafiltration; Liquation; Dysgeusia; Emperipolesis; Triacetin; Demotion","score_opus":0.01678962502896809,"score_gpt":0.23287558596141333,"score_spread":0.21608596093244525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986502063","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9396447,0.0024847575,0.0023364958,0.012490894,0.0006796986,0.00050381443,0.0003619856,0.000058698693,0.04143898],"genre_scores_gemma":[0.9963564,0.000669184,0.0012342298,0.00016084574,0.00009898971,2.400411e-7,0.00013100827,0.000007095126,0.0013419698],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991385,0.000053965658,0.00020708605,0.00026187883,0.00023371255,0.0001048707],"domain_scores_gemma":[0.9990965,0.000047603844,0.00029198892,0.0004237183,0.00007067066,0.00006949801],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017679413,0.00009708875,0.00014926954,0.000024365458,0.00017923847,0.000019386887,0.00093551865,0.000059243932,0.000014365118],"category_scores_gemma":[0.000122154,0.00008262115,0.00004206389,0.00005927171,0.0003091283,0.000030747033,0.00083416136,0.00008500425,0.0000011117364],"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":[0.0008551073,0.00033411174,0.18467315,0.00026184428,0.0009272815,0.000064699,0.0008439553,0.0005753098,0.0523096,0.0013906275,0.74533945,0.012424864],"study_design_scores_gemma":[0.0009533546,0.00039771263,0.0075324904,0.000028926988,0.0001148197,0.000039933653,0.00051850936,0.0028511668,0.0034185871,0.000026295687,0.9839333,0.00018485516],"about_ca_topic_score_codex":0.0017143132,"about_ca_topic_score_gemma":0.0003675296,"teacher_disagreement_score":0.23859389,"about_ca_system_score_codex":0.000038248945,"about_ca_system_score_gemma":0.00006454336,"threshold_uncertainty_score":0.33691928},"labels":[],"label_agreement":null},{"id":"W6986503123","doi":"","title":"Port Dalhousie Housing Commission, 1919-1933 and Board of Health, 1923-1929","year":2023,"lang":"en","type":"other","venue":"Brock University Digital Repository (Brock University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Commission; Port (circuit theory); On board; Toilet; Health board","score_opus":0.007597849452186351,"score_gpt":0.20443863890101477,"score_spread":0.1968407894488284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986503123","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":[0.021157859,0.0006774811,0.0028514105,0.000015275402,0.000719118,0.00074785337,0.00042483822,0.000837758,0.9725684],"genre_scores_gemma":[0.0062689553,0.00047623142,0.00038100412,0.000026599326,0.00011349497,7.665402e-8,0.00015511,0.0002648441,0.9923137],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984135,0.000094432595,0.00029844025,0.0005278902,0.0002975316,0.00036821698],"domain_scores_gemma":[0.99833983,0.00003107206,0.0006950602,0.0005650501,0.000106242354,0.0002627391],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0000063565276,0.00040135573,0.00050114264,0.0005301546,0.0002697769,0.000050728337,0.0005348415,0.00051767164,0.0000068943978],"category_scores_gemma":[0.000055318702,0.00050054945,0.0002068183,0.00033553666,0.0002273621,0.00004151987,0.00087235024,0.00028671755,0.000013880633],"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":[0.00019782722,0.00013708945,0.054628193,0.0006477422,0.00044634688,0.00010557826,0.000043291504,0.00011026197,0.0036290346,0.00004485926,0.9366263,0.003383442],"study_design_scores_gemma":[0.00068230083,0.0002726638,0.0019127443,0.0003112974,0.00007853294,0.00004720148,0.0013236824,0.0000053347608,0.00019745273,0.0000029455025,0.9946807,0.00048512616],"about_ca_topic_score_codex":0.00047663596,"about_ca_topic_score_gemma":0.0011123887,"teacher_disagreement_score":0.058054388,"about_ca_system_score_codex":0.00010904999,"about_ca_system_score_gemma":0.00029768332,"threshold_uncertainty_score":0.9997446},"labels":[],"label_agreement":null},{"id":"W6986509693","doi":"","title":"President Trump On United States-Mexico-Canada Agreement : CSPAN : October 1, 2018 9:24pm-10:46pm EDT","year":2018,"lang":"en","type":"other","venue":"Internet Archive (Internet Archive)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"White (mutation); Supreme court; Order (exchange); House of Representatives; Free trade agreement; Executive order; Legislation; Executive branch","score_opus":0.0072809021612013376,"score_gpt":0.23443603655083423,"score_spread":0.2271551343896329,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986509693","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":[0.005886799,0.00019816487,0.0067520835,0.0003170381,0.0016844523,0.001230552,0.0017917892,0.0001574627,0.98198164],"genre_scores_gemma":[0.0043876353,0.00027887986,0.0021421483,0.0023424781,0.0013101003,0.0000981866,0.012887399,0.000654883,0.97589827],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951858,0.00048150064,0.0010299903,0.0013160304,0.00086646026,0.0011202546],"domain_scores_gemma":[0.9967059,0.00013409805,0.00091287744,0.0016607412,0.0000837817,0.0005026238],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00026007008,0.0012664185,0.0007918959,0.00063713983,0.000064304455,0.0001555122,0.0019140561,0.00036420772,0.022772452],"category_scores_gemma":[0.00019492059,0.0011582589,0.00040255184,0.0001316959,0.0005423318,0.000007668688,0.001544685,0.00081296475,0.0031925733],"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":[0.00062972505,0.00017261089,0.0006438354,0.00021385937,0.0009994197,0.00005583642,0.0005346384,0.00020454511,0.00027654093,0.00017129422,0.99570596,0.00039172484],"study_design_scores_gemma":[0.0011289344,0.0018685468,0.00045584427,0.0009293396,0.00010632278,0.00004536613,0.000067242276,0.005106301,0.0026472665,0.00010417959,0.98634696,0.0011937176],"about_ca_topic_score_codex":0.27102426,"about_ca_topic_score_gemma":0.5955358,"teacher_disagreement_score":0.32451156,"about_ca_system_score_codex":0.00014377334,"about_ca_system_score_gemma":0.0003691448,"threshold_uncertainty_score":0.99908674},"labels":[],"label_agreement":null},{"id":"W6986521008","doi":"","title":"Practical Inclusion: Representing French-Canadians in the Army during the Second World War","year":2024,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"French; Representation (politics); World War II; Parliament; Economic shortage; Politics; Poison control","score_opus":0.006365266802609463,"score_gpt":0.23120410017824547,"score_spread":0.224838833375636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986521008","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98700243,0.00021250632,0.0000037590246,0.003651606,0.00019908896,0.00022923882,0.000021257792,0.000010533791,0.008669559],"genre_scores_gemma":[0.35652465,0.000064919645,0.0006310266,0.00010338535,0.00012245,0.0000010473393,0.00043576595,0.000021843141,0.6420949],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9989947,0.00012075147,0.00014933653,0.0002609409,0.00023925534,0.00023498634],"domain_scores_gemma":[0.9992097,0.000043287087,0.00018458805,0.00046672858,0.000053200245,0.000042498497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037175565,0.00017333012,0.00016647944,0.00015286612,0.00038928527,0.000029949073,0.0005387348,0.0002076009,0.00020692447],"category_scores_gemma":[0.00006644785,0.00013402439,0.00012764457,0.00021577111,0.00008258381,0.0000113362,0.00042915458,0.0006337909,0.000024484527],"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":[0.0003072382,0.00015496674,0.006088938,0.0031371408,0.0005729684,0.000551281,0.84953016,0.00040558676,0.038363084,0.00046749477,0.09911929,0.0013018403],"study_design_scores_gemma":[0.0013363298,0.0002509231,0.042411882,0.00075786083,0.00040004877,0.00013831022,0.6848134,0.0030238277,0.009085906,0.0003671506,0.25620243,0.0012119858],"about_ca_topic_score_codex":0.021766013,"about_ca_topic_score_gemma":0.54713976,"teacher_disagreement_score":0.63342535,"about_ca_system_score_codex":0.000033897784,"about_ca_system_score_gemma":0.000112396636,"threshold_uncertainty_score":0.9847481},"labels":[],"label_agreement":null},{"id":"W6986537671","doi":"","title":"Port St Johns AFS 2010-11 final (Autosaved)(1)","year":2011,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Port (circuit theory); Work (physics); Payment; Financial Audit","score_opus":0.0075707684956668395,"score_gpt":0.19455187284987363,"score_spread":0.18698110435420678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986537671","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":[0.00020218022,0.00022888771,0.000006048001,0.000058916776,0.00047872445,0.0003878369,0.00026823854,0.000108317814,0.99826086],"genre_scores_gemma":[0.00053841545,0.000544362,0.0033987274,0.00034164908,0.00029367267,0.000016526306,0.0015235769,0.00017881738,0.99316424],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99812466,0.00006525021,0.000773023,0.00026214914,0.00037167806,0.00040323765],"domain_scores_gemma":[0.9980427,0.000016394706,0.0008965243,0.0007375971,0.0001517309,0.00015504863],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00025505814,0.0004765576,0.00042947583,0.00010227657,0.00006740998,0.000039789444,0.00055874995,0.0007965233,0.31303293],"category_scores_gemma":[0.00016464574,0.0004723741,0.00023525713,0.000008839815,0.00018581131,4.214525e-8,0.00024092317,0.00032307193,0.0075267],"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":[0.0000534507,0.00004770871,0.00006268515,0.0004002821,0.00009566534,0.000008073108,0.00007001559,0.00006288719,0.0000030268106,0.00003124852,0.9984162,0.00074875413],"study_design_scores_gemma":[0.000528164,0.00027473786,0.000054032924,0.00013653637,0.00006306105,0.00013331287,0.000033121723,0.00002777901,0.000070927425,0.0000025238303,0.9981712,0.00050461345],"about_ca_topic_score_codex":0.005001404,"about_ca_topic_score_gemma":0.0026042634,"teacher_disagreement_score":0.30550623,"about_ca_system_score_codex":0.000019755533,"about_ca_system_score_gemma":0.00007724038,"threshold_uncertainty_score":0.9997728},"labels":[],"label_agreement":null},{"id":"W6986541135","doi":"","title":"Prevalence and patterns of antimicrobial resistance of fecal Escherichia coli among pigs on 47 farrow-to-finish farms with different in-feed medication policies in Ontario and British Columbia","year":2008,"lang":"en","type":"article","venue":"PubMed Central","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"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":"Feces; Antibiotic resistance; Antimicrobial; Escherichia coli; Drug resistance; Multiple drug resistance","score_opus":0.005316895329789146,"score_gpt":0.18507799605798883,"score_spread":0.17976110072819967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986541135","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9992841,0.0000342105,0.000044868004,0.000065011496,0.000037190635,0.00035353712,0.00003401988,0.0000034181749,0.0001436429],"genre_scores_gemma":[0.99911493,0.00023972006,0.00019453738,0.00008457688,0.000016393506,0.000025723406,0.00003437271,0.000008752488,0.00028097405],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990325,0.000041408053,0.00026795958,0.00018067163,0.0001310068,0.00034647048],"domain_scores_gemma":[0.9995911,0.0000120693,0.00013224526,0.00013012026,0.000024507579,0.00010993559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011701726,0.00009096429,0.00018123076,0.000029952509,0.000027879234,0.000021399452,0.00009940282,0.00008364809,0.0000063655903],"category_scores_gemma":[0.0000800504,0.00010875143,0.000015317853,0.000057536687,0.00020511601,0.000006904059,0.000057113357,0.0001371921,3.397465e-8],"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":[0.0001092157,0.00008005808,0.995907,0.00014660633,0.000011213832,0.000002615994,0.0008949651,0.000029048888,0.0025056691,0.000003512031,0.00008846701,0.00022162028],"study_design_scores_gemma":[0.0008558254,0.00011381861,0.9955752,0.00015029708,0.000007179939,0.0000074466307,0.000037810685,0.000019910467,0.0030279818,0.0000016789952,0.00009136623,0.00011146591],"about_ca_topic_score_codex":0.0437916,"about_ca_topic_score_gemma":0.6989485,"teacher_disagreement_score":0.6551569,"about_ca_system_score_codex":0.000047716472,"about_ca_system_score_gemma":0.00006889759,"threshold_uncertainty_score":0.96257585},"labels":[],"label_agreement":null},{"id":"W6986548367","doi":"","title":"Politique monétaire, prix du pétrole et incertitudes macroéconomiques : une approche FAVAR pour l'économie canadienne","year":2023,"lang":"fr","type":"other","venue":"Archipelago (University of Quebec in Montreal)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Bayesian vector autoregression; Limiting","score_opus":0.006427808756516575,"score_gpt":0.19821109356034572,"score_spread":0.19178328480382914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986548367","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7942485,0.0003934818,0.0026848933,0.008781661,0.00023546188,0.0008140242,0.00042297537,0.00011615366,0.19230284],"genre_scores_gemma":[0.7492029,0.0031773078,0.014685796,0.0005500432,0.0003250038,0.0000075556077,0.0006598079,0.00037835972,0.23101322],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976549,0.00032906147,0.00046847158,0.0006587604,0.00011630047,0.0007724806],"domain_scores_gemma":[0.99812835,0.00017356174,0.00059886154,0.00071977725,0.0000844558,0.00029498286],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004569325,0.00055007706,0.00076472136,0.00040538062,0.00013903504,0.00003151583,0.0008857014,0.00073151494,0.00042783626],"category_scores_gemma":[0.00020433683,0.0007082765,0.0002947425,0.00021300101,0.0005611759,0.00003378956,0.0006082941,0.00060796813,0.00013987023],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015357452,0.0013453842,0.06572424,0.003101764,0.0029642268,0.00073683873,0.07828675,0.023821877,0.0030254684,0.14889967,0.045871697,0.62468636],"study_design_scores_gemma":[0.007252717,0.0011367867,0.39611992,0.0017958784,0.0005129649,0.00009707228,0.040016163,0.042863972,0.0006658348,0.026729703,0.479222,0.0035870052],"about_ca_topic_score_codex":0.919374,"about_ca_topic_score_gemma":0.99758697,"teacher_disagreement_score":0.62109935,"about_ca_system_score_codex":0.0004530301,"about_ca_system_score_gemma":0.0008405595,"threshold_uncertainty_score":0.9995368},"labels":[],"label_agreement":null},{"id":"W6986598114","doi":"","title":"PRESS RELEASE: PSEG Announces 2012 Second Quarter Results-$0.42 Per Share Income From Continuing Operations-$0.43 Per Share Of Operating Earnings","year":2012,"lang":"en","type":"other","venue":"Business week","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Earnings; Earnings per share; Earnings before interest and taxes","score_opus":0.009420269623205123,"score_gpt":0.2400794520901495,"score_spread":0.23065918246694436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986598114","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":[0.24566807,0.0466623,0.0051898668,0.0010525646,0.0040996955,0.004279121,0.03363661,0.0006976639,0.6587141],"genre_scores_gemma":[0.16800764,0.0005622315,0.020323696,0.00046304063,0.00505929,0.00023272366,0.037124366,0.00104659,0.7671804],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99739033,0.00016891785,0.0008836628,0.00064595375,0.00040174936,0.0005094083],"domain_scores_gemma":[0.99765867,0.000045806148,0.00070571713,0.0009311885,0.0005195008,0.00013911718],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00031609868,0.000627175,0.000680538,0.00014908056,0.0001421781,0.00019567377,0.0006376714,0.000797291,0.0058202264],"category_scores_gemma":[0.00043303723,0.0005679763,0.00015573468,0.00013301843,0.00014985299,0.00005746367,0.0003801629,0.00049385114,0.0001903477],"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":[0.0002587899,0.0003517431,0.006713456,0.0023066367,0.00073321955,0.0000108557215,0.0038145543,0.0014338434,0.037117206,0.00005414537,0.9438679,0.0033376082],"study_design_scores_gemma":[0.0012391818,0.0001124854,0.009883616,0.0010569467,0.000111771005,0.000016023905,0.0003119296,0.0006744072,0.00124154,9.315456e-7,0.9844607,0.0008904304],"about_ca_topic_score_codex":0.00086589623,"about_ca_topic_score_gemma":0.00054352405,"teacher_disagreement_score":0.108466305,"about_ca_system_score_codex":0.000024209508,"about_ca_system_score_gemma":0.00012299894,"threshold_uncertainty_score":0.9996772},"labels":[],"label_agreement":null},{"id":"W6986633970","doi":"","title":"Profil de l'enseignement à domicile au Canada = A profile of home schooling in Canada /","year":2015,"lang":"fr","type":"other","venue":"Bibliothèque et Archives nationales du Québec (Québec government)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Agency (philosophy); Work (physics); Metropolitan area; Government (linguistics); Population; Ethnic group","score_opus":0.004229402373072344,"score_gpt":0.19647741179311207,"score_spread":0.19224800942003972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986633970","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58520293,0.009563811,0.00033064483,0.0033674128,0.00035106298,0.0010239509,0.001755117,0.000016135613,0.39838895],"genre_scores_gemma":[0.8799971,0.0004537732,0.0031979028,0.0011573678,0.00041509076,0.00016300524,0.0003208907,0.00019667736,0.11409823],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963831,0.00028437653,0.0009845308,0.00051455066,0.0011864252,0.00064702507],"domain_scores_gemma":[0.99723256,0.00091787503,0.0009243231,0.0005012383,0.00011336012,0.0003106741],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000451662,0.0005678576,0.0006005499,0.00038593888,0.00009746912,0.000055671706,0.00080128247,0.00016579566,0.0031211316],"category_scores_gemma":[0.0027371391,0.000597221,0.00012652301,0.00043304803,0.00018258367,0.000021895223,0.0005131679,0.0005186762,0.000021119276],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0003642768,0.0002640606,0.36271617,0.0014685665,0.0005663595,0.000043389235,0.0021147556,0.009988109,0.0037921355,0.0010715354,0.61689484,0.00071579433],"study_design_scores_gemma":[0.0020939666,0.00022511657,0.12547424,0.0008051071,0.00008608731,0.00005647998,0.0007676433,0.0060748793,0.0032726298,0.000024911427,0.8601257,0.0009932081],"about_ca_topic_score_codex":0.9998454,"about_ca_topic_score_gemma":0.9999995,"teacher_disagreement_score":0.60275376,"about_ca_system_score_codex":0.034617294,"about_ca_system_score_gemma":0.637371,"threshold_uncertainty_score":0.9996479},"labels":[],"label_agreement":null},{"id":"W6986635123","doi":"","title":"Properties of vacuum insulation panels: results from experimental investigations at NRC Canada","year":2004,"lang":"en","type":"article","venue":"NPARC","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Permeance; Water vapor; Thermal insulation; Relative humidity; Humidity; Thermal; Core (optical fiber); Enhanced Data Rates for GSM Evolution","score_opus":0.016327768324726405,"score_gpt":0.22099648487700593,"score_spread":0.20466871655227953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986635123","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9958118,0.0000720781,0.00007021219,0.0004608348,0.00007670473,0.00009411977,0.000077163364,0.000007987202,0.0033290584],"genre_scores_gemma":[0.9937191,0.0000057147877,0.005550587,0.0001717436,0.00005736566,0.000006960436,0.00027305,0.000008669374,0.00020680949],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99933755,0.00002094313,0.00023379496,0.00011927502,0.00019022077,0.00009821192],"domain_scores_gemma":[0.99948454,0.00000534609,0.00011024201,0.000287574,0.0000647281,0.000047552476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000064425054,0.0000817536,0.000075559794,0.000014107031,0.00006389296,0.000006778575,0.0001333715,0.000059701677,0.000018569577],"category_scores_gemma":[0.00026405038,0.00007364737,0.000021934777,0.000038892096,0.000058642174,0.0000038983862,0.00011925534,0.000050312887,0.0000034186003],"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":[0.000047055222,0.00001797996,0.00058146426,0.0000075103762,0.0000155596,3.5877542e-7,0.0004676553,0.0009638939,0.9971608,0.00006845173,0.000625181,0.000044100376],"study_design_scores_gemma":[0.00062830077,0.0000652693,0.004860961,0.000022834289,0.000005207941,0.0000022089685,0.00015673277,0.00046989718,0.98938745,0.00018822712,0.0041173855,0.00009549694],"about_ca_topic_score_codex":0.034638494,"about_ca_topic_score_gemma":0.020740833,"teacher_disagreement_score":0.013897661,"about_ca_system_score_codex":0.000093624585,"about_ca_system_score_gemma":0.00030928693,"threshold_uncertainty_score":0.99712807},"labels":[],"label_agreement":null},{"id":"W6986665022","doi":"","title":"P. Vergilii Maronis Opera : Preservation Lab Treatment Report","year":2020,"lang":"en","type":"other","venue":"Ohio Digital Resource Commons (University of Cincinnati)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Opera; Minor (academic); Volume (thermodynamics)","score_opus":0.00890622201789522,"score_gpt":0.20854893056396515,"score_spread":0.1996427085460699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986665022","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":[0.005946911,0.00069511443,0.0010213709,0.0009057056,0.000070497874,0.00039393047,0.00029541625,0.00009129584,0.9905798],"genre_scores_gemma":[0.038064074,0.00042677132,0.0013564965,0.00009879507,0.00016293446,0.0000012932276,0.0046524797,0.00021851655,0.95501864],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99890006,0.000047772886,0.00020919493,0.00035906088,0.00028097813,0.00020293583],"domain_scores_gemma":[0.9985995,0.000022338927,0.00043423235,0.0007573006,0.000052320065,0.00013424917],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00006802015,0.0002932477,0.00036678635,0.0001357998,0.00008741075,0.000073575786,0.00051742775,0.0003369696,0.00035163248],"category_scores_gemma":[0.000120526856,0.00033034122,0.00019682501,0.00016021087,0.00014652348,0.000028198074,0.00048076728,0.0001630581,0.00005080918],"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":[0.000300837,0.00032717202,0.0030590692,0.00036426805,0.00095113856,0.00034391214,0.0011185217,0.0002639242,0.0005002461,0.0004478326,0.93919367,0.053129416],"study_design_scores_gemma":[0.00062712625,0.00042439034,0.00028573905,0.00010331057,0.00005716762,0.00003551515,0.0004403369,0.0003265566,0.00012428283,0.0000060649186,0.99728054,0.000288968],"about_ca_topic_score_codex":0.00019459568,"about_ca_topic_score_gemma":0.00051464746,"teacher_disagreement_score":0.05808688,"about_ca_system_score_codex":0.00006602122,"about_ca_system_score_gemma":0.0001366918,"threshold_uncertainty_score":0.9999149},"labels":[],"label_agreement":null},{"id":"W6986678277","doi":"","title":"Quebec wind farm gets the green light","year":2011,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.006167450401232582,"score_gpt":0.2229047510488512,"score_spread":0.21673730064761862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986678277","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":[0.00007730883,0.00088162994,0.00040420104,0.00025355633,0.0002312614,0.00021855085,0.000016364767,0.0000560231,0.9978611],"genre_scores_gemma":[0.00035661162,0.0001921082,0.0009111919,0.00093556556,0.0006593433,0.0000061471205,0.00015370581,0.00022150886,0.9965638],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99925935,0.0000395461,0.0001656831,0.0002080211,0.00011764265,0.00020978015],"domain_scores_gemma":[0.9990439,0.0000033053373,0.00016611657,0.00071649987,0.000020721449,0.000049468796],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000097393095,0.00024637004,0.00015349952,0.00004410949,0.000043072647,0.000022606851,0.00048322405,0.0004309674,0.002498647],"category_scores_gemma":[0.000025169637,0.00014885378,0.00009959301,0.00002609097,0.000072189716,5.2592134e-7,0.00022033052,0.00020152933,0.00056269596],"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":[0.000007572325,0.000017616778,0.000118696036,0.00005483891,0.00014779418,0.0000019673605,0.00012141899,7.49883e-7,0.00080710975,0.0005215004,0.9903158,0.007884956],"study_design_scores_gemma":[0.000122005906,0.00004935223,0.00015954528,0.000019171885,0.000024120125,0.000008063258,0.00002080622,0.000010588986,0.0015407209,0.000011659632,0.99780524,0.00022872363],"about_ca_topic_score_codex":0.010768158,"about_ca_topic_score_gemma":0.042134125,"teacher_disagreement_score":0.03136597,"about_ca_system_score_codex":0.000006353475,"about_ca_system_score_gemma":0.00005935571,"threshold_uncertainty_score":0.9984132},"labels":[],"label_agreement":null},{"id":"W6986678837","doi":"","title":"Qui seront les collégiens de l'an 2010?","year":2006,"lang":"fr","type":"other","venue":"Bibliothèque et Archives nationales du Québec (Québec government)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Cegep de Sainte Foy","funders":"","keywords":"Context (archaeology); Set (abstract data type); Relation (database)","score_opus":0.00649602460981191,"score_gpt":0.22397882252870652,"score_spread":0.2174827979188946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986678837","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":[0.22570038,0.010575785,0.009114266,0.0071198354,0.0004165174,0.0008575263,0.0007978134,0.00014263869,0.74527526],"genre_scores_gemma":[0.22110642,0.0014636323,0.011420935,0.001993167,0.001551619,0.00016894769,0.0005685511,0.00046177456,0.761265],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99603736,0.0005045946,0.0008929708,0.00085613277,0.0009310431,0.0007779129],"domain_scores_gemma":[0.99636114,0.0014284321,0.00092276913,0.0008794502,0.00009021764,0.0003179924],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00048456443,0.00089629105,0.00058051734,0.000601118,0.00036731712,0.00038807347,0.0012602131,0.00052053126,0.006579473],"category_scores_gemma":[0.002181277,0.00093419576,0.00042243738,0.00034909605,0.000655527,0.0000528569,0.0006671176,0.00072902173,0.00040070747],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030156848,0.0010682784,0.20797,0.0006796556,0.0007369307,0.000030428588,0.0023990264,0.0048056734,0.012776354,0.0113251405,0.75462455,0.0032824355],"study_design_scores_gemma":[0.0010584511,0.00047309726,0.11097489,0.00020565963,0.00013608631,0.00011201028,0.00016383121,0.0040173046,0.0011932979,0.000088408735,0.8805787,0.0009982542],"about_ca_topic_score_codex":0.18081407,"about_ca_topic_score_gemma":0.97195107,"teacher_disagreement_score":0.79113704,"about_ca_system_score_codex":0.0034801832,"about_ca_system_score_gemma":0.0380219,"threshold_uncertainty_score":0.99931085},"labels":[],"label_agreement":null},{"id":"W6986722534","doi":"","title":"In Q1 2022, production costs in construction rose by 3.0% : Costs of production indices in construction - first quarter 2022 / Insee (France)","year":2022,"lang":"fr","type":"article","venue":"Gallica (Bibliothèque nationale de France)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Production (economics); Rose (mathematics); Quarter (Canadian coin); Production cost","score_opus":0.0037482424277878396,"score_gpt":0.23001152626259,"score_spread":0.22626328383480215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986722534","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9712482,0.012519457,0.00037788617,0.010170921,0.0032165684,0.0012886107,0.00027492427,0.000023433307,0.0008799704],"genre_scores_gemma":[0.9830316,0.007817108,0.0027738174,0.0004382635,0.000643794,0.0005871328,0.0010336443,0.00006229727,0.0036123795],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959289,0.0006399401,0.0012578524,0.00081306795,0.0007936973,0.0005665298],"domain_scores_gemma":[0.99819726,0.00010761746,0.00084600935,0.0004527375,0.00030440118,0.000091971015],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017858902,0.00037966497,0.00046241985,0.0024433483,0.00022637942,0.000071749506,0.00037430698,0.0005684144,0.00067123363],"category_scores_gemma":[0.00096485706,0.00051461917,0.00011023448,0.004825123,0.000433186,0.00024770742,0.00016057405,0.0015175608,0.000009452099],"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":[0.0006796535,0.0016043672,0.83269876,0.0009053332,0.000106262494,0.0000137621055,0.0023198493,0.04935516,0.058268487,0.0030165224,0.03693434,0.014097503],"study_design_scores_gemma":[0.009537197,0.0012461259,0.35280722,0.0010621805,0.000083659164,0.0012148017,0.0032595017,0.01712397,0.05401114,0.0016016995,0.55584186,0.0022106266],"about_ca_topic_score_codex":0.0009327579,"about_ca_topic_score_gemma":0.0023935416,"teacher_disagreement_score":0.51890755,"about_ca_system_score_codex":0.0012670289,"about_ca_system_score_gemma":0.00066646765,"threshold_uncertainty_score":0.9997305},"labels":[],"label_agreement":null},{"id":"W6986726103","doi":"","title":"Rebooting multilateral trade cooperation : perspectives from China and Europe","year":2021,"lang":"en","type":"book","venue":"Cadmus - EUI Research Repository (European University Institute)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Global Affairs Canada; Queen's University","keywords":"China; Safeguard; Reboot; Work (physics); Product (mathematics); Trade barrier; Joint (building)","score_opus":0.01772316047432253,"score_gpt":0.2557355553838088,"score_spread":0.23801239490948628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986726103","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":[0.20249063,0.0014281847,0.00029902603,0.00012770068,0.0004482205,0.00041244575,0.00007392269,0.000074763775,0.79464513],"genre_scores_gemma":[0.19197851,0.0017357053,0.000984552,0.000047937192,0.0017007581,8.2268707e-7,0.0017405868,0.000115104434,0.801696],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967779,0.0011315275,0.00032054607,0.0008747417,0.00046945974,0.00042581322],"domain_scores_gemma":[0.99831814,0.000054076372,0.00020096403,0.00077163865,0.00038119237,0.00027400855],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00062547444,0.00038178233,0.00031792576,0.00021704711,0.0009919552,0.00028641568,0.00061083696,0.00032280528,0.000019601264],"category_scores_gemma":[0.0004985849,0.0004304868,0.00012870252,0.00014679751,0.0008016289,0.00004436511,0.0010494085,0.0014339787,0.00003927863],"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":[0.0020197956,0.0008565078,0.0033528383,0.0017312116,0.0034428148,0.025373729,0.038875755,0.0038740379,0.6046222,0.020260707,0.27514893,0.020441482],"study_design_scores_gemma":[0.00078971917,0.00026822212,0.0039168126,0.00030269995,0.00007023878,0.00017443902,0.0006511949,0.00050419255,0.002197294,0.000003987219,0.99054116,0.0005800496],"about_ca_topic_score_codex":0.00013698214,"about_ca_topic_score_gemma":0.00005563654,"teacher_disagreement_score":0.71539223,"about_ca_system_score_codex":0.00025203964,"about_ca_system_score_gemma":0.00082699733,"threshold_uncertainty_score":0.9998147},"labels":[],"label_agreement":null},{"id":"W6986731599","doi":"","title":"Rôle de l'acétylation du facteur de transcription IRF3","year":2012,"lang":"fr","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Transcription factor; Transcription (linguistics); Interferon; Activating transcription factor; General transcription factor","score_opus":0.0018356477929345337,"score_gpt":0.1372455022153827,"score_spread":0.13540985442244816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986731599","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056541048,0.0022929374,0.0068546296,0.0044388804,0.0004676949,0.00029721032,0.0004164741,0.000010815444,0.9286803],"genre_scores_gemma":[0.7887276,0.0009874552,0.0055993996,0.0014039009,0.00040553074,0.000008395295,0.00015377541,0.0000933404,0.20262064],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982447,0.00015554126,0.00032332295,0.0002133387,0.0006185691,0.00044451252],"domain_scores_gemma":[0.99911624,0.00005310784,0.0002848978,0.0002297978,7.957711e-7,0.00031513022],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000027733275,0.0002995248,0.00025217223,0.0000231504,0.00014112213,0.000024433231,0.00022869286,0.00016831417,0.00038875485],"category_scores_gemma":[0.00000951944,0.000324504,0.000057144214,0.00003669065,0.00010065924,0.000032085456,0.00009183801,0.00023380852,1.9721623e-8],"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":[0.0008095393,0.0001760396,0.16650116,0.0025882074,0.000651833,0.000041200547,0.0008178123,0.0014066031,0.5909013,0.13207611,0.015309608,0.08872056],"study_design_scores_gemma":[0.00043199048,0.00010172441,0.043200735,0.00014766803,0.000063285304,0.000029170875,0.0006391273,0.004580591,0.10569391,0.00016503873,0.8445419,0.00040483588],"about_ca_topic_score_codex":0.004524307,"about_ca_topic_score_gemma":0.027362889,"teacher_disagreement_score":0.82923234,"about_ca_system_score_codex":0.000016685908,"about_ca_system_score_gemma":0.002158843,"threshold_uncertainty_score":0.9999207},"labels":[],"label_agreement":null},{"id":"W6986758498","doi":"","title":"Re Health Care Corp of St. John's and NAPE","year":2002,"lang":"en","type":"article","venue":"eYLS (Yale Law School)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Grievance; Memorandum; Health care; Complaint; Permission; Legislation","score_opus":0.009275837882174504,"score_gpt":0.25087700321949874,"score_spread":0.24160116533732423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986758498","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9014975,0.021972742,0.00044191148,0.0019843627,0.00036264706,0.00057224534,0.00019783553,0.000074664975,0.07289611],"genre_scores_gemma":[0.9924131,0.0005152689,0.0040245564,0.0018229203,0.00012804009,0.0000055402816,0.00012114075,0.000020548701,0.0009488987],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99912786,0.00005759973,0.00026515286,0.00019097401,0.00013941205,0.00021897284],"domain_scores_gemma":[0.9992351,0.000011489659,0.00015867676,0.00037998945,0.00006850988,0.00014625712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012354343,0.00013414283,0.00017898691,0.000023428069,0.0001047826,0.000023744036,0.00015437245,0.000118573465,0.00021025438],"category_scores_gemma":[0.00009156513,0.00012857522,0.000050944254,0.000060214577,0.00010019034,0.0000058033534,0.00011468681,0.00016650239,0.000026898146],"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":[0.00057380984,0.00079406326,0.18915571,0.0068144044,0.0009060662,0.00005007978,0.01194107,0.0013927128,0.05842062,0.03145919,0.5575407,0.14095157],"study_design_scores_gemma":[0.0011833423,0.001018403,0.0032049662,0.00008536735,0.000019113599,0.000025397014,0.00086723285,0.00059061626,0.0078757545,0.00005216606,0.98469025,0.0003873826],"about_ca_topic_score_codex":0.00015088073,"about_ca_topic_score_gemma":0.00038142904,"teacher_disagreement_score":0.42714956,"about_ca_system_score_codex":0.000015524141,"about_ca_system_score_gemma":0.000031738884,"threshold_uncertainty_score":0.5243145},"labels":[],"label_agreement":null},{"id":"W6986760914","doi":"","title":"Quantum Technologies Reports 2012 Fourth Quarter and Annual Financial Results - KPTV - FOX 12","year":2013,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Payment; Financial services; Work (physics)","score_opus":0.004245741534829316,"score_gpt":0.2212166131266647,"score_spread":0.2169708715918354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986760914","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":[0.0016067852,0.0034329274,0.0039055191,0.0008877552,0.00091910403,0.000848195,0.00028393825,0.0006214696,0.9874943],"genre_scores_gemma":[0.0056776986,0.0007109681,0.009263281,0.00023666173,0.00041840711,0.000046106317,0.0006850981,0.0002268185,0.982735],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985534,0.000029609722,0.00044124373,0.00046427475,0.00016558499,0.0003458642],"domain_scores_gemma":[0.99862266,0.000010743587,0.00045670054,0.0008162827,0.000044530305,0.00004906983],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018374014,0.00036768056,0.000311809,0.00013855819,0.000052502735,0.000045193672,0.00020759345,0.0010639993,0.00018289206],"category_scores_gemma":[0.00039252386,0.00029623962,0.00007783556,0.00004629124,0.0001792945,0.000006560863,0.00029707665,0.0003024967,0.000071406976],"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":[0.000020192669,0.00001878279,0.0001867966,0.00006575458,0.000040211125,0.000011018451,0.000032687578,0.0000012516899,0.0001912831,0.00022865315,0.9957067,0.0034967046],"study_design_scores_gemma":[0.00030122208,0.00028982328,0.000259342,0.000052468517,0.000020194777,0.00011432706,0.00011227765,0.00009830132,0.0003185519,0.0001013396,0.9979095,0.00042263675],"about_ca_topic_score_codex":0.00016181593,"about_ca_topic_score_gemma":0.00016770491,"teacher_disagreement_score":0.005357762,"about_ca_system_score_codex":0.0000067168485,"about_ca_system_score_gemma":0.00006430331,"threshold_uncertainty_score":0.999949},"labels":[],"label_agreement":null},{"id":"W6986818362","doi":"","title":"The relationship between vascular risk factors and vascular cognitive impairment, a secondary analysis of a dataset","year":2000,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cognition; Vascular disease; Risk factor; Blood pressure; Population","score_opus":0.0037133593678722694,"score_gpt":0.1784008251225153,"score_spread":0.17468746575464303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986818362","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50554067,0.005755092,0.00035699303,0.00024532533,0.00012008642,0.00096731714,0.07804284,0.000017313621,0.40895435],"genre_scores_gemma":[0.965662,0.0031400914,0.00044970476,0.00020876218,0.00008341254,0.000010929161,0.008414326,0.0001265115,0.02190427],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984653,0.00014946726,0.0003013663,0.00022968644,0.00066772156,0.00018644847],"domain_scores_gemma":[0.9987747,0.00035356422,0.00039938907,0.00033762993,4.6850215e-7,0.00013425565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000026598032,0.00023333474,0.00034909818,0.00005495757,0.0001467334,0.000017084201,0.00020060956,0.000085649626,0.000060085484],"category_scores_gemma":[0.000019996056,0.00017922689,0.00007988926,0.000103182356,0.000162049,0.000009731659,0.0001591346,0.0002039333,2.0676314e-9],"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":[0.00007984229,0.000012994136,0.97587454,0.00020756075,0.004388902,0.0000021496985,0.000052716667,0.00003332001,0.000057463774,0.00024182322,0.017492209,0.0015564886],"study_design_scores_gemma":[0.00038252558,0.00009998091,0.73348737,0.00008570274,0.0012299601,5.233797e-7,0.0006342509,0.00022466177,0.00073390885,0.000031106287,0.2628146,0.00027539005],"about_ca_topic_score_codex":0.0060854726,"about_ca_topic_score_gemma":0.034393184,"teacher_disagreement_score":0.4601213,"about_ca_system_score_codex":0.000001695025,"about_ca_system_score_gemma":0.0005137101,"threshold_uncertainty_score":0.9832266},"labels":[],"label_agreement":null},{"id":"W6986854660","doi":"","title":"Response of cladocerans to native and invasive invertebrate predators in Lake Simcoe, Canada","year":2021,"lang":"en","type":"dissertation","venue":"QSpace (Queen's University Library)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Predation; Predator; Zooplankton; Phototaxis; Abundance (ecology); Invertebrate; Apex predator","score_opus":0.002957719300856954,"score_gpt":0.18683802977232164,"score_spread":0.1838803104714647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986854660","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99142593,0.00003341626,0.000016299302,0.00384602,0.00011405523,0.00029256818,0.00039942714,0.000012535267,0.003859729],"genre_scores_gemma":[0.83073455,0.00054377946,0.00211401,0.0008531033,0.000036662197,0.0000026167686,0.005487732,0.00007053724,0.160157],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987851,0.0002664703,0.00019711682,0.00035069106,0.00018713482,0.0002134844],"domain_scores_gemma":[0.9991643,0.00008466477,0.00021044968,0.00029480917,0.00009598507,0.00014978563],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000061600265,0.0002552413,0.0003105821,0.00024292571,0.000060823677,0.000023248831,0.00028760885,0.0003121992,0.00008060121],"category_scores_gemma":[0.0002880918,0.0003096243,0.000058508285,0.00037811237,0.000044372788,0.000032594005,0.00020106875,0.00029286058,0.0000011255452],"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":[0.013359356,0.00025391142,0.23029865,0.0026290005,0.0010056699,0.00082103995,0.015812147,0.0022800912,0.006721682,0.0007007646,0.7253537,0.0007639897],"study_design_scores_gemma":[0.0024065324,0.0009872692,0.16805063,0.0010748879,0.0001456191,0.0000022279064,0.029540224,0.000095832795,0.2817966,0.00003413899,0.514082,0.0017840482],"about_ca_topic_score_codex":0.08361808,"about_ca_topic_score_gemma":0.6930583,"teacher_disagreement_score":0.60944027,"about_ca_system_score_codex":0.000052366846,"about_ca_system_score_gemma":0.0022279501,"threshold_uncertainty_score":0.99993557},"labels":[],"label_agreement":null},{"id":"W6986872743","doi":"","title":"Relancer l'emploi et l'économie des quartiers en difficulté de Buckingham, Gatineau et Hull par le développement économique pour le CRÉEOM","year":2008,"lang":"fr","type":"other","venue":"Érudit documents and data repository (Érudit Consortium, University of Montreal)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Diafiltration; Dysgeusia; Liquation; Emperipolesis; Triacetin; Fusible alloy","score_opus":0.01374812847030013,"score_gpt":0.23201927051961452,"score_spread":0.2182711420493144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986872743","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7851717,0.009623911,0.014209118,0.011349441,0.00088927295,0.001834978,0.0021875885,0.00015783218,0.17457615],"genre_scores_gemma":[0.5152599,0.0687541,0.063521795,0.001424429,0.00072555745,0.000015161979,0.006326573,0.00037934378,0.3435931],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969993,0.00053636695,0.0006895297,0.0010185896,0.00017692185,0.00057926134],"domain_scores_gemma":[0.99676734,0.00016700447,0.0011741396,0.001413869,0.00014088443,0.0003367485],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046012594,0.0006477707,0.00076893985,0.00014312749,0.0005878145,0.00009643467,0.0010389052,0.00066967873,0.00013456486],"category_scores_gemma":[0.00018806894,0.00075224275,0.00019597191,0.00007360561,0.00082976813,0.00010567962,0.0011318933,0.00048633845,0.0000224355],"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":[0.0013957475,0.00162856,0.19482067,0.0017419488,0.005312578,0.0007865169,0.0031887803,0.004660599,0.015839728,0.0034507778,0.74741685,0.019757215],"study_design_scores_gemma":[0.0045790714,0.0004350566,0.046546713,0.000572966,0.00044058362,0.00035418832,0.0013612686,0.0018433586,0.0022686434,0.00013535576,0.94027656,0.0011862004],"about_ca_topic_score_codex":0.034377847,"about_ca_topic_score_gemma":0.020230798,"teacher_disagreement_score":0.26991177,"about_ca_system_score_codex":0.000490921,"about_ca_system_score_gemma":0.0014037373,"threshold_uncertainty_score":0.9994929},"labels":[],"label_agreement":null},{"id":"W6986894435","doi":"","title":"(Re)thinking public school architecture as a pedagogical tool","year":2021,"lang":"en","type":"dissertation","venue":"Lu Zone Ul (Laurentian University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Architecture; Context (archaeology); Process (computing); Politics; School education; Educational research","score_opus":0.011724405079232267,"score_gpt":0.24822322010596945,"score_spread":0.2364988150267372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986894435","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73547155,0.0014112429,0.010331088,0.0008056276,0.001598825,0.00073569384,0.000086857195,0.00022256517,0.24933657],"genre_scores_gemma":[0.34933966,0.00066269026,0.008976378,0.0009251296,0.0012377073,0.0000063248385,0.038668234,0.00019527307,0.5999886],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979645,0.0001664065,0.00030050508,0.00063690403,0.00045410686,0.00047756525],"domain_scores_gemma":[0.99847126,0.000019406207,0.0003274585,0.00069254026,0.00024147714,0.00024784237],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001392483,0.00045909226,0.0003700031,0.0003846347,0.00032188607,0.00020770909,0.000788358,0.000898074,0.0016658762],"category_scores_gemma":[0.00032518202,0.000517271,0.00037855734,0.0004127615,0.00006074581,0.000015847258,0.0002853567,0.0010190137,0.00009655345],"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":[0.00889433,0.005123958,0.034331013,0.014809185,0.019389655,0.008947764,0.08093558,0.005452292,0.2049985,0.10970713,0.2668628,0.24054779],"study_design_scores_gemma":[0.0011333042,0.00028724375,0.00051928306,0.00023483275,0.00028498104,0.00005541294,0.022889165,0.000066480294,0.0035534853,0.00012668436,0.9697434,0.0011057605],"about_ca_topic_score_codex":0.000041043208,"about_ca_topic_score_gemma":0.004353981,"teacher_disagreement_score":0.70288056,"about_ca_system_score_codex":0.00006846449,"about_ca_system_score_gemma":0.000606845,"threshold_uncertainty_score":0.9997279},"labels":[],"label_agreement":null},{"id":"W6986902785","doi":"","title":"Review of Sumarliði R. Ísleifsson &amp; Daniel Chartier (eds.) Iceland and Images of the North (Collection Droit au pôle), Québec: Presses de l´Université du Québec 2011, ISBN 9782760530874, xi + 611 pp.","year":2013,"lang":"fr","type":"article","venue":"DiVA at Umeå University (Umeå University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Field (mathematics); Context (archaeology); Government (linguistics); Subject (documents)","score_opus":0.003958254539474647,"score_gpt":0.16411776745860754,"score_spread":0.16015951291913288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986902785","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9306714,0.045346655,0.001022356,0.0059918426,0.000328789,0.0009904008,0.00032122925,0.000042631378,0.0152847115],"genre_scores_gemma":[0.40145352,0.3338858,0.0011048001,0.00044923747,0.00019271077,9.954014e-7,0.00036127988,0.00008476798,0.26246688],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99800134,0.0003878543,0.0003335646,0.00048364289,0.0002852835,0.000508288],"domain_scores_gemma":[0.99760944,0.00011425806,0.00071407587,0.00076205167,0.00053039525,0.00026978852],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021018658,0.0004122788,0.0005480211,0.00021205092,0.0006403124,0.00002418043,0.0009067132,0.0003617018,0.0009692188],"category_scores_gemma":[0.00017576476,0.00044798333,0.00035859208,0.00053902244,0.00086832885,0.0001407266,0.0013986132,0.0003583358,0.000054602227],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004849803,0.0004065595,0.69715357,0.006371181,0.000871043,0.00003948611,0.0023073186,0.00025999165,0.0067259385,0.00021568305,0.28018686,0.004977364],"study_design_scores_gemma":[0.0013773497,0.00030228388,0.0949498,0.00093901646,0.0007683798,0.000050275976,0.0006957297,0.00030864507,0.0019524893,0.0000036848862,0.89815295,0.0004993791],"about_ca_topic_score_codex":0.20923573,"about_ca_topic_score_gemma":0.12056604,"teacher_disagreement_score":0.6179661,"about_ca_system_score_codex":0.0007602453,"about_ca_system_score_gemma":0.0011867436,"threshold_uncertainty_score":0.99994403},"labels":[],"label_agreement":null},{"id":"W6986964091","doi":"","title":"Report to the President for year ended June 30, 2024, Anthropology","year":2024,"lang":"en","type":"other","venue":"DSpace@MIT (Massachusetts Institute of Technology)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Society for Cultural Anthropology; Universitetet i Bergen; Concordia University; Johns Hopkins University; National Academies of Sciences, Engineering, and Medicine; Wenner-Gren Foundation; Radcliffe Institute for Advanced Study, Harvard University; Wellcome Trust; American Association for the Advancement of Science; W. M. Keck Foundation; National Science Foundation","keywords":"Medical anthropology; Government (linguistics); Field (mathematics); Subject (documents)","score_opus":0.008493821226601497,"score_gpt":0.28449648454434107,"score_spread":0.2760026633177396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986964091","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":[0.0012784398,0.01840708,0.032234017,0.070263445,0.021164645,0.008299047,0.0021423062,0.0017076894,0.84450334],"genre_scores_gemma":[0.0034057612,0.00058609486,0.03238896,0.0003599254,0.00095928425,0.00040818838,0.00044593166,0.0005506897,0.9608952],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99773014,0.000028321776,0.0006340115,0.00078230683,0.0002890143,0.0005362206],"domain_scores_gemma":[0.99724495,0.000010721401,0.00056519517,0.0019668795,0.00012211128,0.00009015641],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0003005392,0.00053007464,0.0006170922,0.00066439057,0.000093361115,0.00003533799,0.0011344022,0.0015335943,0.00035772036],"category_scores_gemma":[0.0008929478,0.000418407,0.00026974583,0.00040518868,0.0007771033,0.0000050341564,0.00080354564,0.0006137041,0.00033903302],"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":[0.000029899671,0.00004626206,0.00017127118,0.0003770116,0.0006060455,0.000046946476,0.000048217236,0.00004447119,0.0017573115,0.0023770346,0.99329615,0.0011994109],"study_design_scores_gemma":[0.0003703158,0.0003164491,0.000012697329,0.00021634247,0.0001891696,0.00014305962,0.000087545945,0.000026500127,0.005771887,0.00027708878,0.9921569,0.0004319996],"about_ca_topic_score_codex":0.00006271357,"about_ca_topic_score_gemma":0.00062717835,"teacher_disagreement_score":0.11639183,"about_ca_system_score_codex":0.00004594668,"about_ca_system_score_gemma":0.00024892698,"threshold_uncertainty_score":0.9998268},"labels":[],"label_agreement":null},{"id":"W6987178156","doi":"","title":"Sintering behavior of HA/Ti composites","year":2007,"lang":"en","type":"article","venue":"NPARC","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sintering; Powder metallurgy; Fabrication; Microstructure; Biocompatibility","score_opus":0.007154022671720999,"score_gpt":0.26649727029578274,"score_spread":0.25934324762406175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6987178156","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9563097,0.00002656285,0.008059849,0.000024856989,0.00007205845,0.00006223102,0.0000040478526,0.000010058073,0.03543069],"genre_scores_gemma":[0.97573197,0.0000048024717,0.023729296,0.000071028044,0.000053800493,0.0000017248857,0.000031048017,0.000008739139,0.00036758633],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99953765,0.0000084044805,0.00017366487,0.00007668871,0.000076998265,0.00012658411],"domain_scores_gemma":[0.9996718,0.000008968116,0.000068244095,0.00017774623,0.000037790654,0.000035456684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015754743,0.00006523328,0.00007333778,0.000027109354,0.000023885681,0.0000063426446,0.00011849244,0.00004974575,0.00006957152],"category_scores_gemma":[0.000038324935,0.00006265066,0.00004306307,0.00003281388,0.000045914,0.0000014288818,0.00008079197,0.000060815906,0.000008734804],"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":[0.0000206541,0.000028043289,0.02006266,0.000018722612,0.000009087307,0.0000017543642,0.000045005232,0.000015255785,0.9743595,0.00013577801,0.00040191528,0.0049016313],"study_design_scores_gemma":[0.0002041045,0.00018097243,0.017233126,0.00001322023,0.0000122343845,0.000026568314,0.0000385955,0.00027682897,0.9685705,0.000024173989,0.01331787,0.00010180602],"about_ca_topic_score_codex":0.000003779868,"about_ca_topic_score_gemma":0.0000063248094,"teacher_disagreement_score":0.035063103,"about_ca_system_score_codex":0.0000045663323,"about_ca_system_score_gemma":0.000008810568,"threshold_uncertainty_score":0.255482},"labels":[],"label_agreement":null},{"id":"W6987227411","doi":"","title":"Skriftlig spørsmål fra Anette Trettebergstuen (A) til samferdselsministeren","year":2015,"lang":"no","type":"other","venue":"Duo Research Archive (University of Oslo)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Term (time); Quarter (Canadian coin)","score_opus":0.02771019192879907,"score_gpt":0.2893344996565675,"score_spread":0.2616243077277684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6987227411","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":[0.019330842,0.001272874,0.0029122944,0.0013954213,0.0002901278,0.0012065971,0.002427609,0.00005784993,0.9711064],"genre_scores_gemma":[0.05095201,0.0042902743,0.023040239,0.0002881106,0.0014326071,0.0000043697523,0.008396757,0.0005367778,0.91105884],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943823,0.0013100286,0.0004375186,0.001019461,0.0015876747,0.0012630043],"domain_scores_gemma":[0.99612796,0.00023091934,0.00055500976,0.0016911909,0.0006537517,0.0007411589],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018635025,0.0006321761,0.00090647954,0.00097075466,0.00046141777,0.00007767392,0.002351886,0.00087157043,0.0036025618],"category_scores_gemma":[0.0005985062,0.0007537279,0.00038630076,0.000570441,0.0021390514,0.000022573091,0.0023280506,0.001840273,0.0017483347],"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":[0.0008428744,0.0003209972,0.0022363022,0.00074889656,0.00074050075,0.00017689994,0.003013463,0.000046707293,0.0077800076,0.00039913788,0.9726859,0.0110083595],"study_design_scores_gemma":[0.0017808399,0.0015537302,0.0027537155,0.00032784176,0.00009679228,0.000031177675,0.0022008568,0.0013733037,0.00020040885,0.00031167376,0.9886553,0.000714337],"about_ca_topic_score_codex":0.001005983,"about_ca_topic_score_gemma":0.0013549234,"teacher_disagreement_score":0.06004753,"about_ca_system_score_codex":0.00012105098,"about_ca_system_score_gemma":0.0012025818,"threshold_uncertainty_score":0.9994914},"labels":[],"label_agreement":null},{"id":"W6987278316","doi":"","title":"The sounds of English around the world an introduction to phonetics and phonology","year":2023,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Phonetics; Phonology; Varieties of English; Intonation (linguistics); Active listening; Stress (linguistics)","score_opus":0.004993861353211327,"score_gpt":0.24909807798798214,"score_spread":0.2441042166347708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6987278316","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":[0.012178589,0.0024653238,0.0032284872,0.008403433,0.010223216,0.0018719207,0.00009969535,0.00058135315,0.960948],"genre_scores_gemma":[0.003956498,0.0008619389,0.0020865703,0.0003646687,0.0049621486,0.000028521843,0.000093836876,0.00035683767,0.98728895],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99924433,0.000065729466,0.00019945198,0.00021358009,0.000101545105,0.00017533405],"domain_scores_gemma":[0.99902415,0.000041230316,0.00014937314,0.00066353846,0.00008076843,0.000040925654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028780577,0.00015983403,0.00014041994,0.000073645846,0.00007936519,0.000040710052,0.0002899466,0.00018521695,0.00007172137],"category_scores_gemma":[0.00047378955,0.0000936683,0.00003521234,0.00013233724,0.00020827774,0.0000012459644,0.00019823073,0.00017877204,0.000014215382],"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":[0.000026032445,0.000012759451,0.00029516002,0.000026490776,0.00010521275,1.1070431e-7,0.00027098338,0.000062598425,0.0009907179,0.0012031945,0.9923656,0.004641156],"study_design_scores_gemma":[0.00009563507,0.00015927172,0.0001513668,0.0000058602313,0.00001953198,0.0000021910837,0.00032843632,0.000084753505,0.0010752395,0.000033882217,0.99792504,0.00011881665],"about_ca_topic_score_codex":0.00008094555,"about_ca_topic_score_gemma":0.006532991,"teacher_disagreement_score":0.026340997,"about_ca_system_score_codex":0.0000067073033,"about_ca_system_score_gemma":0.000026386371,"threshold_uncertainty_score":0.38196823},"labels":[],"label_agreement":null},{"id":"W6987335514","doi":"","title":"Stuart Houston: 75 Years of Bird Banding in Saskatchewan","year":2024,"lang":"en","type":"article","venue":"Digital Commons - University of South Florida (University of South Florida)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Ectotherm; Population; Electrocution","score_opus":0.008675217932845748,"score_gpt":0.19251861362625453,"score_spread":0.18384339569340877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6987335514","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99065995,0.00012103376,0.0043606367,0.000051969157,0.00021524183,0.00017944365,0.00046595605,0.000069143454,0.0038766125],"genre_scores_gemma":[0.9979529,0.000020470861,0.0009923447,0.000006338464,0.000047957175,4.3337433e-8,0.00010914249,0.000028826611,0.0008420149],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.998701,0.000043649372,0.00024844828,0.00035358954,0.0003463587,0.0003069872],"domain_scores_gemma":[0.99898857,0.000051894287,0.00023541658,0.00047593334,0.0001168463,0.0001313321],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021960118,0.00022418117,0.00042994044,0.000434539,0.000110505556,0.000028074188,0.000666019,0.00024384905,0.00004730159],"category_scores_gemma":[0.000045863435,0.0003204876,0.00030714154,0.0005491685,0.0005168838,0.000083877276,0.00054441235,0.00031979007,0.000034268265],"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":[0.0033894198,0.00048695097,0.74507743,0.0026766073,0.0017992171,0.00057173794,0.20204712,0.0070887874,0.010672079,0.0019439249,0.0036734687,0.020573229],"study_design_scores_gemma":[0.009312082,0.0031157946,0.23021397,0.0019217447,0.00075658,0.000053008414,0.6895117,0.010386856,0.0040405164,0.0002852534,0.047459926,0.002942541],"about_ca_topic_score_codex":0.00035119042,"about_ca_topic_score_gemma":0.00038206202,"teacher_disagreement_score":0.5148635,"about_ca_system_score_codex":0.00005703677,"about_ca_system_score_gemma":0.00018613621,"threshold_uncertainty_score":0.9999247},"labels":[],"label_agreement":null},{"id":"W6987439709","doi":"","title":"Studi Perbandingan Pembuatan Dan Penggunaan Perangkat Antigen Ebl Galur Lokal Dengan Perangkat Produk IAF Canada","year":2000,"lang":"en","type":"dissertation","venue":"Universitas Airlangga Repository (Universitas Airlangga)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Complement fixation test; Antigen; Enzootic; Serology; Ouchterlony double immunodiffusion; Leucosis; Immunodiffusion; Inoculation","score_opus":0.0024126647991971365,"score_gpt":0.18436095133263686,"score_spread":0.18194828653343972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6987439709","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8826291,0.0021148012,0.000026767138,0.00015294625,0.0016252766,0.00095605565,0.00032326463,0.00019174394,0.11198007],"genre_scores_gemma":[0.94181395,0.00036260835,0.00046499877,0.00019164292,0.00086680043,0.000008416274,0.01211889,0.00021954738,0.04395314],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99514747,0.00033513937,0.0006482342,0.001499659,0.0011985023,0.0011709983],"domain_scores_gemma":[0.99664235,0.000039357667,0.0007097959,0.0015130865,0.0004981362,0.00059728365],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00026340433,0.001244611,0.0009600922,0.0005355994,0.00169692,0.0002008276,0.0016185325,0.001008884,0.00083585235],"category_scores_gemma":[0.00006502667,0.0014533557,0.00056521076,0.00050826307,0.00020943399,0.00010521492,0.00033526003,0.0012457065,0.00006730361],"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":[0.0045776605,0.00072370906,0.05194602,0.0017556123,0.0039551565,0.005317683,0.01727227,0.0021303613,0.054728813,0.00062400236,0.85469115,0.002277543],"study_design_scores_gemma":[0.0069898823,0.002724173,0.0748273,0.0010260155,0.0032364833,0.0012763384,0.31251794,0.0011443475,0.014332275,0.00001215227,0.5747866,0.007126515],"about_ca_topic_score_codex":0.029419849,"about_ca_topic_score_gemma":0.06997581,"teacher_disagreement_score":0.29524568,"about_ca_system_score_codex":0.0010478792,"about_ca_system_score_gemma":0.0020265367,"threshold_uncertainty_score":0.99960274},"labels":[],"label_agreement":null},{"id":"W6987620292","doi":"","title":"Town of Blue Hill Maine Financial Report 2018","year":2018,"lang":"en","type":"article","venue":"DigitalCommons (California Polytechnic State University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Medical Research Council","keywords":"Audit; Financial Audit; Financial management; Work (physics); Quarter (Canadian coin)","score_opus":0.007879975301047996,"score_gpt":0.21717641867030799,"score_spread":0.20929644336925998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6987620292","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78992635,0.00005135186,0.04190728,0.00029074418,0.0002422027,0.0003761918,0.0011038961,0.00014881074,0.16595319],"genre_scores_gemma":[0.99144167,0.000038383903,0.002062076,0.00011990074,0.00010864995,8.717729e-7,0.00040687187,0.00002340285,0.0057981517],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987745,0.000038726357,0.0003770174,0.00028855124,0.00017972836,0.00034144678],"domain_scores_gemma":[0.998662,0.000021455662,0.00031320396,0.00070839445,0.00016321443,0.00013170767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022592282,0.00021086431,0.00022590032,0.00023900789,0.00011534682,0.000019887384,0.0004583241,0.00017363818,0.000057362136],"category_scores_gemma":[0.00030851449,0.00022186874,0.00015923053,0.0004000885,0.00043799577,0.000016602038,0.00044164027,0.00015310077,0.00005134421],"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":[0.0040179486,0.002313025,0.13232942,0.0005771312,0.0014460187,0.001698225,0.0009721161,0.0012692478,0.2583756,0.027779099,0.44766173,0.12156041],"study_design_scores_gemma":[0.0005708243,0.00052101474,0.0013354105,0.000030417003,0.000029874922,0.00014541432,0.0000646952,0.00028489728,0.040164616,0.00011960364,0.95639443,0.00033880977],"about_ca_topic_score_codex":0.00004965602,"about_ca_topic_score_gemma":0.00008504328,"teacher_disagreement_score":0.5087327,"about_ca_system_score_codex":0.000045787816,"about_ca_system_score_gemma":0.00016149174,"threshold_uncertainty_score":0.9047545},"labels":[],"label_agreement":null},{"id":"W6987770772","doi":"","title":"4-5\\tYouth, Masculinity, and Sexuality","year":2021,"lang":"en","type":"article","venue":"Scholarship@Western (Western University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Human sexuality; Class (philosophy); Homosexuality; Working class; Lesbian; Heteronormativity","score_opus":0.055848485885059584,"score_gpt":0.3211504019609161,"score_spread":0.2653019160758565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6987770772","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99662995,0.00017108845,0.001629507,0.0002684466,0.0001477288,0.00010418151,0.00003536505,0.00005094661,0.0009627825],"genre_scores_gemma":[0.9894766,0.00018041726,0.00039105662,0.0006294097,0.00013292805,4.7540468e-7,0.00017532539,0.000028521077,0.008985247],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985468,0.00026410117,0.00020711805,0.0004512948,0.0002150842,0.0003156162],"domain_scores_gemma":[0.9988875,0.000027447026,0.00012266483,0.00059133465,0.00016038433,0.00021070142],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031512478,0.0002308625,0.00021176403,0.00008999687,0.00018822997,0.00015962766,0.00033743202,0.00025260224,0.000023796398],"category_scores_gemma":[0.00014724744,0.00026745014,0.00009169403,0.00018846673,0.000120811455,0.000049373557,0.0007673657,0.0003705689,0.00005913232],"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":[0.00004533341,0.00005635056,0.9901627,0.000072659765,0.00007484918,0.000089788606,0.00019062746,0.000023248727,0.008681057,0.00005642521,0.000003985976,0.0005430307],"study_design_scores_gemma":[0.0011946996,0.00016290281,0.9441979,0.000047950576,0.0000676487,0.00019708276,0.00045529942,0.0000015048628,0.02119066,0.000059317113,0.031932235,0.00049280643],"about_ca_topic_score_codex":0.0000017704429,"about_ca_topic_score_gemma":0.00043614552,"teacher_disagreement_score":0.04596475,"about_ca_system_score_codex":0.000028986839,"about_ca_system_score_gemma":0.000111498135,"threshold_uncertainty_score":0.99997777},"labels":[],"label_agreement":null},{"id":"W6988009182","doi":"","title":"Worker Empowerment through Multi-Stakeholder Governance? A Solidarity Co-operative Case Study","year":2022,"lang":"en","type":"dissertation","venue":"Spectrum Research Repository (Concordia University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Solidarity; Solidarity economy; Corporate governance; Empowerment; Participant observation; Democracy; Perspective (graphical); Democratic governance","score_opus":0.04212633389572999,"score_gpt":0.3512682429572416,"score_spread":0.3091419090615116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6988009182","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9038906,0.000262556,0.000047607766,0.000051691888,0.0007326278,0.001511844,0.000082139406,0.000047777055,0.09337312],"genre_scores_gemma":[0.8614178,0.00016240266,0.00009263715,0.000018804687,0.00024138443,0.00003097433,0.00066555187,0.000075394586,0.1372951],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99541533,0.0012746047,0.0004423666,0.0010232503,0.0010265523,0.00081787986],"domain_scores_gemma":[0.99789274,0.00007546785,0.00038159295,0.0011271646,0.00029063685,0.00023237725],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00071297796,0.0005019076,0.00047346437,0.00027213892,0.0017598285,0.00020970924,0.00090607576,0.00041431197,0.0003411189],"category_scores_gemma":[0.00013549915,0.0005634505,0.0002563646,0.0005877096,0.00023945393,0.000038759066,0.0005577037,0.00214018,0.00002544932],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0135156885,0.013286699,0.531457,0.0017464213,0.009758374,0.19201507,0.1015833,0.0020537013,0.05549213,0.002037038,0.07317675,0.0038778498],"study_design_scores_gemma":[0.008365161,0.008305692,0.06688425,0.00019255115,0.00043869868,0.0023626748,0.30958965,0.00058501324,0.037179902,0.000032109183,0.5631069,0.0029573904],"about_ca_topic_score_codex":0.014655297,"about_ca_topic_score_gemma":0.03645848,"teacher_disagreement_score":0.48993015,"about_ca_system_score_codex":0.0007344149,"about_ca_system_score_gemma":0.0013778502,"threshold_uncertainty_score":0.9996817},"labels":[],"label_agreement":null},{"id":"W6995693351","doi":"","title":"Philippines Quarterly Update, December 2011 : Sustaining Growth in Uncertain Times","year":2017,"lang":"en","type":"report","venue":"The World Bank Open Knowledge Repository (World Bank)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Disbursement; Government (linguistics); Quarter (Canadian coin); Consumption (sociology); Public sector; Production (economics); Agriculture; Investment (military)","score_opus":0.020678704092397596,"score_gpt":0.3245818618222803,"score_spread":0.30390315772988274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6995693351","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":[0.0029824194,0.008466911,0.000037648795,0.0009980267,0.0035128202,0.0019758048,0.00004376369,0.000090167414,0.98189247],"genre_scores_gemma":[0.20317051,0.0005528923,0.0008983339,0.00017653612,0.0036458203,0.0003776147,0.00072110945,0.00028423106,0.79017293],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99413687,0.0007943637,0.0017715273,0.0013487064,0.00077264087,0.0011759014],"domain_scores_gemma":[0.9932377,0.00019998506,0.0017978899,0.0033048098,0.0012180881,0.0002415317],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0032030644,0.0012322421,0.0013946199,0.0006742918,0.001132533,0.0010582213,0.0048649064,0.00057932606,0.00053801533],"category_scores_gemma":[0.00050579285,0.00097645214,0.0004951545,0.00048093498,0.0005572471,0.000076376455,0.0021982046,0.0016928209,0.0003610939],"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":[0.00041088677,0.00039417075,0.010406025,0.001070358,0.0008630656,0.00021400658,0.0009900321,0.00008947211,0.0007692738,0.0006336209,0.9669759,0.017183177],"study_design_scores_gemma":[0.0010406428,0.00024243044,0.004002118,0.00096877577,0.00027393608,0.00032006865,0.00014969359,0.0003843609,0.0017487801,0.00028780906,0.9890756,0.001505756],"about_ca_topic_score_codex":0.0015028059,"about_ca_topic_score_gemma":0.014846696,"teacher_disagreement_score":0.20018809,"about_ca_system_score_codex":0.0004607233,"about_ca_system_score_gemma":0.003335777,"threshold_uncertainty_score":0.9999788},"labels":[],"label_agreement":null},{"id":"W7001366262","doi":"","title":"International Contracts","year":2018,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Variety (cybernetics); Agency (philosophy); Cover (algebra); Product (mathematics); Commercial law; Key (lock)","score_opus":0.005083616238602752,"score_gpt":0.2689332316787881,"score_spread":0.2638496154401853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7001366262","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19508158,0.0000078530675,0.013218349,0.0004735593,0.00040981837,0.00003916167,0.0000020536172,0.000018938466,0.7907487],"genre_scores_gemma":[0.9824707,0.00000795659,0.009056221,0.0011750471,0.0005637098,0.0000013083379,0.000037322763,0.000004581964,0.00668314],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99974126,0.0000056663926,0.00006817383,0.00006205785,0.000053923122,0.00006889313],"domain_scores_gemma":[0.9997806,0.0000024193444,0.000023354105,0.000111044006,0.00005868058,0.000023926086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000060828457,0.000037765793,0.00002474876,0.000011603854,0.000023707322,0.0000141441415,0.000110815534,0.00003782605,0.00048520637],"category_scores_gemma":[0.00009506206,0.00003185389,0.00001679498,0.000013843245,0.000040581264,0.0000012279917,0.000053072017,0.000026803757,0.00019927429],"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":[0.00015026038,0.000096252195,0.03130156,0.0000081574435,0.00016441177,0.0000020905875,0.00021427184,0.000034473895,0.65492135,0.009026414,0.2489793,0.05510144],"study_design_scores_gemma":[0.00017046496,0.000094329655,0.0028176007,0.0000010927541,0.0000012990982,0.000010026725,0.000011110788,0.0011023057,0.05712543,0.000024141389,0.93858653,0.00005564564],"about_ca_topic_score_codex":0.000003560284,"about_ca_topic_score_gemma":0.0000060825087,"teacher_disagreement_score":0.78738916,"about_ca_system_score_codex":0.000002350788,"about_ca_system_score_gemma":0.000009420828,"threshold_uncertainty_score":0.5312669},"labels":[],"label_agreement":null},{"id":"W7001613307","doi":"","title":"Johnson, Paul Michael. Affective Geographies: Cervantes, Emotion, and the Literary Mediterranean. Toronto/Buffalo/London: University ofToronto Press, 2020. 307 pp. (ISBN: 978-1-4875-0751-0) [RESEÑA]","year":2021,"lang":"en","type":"other","venue":"Deposito Adademico Digital Universidad De Navarra (University of Navarra)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Narrative; Affect (linguistics); Perception; Subject (documents)","score_opus":0.003696430629021543,"score_gpt":0.19372351503997998,"score_spread":0.19002708441095845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7001613307","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":[0.058544192,0.28011787,0.014902076,0.0029116683,0.0020110933,0.0047207307,0.006243144,0.0008435985,0.6297056],"genre_scores_gemma":[0.20480579,0.19769755,0.008400071,0.00069698755,0.002146701,0.0000041135254,0.0110367285,0.0010741117,0.5741379],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99680465,0.0004567557,0.0003670181,0.0010314544,0.00062885083,0.0007112464],"domain_scores_gemma":[0.9971287,0.00018341142,0.00087529543,0.0010736344,0.00031283937,0.00042607915],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00029814575,0.0008106211,0.0009601609,0.00016108318,0.0004706208,0.0001567708,0.0014693224,0.0013404592,0.00038120433],"category_scores_gemma":[0.00014359895,0.0008900853,0.0005930242,0.00038445258,0.0013543261,0.00019156162,0.0012213002,0.00081618375,0.0000088849365],"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":[0.0026842644,0.00033082126,0.003744837,0.0012047085,0.0030729081,0.000880349,0.0052239634,0.00005259512,0.0018979376,0.0005778091,0.97416335,0.0061664768],"study_design_scores_gemma":[0.0056868223,0.00040414682,0.0014795678,0.0007615595,0.00055183854,0.00043061725,0.009019934,0.00070083496,0.00018118462,0.000044560747,0.9795671,0.0011718229],"about_ca_topic_score_codex":0.0071678306,"about_ca_topic_score_gemma":0.0029354095,"teacher_disagreement_score":0.1462616,"about_ca_system_score_codex":0.00029946628,"about_ca_system_score_gemma":0.00033087225,"threshold_uncertainty_score":0.999956},"labels":[],"label_agreement":null},{"id":"W7001624361","doi":"","title":"Les opérations scrutées sous l'angle de l'intérêt public par les organismes de réglementation des valeurs mobilières : entre efficience et duplicité","year":2008,"lang":"fr","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Vulnerability (computing); Pilotage; Criminal liability; Decantation","score_opus":0.005149604060940892,"score_gpt":0.18140097452730464,"score_spread":0.17625137046636374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7001624361","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6393151,0.0030556184,0.013834614,0.0045651975,0.00022203791,0.0006194771,0.0009559665,0.000031828014,0.33740014],"genre_scores_gemma":[0.9370845,0.0033299336,0.015099061,0.001200278,0.00013391272,0.000028228003,0.00023923862,0.00010650785,0.042778336],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.997518,0.0002405846,0.0004540821,0.00037814808,0.00084114115,0.000568025],"domain_scores_gemma":[0.99876064,0.00017889698,0.00040668697,0.0003203611,0.0000039099095,0.00032949887],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000037935377,0.00041344052,0.000315583,0.000052293093,0.0005558114,0.00008536918,0.0004512752,0.00015446647,0.0005395041],"category_scores_gemma":[0.00005440697,0.00042495615,0.000066285436,0.000100742574,0.00050001993,0.00005404307,0.0002671089,0.00026942152,2.9869287e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024695188,0.00039146966,0.5328689,0.0020619843,0.00078477093,0.000116634226,0.003088934,0.008228897,0.22795698,0.08277899,0.01671928,0.12475618],"study_design_scores_gemma":[0.001346204,0.0007886632,0.16017415,0.0007118613,0.00021297047,0.00020123189,0.019138476,0.015400736,0.37338263,0.0008517544,0.42604,0.0017513263],"about_ca_topic_score_codex":0.0095550595,"about_ca_topic_score_gemma":0.089104496,"teacher_disagreement_score":0.4093207,"about_ca_system_score_codex":0.000040646573,"about_ca_system_score_gemma":0.0031760475,"threshold_uncertainty_score":0.99982023},"labels":[],"label_agreement":null},{"id":"W7001716865","doi":"","title":"La obligación de negociar con buena fe una convención colectiva de trabajo en el régimen laboral quebequense","year":2013,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Constitution; Jurisprudence; Negotiation; Good faith; State (computer science); Doctrine; Collective bargaining; Labour law","score_opus":0.05889207788669838,"score_gpt":0.5069242289239074,"score_spread":0.44803215103720906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7001716865","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9858024,0.0027231607,0.001312704,0.000347698,0.0001756417,0.00058633764,0.000049310216,0.000038408412,0.008964345],"genre_scores_gemma":[0.99325275,0.0028037424,0.0017641743,0.001102264,0.00025714183,0.000075102034,0.00005912432,0.00007639658,0.00060932845],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99700516,0.0007914118,0.00077395054,0.00038194587,0.00041249034,0.0006350329],"domain_scores_gemma":[0.9976928,0.00022439775,0.0007337762,0.0005549354,0.00039631975,0.00039776813],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016337556,0.00039904204,0.0005810958,0.00029611037,0.00020955238,0.0008112477,0.0019799408,0.00041891224,0.0019391837],"category_scores_gemma":[0.00095506536,0.00038251048,0.00020046701,0.00044630826,0.00022919626,0.00017267016,0.0006876887,0.00068095507,0.000034878758],"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":[0.0001445669,0.00015390269,0.23909281,0.00013332846,0.00026466456,0.000022402735,0.00043820293,0.00039973517,0.7191901,0.00020491892,0.035279445,0.004675896],"study_design_scores_gemma":[0.0016780884,0.000102749276,0.545411,0.00037530332,0.000118900345,0.00019482577,0.0003766432,0.0016384147,0.4109784,0.0047557615,0.03337614,0.0009937589],"about_ca_topic_score_codex":0.003256234,"about_ca_topic_score_gemma":0.000093799645,"teacher_disagreement_score":0.3082117,"about_ca_system_score_codex":0.00016294158,"about_ca_system_score_gemma":0.00061098905,"threshold_uncertainty_score":0.9998627},"labels":[],"label_agreement":null},{"id":"W7001724399","doi":"","title":"Le portage du Témiscouata","year":2013,"lang":"fr","type":"other","venue":"Érudit documents and data repository (Érudit Consortium, University of Montreal)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"College of Engineering, Michigan State University; University of Illinois at Urbana-Champaign; University of Toronto; Queen's University; University of Missouri; McGill University; University of Alberta; Université Laval; Michigan State University; National Geographic Society","keywords":"","score_opus":0.0049493724091625585,"score_gpt":0.19852519689488551,"score_spread":0.19357582448572297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7001724399","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":[0.03835228,0.012058771,0.0023596643,0.0018394,0.0014650893,0.0014173739,0.0025040386,0.000082971485,0.9399204],"genre_scores_gemma":[0.13387287,0.01754077,0.0031940043,0.00016972604,0.0007192288,0.0000023469386,0.006191747,0.00017334119,0.83813596],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99715334,0.00022294467,0.0006338911,0.001105116,0.00038181673,0.00050289195],"domain_scores_gemma":[0.9956566,0.000077244455,0.0012716157,0.0024624413,0.00017541541,0.0003566744],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00026981562,0.0006158346,0.0007577022,0.0001471338,0.00051315007,0.000107567386,0.0016083873,0.000713525,0.0012431395],"category_scores_gemma":[0.00014993375,0.0007099164,0.00016790937,0.00009136201,0.0008936137,0.000094391864,0.0021790548,0.00037930015,0.00011049441],"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":[0.00028312826,0.0005944108,0.017695406,0.0011535564,0.0024371478,0.0006044418,0.0001916146,0.00007915583,0.0039943894,0.0053025875,0.94570076,0.021963384],"study_design_scores_gemma":[0.0017369135,0.00024603645,0.0034019703,0.00025937034,0.0005030493,0.00022492088,0.00040348197,0.00090575754,0.00028971673,0.000018396635,0.99132144,0.00068893767],"about_ca_topic_score_codex":0.024716655,"about_ca_topic_score_gemma":0.009949153,"teacher_disagreement_score":0.101784445,"about_ca_system_score_codex":0.00009780439,"about_ca_system_score_gemma":0.00041751124,"threshold_uncertainty_score":0.99966985},"labels":[],"label_agreement":null},{"id":"W7001761431","doi":"","title":"Les facteurs associés à la fatigue persistante chez des femmes atteintes du cancer du sein en phase post-traitement","year":2001,"lang":"fr","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Breast cancer; Risk factor; Epidemiology; Cancer; Disease","score_opus":0.006698433712045139,"score_gpt":0.20389589508890804,"score_spread":0.1971974613768629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7001761431","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41692534,0.004963671,0.0009334956,0.008515291,0.00038247748,0.0004907383,0.0033838188,0.000017321046,0.56438786],"genre_scores_gemma":[0.7967122,0.0053748447,0.0015425476,0.0012801901,0.0003505463,0.000022714737,0.00028006357,0.00013830393,0.19429858],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.997313,0.0002649034,0.0004928347,0.00040947908,0.0010048058,0.0005149374],"domain_scores_gemma":[0.998688,0.00020068402,0.0004940166,0.00028096102,0.00000382443,0.00033254232],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0000356312,0.00055412686,0.00047329158,0.00003714112,0.00024456892,0.0000624011,0.0004263518,0.00019323303,0.0016111224],"category_scores_gemma":[0.000033259752,0.00054307847,0.000112892696,0.00006155672,0.00035962486,0.000032689728,0.000287674,0.00034206657,1.6252756e-8],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012001414,0.00047143007,0.5340025,0.0035532892,0.0030298429,0.0004016385,0.002215428,0.0008328418,0.17187046,0.021705955,0.016944299,0.24377221],"study_design_scores_gemma":[0.0014120003,0.00044393705,0.033893805,0.0007946487,0.00017550608,0.000047201567,0.0073715276,0.0020232962,0.044587053,0.000024506266,0.90833527,0.00089125044],"about_ca_topic_score_codex":0.033264894,"about_ca_topic_score_gemma":0.17506774,"teacher_disagreement_score":0.891391,"about_ca_system_score_codex":0.000038721973,"about_ca_system_score_gemma":0.0017956108,"threshold_uncertainty_score":0.9997021},"labels":[],"label_agreement":null},{"id":"W7001773734","doi":"","title":"Le développement de l'agression indirecte chez les filles : facteurs de risque à l'enfance et conséquences associées à l'adolescence","year":2016,"lang":"fr","type":"dissertation","venue":"Knowledge UdeS (Institutional Deposit of the University of Sherbrooke)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Université de Sherbrooke","keywords":"Indeterminism; Social relationship; Social partners","score_opus":0.008872819663946674,"score_gpt":0.2461815097040487,"score_spread":0.23730869004010202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7001773734","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9451487,0.008306908,0.03184434,0.0007267173,0.00041061285,0.00033525022,0.00008768039,0.000019918409,0.013119864],"genre_scores_gemma":[0.97990954,0.006072428,0.010918908,0.000040789215,0.000055927783,0.0000014382019,0.00016648734,0.000017335107,0.0028171532],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99823856,0.00037731786,0.00039143092,0.00034030707,0.00031522996,0.00033712212],"domain_scores_gemma":[0.99865836,0.00007624886,0.0005310193,0.00032019074,0.00030068422,0.000113488044],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004064785,0.00034773035,0.0003803493,0.0001010698,0.00075290794,0.000020468684,0.0009539831,0.00058114255,0.000032206262],"category_scores_gemma":[0.00029552155,0.00031117827,0.00034159105,0.00014148402,0.0010740937,0.000032850392,0.00031773376,0.00037988252,0.000010479314],"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":[0.00035939,0.00041855886,0.26129144,0.0061241365,0.00051947095,0.0000067177407,0.016944509,0.011002836,0.6915981,0.0047247205,0.0013336239,0.0056765024],"study_design_scores_gemma":[0.00078979507,0.00012304932,0.3528556,0.010868254,0.0001939305,0.000024864294,0.0013023216,0.0024053229,0.62196136,0.00012769885,0.008916067,0.00043172913],"about_ca_topic_score_codex":0.0018579662,"about_ca_topic_score_gemma":0.014301598,"teacher_disagreement_score":0.09156416,"about_ca_system_score_codex":0.0006617787,"about_ca_system_score_gemma":0.0016377219,"threshold_uncertainty_score":0.999934},"labels":[],"label_agreement":null},{"id":"W7001882998","doi":"","title":"Les enjeux et les défis de la gestion stratégique du changement dans les organismes de développement local au Québec : pour une meilleure performance organisationnelle","year":2012,"lang":"fr","type":"dissertation","venue":"Le dépôt institutionnel (Université du Québec à Trois-Rivières)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Work (physics); Pilotage","score_opus":0.010042095218530559,"score_gpt":0.22978192307534703,"score_spread":0.21973982785681648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7001882998","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60668147,0.0007655915,0.37929755,0.010904283,0.00022896961,0.00038217424,0.000058361078,0.00008717856,0.0015944134],"genre_scores_gemma":[0.98532283,0.0016709651,0.007363209,0.00021161244,0.00060823647,0.000052451847,0.0018770886,0.000117362535,0.0027762437],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99660784,0.000742445,0.00066660787,0.000663544,0.00046761942,0.0008519369],"domain_scores_gemma":[0.99771696,0.00019929836,0.0007003279,0.0005650917,0.0004583307,0.00035999133],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.000989527,0.0008725566,0.00052663026,0.0002817444,0.0023230081,0.00012382778,0.0007970601,0.0013366959,0.00048420407],"category_scores_gemma":[0.0004381203,0.0009599904,0.00028453275,0.00034477978,0.0006854104,0.00012687608,0.00031921163,0.0010799919,0.00006908952],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0005304176,0.0011952058,0.57947975,0.0017311224,0.0009170588,0.000060936218,0.17496274,0.13756801,0.037795354,0.035276644,0.0015233778,0.028959379],"study_design_scores_gemma":[0.002899664,0.00058645796,0.8093491,0.000600054,0.0006787244,0.00034554943,0.09989726,0.043242525,0.017688511,0.000052645235,0.023043258,0.0016162326],"about_ca_topic_score_codex":0.7604995,"about_ca_topic_score_gemma":0.8847866,"teacher_disagreement_score":0.37864134,"about_ca_system_score_codex":0.0038369785,"about_ca_system_score_gemma":0.007062419,"threshold_uncertainty_score":0.9999871},"labels":[],"label_agreement":null},{"id":"W7001901072","doi":"","title":"Lífsglaðar í líkamsrækt","year":2007,"lang":"is","type":"dissertation","venue":"Skemman","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Nunavut Arctic College","funders":"","keywords":"Object (grammar); Work (physics); Verisimilitude","score_opus":0.0065560032583294615,"score_gpt":0.3156270109981664,"score_spread":0.309071007739837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7001901072","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6736798,0.0028069313,0.0023198065,0.00016591894,0.0037020529,0.00092516193,0.00011881664,0.00010572947,0.31617576],"genre_scores_gemma":[0.8208948,0.001342051,0.0076643038,0.0013003019,0.0029119283,0.00004735006,0.02659815,0.0003297614,0.13891137],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99695617,0.00010096073,0.000907566,0.0007006381,0.00052389083,0.0008107953],"domain_scores_gemma":[0.9976665,0.00003528267,0.00066729565,0.0010804234,0.00028166742,0.00026887233],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006008903,0.0007383457,0.0005124853,0.00023738034,0.00029128508,0.000115929666,0.000738952,0.001530843,0.00050850067],"category_scores_gemma":[0.00033211042,0.000785073,0.0004008444,0.00024042201,0.00012621905,0.000007217006,0.00017000354,0.0009055329,0.0009966862],"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":[0.0033849527,0.001853848,0.04339334,0.01180018,0.0047231554,0.00035747996,0.015417198,0.0015549079,0.32366675,0.008165318,0.18470758,0.4009753],"study_design_scores_gemma":[0.0012426705,0.0009592721,0.010471991,0.00033115075,0.00029210802,0.000065031774,0.00143257,0.001107766,0.073438875,0.00010083861,0.9087292,0.0018285299],"about_ca_topic_score_codex":0.00011319308,"about_ca_topic_score_gemma":0.00034344938,"teacher_disagreement_score":0.7240216,"about_ca_system_score_codex":0.0000638779,"about_ca_system_score_gemma":0.00028788802,"threshold_uncertainty_score":0.99978113},"labels":[],"label_agreement":null},{"id":"W7002064851","doi":"","title":"Measurement of B(D+-&gt;(K)over-bar(*0)l(+)nu(l))","year":2002,"lang":"en","type":"article","venue":"KU ScholarWorks (The University of Kansas)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; U.S. Department of Energy; National Science Foundation","keywords":"Branching (polymer chemistry); Bar (unit); Branching fraction; Fraction (chemistry); Measurement uncertainty","score_opus":0.010405257194269407,"score_gpt":0.1903987651565718,"score_spread":0.1799935079623024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7002064851","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95111316,0.0017550006,0.0155385425,0.00082538085,0.0001960805,0.0003403207,0.000020954723,0.000031718453,0.030178828],"genre_scores_gemma":[0.99656063,0.00023662242,0.0018346439,0.00009232152,0.000041376134,1.7555844e-7,0.00000792305,0.00001095404,0.0012153772],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99896735,0.000097001284,0.00019323049,0.00016888225,0.00038636936,0.00018716144],"domain_scores_gemma":[0.9989535,0.0000138911455,0.00022065797,0.0005395893,0.00020513951,0.000067207046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004629548,0.00013404143,0.00017014194,0.000052986066,0.00016672145,0.000011104232,0.0005738354,0.00016234386,0.00045534177],"category_scores_gemma":[0.00014656453,0.00012465745,0.00015638748,0.00013975812,0.0001958426,0.000014141718,0.00017775367,0.0002564414,0.000047798923],"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":[0.0010472016,0.0017151441,0.14289136,0.0009603918,0.0021922416,0.00003144182,0.00849124,0.022416921,0.5604475,0.0035690537,0.1596211,0.09661639],"study_design_scores_gemma":[0.0047504604,0.0010871734,0.07022407,0.0003955307,0.00040101458,0.00003389792,0.0020932024,0.016829379,0.053150706,0.00009116761,0.84989977,0.0010436024],"about_ca_topic_score_codex":0.000030466732,"about_ca_topic_score_gemma":0.00003362878,"teacher_disagreement_score":0.6902787,"about_ca_system_score_codex":0.000027954979,"about_ca_system_score_gemma":0.00002800505,"threshold_uncertainty_score":0.50833833},"labels":[],"label_agreement":null},{"id":"W7002093673","doi":"","title":"Mass media and erosion of culture","year":2006,"lang":"en","type":"other","venue":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Commodification; Argument (complex analysis); Mass media; Reflexivity; Citizen journalism; New media; Cultural heritage; Disenchantment","score_opus":0.025741596054320425,"score_gpt":0.34947492030877914,"score_spread":0.3237333242544587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7002093673","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":[0.019630816,0.039365757,0.004639512,0.0009991818,0.0006367527,0.0046156216,0.0026200842,0.00036684616,0.92712545],"genre_scores_gemma":[0.25774235,0.017804986,0.05104692,0.00006994277,0.0008794143,0.0007356338,0.0043211374,0.00046028866,0.6669393],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976086,0.000032853233,0.0003122966,0.00059106865,0.0009147361,0.00054045534],"domain_scores_gemma":[0.9987155,0.000055052897,0.0002474267,0.00026777163,0.0006269111,0.0000873332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018271204,0.00022584524,0.00024523318,0.0017286506,0.00028704928,0.00004247225,0.0005572506,0.00065884204,0.000011782185],"category_scores_gemma":[0.0017897623,0.00019113885,0.000040608535,0.0011481382,0.0024080214,0.00001394377,0.0002931968,0.00041302887,0.0000017302424],"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":[0.00005526698,0.00014673139,0.0033679346,0.0004249926,0.00006400996,0.0000021263106,0.00009634607,7.367323e-7,0.16731146,0.020620748,0.79257005,0.0153395785],"study_design_scores_gemma":[0.0021900476,0.0030872207,0.0011222397,0.0008484397,0.000050466166,0.000114110015,0.0004035253,0.0014136588,0.059083767,0.0381027,0.8922528,0.0013309972],"about_ca_topic_score_codex":0.00004996793,"about_ca_topic_score_gemma":0.000031806856,"teacher_disagreement_score":0.26018608,"about_ca_system_score_codex":0.00005020124,"about_ca_system_score_gemma":0.0006028927,"threshold_uncertainty_score":0.8872455},"labels":[],"label_agreement":null},{"id":"W7002137666","doi":"","title":"Metodik för krocksimulering av ryggstöd på truck : En jämförelse mellan de två lösarna OptiStruct och RADIOSS","year":2025,"lang":"en","type":"article","venue":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Engineering Link (Canada)","funders":"","keywords":"Pallet; Truck; Beam (structure); Crashworthiness; Finite element method; Crash; Pendulum; Rack","score_opus":0.006735511219244692,"score_gpt":0.2711999997559643,"score_spread":0.2644644885367196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7002137666","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7469606,0.0016570898,0.19601086,0.012066055,0.0013332174,0.0015213913,0.0011399051,0.000889577,0.03842132],"genre_scores_gemma":[0.86582154,0.00034194975,0.12559463,0.0006739813,0.00015294427,0.00013278055,0.0038302275,0.000048074235,0.0034038427],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977499,0.000065244414,0.00077401084,0.0006216418,0.0002575247,0.0005316771],"domain_scores_gemma":[0.9972878,0.000033242377,0.0004402713,0.0017596496,0.00034570202,0.00013332347],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006172742,0.00036712905,0.00039620372,0.0006690199,0.00023974912,0.00008241423,0.0014853008,0.00057243963,0.0000761184],"category_scores_gemma":[0.0026716972,0.00038234002,0.0001318642,0.00084164797,0.0004246859,0.00005605173,0.0010965766,0.0005627879,0.00002598075],"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":[0.00059430266,0.0011512623,0.15219228,0.0027638115,0.00204844,0.00005500138,0.0003628878,0.024521304,0.26143187,0.19425932,0.16790973,0.1927098],"study_design_scores_gemma":[0.001483402,0.00015088098,0.002820072,0.00014415474,0.000116024676,0.00006317332,0.00011162633,0.01791858,0.12751599,0.00026777448,0.84882796,0.0005803654],"about_ca_topic_score_codex":0.000113552844,"about_ca_topic_score_gemma":0.000041964187,"teacher_disagreement_score":0.6809182,"about_ca_system_score_codex":0.000120980665,"about_ca_system_score_gemma":0.00042596587,"threshold_uncertainty_score":0.99986285},"labels":[],"label_agreement":null},{"id":"W7002139356","doi":"","title":"Međusoban odnos bolesti i svakodnevice. Mitchell L. Hammond, Epidemics and the Modern World, Toronto: University of Toronto Press, 2020, 536 str.","year":2021,"lang":"hr","type":"article","venue":"University of Zagreb University Computing Centre (SRCE)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Disease; Epidemiology; Pandemic; Public health; Incidence (geometry)","score_opus":0.004127639256731549,"score_gpt":0.18512903126207259,"score_spread":0.18100139200534104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7002139356","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9536521,0.014542471,0.009795283,0.0015897535,0.0005895051,0.0009483631,0.00061124034,0.000095514646,0.018175796],"genre_scores_gemma":[0.951298,0.014082323,0.0073190946,0.00008441062,0.0000995988,1.19019265e-11,0.00025438587,0.00002912303,0.02683306],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9969012,0.0008497585,0.00041014957,0.000787747,0.00043235224,0.00061878393],"domain_scores_gemma":[0.9965725,0.00040908842,0.0010001418,0.0009885432,0.0007008315,0.00032891013],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005217039,0.0005065311,0.00085446506,0.000026202586,0.00066373777,0.00004910701,0.0011153183,0.00046877397,0.00030896426],"category_scores_gemma":[0.00017646485,0.0006182946,0.0004873368,0.00016458076,0.0011479297,0.00013073362,0.0023509758,0.00047417358,0.000006444335],"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":[0.013642534,0.0028308898,0.030716246,0.00513098,0.01016004,0.001627196,0.6938003,0.04515897,0.011610253,0.01867959,0.1120282,0.054614842],"study_design_scores_gemma":[0.016470227,0.00038190128,0.010981855,0.0010931515,0.002914694,0.00008923977,0.502615,0.26544684,0.0014197426,0.00008796772,0.19639115,0.0021082608],"about_ca_topic_score_codex":0.030981615,"about_ca_topic_score_gemma":0.049244195,"teacher_disagreement_score":0.22028786,"about_ca_system_score_codex":0.00042377715,"about_ca_system_score_gemma":0.00042444534,"threshold_uncertainty_score":0.9996268},"labels":[],"label_agreement":null},{"id":"W7002161030","doi":"","title":"Maritime distress and safety communications in Canada","year":2001,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Distress; Marine safety; Government (linguistics); Occupational safety and health","score_opus":0.0038234359039486317,"score_gpt":0.1892749091095861,"score_spread":0.18545147320563748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7002161030","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":[0.00010980104,0.0006298777,0.0000012573885,0.0001653734,0.00006210703,0.00023008374,0.00029508487,0.000015783335,0.99849063],"genre_scores_gemma":[0.00328837,0.002037187,0.001648087,0.0002439542,0.00003799972,0.00000905129,0.0013229349,0.00005939249,0.99135303],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999006,0.000060908485,0.00046311854,0.00011792097,0.0001640209,0.00018803701],"domain_scores_gemma":[0.9989664,0.000035007975,0.0003200979,0.00056064746,0.000046628193,0.00007121434],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00011028361,0.00020538994,0.00023460561,0.0000343534,0.000039211485,0.000018197179,0.00036256737,0.00022849503,0.03397389],"category_scores_gemma":[0.000095672476,0.00021898864,0.000038877613,0.000005926417,0.000107865744,1.7190576e-8,0.00024573805,0.00021676786,0.00013877472],"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":[0.000033385706,0.00001253115,0.00029932757,0.00020899353,0.000026409241,0.0000031582258,0.000018614963,0.0001283637,3.7924403e-7,0.000014764561,0.99681556,0.002438488],"study_design_scores_gemma":[0.00036963058,0.000037622583,0.00019937662,0.00012548981,0.000013097179,0.000047504225,0.00008093581,0.00011878746,0.0000030594604,0.0000012122325,0.99878335,0.0002199502],"about_ca_topic_score_codex":0.8216301,"about_ca_topic_score_gemma":0.9530455,"teacher_disagreement_score":0.13141538,"about_ca_system_score_codex":0.00005546829,"about_ca_system_score_gemma":0.00010893219,"threshold_uncertainty_score":0.96690917},"labels":[],"label_agreement":null},{"id":"W7002184179","doi":"","title":"”Minussa on parasta oma itseni” : Neljäsluokkalaisten käsityksiä hyvinvoinnista","year":2010,"lang":"fi","type":"other","venue":"Theseus (Ammattikorkeakoulujen)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Health Care Foundation","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Diafiltration; Fusible alloy; Liquation; Dysgeusia; Hyporeflexia","score_opus":0.010437781422957712,"score_gpt":0.25383458217372407,"score_spread":0.24339680075076636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7002184179","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":[0.02052847,0.0008947474,0.00058793963,0.0019719407,0.002346422,0.0015285149,0.0005355396,0.00032020468,0.97128624],"genre_scores_gemma":[0.06536011,0.0006269118,0.0033548358,0.0019451564,0.00252843,0.00011064638,0.0018126599,0.0011902739,0.92307097],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9921964,0.0006588564,0.0016905426,0.0019743892,0.0012625353,0.0022172665],"domain_scores_gemma":[0.99245423,0.00026483543,0.0017652371,0.0043318975,0.00031317194,0.0008706151],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.0012914734,0.0023107165,0.0016882828,0.0006134809,0.000625456,0.0005022783,0.0030995188,0.0036677823,0.0061320257],"category_scores_gemma":[0.0009402452,0.0021891664,0.0009833119,0.00052715454,0.0010315423,0.000027312632,0.0014060951,0.0034008196,0.0092630945],"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":[0.0020653158,0.001630635,0.0015678264,0.0020506934,0.0026308296,0.00040242943,0.0015636508,0.0003344031,0.039899237,0.007132536,0.020987019,0.91973543],"study_design_scores_gemma":[0.0016745086,0.0012986385,0.0007043888,0.0005687854,0.00029650592,0.00027061606,0.00019539127,0.0007530794,0.0060560745,0.00019492143,0.9855931,0.002393995],"about_ca_topic_score_codex":0.00032540466,"about_ca_topic_score_gemma":0.0008678095,"teacher_disagreement_score":0.9646061,"about_ca_system_score_codex":0.00016949145,"about_ca_system_score_gemma":0.0005650496,"threshold_uncertainty_score":0.9989632},"labels":[],"label_agreement":null},{"id":"W7002192546","doi":"","title":"New rules on renewable energy are driving away investment, Alberta government told","year":2024,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Renewable energy; Energy policy; Energy (signal processing); Subsidy; Boom","score_opus":0.004836463668610334,"score_gpt":0.22006836556787876,"score_spread":0.2152319018992684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7002192546","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":[0.000013889139,0.0008981961,0.0018499746,0.00027096356,0.0004544837,0.00011238923,0.000034434528,0.00006895594,0.9962967],"genre_scores_gemma":[0.00019566694,0.00032400587,0.0050450214,0.0028275158,0.0007786201,0.000015443235,0.00025412528,0.00041203783,0.9901476],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987007,0.000028541788,0.00024111483,0.00043581735,0.00031232924,0.0002815481],"domain_scores_gemma":[0.9989394,0.000012099892,0.00021834398,0.0006863505,0.000007777072,0.00013601965],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000057341687,0.00039080158,0.000254851,0.000056239754,0.00002541428,0.00007381163,0.00030338997,0.00037173298,0.0018791977],"category_scores_gemma":[0.00006992225,0.00032633217,0.0001316072,0.000048858667,0.000025182493,0.0000013865804,0.0002911368,0.00015404605,0.0005190675],"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":[0.000005771141,0.000019145022,0.0001032105,0.00009618128,0.00017543498,0.000003721258,0.000010016217,0.00006998366,0.0004360786,0.001892726,0.9966415,0.00054622174],"study_design_scores_gemma":[0.00016534989,0.00013383322,0.0000074780305,0.00032801286,0.000038905888,0.000005755706,0.000025123749,0.0001578878,0.0044006887,0.00012507048,0.9942265,0.00038538134],"about_ca_topic_score_codex":0.004342632,"about_ca_topic_score_gemma":0.012470381,"teacher_disagreement_score":0.008127749,"about_ca_system_score_codex":0.00005437288,"about_ca_system_score_gemma":0.000068997266,"threshold_uncertainty_score":0.9999189},"labels":[],"label_agreement":null},{"id":"W7002277712","doi":"","title":"Montsoriu als segles X-XII. La gènesi d'un castell medieval a la Catalunya Vella","year":2001,"lang":"ca","type":"article","venue":"RACO (Revistes Catalanes amb Accés Obert) (Consorci de Serveis Universitaris de Catalunya)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Musée de la Civilisation","funders":"","keywords":"Middle Ages; German; Period (music); Context (archaeology)","score_opus":0.005574839046700632,"score_gpt":0.23297940734768033,"score_spread":0.2274045683009797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7002277712","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9470326,0.022440229,0.0009827845,0.0013115589,0.0005418166,0.0013472912,0.0015570878,0.0002659623,0.024520699],"genre_scores_gemma":[0.9575337,0.014066459,0.0020730293,0.0008690354,0.0007777348,0.00003142472,0.007865892,0.00033532517,0.016447412],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99221474,0.0013545814,0.0014737621,0.0017625703,0.00090771564,0.0022866044],"domain_scores_gemma":[0.9936358,0.0010137565,0.0011841346,0.0023496684,0.00056655245,0.0012501224],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0018170399,0.0017378994,0.0015209866,0.000546352,0.0008142938,0.0005556876,0.0024939035,0.0020491846,0.00058427994],"category_scores_gemma":[0.0011090044,0.001965665,0.00095596013,0.00097454735,0.0010034341,0.00020882145,0.0017048048,0.0016561652,0.0005265436],"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":[0.00762971,0.004610936,0.613496,0.013230068,0.012226967,0.021603897,0.028929107,0.009414443,0.0820689,0.0036363932,0.11921209,0.08394149],"study_design_scores_gemma":[0.008777063,0.0014640328,0.04555408,0.001635479,0.0037849997,0.01801333,0.01135546,0.011487215,0.022391824,0.00011585729,0.8697099,0.005710724],"about_ca_topic_score_codex":0.0029060617,"about_ca_topic_score_gemma":0.00083174504,"teacher_disagreement_score":0.7504978,"about_ca_system_score_codex":0.0006554108,"about_ca_system_score_gemma":0.0012286049,"threshold_uncertainty_score":0.9995367},"labels":[],"label_agreement":null},{"id":"W7002284975","doi":"","title":"Missouri S&amp;T Hydrogen Fuel Cell EcoCAR","year":2009,"lang":"en","type":"other","venue":"MOspace Institutional Repository (University of Missouri)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Hydrogen fuel; Hydrogen economy; Automotive industry; Hydrogen vehicle; Steam reforming; Natural gas; Fuel cells; Renewable energy; Greenhouse gas","score_opus":0.004902975563084963,"score_gpt":0.1888889824212202,"score_spread":0.18398600685813524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7002284975","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":[0.015699014,0.0040062605,0.0017462312,0.00020333235,0.00028294206,0.0002750191,0.00009548662,0.0000958421,0.97759587],"genre_scores_gemma":[0.023178788,0.0006192632,0.012973949,0.00009692543,0.00045204605,4.4552394e-7,0.00053658773,0.00011057412,0.9620314],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986551,0.0000725178,0.00019090202,0.00042087716,0.00039062076,0.0002700067],"domain_scores_gemma":[0.9985886,0.00001011369,0.0004893053,0.0006331784,0.000095690186,0.00018306311],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00011751842,0.00033647576,0.0003357054,0.00012448,0.00026132958,0.00001729181,0.00057933206,0.0006604703,0.00029402415],"category_scores_gemma":[0.000037553804,0.00041975625,0.00027933583,0.0001039282,0.0003469665,0.0000076201895,0.00018705674,0.0002924667,0.00013057364],"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":[0.00017349559,0.00034232048,0.0011085038,0.0008164604,0.00043569278,0.0001687743,0.0004816037,0.0044752415,0.022807602,0.00024990586,0.9685551,0.00038528713],"study_design_scores_gemma":[0.0005894874,0.00012166317,0.0002252278,0.00012958651,0.00009907598,0.000094360505,0.00010470662,0.00014528175,0.0015884428,0.00001749932,0.9964633,0.0004213979],"about_ca_topic_score_codex":0.00040028768,"about_ca_topic_score_gemma":0.0001996436,"teacher_disagreement_score":0.027908158,"about_ca_system_score_codex":0.00007343489,"about_ca_system_score_gemma":0.00034732878,"threshold_uncertainty_score":0.9998254},"labels":[],"label_agreement":null},{"id":"W7002495588","doi":"","title":"11: James Thunder","year":2018,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Thunder; Conversation; Pledge; Happening; Action (physics); Indigenous","score_opus":0.004303345655592898,"score_gpt":0.19740152330188024,"score_spread":0.19309817764628734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7002495588","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":[0.00009539102,0.000256661,0.000004805585,0.000093422204,0.00030612395,0.00027596555,0.000066560424,0.00008698855,0.9988141],"genre_scores_gemma":[0.00047729368,0.00021265825,0.0033361875,0.00049330905,0.00040147704,0.000009813786,0.0004973613,0.00014765264,0.9944242],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998651,0.000056241304,0.0005171153,0.00019274783,0.00030000941,0.00028286863],"domain_scores_gemma":[0.99860597,0.000016248112,0.0005843302,0.00055979524,0.00013678052,0.00009685423],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001849029,0.00034148293,0.00030285888,0.00005826595,0.00005325831,0.000041531253,0.0004075482,0.0006065798,0.24318497],"category_scores_gemma":[0.00018122696,0.0003286918,0.00016177744,0.000005404003,0.00020632878,1.5151093e-8,0.00018715319,0.00015789436,0.014312985],"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":[0.000051281084,0.00002141145,0.000017502769,0.0003519394,0.000077140176,0.0000016779936,0.00003298327,0.00004084587,0.0000023879782,0.000017244365,0.9986511,0.0007344995],"study_design_scores_gemma":[0.00036779488,0.0002856591,0.000009522166,0.00013715778,0.000037034402,0.000050803013,0.000050732713,0.00002145555,0.00007949013,0.0000035010337,0.99859965,0.00035719693],"about_ca_topic_score_codex":0.0011625667,"about_ca_topic_score_gemma":0.0009051188,"teacher_disagreement_score":0.22887197,"about_ca_system_score_codex":0.000014687615,"about_ca_system_score_gemma":0.00003874228,"threshold_uncertainty_score":0.9999165},"labels":[],"label_agreement":null},{"id":"W7002520089","doi":"","title":"Nova Law Journal Staff 1981-1982","year":2019,"lang":"en","type":"article","venue":"NSUWorks (Nova Southeastern University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Wright; Nova (rocket); Nova scotia; Work (physics); First amendment","score_opus":0.009136969455963559,"score_gpt":0.21535977608570586,"score_spread":0.2062228066297423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7002520089","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74855167,0.000069791146,0.011212442,0.0001971169,0.0008558278,0.00021533876,0.000037361297,0.000046749385,0.23881371],"genre_scores_gemma":[0.97827244,0.000016838823,0.0017511086,0.00021588827,0.00024803157,8.4290946e-8,0.000060771144,0.000032391636,0.019402433],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988366,0.000077316894,0.0002124945,0.00026497216,0.00022968139,0.00037893368],"domain_scores_gemma":[0.9990051,0.000014143761,0.00019886106,0.0004845909,0.00013713556,0.00016021027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001916457,0.0002191353,0.0001937049,0.00013918093,0.00015780784,0.00008035367,0.00053868425,0.00026164416,0.00043674483],"category_scores_gemma":[0.000021264957,0.00022429116,0.00015699174,0.00019878098,0.00009834618,0.000019309178,0.00028351453,0.00046359876,0.00062073057],"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":[0.0077318596,0.0025451593,0.5366308,0.0013013701,0.00455527,0.0010607382,0.013068156,0.061524164,0.12784094,0.13505808,0.015119728,0.093563735],"study_design_scores_gemma":[0.004449281,0.0011418355,0.0016478448,0.00016698254,0.00011670503,0.00037728823,0.006417343,0.0035650674,0.0019808568,0.00011446153,0.97886664,0.0011556883],"about_ca_topic_score_codex":0.000065633285,"about_ca_topic_score_gemma":0.00016856063,"teacher_disagreement_score":0.9637469,"about_ca_system_score_codex":0.00002807079,"about_ca_system_score_gemma":0.000073477524,"threshold_uncertainty_score":0.9146328},"labels":[],"label_agreement":null},{"id":"W7002982472","doi":"","title":"Bibliographie","year":2025,"lang":"fr","type":"book-chapter","venue":"Industrias Culturais (Universidade de Coimbra)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Agency (philosophy); Ligne; Government (linguistics); Context (archaeology)","score_opus":0.018641940676752313,"score_gpt":0.24490779173551291,"score_spread":0.2262658510587606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7002982472","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":[0.0030106576,0.0020234904,0.0010699141,0.009968769,0.0011578437,0.0007604015,0.0012416608,0.00012775614,0.9806395],"genre_scores_gemma":[0.036799647,0.004538695,0.0036574388,0.001496569,0.0011264278,0.000011903598,0.0028817137,0.00012729575,0.9493603],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99687177,0.00016699416,0.00066920894,0.0008921434,0.00048035412,0.00091955607],"domain_scores_gemma":[0.99718595,0.0001233245,0.00070021616,0.0010822563,0.00044047742,0.00046779533],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00039325186,0.0010089977,0.0007443404,0.0019526359,0.000530743,0.00023018823,0.0012667349,0.003712004,0.0017316156],"category_scores_gemma":[0.0003872648,0.0011321236,0.0008186294,0.0012372169,0.0008437139,0.000039891675,0.0007763759,0.0021473877,0.00029837555],"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":[0.00033533413,0.00015146364,0.002175634,0.0005511429,0.0027144623,0.00027509942,0.00025170346,0.0005967241,0.008489989,0.29681164,0.626437,0.061209794],"study_design_scores_gemma":[0.0015687031,0.00040972396,0.0047873375,0.0006247774,0.00055263017,0.00016411679,0.00030312192,0.000364785,0.0014571133,0.00024646896,0.9882938,0.0012273848],"about_ca_topic_score_codex":0.00032370575,"about_ca_topic_score_gemma":0.00014049104,"teacher_disagreement_score":0.36185682,"about_ca_system_score_codex":0.00021757695,"about_ca_system_score_gemma":0.0005294333,"threshold_uncertainty_score":0.9991809},"labels":[],"label_agreement":null},{"id":"W7003262942","doi":"","title":"6-Canada","year":2018,"lang":"da","type":"other","venue":"AMS Acta - Institutional Research Repository","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.020320849488035527,"score_gpt":0.3143413784842272,"score_spread":0.2940205289961917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7003262942","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":[0.01193714,0.0013982708,0.00014059774,0.00051339844,0.0025441218,0.00062818814,0.00015830991,0.000026007954,0.982654],"genre_scores_gemma":[0.3171704,0.00056490843,0.0009312522,0.00035244916,0.005941305,0.000068083755,0.00096341304,0.00017276031,0.6738354],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943403,0.00054021645,0.00070690655,0.0009108787,0.0024030833,0.0010986119],"domain_scores_gemma":[0.9966515,0.00013434379,0.0003482393,0.0014238548,0.00094349345,0.0004986163],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012036368,0.0005558642,0.00041245227,0.00027056035,0.0012328813,0.00023616024,0.0014294528,0.00097384054,0.0018764224],"category_scores_gemma":[0.001620712,0.0005383202,0.00019209595,0.00033050272,0.002132434,0.000016074939,0.0010164704,0.0013547894,0.0010896714],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001397743,0.00013122467,0.00074840226,0.0003410931,0.00042493548,0.00014236197,0.000022393275,0.000051483305,0.015283131,0.0027748034,0.9788586,0.001081821],"study_design_scores_gemma":[0.00041089836,0.0004114553,0.00092421164,0.0003519108,0.00002655786,0.00023006853,0.000037685542,0.00047489442,0.005980897,0.000017576403,0.9905771,0.0005567292],"about_ca_topic_score_codex":0.19744605,"about_ca_topic_score_gemma":0.118568465,"teacher_disagreement_score":0.30881855,"about_ca_system_score_codex":0.00078930886,"about_ca_system_score_gemma":0.017698871,"threshold_uncertainty_score":0.9997068},"labels":[],"label_agreement":null},{"id":"W7003598794","doi":"","title":"","year":2023,"lang":"fr","type":"other","venue":"Directory of Open access Books (OAPEN Foundation)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Excavation; Reign; Quarter (Canadian coin); Capital (architecture); Ancient city; Work (physics); Period (music)","score_opus":0.04809797334598747,"score_gpt":0.39831275421582923,"score_spread":0.35021478086984176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7003598794","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":[0.044507317,0.0006580198,0.003071399,0.0013115495,0.004500413,0.005790103,0.000051356787,0.00031782285,0.93979204],"genre_scores_gemma":[0.07905553,0.0025686922,0.0064550554,0.0012868051,0.0013339757,0.00078086474,0.0036519452,0.0023671212,0.90250003],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99233276,0.0008771603,0.0026899811,0.0018440682,0.0010420393,0.0012140229],"domain_scores_gemma":[0.9913493,0.00043774824,0.0040969006,0.0028123546,0.0008044223,0.0004992863],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaepi_narrow","open_science","insufficient_payload"],"category_scores_codex":[0.0020478405,0.0015707274,0.0020064653,0.0007439532,0.0006741552,0.003932977,0.0117523065,0.0008581286,0.023260692],"category_scores_gemma":[0.0024848296,0.0017470533,0.0006406071,0.00075683487,0.001239687,0.00047853627,0.011432469,0.00093311595,0.0025820625],"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":[0.0010861991,0.0008307522,0.15130508,0.0029197547,0.0040631574,0.00004044732,0.0007785344,0.0026879443,0.014811411,0.05257458,0.010937338,0.7579648],"study_design_scores_gemma":[0.0022371102,0.00038366625,0.07199849,0.0011378572,0.00030735467,0.000022458054,0.00012395221,0.00088004884,0.010199638,0.00036225066,0.9105286,0.0018185601],"about_ca_topic_score_codex":0.005325164,"about_ca_topic_score_gemma":0.014184426,"teacher_disagreement_score":0.89959127,"about_ca_system_score_codex":0.0003298147,"about_ca_system_score_gemma":0.001551538,"threshold_uncertainty_score":0.99970406},"labels":[],"label_agreement":null},{"id":"W7003667573","doi":"","title":"Richwood, Ohio","year":2009,"lang":"en","type":"other","venue":"OhioLink ETD Center (Ohio Library and Information Network)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"State (computer science); Block (permutation group theory); Quarter (Canadian coin); Table (database)","score_opus":0.0044304355515969686,"score_gpt":0.201799519970593,"score_spread":0.19736908441899603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7003667573","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":[0.000021673039,0.0012816598,0.0013356764,0.00030098736,0.00054858375,0.00039851043,0.00014544965,0.00023015284,0.9957373],"genre_scores_gemma":[0.0070752082,0.03150919,0.02132143,0.036311425,0.009487378,0.00007927728,0.037903067,0.0008048782,0.85550815],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99835646,0.00008326351,0.00060666096,0.00025744678,0.00019999756,0.0004961923],"domain_scores_gemma":[0.99868083,0.000012467786,0.0005448884,0.0005481429,0.000016784816,0.00019689457],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00011613568,0.00048153303,0.00035662015,0.00018871424,0.000118049,0.00021547583,0.00038699378,0.00072766887,0.0011075571],"category_scores_gemma":[0.00001749384,0.0004484774,0.00013822597,0.00017998483,0.00007855062,0.00022398474,0.00030576967,0.0004308316,0.00017771736],"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":[0.000056410958,0.000025282789,0.00017432794,0.00017045044,0.00008859176,0.000001137307,0.000038857394,0.0001664945,0.0000045025868,0.045405895,0.9413496,0.0125184385],"study_design_scores_gemma":[0.0006986839,0.00016859041,0.00035182142,0.0002242174,0.00002298558,0.00003163244,0.0000024629828,0.000756892,0.000038217564,0.00007231055,0.99713314,0.0004990559],"about_ca_topic_score_codex":8.382966e-8,"about_ca_topic_score_gemma":0.0000011782032,"teacher_disagreement_score":0.14022917,"about_ca_system_score_codex":0.0000049091914,"about_ca_system_score_gemma":0.000061457715,"threshold_uncertainty_score":0.99980557},"labels":[],"label_agreement":null},{"id":"W7003687283","doi":"","title":"Boy's Life","year":2007,"lang":"en","type":"other","venue":"Goldsmiths (University of London)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Privilege (computing); Appropriation; Exhibition; Iconography; Power (physics); Musical; Emphasis (telecommunications); Everyday life","score_opus":0.0047524173229814845,"score_gpt":0.20183825892845658,"score_spread":0.1970858416054751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7003687283","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":[0.002841882,0.0009943588,0.008295549,0.0001372816,0.00022782385,0.0002195201,0.00009134158,0.000081427046,0.9871108],"genre_scores_gemma":[0.0052917893,0.00062576897,0.011846699,0.00024312522,0.00025794486,1.2583868e-7,0.0002617764,0.00018591761,0.9812868],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991934,0.000031922715,0.00012098562,0.00023732589,0.00019304795,0.00022336413],"domain_scores_gemma":[0.9990042,0.0000072852417,0.00031953125,0.00049607205,0.00004543934,0.00012748722],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00013934853,0.00020449709,0.0002700931,0.0002578516,0.000043742388,0.0000059930335,0.00044632182,0.0005163289,0.001399923],"category_scores_gemma":[0.000050546627,0.0002525154,0.00016001415,0.00012461668,0.00013557893,0.0000025239146,0.00023846314,0.00019106688,0.00025309846],"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":[0.000060059083,0.00003651839,0.0013361268,0.00017587547,0.0001821648,0.000012583234,0.0000679763,0.000019145282,0.00030302326,0.00020446988,0.9949238,0.0026782851],"study_design_scores_gemma":[0.00056600047,0.00011840291,0.0006065315,0.00006119184,0.000049769613,0.0000069758958,0.00020358781,0.0000784382,0.00012807676,0.0000042841652,0.9979083,0.00026841954],"about_ca_topic_score_codex":0.00028562653,"about_ca_topic_score_gemma":0.00025601173,"teacher_disagreement_score":0.005823963,"about_ca_system_score_codex":0.000012820056,"about_ca_system_score_gemma":0.000105102255,"threshold_uncertainty_score":0.9999927},"labels":[],"label_agreement":null},{"id":"W7005111838","doi":"","title":"Poster Competition Abstract Booklet 2017","year":2017,"lang":"en","type":"article","venue":"oURspace (University of Regina)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Agency (philosophy); Firefly protocol; Recreation; Recreational Drug; Competition (biology); Taiga; Monoculture; Bestiary; Depiction; Creatures","score_opus":0.010415361920390555,"score_gpt":0.2304681446743051,"score_spread":0.22005278275391454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7005111838","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6591352,0.0000434978,0.0015711024,0.3049946,0.00012508355,0.00009875672,0.000019388715,0.0000150401975,0.03399732],"genre_scores_gemma":[0.9202605,0.00015114306,0.003147853,0.000070692884,0.00007035644,8.488159e-8,0.0000709159,0.000010215506,0.076218255],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999636,0.0000125838,0.000009243144,0.00012236468,0.00009747068,0.00012234997],"domain_scores_gemma":[0.99907273,0.000004382876,0.0002428494,0.0005616927,0.00006672818,0.000051594063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000104858984,0.00007815202,0.000097359145,0.000030130757,0.00029210697,0.000026038651,0.0003861931,0.000100093646,0.000010460897],"category_scores_gemma":[0.000041346684,0.00009535029,0.000070657465,0.000010197137,0.00018651734,0.000016778635,0.00016888464,0.00008724871,0.000047716527],"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":[0.00012644785,0.000028864974,0.0162375,0.00010006081,0.00008120864,0.00002796823,0.00016871374,0.000057301895,0.044846643,0.0015413567,0.9348141,0.0019698418],"study_design_scores_gemma":[0.00045071766,0.000114747185,0.041880608,0.000030646042,0.000016517492,0.000015210772,0.00026470883,0.000084361,0.0012626714,0.0000051351058,0.95575166,0.00012301006],"about_ca_topic_score_codex":0.000012126223,"about_ca_topic_score_gemma":0.000097472446,"teacher_disagreement_score":0.3049239,"about_ca_system_score_codex":0.000009188596,"about_ca_system_score_gemma":0.000029032795,"threshold_uncertainty_score":0.3888272},"labels":[],"label_agreement":null},{"id":"W7007126882","doi":"","title":"砂質地盤の液状化と静的コーン貫入抵抗(続報)","year":2009,"lang":"en","type":"other","venue":"Kyoto University Research Information Repository (Kyoto University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; Diafiltration; TSG101; Liquation; Dysgeusia; Fusible alloy; Demotion; Emperipolesis","score_opus":0.010168075813233724,"score_gpt":0.246933279893709,"score_spread":0.23676520408047527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7007126882","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":[0.0018434332,0.000053167085,0.0006128342,0.00013595975,0.00023186613,0.0009003128,0.00005890642,0.00024813728,0.9959154],"genre_scores_gemma":[0.0045171073,0.0005489099,0.00081166823,0.00019651905,0.00027439115,7.308888e-7,0.0006171286,0.00010477473,0.99292874],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971955,0.00043649887,0.00029167795,0.00044334825,0.00094066304,0.00069230754],"domain_scores_gemma":[0.9974889,0.000036177502,0.0004279984,0.0010711465,0.0005411209,0.00043465878],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00042567923,0.00042602254,0.00034041252,0.0022510246,0.0006719231,0.0001664279,0.0015399887,0.0009858416,0.00065763027],"category_scores_gemma":[0.0001838455,0.00053189666,0.00024099514,0.00093906827,0.00042638413,0.0001218471,0.0007605487,0.00093444926,0.0017510589],"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":[0.0005149879,0.000099896584,0.00062606693,0.0002454289,0.00027448114,0.00028072478,0.00038990626,0.00013037624,0.0005256473,0.006541089,0.9885642,0.0018072109],"study_design_scores_gemma":[0.001019147,0.0005433029,0.0001848546,0.00012863893,0.00004266093,0.000076801785,0.0015976714,0.00011271202,0.0006378017,0.0000137043935,0.995105,0.0005376507],"about_ca_topic_score_codex":0.0014630818,"about_ca_topic_score_gemma":0.00013380441,"teacher_disagreement_score":0.00654087,"about_ca_system_score_codex":0.00037078236,"about_ca_system_score_gemma":0.00087984547,"threshold_uncertainty_score":0.99971324},"labels":[],"label_agreement":null},{"id":"W7010024330","doi":"","title":"Globalization, Neoliberalism, and International Student Enrolments in Higher Education: Expanding Global Interconnectedness and Academic Commodification","year":2022,"lang":"en","type":"other","venue":"Brock University Digital Repository (Brock University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corporatization; Commodification; Internationalization; International education; Commercialization; Developing country; Neoliberalism (international relations); Higher education","score_opus":0.0121007163162299,"score_gpt":0.24851459903743386,"score_spread":0.23641388272120395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7010024330","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":[0.10582621,0.0006037005,0.00043211304,0.000043838965,0.0012407134,0.0005485421,0.00026845155,0.00014401443,0.89089245],"genre_scores_gemma":[0.042192474,0.00032328,0.00008861172,0.00010081813,0.00012644783,5.762861e-7,0.0007228255,0.00004433869,0.95640063],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99901915,0.00007569028,0.00016027685,0.00040581098,0.0001805107,0.00015858139],"domain_scores_gemma":[0.9993532,0.000009882976,0.0002518146,0.00021653158,0.000056335746,0.000112238544],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0000033347555,0.00023125239,0.00017010325,0.00028041247,0.00012710273,0.00008141411,0.00046387874,0.00028126378,0.000038345115],"category_scores_gemma":[0.000013715017,0.00031198212,0.00004680595,0.00022433762,0.00008508626,0.00006633295,0.0009147206,0.00021068225,0.000002499312],"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":[0.00021579114,0.00022133828,0.5353829,0.00012520952,0.0002719821,0.00001580676,0.000081915525,0.00011559533,0.0010126074,0.001368927,0.46005452,0.0011333778],"study_design_scores_gemma":[0.00080750993,0.00006604154,0.020978658,0.000084746556,0.000043973654,0.000051753614,0.003664751,0.0000051237207,0.000008161964,0.000019579016,0.9739327,0.000336993],"about_ca_topic_score_codex":0.00008248839,"about_ca_topic_score_gemma":0.00012099007,"teacher_disagreement_score":0.51440424,"about_ca_system_score_codex":0.00039833592,"about_ca_system_score_gemma":0.00010855194,"threshold_uncertainty_score":0.99993324},"labels":[],"label_agreement":null},{"id":"W7011068359","doi":"","title":"Lignin Degradation by some wood-rot fungi with emphasis on cylindrocladium camelliae","year":2012,"lang":"en","type":"dissertation","venue":"Knowledge Commons (Lakehead University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Lakehead University","funders":"","keywords":"Lignin; Degradation (telecommunications); Biodegradation; Cellulose; Fungus","score_opus":0.010734905657213443,"score_gpt":0.23711817452725373,"score_spread":0.2263832688700403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7011068359","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77622324,0.002379998,0.00025573466,0.000063278756,0.00059024105,0.0005387056,0.00020339934,0.00009495353,0.21965043],"genre_scores_gemma":[0.83067065,0.00004811475,0.0001119237,0.000013346418,0.00027769228,0.000007679848,0.013945724,0.000102129314,0.1548227],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983049,0.00016460521,0.00028777914,0.0004931729,0.0002443475,0.0005052033],"domain_scores_gemma":[0.9983744,0.000051471572,0.00034829447,0.0007411282,0.00023348852,0.00025120293],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013358629,0.0005608289,0.00040912651,0.00042099334,0.00033563236,0.000051830175,0.0006417569,0.0007685912,0.000049748567],"category_scores_gemma":[0.000040801464,0.0005834798,0.00018080915,0.00040182658,0.00008807878,0.000029681336,0.00010299252,0.00062931044,0.00022483461],"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":[0.0069057303,0.006425077,0.07178729,0.0036147353,0.004439699,0.0001433845,0.008299445,0.0004219458,0.15713795,0.019833095,0.59196806,0.12902358],"study_design_scores_gemma":[0.00134954,0.0009035037,0.0052308245,0.0002782021,0.0003385651,0.000013034365,0.00043938702,0.000043975735,0.04577871,0.0000066454127,0.944581,0.0010366214],"about_ca_topic_score_codex":0.00003656815,"about_ca_topic_score_gemma":0.019066414,"teacher_disagreement_score":0.3526129,"about_ca_system_score_codex":0.0001597401,"about_ca_system_score_gemma":0.0002829958,"threshold_uncertainty_score":0.9996617},"labels":[],"label_agreement":null},{"id":"W7012151354","doi":"","title":"CBCR 3 2010 10 15","year":2010,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Staring; Zoom; Window (computing); Face (sociological concept); Key (lock)","score_opus":0.0036995231439714026,"score_gpt":0.19031683164913724,"score_spread":0.18661730850516584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7012151354","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":[0.00007190901,0.00024188898,0.0000022846689,0.00009418826,0.00055231625,0.00031982703,0.0001517779,0.00009412042,0.9984717],"genre_scores_gemma":[0.00017007205,0.00019686442,0.004342726,0.00035073035,0.00037927617,0.000012547867,0.0010557915,0.00016709475,0.9933249],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985148,0.0000481228,0.0005881669,0.00020803079,0.0003281094,0.00031278038],"domain_scores_gemma":[0.9983261,0.000019258317,0.00068576826,0.0006900373,0.00014885594,0.00012992791],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00021570447,0.000384757,0.00034226797,0.00006857447,0.000055920154,0.000045879748,0.00048785374,0.0010147378,0.46942768],"category_scores_gemma":[0.00028149888,0.0003781194,0.00018652478,0.0000057170996,0.00017065092,1.8515845e-8,0.00019577518,0.0004781382,0.016631894],"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":[0.000053636315,0.0000268298,0.0000059007666,0.0003112725,0.000066055356,0.0000025398874,0.000026105707,0.000058616544,0.00002190985,0.000008974282,0.99788445,0.001533681],"study_design_scores_gemma":[0.00042590435,0.0001933555,0.000008889559,0.00007660858,0.00003771309,0.00006820286,0.000020463258,0.000025708337,0.00013382072,0.0000021070189,0.9986041,0.00040307982],"about_ca_topic_score_codex":0.0012168813,"about_ca_topic_score_gemma":0.0017993541,"teacher_disagreement_score":0.45279577,"about_ca_system_score_codex":0.000010607196,"about_ca_system_score_gemma":0.000048707192,"threshold_uncertainty_score":0.9998671},"labels":[],"label_agreement":null},{"id":"W7015862585","doi":"","title":"Un évêque à Vatican II, Mgr. Albert Sanschagrin, o.m.i","year":2000,"lang":"de","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Relation (database); Subject (documents); Context (archaeology); Period (music)","score_opus":0.0012581968819053671,"score_gpt":0.1365894341847244,"score_spread":0.13533123730281904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7015862585","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":[0.009583995,0.0022268228,0.000074517724,0.0031298427,0.00038614363,0.00036733405,0.0008910505,0.000010840017,0.9833295],"genre_scores_gemma":[0.25765422,0.003905576,0.0035340795,0.004777126,0.0006046617,0.000017967215,0.0004575835,0.00024706105,0.7288017],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965742,0.0001271174,0.00066467683,0.0005334453,0.0014816166,0.00061892695],"domain_scores_gemma":[0.9982556,0.00009885421,0.0004961398,0.00066886516,7.407874e-7,0.00047980782],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000015409985,0.00063420733,0.00059117057,0.000041970943,0.00029088138,0.000036773872,0.0006159518,0.0002266559,0.0020566448],"category_scores_gemma":[0.000009038123,0.000628196,0.0000963602,0.00008851422,0.00021796193,0.000020031377,0.0004817257,0.00043301223,5.8943428e-8],"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":[0.0040186457,0.0006457575,0.038703687,0.0057930453,0.006227684,0.00048238182,0.00076155644,0.0010501754,0.09018618,0.057657827,0.6103537,0.18411937],"study_design_scores_gemma":[0.0005379061,0.000278412,0.0023101156,0.00025146772,0.00008396089,0.000018464634,0.00028645794,0.00087953976,0.046109173,0.00009699437,0.94844794,0.0006995871],"about_ca_topic_score_codex":0.0032849433,"about_ca_topic_score_gemma":0.02905674,"teacher_disagreement_score":0.33809423,"about_ca_system_score_codex":0.0000063011994,"about_ca_system_score_gemma":0.0024722351,"threshold_uncertainty_score":0.9996169},"labels":[],"label_agreement":null},{"id":"W7016110106","doi":"","title":"2017 04 20 Yannick Jean des Saguennens de Chicoutimi","year":2017,"lang":"fr","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Period (music); Context (archaeology); White (mutation)","score_opus":0.006612656404309775,"score_gpt":0.2093233734992506,"score_spread":0.20271071709494082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7016110106","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":[0.0011405409,0.0020514063,0.000017001339,0.00046356313,0.0005409145,0.00052890787,0.00029138417,0.000058670972,0.9949076],"genre_scores_gemma":[0.0042480323,0.0026438283,0.0076282057,0.00046695085,0.00049812184,0.000017605926,0.0008271158,0.00013204209,0.9835381],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972452,0.00018119611,0.00097598217,0.0003610139,0.00041331677,0.00082328165],"domain_scores_gemma":[0.99629676,0.000102055725,0.0016076077,0.0012943239,0.00035716585,0.00034208375],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00062747445,0.0007272275,0.0006603176,0.000075192336,0.00042588913,0.00019621932,0.0011485919,0.0013008264,0.3915175],"category_scores_gemma":[0.0013245998,0.00076319964,0.0004258164,0.000006210604,0.00087693986,1.5625733e-7,0.00042184608,0.00067188276,0.019502968],"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":[0.00014771512,0.00008315529,0.00013328069,0.001397483,0.00025603853,0.000022138876,0.00037294236,0.0031188696,0.000042260755,0.000043554577,0.9849021,0.0094805015],"study_design_scores_gemma":[0.00090598676,0.00048501146,0.00019616901,0.000639065,0.00016748051,0.00032166176,0.00008288353,0.0006090668,0.00021415067,0.000015476413,0.99558944,0.0007736426],"about_ca_topic_score_codex":0.00573652,"about_ca_topic_score_gemma":0.008766313,"teacher_disagreement_score":0.37201452,"about_ca_system_score_codex":0.00011305655,"about_ca_system_score_gemma":0.00017501476,"threshold_uncertainty_score":0.9999957},"labels":[],"label_agreement":null},{"id":"W7016228162","doi":"","title":"Workbook on demographic data evaluation and analysis :based on ECA subregional training workshop for Anglophone countries held at Rips, Accra. 1-19 August 1988","year":2014,"lang":"en","type":"book","venue":"Economic Commission for Africa Knowledge Repository (Economic Commission for Africa)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Workbook; Training (meteorology); Distribution (mathematics); Population; Process (computing); Social policy; Production (economics); Social change; Demographic change; Sustainability","score_opus":0.05680989971471129,"score_gpt":0.31397161677756236,"score_spread":0.25716171706285107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7016228162","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":[0.00062951184,0.0041008093,0.017517325,0.00085556944,0.0026860218,0.0054804957,0.0035924278,0.00021833017,0.9649195],"genre_scores_gemma":[0.04173917,0.000049938204,0.0034136272,0.000013622943,0.0013405508,0.00094095315,0.0063094436,0.00027173635,0.94592094],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99514604,0.0002967755,0.0016614872,0.0018695346,0.00028289284,0.0007432641],"domain_scores_gemma":[0.99230516,0.0025886637,0.0015824116,0.0026158614,0.0002538469,0.0006540712],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00265329,0.0011093765,0.0014946708,0.0008508441,0.001447712,0.00028590497,0.0015350151,0.0012098101,0.0001961711],"category_scores_gemma":[0.00056471094,0.0011154448,0.0009913844,0.00012960282,0.0003203313,0.00004204271,0.00074999954,0.00047961864,0.000034844223],"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":[0.002512104,0.0001640051,0.00026867248,0.0004571248,0.0010620743,5.827762e-7,0.00034584163,0.0051613003,0.00008272931,0.0004465574,0.9820713,0.007427741],"study_design_scores_gemma":[0.0024453448,0.0007992865,0.000059096736,0.00028837254,0.0011079191,0.000008024098,0.0000572303,0.27469757,0.00014592247,0.00030312804,0.7192175,0.00087060034],"about_ca_topic_score_codex":0.0000036386762,"about_ca_topic_score_gemma":0.000056425983,"teacher_disagreement_score":0.2695363,"about_ca_system_score_codex":0.0012068368,"about_ca_system_score_gemma":0.0016030471,"threshold_uncertainty_score":0.99985224},"labels":[],"label_agreement":null},{"id":"W7016317451","doi":"","title":"William Inglis (Canadian 158663)","year":2011,"lang":"en","type":"other","venue":"OhioLink ETD Center (Ohio Library and Information Network)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corporation; George (robot); Ticket; Launched","score_opus":0.005440423583306445,"score_gpt":0.19011263903275555,"score_spread":0.18467221544944912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7016317451","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":[0.000016995395,0.00074948644,0.0004495637,0.00014355489,0.00075142074,0.0003560542,0.00027166028,0.00014162765,0.99711967],"genre_scores_gemma":[0.012184771,0.025633838,0.016836163,0.034569137,0.008058821,0.00011408172,0.044760205,0.0010804645,0.8567625],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985297,0.000063910535,0.0005033417,0.00022609098,0.00013251709,0.0005444385],"domain_scores_gemma":[0.99870896,0.0000075914622,0.00040418995,0.00050567795,0.000018349403,0.00035524252],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001053095,0.00042085335,0.00028886675,0.00027231628,0.00013151481,0.00016949754,0.0003883254,0.0007488379,0.0029102515],"category_scores_gemma":[0.000017508919,0.00040337362,0.000109847424,0.00015516444,0.0000958263,0.00022940108,0.0002600403,0.00038862304,0.0002556599],"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":[0.000030962954,0.0000110558685,0.0006455539,0.00015977315,0.00009531193,0.000001216835,0.000088271285,0.00003822052,0.000001081544,0.03795073,0.95590836,0.005069472],"study_design_scores_gemma":[0.00042609134,0.00009764157,0.00035700013,0.00021041361,0.000018178964,0.000020354084,0.0000033267302,0.00026973817,0.000024030855,0.00005523975,0.99806124,0.00045672932],"about_ca_topic_score_codex":0.000007535471,"about_ca_topic_score_gemma":0.0001918941,"teacher_disagreement_score":0.14035712,"about_ca_system_score_codex":0.0000072328803,"about_ca_system_score_gemma":0.00013326782,"threshold_uncertainty_score":0.9998418},"labels":[],"label_agreement":null},{"id":"W7016373832","doi":"","title":"Бронзовый нагрудник панцыря с изображением головы Медузы из кургана № 6/1914-1915 у ст. Елизаветинской в Прикубанье","year":2009,"lang":"en","type":"article","venue":"The scientific electronic library of periodicals of the National Academy of Sciences of Ukraine (National Academy of Sciences of Ukraine)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bronze; Context (archaeology); Plank; Head (geology); Quarter (Canadian coin); Period (music)","score_opus":0.02305598428189586,"score_gpt":0.30778285827140306,"score_spread":0.2847268739895072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7016373832","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94934565,0.004312575,0.00008551549,0.032673538,0.00012871533,0.00084712746,0.00047451328,0.000028313832,0.012104037],"genre_scores_gemma":[0.992436,0.00042832462,0.004925908,0.0010679865,0.00018068672,0.000008648061,0.000024271638,0.00001571627,0.00091248803],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9907097,0.00033136748,0.0022080285,0.00081693265,0.0051569915,0.0007769859],"domain_scores_gemma":[0.99543685,0.00064144155,0.0030547634,0.00018334624,0.0005298094,0.0001538064],"candidate_categories":["metaepi_narrow","sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.00912302,0.00041991143,0.0007750673,0.0007626659,0.0007353232,0.00007329115,0.00592641,0.0004048018,0.00022491765],"category_scores_gemma":[0.0023408714,0.00028159568,0.0005836197,0.0030072194,0.015486388,0.00038416937,0.0008096341,0.0007143523,0.00000404028],"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":[0.00021013751,0.0005747639,0.0012054514,0.0003160119,0.00017295052,5.448471e-8,0.00080519123,0.019506354,0.78517985,0.18187363,0.008229714,0.0019258609],"study_design_scores_gemma":[0.0014804625,0.0017464967,0.027263246,0.0004967967,0.00009638905,0.000057160276,0.00029483004,0.021113593,0.8484937,0.07887445,0.019400451,0.00068246183],"about_ca_topic_score_codex":0.000014762471,"about_ca_topic_score_gemma":5.7742204e-7,"teacher_disagreement_score":0.10299919,"about_ca_system_score_codex":0.00004509578,"about_ca_system_score_gemma":0.0015626281,"threshold_uncertainty_score":0.99996364},"labels":[],"label_agreement":null},{"id":"W7016484340","doi":"","title":"صناع الملاحم 2 | ولاية سيناء","year":2022,"lang":"ar","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Brother; Islam; State (computer science); Supporter; Spanish Civil War","score_opus":0.00373552084348449,"score_gpt":0.18718070542130424,"score_spread":0.18344518457781975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7016484340","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":[0.0006472917,0.0009830148,0.0000011270384,0.00029452433,0.0007288235,0.00074608234,0.00046857315,0.000086913984,0.9960436],"genre_scores_gemma":[0.0036088242,0.0010190743,0.002080728,0.001098706,0.0004007424,0.000042827196,0.002462092,0.00019993058,0.9890871],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962415,0.000279715,0.0015040729,0.00045978944,0.00081831636,0.00069660344],"domain_scores_gemma":[0.9966636,0.00009278548,0.0015681244,0.0011611267,0.00025713406,0.00025724687],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00062634615,0.0007952253,0.0007409276,0.00012260993,0.000287717,0.00010816343,0.0010582599,0.00091832987,0.7940706],"category_scores_gemma":[0.0005118427,0.00085563544,0.0004809854,0.00001845697,0.00030415575,5.858112e-8,0.0007936967,0.00091473194,0.04153457],"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":[0.0002185219,0.000091427144,0.000043745724,0.0010264914,0.0002792915,0.00001737179,0.00032869919,0.0022076156,0.000008383646,0.000044188568,0.9938164,0.0019178902],"study_design_scores_gemma":[0.0010379587,0.0008282978,0.00002231749,0.00012379822,0.00013961195,0.00022253451,0.00043624936,0.00017627658,0.000069037495,0.0000052788473,0.9960625,0.0008761491],"about_ca_topic_score_codex":0.001323832,"about_ca_topic_score_gemma":0.00044080752,"teacher_disagreement_score":0.75253606,"about_ca_system_score_codex":0.00010854347,"about_ca_system_score_gemma":0.00014496449,"threshold_uncertainty_score":0.99938947},"labels":[],"label_agreement":null},{"id":"W7016937645","doi":"","title":"Across cultures, across borders Canadian aboriginal and native American literatures","year":2010,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Native american; Indigenous; Ethnic group; Immigration; Identity (music)","score_opus":0.0020129886832222486,"score_gpt":0.3205396823356491,"score_spread":0.31852669365242686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7016937645","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":[0.012917797,0.0016608564,0.0001533885,0.00043972032,0.00044954987,0.00041422874,0.001682563,0.00009001913,0.98219186],"genre_scores_gemma":[0.012506269,0.0009362622,0.0075149527,0.0025577147,0.00087510626,0.000025114861,0.0018011814,0.00034432946,0.9734391],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988222,0.00002900635,0.0001529964,0.00035376652,0.00012911204,0.0005128813],"domain_scores_gemma":[0.9991136,0.0000059191284,0.00017840156,0.0003729369,0.00006137061,0.0002677446],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00010510968,0.00034361743,0.00024289273,0.00005387156,0.00014705528,0.00017116133,0.00027347938,0.0005659711,0.00023779966],"category_scores_gemma":[0.00006127528,0.0002823008,0.00005889071,0.00009586081,0.0004418951,0.0000023381099,0.000076123746,0.0005634589,0.000015485268],"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":[0.000021832768,0.000014351738,0.0025508965,0.00008476062,0.00018887901,0.000009905857,0.0014943004,0.0000026057987,0.0008978796,0.00031039986,0.9834181,0.011006068],"study_design_scores_gemma":[0.00020893355,0.00008737429,0.00058615545,0.000023024651,0.000007813083,0.000024567604,0.0003343749,0.000019001724,0.0003032078,0.0000037998427,0.99802226,0.00037950766],"about_ca_topic_score_codex":0.12896436,"about_ca_topic_score_gemma":0.730378,"teacher_disagreement_score":0.6014136,"about_ca_system_score_codex":0.000016438978,"about_ca_system_score_gemma":0.00020339586,"threshold_uncertainty_score":0.9999629},"labels":[],"label_agreement":null},{"id":"W7016940621","doi":"","title":"Administration, Faculty, Trustees, and Visitors/Examiners of Ohio Wesleyan University and Ohio Wesleyan Female College, 1842-1901","year":2009,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Position (finance); Government (linguistics); Quarter (Canadian coin); Poorhouse","score_opus":0.005995901934953895,"score_gpt":0.23560656319747234,"score_spread":0.22961066126251845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7016940621","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":[0.020545337,0.0005065216,0.00056827563,0.00018760358,0.00012767132,0.00048693645,0.0005165976,0.00006944215,0.9769916],"genre_scores_gemma":[0.12022453,0.0009023343,0.0131570585,0.00018137012,0.00026819465,0.0000017130147,0.0012887766,0.00014700547,0.863829],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988638,0.000063326144,0.0002797731,0.0003872837,0.00017909668,0.00022670522],"domain_scores_gemma":[0.99906766,0.000014226189,0.00032944707,0.0003747229,0.00006281847,0.000151096],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001252427,0.00034844672,0.0003738587,0.00015163817,0.00007418655,0.000026443544,0.00022340915,0.00056657457,0.00022075903],"category_scores_gemma":[0.00004754724,0.00034093688,0.000070777554,0.00009330557,0.00020039773,0.000005968982,0.00016103407,0.00017094213,0.0000059983413],"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":[0.00027984224,0.00023631773,0.011842736,0.00092734385,0.00056689687,0.00003145472,0.00031362267,0.000011828252,0.0033573827,0.0028639378,0.9710505,0.008518159],"study_design_scores_gemma":[0.0010076705,0.0006408846,0.004956801,0.000072064206,0.00008842679,0.00004166984,0.00031861477,0.000090888214,0.0013832913,0.000005573258,0.99093646,0.000457676],"about_ca_topic_score_codex":0.0001142813,"about_ca_topic_score_gemma":0.0006685995,"teacher_disagreement_score":0.11316259,"about_ca_system_score_codex":0.000016659616,"about_ca_system_score_gemma":0.00014827629,"threshold_uncertainty_score":0.9999043},"labels":[],"label_agreement":null},{"id":"W7016961454","doi":"","title":"Addressing disparities in colorectal cancer screening participation in Canada","year":2025,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Colorectal cancer screening; Socioeconomic status; Psychological intervention; Cancer screening; Health equity; Colorectal cancer; Affect (linguistics)","score_opus":0.015747062433176834,"score_gpt":0.30824119433133,"score_spread":0.2924941318981532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7016961454","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08241327,0.0020976493,0.0018684573,0.00031701304,0.0004895434,0.00049903244,0.00014419574,0.000033838332,0.912137],"genre_scores_gemma":[0.73517925,0.00039691993,0.0028319915,0.00073013874,0.00019294264,0.00013627361,0.0005749185,0.00014883066,0.25980878],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993188,0.000038831793,0.00019833668,0.0001506124,0.00009427118,0.00019916896],"domain_scores_gemma":[0.99976385,0.000010990948,0.000088556815,0.00010012126,0.000011635492,0.000024835103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006202596,0.0001347687,0.0001595156,0.00009475349,0.000013261835,0.000014014797,0.000103255246,0.00015947713,0.00034066357],"category_scores_gemma":[0.00007692085,0.00013439174,0.00001751056,0.000080005426,0.000018596698,0.0000012052961,0.000075770986,0.00015930436,7.891113e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004696964,0.0000241535,0.7107961,0.00034811776,0.000062507024,0.0000075971825,0.000040308387,0.0050130202,0.0005879866,0.00009520304,0.26593098,0.017047051],"study_design_scores_gemma":[0.0024172592,0.00009400629,0.45345038,0.0033766108,0.000056369296,0.000002741944,0.00045540844,0.041322928,0.012159624,0.000020007501,0.48492295,0.0017217114],"about_ca_topic_score_codex":0.96914107,"about_ca_topic_score_gemma":0.99836075,"teacher_disagreement_score":0.6527659,"about_ca_system_score_codex":0.00009257103,"about_ca_system_score_gemma":0.00084548694,"threshold_uncertainty_score":0.5480336},"labels":[],"label_agreement":null},{"id":"W7016993623","doi":"","title":"adutlocker .W.a.t.c.h. Welcome to Sudden Death (2020) Full Movie Online Free HD","year":2020,"lang":"en","type":"other","venue":"OSF Preprints (OSF Preprints)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sudden death; Officer; Action (physics); Guard (computer science); Counterattack; Comedy","score_opus":0.008931904745329646,"score_gpt":0.25635743232008656,"score_spread":0.24742552757475691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7016993623","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":[0.003073005,0.00002229744,0.0038563812,0.0010944463,0.00075947575,0.0014766799,0.00059341243,0.0003031491,0.98882115],"genre_scores_gemma":[0.0013614412,0.00043762318,0.027823055,0.0016529752,0.0015199517,0.00015938866,0.0011927708,0.0006782117,0.96517456],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948339,0.00036570188,0.0008705577,0.0025846944,0.00061946374,0.00072569057],"domain_scores_gemma":[0.9920137,0.00006990953,0.00058434316,0.006604007,0.000112082234,0.0006159495],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011562745,0.00084327994,0.00083067664,0.00020501706,0.00010722193,0.00011946484,0.0030876761,0.0010246641,0.3632532],"category_scores_gemma":[0.003967137,0.00092310115,0.00039616137,0.00023937717,0.000121554905,0.000009146791,0.0057870736,0.00095541874,0.5005661],"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":[0.00017637614,0.0002031845,0.0037504525,0.0003529331,0.0004486686,0.000041497326,0.00019880061,0.0004019492,0.006399826,0.00015099213,0.9837162,0.004159116],"study_design_scores_gemma":[0.0007100369,0.000012653276,0.0013393988,0.00017378437,0.00011077179,0.00006702867,0.00003850545,0.00033703138,0.0018283357,0.0001581564,0.9942892,0.0009350825],"about_ca_topic_score_codex":0.0003712201,"about_ca_topic_score_gemma":0.0005759303,"teacher_disagreement_score":0.13731295,"about_ca_system_score_codex":0.000095111165,"about_ca_system_score_gemma":0.00026315785,"threshold_uncertainty_score":0.99932194},"labels":[],"label_agreement":null},{"id":"W7017009879","doi":"","title":"Achieving and Underachieving Students' Problem-Solving Performance: Detection of Linguistic Ambiguity, Reflection-Impulsivity, Tolerance-Intolerance of Ambiguity, and Hypothesis Testing","year":2021,"lang":"en","type":"dissertation","venue":"University Library (University of Saskatchewan)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Ambiguity; Matching (statistics); Test (biology); Perception; Ambiguity tolerance; Statistical hypothesis testing","score_opus":0.00814210820698076,"score_gpt":0.20737944145622464,"score_spread":0.1992373332492439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017009879","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961669,0.0003329936,0.00038174255,0.000020512092,0.00010308161,0.00023331883,0.00004232845,0.000030427593,0.002688686],"genre_scores_gemma":[0.9828841,0.0007938011,0.013368658,0.000011320137,0.000049229933,9.605787e-8,0.00014247093,0.000030368547,0.0027199753],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985821,0.00013678295,0.00031343894,0.0004355573,0.00031140746,0.00022067873],"domain_scores_gemma":[0.9983412,0.00012475354,0.0008749799,0.00031693326,0.000248607,0.000093498056],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020296568,0.00029275828,0.00054839713,0.00028994554,0.00035922613,0.00003473787,0.00042861153,0.00036904492,0.000017557304],"category_scores_gemma":[0.00013986441,0.00040964579,0.00012992606,0.00039578523,0.0002241583,0.000107869055,0.00061338936,0.00038697413,3.5277068e-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":[0.0015511775,0.0004286897,0.5387904,0.013580214,0.0008729254,0.00003552556,0.05539962,0.00088657334,0.33203804,0.00001940432,0.000043322714,0.056354087],"study_design_scores_gemma":[0.003007496,0.0018182977,0.73620707,0.005258639,0.001077316,0.000063874155,0.14981028,0.0032038488,0.09698628,0.00018731292,0.0007027607,0.0016768324],"about_ca_topic_score_codex":0.0009127667,"about_ca_topic_score_gemma":0.001864689,"teacher_disagreement_score":0.23505177,"about_ca_system_score_codex":0.000035351273,"about_ca_system_score_gemma":0.0002726009,"threshold_uncertainty_score":0.99983555},"labels":[],"label_agreement":null},{"id":"W7017042618","doi":"","title":"Aimé Césaire, Paul Chamberland et le pays imaginaire","year":2000,"lang":"fr","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Liquation; Diafiltration; Emperipolesis; Triacetin; Fusible alloy","score_opus":0.001389138852764239,"score_gpt":0.14626294669044607,"score_spread":0.14487380783768183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017042618","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":[0.0053695687,0.0031043203,0.00011100756,0.011052418,0.00029846752,0.00025223187,0.00089677505,0.0000095071955,0.9789057],"genre_scores_gemma":[0.41818613,0.0045992085,0.002564677,0.004601669,0.00031570077,0.000013363485,0.00040600714,0.0001877708,0.5691255],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975125,0.00013783095,0.0004475786,0.0004145451,0.0009997583,0.00048776474],"domain_scores_gemma":[0.99876946,0.000071306444,0.00035252975,0.00046186827,6.7306263e-7,0.00034414238],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000015376758,0.00049406744,0.0004460788,0.000027552656,0.00016135785,0.00004179035,0.0003788833,0.00016237653,0.0005950511],"category_scores_gemma":[0.0000057953025,0.00049566303,0.000075238946,0.000056640638,0.0002266695,0.000030207351,0.00027811725,0.0003661056,3.9750123e-8],"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":[0.0022648918,0.00045564497,0.068344876,0.005738365,0.0021333226,0.000787121,0.0004396106,0.0014361348,0.03304519,0.19060132,0.39553824,0.2992153],"study_design_scores_gemma":[0.00060793053,0.00015409,0.0075453254,0.00029387174,0.00004186119,0.000054976943,0.00039992802,0.0012658747,0.013289723,0.0001579838,0.9756188,0.0005696741],"about_ca_topic_score_codex":0.0059539597,"about_ca_topic_score_gemma":0.086638436,"teacher_disagreement_score":0.5800805,"about_ca_system_score_codex":0.000005942369,"about_ca_system_score_gemma":0.003110074,"threshold_uncertainty_score":0.9997495},"labels":[],"label_agreement":null},{"id":"W7017061443","doi":"","title":"Accidents With Nature and Each Other","year":2005,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Guitar; Style (visual arts); Violin; Movement (music); String (physics); Melody; Shot (pellet); Laughter","score_opus":0.0022427672131555124,"score_gpt":0.19006872096660127,"score_spread":0.18782595375344577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017061443","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":[0.0004047371,0.0006969935,0.0000016929444,0.00007783341,0.00007598003,0.00026908543,0.000067661225,0.00004848925,0.99835753],"genre_scores_gemma":[0.001604486,0.00025507432,0.0039927308,0.00068679993,0.0002135633,0.000007772236,0.00026821997,0.0001283495,0.99284303],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999011,0.000033829816,0.00032213985,0.00017081224,0.0002545472,0.00020770376],"domain_scores_gemma":[0.9990534,0.000013108384,0.00042116508,0.00035717757,0.00007323639,0.00008190214],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000115639516,0.00029679586,0.00024748722,0.0000474928,0.00004193744,0.000039973933,0.00023531418,0.00069854624,0.075225115],"category_scores_gemma":[0.00006471775,0.0002525042,0.000060670285,0.0000044453027,0.00010884,2.548109e-8,0.00010919561,0.00034675107,0.0010275978],"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":[0.000076007236,0.000016941018,0.00008070385,0.0002348735,0.00008666596,0.0000019031205,0.000038360435,0.00006963994,0.0000024285423,0.000008561274,0.99768424,0.0016996705],"study_design_scores_gemma":[0.00052417465,0.0001988142,0.000056393565,0.0001374638,0.000036859656,0.000106335785,0.000027742322,0.000014301921,0.000051964766,5.598846e-7,0.99854815,0.00029724019],"about_ca_topic_score_codex":0.00061739265,"about_ca_topic_score_gemma":0.0009302059,"teacher_disagreement_score":0.074197516,"about_ca_system_score_codex":0.000009506875,"about_ca_system_score_gemma":0.000022347373,"threshold_uncertainty_score":0.9999927},"labels":[],"label_agreement":null},{"id":"W7017243840","doi":"","title":"Anger in healing from childhood sexual abuse, a group intervention","year":2000,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Anger; Intervention (counseling); Sexual abuse; Practicum; Anger management; Treatment and control groups; Group psychotherapy","score_opus":0.001615844702540651,"score_gpt":0.15042699409622962,"score_spread":0.14881114939368897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017243840","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10548373,0.0016694459,0.000116949166,0.00022267517,0.00021221102,0.00026958663,0.00095580594,0.00001345631,0.8910561],"genre_scores_gemma":[0.6840502,0.0016557544,0.005468863,0.002457911,0.0006678937,0.000025309806,0.001767446,0.00038922476,0.30351737],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99875164,0.00005693715,0.00026657718,0.00023114117,0.0004987461,0.00019497995],"domain_scores_gemma":[0.99947786,0.000021402408,0.00018658351,0.00021563,1.02425e-7,0.000098423014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000007217539,0.00020412286,0.00021831853,0.00003086492,0.000029265982,0.000012804907,0.00018380748,0.00008961943,0.00016728352],"category_scores_gemma":[0.0000017008381,0.00020940072,0.00002704242,0.000033446664,0.00003542262,0.000008311608,0.0000865423,0.00016714049,5.2529834e-9],"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":[0.0031001663,0.00091459684,0.2031653,0.0036393409,0.0023413496,0.0003547774,0.0018448624,0.0009129271,0.06941321,0.004781207,0.3981767,0.31135556],"study_design_scores_gemma":[0.0013591353,0.00030295443,0.033211987,0.00077031786,0.00003560461,0.000007906887,0.0013886945,0.00090055657,0.0075456356,0.0000773911,0.95368683,0.00071295263],"about_ca_topic_score_codex":0.015726214,"about_ca_topic_score_gemma":0.2522211,"teacher_disagreement_score":0.5875388,"about_ca_system_score_codex":0.000002434511,"about_ca_system_score_gemma":0.0002942589,"threshold_uncertainty_score":0.99082816},"labels":[],"label_agreement":null},{"id":"W7017264658","doi":"","title":"All the things you learn by forgetting: Poetic texts as a source of educational and pedagogical knowledge","year":2023,"lang":"fi","type":"other","venue":"Aaltodoc (Aalto University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Poetry; Context (archaeology)","score_opus":0.020231670787344693,"score_gpt":0.27997526727945066,"score_spread":0.259743596492106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017264658","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":[0.046794705,0.00440772,0.00062118785,0.0073391004,0.0005627719,0.00097218517,0.00010097324,0.00011484192,0.9390865],"genre_scores_gemma":[0.032212283,0.001745518,0.0003266193,0.00043983638,0.00029618628,0.0000019319841,0.00023065339,0.00022563383,0.96452135],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99808866,0.00024441368,0.0003560293,0.000563199,0.0002700128,0.00047771508],"domain_scores_gemma":[0.9982455,0.0002879465,0.0005475917,0.0005680658,0.00014344559,0.00020749982],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000353757,0.00045157064,0.00040577268,0.00024005276,0.0002698706,0.00005111176,0.00079059415,0.0006484199,0.0008676526],"category_scores_gemma":[0.00054872094,0.0004053314,0.00021520967,0.00032662885,0.0005471669,0.000017394594,0.0007707388,0.00063438795,0.00038570777],"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":[0.0009598356,0.0017957251,0.02404304,0.0037449857,0.0042871116,0.000051351384,0.033050757,0.0002637829,0.010831464,0.06805221,0.786423,0.06649669],"study_design_scores_gemma":[0.0005991593,0.00031249988,0.00034395183,0.0001538879,0.00020092622,0.00003345712,0.0014794604,0.00026589818,0.0002192497,0.00007194284,0.99588907,0.00043051445],"about_ca_topic_score_codex":0.00045758032,"about_ca_topic_score_gemma":0.00013186796,"teacher_disagreement_score":0.20946601,"about_ca_system_score_codex":0.000069097834,"about_ca_system_score_gemma":0.00037989032,"threshold_uncertainty_score":0.99983984},"labels":[],"label_agreement":null},{"id":"W7017289285","doi":"","title":"Aide-memoire du carabinier volontiare, comprenant une compilation des termes de commandement usites dan l'armee anglaise,... aussi Le manuel su sergent...","year":2014,"lang":"fr","type":"article","venue":"QSpace (Queen's University Library)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Diafiltration; Liquation; Emperipolesis; Triacetin; Fusible alloy","score_opus":0.005305577433470734,"score_gpt":0.1847739245376626,"score_spread":0.17946834710419185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017289285","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.881071,0.0004361784,0.028548056,0.07064088,0.0005638676,0.0005215607,0.00021899246,0.00019214579,0.01780738],"genre_scores_gemma":[0.9314784,0.000993475,0.015112624,0.000579768,0.00024121723,0.000001631033,0.0013790064,0.000070115355,0.05014377],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976916,0.0005261763,0.00032927786,0.0004938488,0.00024790352,0.00071120163],"domain_scores_gemma":[0.99845886,0.000066712426,0.00034202661,0.00066888804,0.00010365223,0.00035986747],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017368341,0.00047768347,0.00041625745,0.00017137329,0.00071915146,0.0001738647,0.00065820204,0.00044356353,0.00011923221],"category_scores_gemma":[0.00005598314,0.00054535514,0.00024214262,0.00032080652,0.0005355039,0.00020360858,0.00080631673,0.00039623442,0.000038270504],"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":[0.00029132463,0.00041148346,0.7928349,0.00075711164,0.0003925419,0.00007316393,0.001422288,0.007144899,0.00076382654,0.011255814,0.18143505,0.0032176021],"study_design_scores_gemma":[0.0017177194,0.00049367774,0.15655187,0.00024682758,0.0001810043,0.0000106773505,0.0011457083,0.005583389,0.01058047,0.00026495173,0.8224737,0.00074999017],"about_ca_topic_score_codex":0.003076596,"about_ca_topic_score_gemma":0.00031696394,"teacher_disagreement_score":0.64103866,"about_ca_system_score_codex":0.00013149646,"about_ca_system_score_gemma":0.000255199,"threshold_uncertainty_score":0.9996998},"labels":[],"label_agreement":null},{"id":"W7017292847","doi":"","title":"All-In Advertising is the Law, Jaguar F-Type Review","year":2017,"lang":"en","type":"other","venue":"Internet Archive (Internet Archive)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Jaguar; Advice (programming); Work (physics); Collectable","score_opus":0.01450992309716179,"score_gpt":0.2911447820132765,"score_spread":0.27663485891611467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017292847","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":[0.00016421104,0.012545377,0.00175087,0.00070325314,0.000707602,0.0009648981,0.00021432312,0.000070037626,0.9828794],"genre_scores_gemma":[0.0030016375,0.014191915,0.0019651419,0.008108431,0.0006403508,0.000057020723,0.0012687293,0.0004475554,0.9703192],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99723107,0.0003432837,0.00063735293,0.0007885002,0.00035231406,0.00064747676],"domain_scores_gemma":[0.9972172,0.00007895543,0.0007507659,0.0017641803,0.000034991677,0.00015393416],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00037979253,0.00070734293,0.00068480405,0.00016975442,0.000050634862,0.0001209542,0.0022719873,0.0002630707,0.0019798053],"category_scores_gemma":[0.00028852173,0.0005418698,0.0004168191,0.000048018297,0.00056893675,0.000008479445,0.0013934282,0.0009481044,0.0008623023],"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":[0.00007551496,0.00004181817,0.00047218005,0.0008117903,0.00034816627,0.00003218789,0.00052434247,0.000003019714,0.00032034348,0.00065105065,0.99587774,0.00084187125],"study_design_scores_gemma":[0.00044189248,0.0002482841,0.00018512302,0.007242863,0.000099927434,0.000087714485,0.0000107758915,0.00065343076,0.00043884714,0.00019362963,0.98979884,0.0005986845],"about_ca_topic_score_codex":0.009092821,"about_ca_topic_score_gemma":0.01826026,"teacher_disagreement_score":0.01256021,"about_ca_system_score_codex":0.00002458607,"about_ca_system_score_gemma":0.00008700021,"threshold_uncertainty_score":0.99991566},"labels":[],"label_agreement":null},{"id":"W7017330511","doi":"","title":"&amp;quot;To be sold, a Negro wench&amp;quot; : slave ads of the Montreal Gazette, 1785-1805","year":2006,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Newspaper; Representation (politics); National identity; Identity (music); Presentation (obstetrics); Reading (process); Race (biology); National Identities","score_opus":0.0029287394631232985,"score_gpt":0.15820591250841445,"score_spread":0.15527717304529115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017330511","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":[0.010637019,0.00057695055,0.0002700235,0.0022601371,0.0002979532,0.00042467954,0.0017105065,0.000012868645,0.9838099],"genre_scores_gemma":[0.05933798,0.0002316365,0.0045058965,0.0035117615,0.0003582437,0.000020112488,0.0003390193,0.00023037274,0.93146497],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975,0.00008696077,0.00042702994,0.00033330274,0.0012697025,0.00038301526],"domain_scores_gemma":[0.9985735,0.000053551074,0.00046615017,0.0006921881,0.0000015483693,0.00021308815],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000017954744,0.00038976182,0.00040091973,0.000041235922,0.00009518219,0.000018453795,0.0005740888,0.000147426,0.00009073943],"category_scores_gemma":[0.000015043487,0.00031830082,0.00009373405,0.00008972273,0.00012465546,0.000009057675,0.00044501064,0.00024186903,1.730696e-8],"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":[0.00023071544,0.000048732018,0.007271337,0.0005384183,0.00029126336,0.000008650112,0.000109500885,0.00032268086,0.024167461,0.0018712829,0.9618466,0.0032933808],"study_design_scores_gemma":[0.00032322685,0.00007456794,0.0053253835,0.00017112303,0.000044914777,0.0000086431955,0.00014791526,0.00011940093,0.012291766,0.00005169546,0.98106587,0.0003754867],"about_ca_topic_score_codex":0.021315834,"about_ca_topic_score_gemma":0.4956333,"teacher_disagreement_score":0.47431746,"about_ca_system_score_codex":0.000007026493,"about_ca_system_score_gemma":0.0011573698,"threshold_uncertainty_score":0.9999269},"labels":[],"label_agreement":null},{"id":"W7017339081","doi":"","title":"Arctic Field Summer Schools: training the next generation of Arctic researchers","year":2018,"lang":"en","type":"article","venue":"Duo Research Archive (University of Oslo)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Arctic; Norwegian; The arctic; Training (meteorology); Field (mathematics); Research council; Permafrost; Circumpolar star","score_opus":0.13724009698652848,"score_gpt":0.33698017509963024,"score_spread":0.19974007811310177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017339081","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9697015,0.00011599907,0.017799355,0.0025868607,0.00006696128,0.00039782815,0.000024773812,0.00000934618,0.009297356],"genre_scores_gemma":[0.9905929,0.00018074473,0.008115787,0.00008142875,0.00017824907,0.000001026928,0.00006574782,0.000011270418,0.0007728216],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980894,0.0005905698,0.00016781504,0.00023221626,0.0005251396,0.00039486538],"domain_scores_gemma":[0.9984219,0.00026831866,0.00011651778,0.00053421344,0.0005349057,0.00012415025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018001371,0.000097467106,0.00013982334,0.00019511035,0.00042252298,0.000026647585,0.0006960429,0.00009201412,0.00021885248],"category_scores_gemma":[0.0020911554,0.00009032524,0.000105183644,0.00029351003,0.0009746807,0.000022029586,0.00048589424,0.0005608637,0.00003859599],"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":[0.0010069297,0.00014274401,0.017259791,0.00035977995,0.00034170126,0.000010762433,0.016758353,0.00015030974,0.9014947,0.0027998472,0.032457057,0.027218051],"study_design_scores_gemma":[0.009162477,0.020960147,0.10964634,0.001191175,0.00021945799,0.00011545349,0.17718467,0.16326164,0.18540207,0.011602095,0.31924784,0.0020066334],"about_ca_topic_score_codex":0.0011256147,"about_ca_topic_score_gemma":0.0010469431,"teacher_disagreement_score":0.7160926,"about_ca_system_score_codex":0.000026971979,"about_ca_system_score_gemma":0.0002609282,"threshold_uncertainty_score":0.36833563},"labels":[],"label_agreement":null},{"id":"W7017363066","doi":"","title":"Artefacts for surface measurement","year":2011,"lang":"en","type":"article","venue":"NPARC","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Verein Deutscher Ingenieure","keywords":"Object (grammar); Structured light; Surface (topology); Line (geometry); Range (aeronautics); System of measurement; Digital camera; Variety (cybernetics)","score_opus":0.0417663109475139,"score_gpt":0.24902747604412545,"score_spread":0.20726116509661155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017363066","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6497326,0.000101828264,0.056159668,0.00024933394,0.00037633567,0.00058326684,0.000018546163,0.000053723325,0.2927247],"genre_scores_gemma":[0.9467297,0.000008407283,0.052287582,0.000220376,0.00006130208,0.000010399867,0.00002054521,0.000012769496,0.0006489194],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99949133,0.000014484111,0.00011446642,0.00010998875,0.000112775255,0.00015697732],"domain_scores_gemma":[0.9995892,0.0000033944489,0.000048110964,0.0002157483,0.00009504595,0.000048507845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025657442,0.000077751574,0.000062846644,0.000009111557,0.000042879987,0.00000732255,0.00011953432,0.00006256991,0.00009958156],"category_scores_gemma":[0.00010863567,0.000070788934,0.000047030906,0.000019570985,0.000021855081,0.0000015580584,0.000037741593,0.000041673633,0.000028726776],"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":[0.00011722118,0.00007555305,0.0029785759,0.00006406938,0.00006836176,5.0547277e-7,0.00035816486,0.000047959868,0.95775795,0.0015829968,0.03151331,0.005435324],"study_design_scores_gemma":[0.00081968453,0.0005890123,0.0036965336,0.000014309435,0.000024249202,0.000008357593,0.000066313936,0.0014051729,0.72902155,0.0016736129,0.26237893,0.00030229846],"about_ca_topic_score_codex":0.000002627993,"about_ca_topic_score_gemma":0.0000062391805,"teacher_disagreement_score":0.2969971,"about_ca_system_score_codex":0.000008142191,"about_ca_system_score_gemma":0.000032766,"threshold_uncertainty_score":0.2886689},"labels":[],"label_agreement":null},{"id":"W7017484510","doi":"","title":"+91-9829791419^% Black Magic To Kill Enemy In Delhi, Goa","year":2021,"lang":"en","type":"other","venue":"OSF Preprints (OSF Preprints)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mantra; MAGIC (telescope); Spell; nobody; Unicorn","score_opus":0.00749757131324705,"score_gpt":0.2602182729025893,"score_spread":0.25272070158934223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017484510","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":[0.0070800474,0.000020695968,0.0019386272,0.00019004603,0.00038669404,0.0010253856,0.000047031193,0.000084750245,0.9892267],"genre_scores_gemma":[0.003978033,0.00046391925,0.008150077,0.0007982591,0.00033768817,0.00009692138,0.00053815497,0.00041379954,0.9852232],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995347,0.0004886732,0.0007677255,0.002286781,0.0004213906,0.0006884177],"domain_scores_gemma":[0.99446464,0.000067769055,0.000401982,0.004638289,0.00010374526,0.0003235513],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017384741,0.0006540799,0.0006713796,0.0003384786,0.00004890107,0.000107471424,0.0015107285,0.000994889,0.44536677],"category_scores_gemma":[0.002400522,0.00075811,0.00028571143,0.00030085622,0.0001592188,0.0000063944713,0.002899276,0.00077679043,0.45941797],"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":[0.00010750783,0.00034924716,0.0134904,0.0007217526,0.00036501753,0.000068856105,0.00077766716,0.0032379872,0.01371359,0.00024844258,0.95944804,0.0074714688],"study_design_scores_gemma":[0.0005800276,0.0000037639184,0.0016987161,0.00035259794,0.00003926734,0.00003776628,0.00009115794,0.00033654313,0.0052595274,0.00007945072,0.99073786,0.00078331266],"about_ca_topic_score_codex":0.0004670579,"about_ca_topic_score_gemma":0.0010379845,"teacher_disagreement_score":0.031289805,"about_ca_system_score_codex":0.00014241145,"about_ca_system_score_gemma":0.00027816778,"threshold_uncertainty_score":0.999487},"labels":[],"label_agreement":null},{"id":"W7017571953","doi":"","title":"Canadian Provincial Elections during the Covid-19 Pandemic: C-Dem Forum","year":2022,"lang":"en","type":"article","venue":"Scholarship@Western (Western University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Work (physics); Field (mathematics); Agency (philosophy)","score_opus":0.04450724914018625,"score_gpt":0.30230044656482014,"score_spread":0.2577931974246339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017571953","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9970433,0.000047210833,0.00043842426,0.0012085736,0.00023383221,0.000360329,0.00013600795,0.00007629191,0.0004560424],"genre_scores_gemma":[0.98035663,0.000019993551,0.00002176167,0.0026896356,0.00012591295,0.000007960657,0.00014629101,0.000034531713,0.016597299],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99823624,0.00035748474,0.00019821682,0.00037012025,0.0002798897,0.00055802026],"domain_scores_gemma":[0.998787,0.00002980012,0.00015587981,0.0005460645,0.0000601736,0.00042108732],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0004319542,0.00022095427,0.00014207233,0.00027018128,0.0019709682,0.0001237808,0.0009532982,0.00014408247,0.000080033686],"category_scores_gemma":[0.00014671733,0.00022692743,0.00012571269,0.00036970997,0.00009026593,0.000041199855,0.0007349727,0.0007818011,0.00003257246],"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":[0.0000790534,0.000020938312,0.99618286,0.000021674356,0.000050976883,0.00004108931,0.00021841048,0.0009548272,0.0022827995,0.00004284678,0.000024163144,0.00008035493],"study_design_scores_gemma":[0.0012076545,0.00029298366,0.5253796,0.0000065988747,0.000058930596,0.00069332623,0.0010998046,0.00000467702,0.00070113596,0.000037490903,0.46996623,0.00055159815],"about_ca_topic_score_codex":0.0016152401,"about_ca_topic_score_gemma":0.4025859,"teacher_disagreement_score":0.4708033,"about_ca_system_score_codex":0.0008212235,"about_ca_system_score_gemma":0.00090906845,"threshold_uncertainty_score":0.9993283},"labels":[],"label_agreement":null},{"id":"W7017603009","doi":"","title":"Bank Of New York Mellon Corporation (The)’s (BK) Hold Rating Reaffirmed at Royal Bank Of Canada","year":2017,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corporation; Central bank; Liability","score_opus":0.011452900116899404,"score_gpt":0.22884878941779896,"score_spread":0.21739588930089956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017603009","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":[0.005253115,0.00080404035,0.00084390206,0.0001547269,0.00049393077,0.0004283423,0.00007023302,0.000020016507,0.9919317],"genre_scores_gemma":[0.050495155,0.000049120415,0.0025576842,0.000114333765,0.00035956403,0.0000046264677,0.0005898587,0.00011724533,0.9457124],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99891585,0.000047643294,0.00036085825,0.0002061216,0.00027840532,0.00019114891],"domain_scores_gemma":[0.9977632,0.000018396331,0.0012386265,0.00085168437,0.000058870603,0.00006922341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019147826,0.00023963695,0.00031712002,0.000035839945,0.00007989008,0.000015433057,0.00044008394,0.00033210276,0.00065035606],"category_scores_gemma":[0.00021580343,0.00018339307,0.00008668863,0.00003266972,0.000095684074,0.0000013152365,0.00016836013,0.00014416352,0.0000039797387],"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":[0.00002507203,0.000007980123,0.00055679627,0.00014086386,0.00009926686,7.0494025e-7,0.000035362587,0.00023111426,0.007017886,0.00006029181,0.9903958,0.0014288725],"study_design_scores_gemma":[0.00043034524,0.00013309185,0.00021854015,0.000146228,0.000056399218,0.000005003065,0.000034628487,0.0011316264,0.045776874,0.0000059486315,0.95177287,0.00028844798],"about_ca_topic_score_codex":0.28072926,"about_ca_topic_score_gemma":0.6380163,"teacher_disagreement_score":0.35728705,"about_ca_system_score_codex":0.00003338099,"about_ca_system_score_gemma":0.00072920934,"threshold_uncertainty_score":0.74785525},"labels":[],"label_agreement":null},{"id":"W7017641223","doi":"","title":"Canadian physiciansâ knowledge and counseling practices related to antibiotic use and antimicrobial resistance: Two-cycle national survey","year":2017,"lang":"en","type":"article","venue":"PubMed Central","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Antimicrobial; Antibiotics; Antimicrobial drug; MEDLINE; Antibiotic resistance","score_opus":0.0166744736935181,"score_gpt":0.2824231400928296,"score_spread":0.2657486663993115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017641223","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9966035,0.00014890163,0.000021220025,0.0005512409,0.00029107006,0.00022618296,0.000120933684,0.0000086224945,0.0020283365],"genre_scores_gemma":[0.9979048,0.00013172884,0.00065868674,0.00028408706,0.00014018528,0.000003288831,0.00015425024,0.000016266891,0.0007067332],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988237,0.00008063707,0.00016204252,0.00024545536,0.000099185505,0.000589],"domain_scores_gemma":[0.9990384,0.00003956367,0.00021890225,0.00023115856,0.00012202108,0.0003499367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007218291,0.0001288484,0.00011453266,0.000046745627,0.0004078661,0.00036190852,0.00016968066,0.000095092575,0.0000020372356],"category_scores_gemma":[0.0021944747,0.00013551155,0.000019966837,0.000041942338,0.000090185094,0.00004028783,0.00007971187,0.00013162279,0.000004347631],"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":[0.00012524909,0.00004542533,0.98113626,0.00008326545,0.00010928629,0.000005130257,0.000683505,0.00020115176,0.0066741263,0.00029075547,0.008513131,0.0021327198],"study_design_scores_gemma":[0.00048989773,0.000015745969,0.98229665,0.000025454377,0.000014268583,0.000010444265,0.000013375683,0.00069208996,0.001644222,0.000015478001,0.014584368,0.00019803255],"about_ca_topic_score_codex":0.009234866,"about_ca_topic_score_gemma":0.1907402,"teacher_disagreement_score":0.18150534,"about_ca_system_score_codex":0.00006786934,"about_ca_system_score_gemma":0.000258751,"threshold_uncertainty_score":0.99736273},"labels":[],"label_agreement":null},{"id":"W7017672023","doi":"","title":"Bassins d'eaux pluviales en territoire urbain : Patrons de biodiversité et perception par les citadins","year":2024,"lang":"fr","type":"other","venue":"EspaceINRS Institutional Digital Repository (Institut National de la Recherche Scientifique)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Ile de france; Western europe; Drainage network; Statistical analysis","score_opus":0.03489642115076583,"score_gpt":0.3064920108876442,"score_spread":0.27159558973687836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017672023","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":[0.021176996,0.002333893,0.037864644,0.0027300145,0.0022119193,0.00076619,0.0016560116,0.00021971659,0.93104064],"genre_scores_gemma":[0.38685077,0.00070084207,0.03951509,0.0005210581,0.0016895712,0.000117656404,0.0022000424,0.00019090653,0.56821406],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99457854,0.0016710187,0.0007280014,0.0011580053,0.0011342616,0.00073018647],"domain_scores_gemma":[0.99756384,0.00061935687,0.00037749865,0.00049225276,0.00050129805,0.00044574935],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0031581372,0.0008226641,0.00044125918,0.00060372823,0.00083098013,0.0015007459,0.00083959685,0.0025717984,0.00035994302],"category_scores_gemma":[0.006238989,0.0008432059,0.00062419596,0.0005176359,0.002662321,0.00018487117,0.0005408876,0.002115426,0.0005797012],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00037316955,0.0017806245,0.022617906,0.0032265035,0.0021249203,0.0005706031,0.0061453353,0.034798548,0.16768168,0.34494475,0.38801262,0.027723338],"study_design_scores_gemma":[0.0005413895,0.000115825416,0.006045071,0.0012643018,0.00015884424,0.00087073667,0.00023554453,0.005047973,0.0026302582,0.0032996144,0.97882164,0.00096882915],"about_ca_topic_score_codex":0.00018661791,"about_ca_topic_score_gemma":0.00033114114,"teacher_disagreement_score":0.590809,"about_ca_system_score_codex":0.004155319,"about_ca_system_score_gemma":0.007727187,"threshold_uncertainty_score":0.9996675},"labels":[],"label_agreement":null},{"id":"W7017688965","doi":"","title":"CAPRI- Content-based Analysis of Protein Structure for Retrieval and Indexing","year":2015,"lang":"en","type":"article","venue":"NPARC","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Protein structure database; Search engine indexing; Protein structure; Protein Data Bank; Task (project management); Domain (mathematical analysis); Protein domain","score_opus":0.025266384945340968,"score_gpt":0.2687159563003702,"score_spread":0.24344957135502923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017688965","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98792106,0.000037086313,0.011121002,0.000096216885,0.00002102281,0.00020152706,0.000063002844,0.000005160284,0.0005339495],"genre_scores_gemma":[0.9741732,6.8609427e-7,0.02535851,0.000088459965,0.000027619817,0.0000036639467,0.0001703932,0.0000069362195,0.00017054415],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99951595,0.000022027829,0.00015490956,0.000107445994,0.000100619174,0.00009903203],"domain_scores_gemma":[0.999518,0.000009692861,0.0001106519,0.0001687413,0.00013659825,0.000056356155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017536737,0.0000722104,0.00014167977,0.00006416288,0.000021474667,0.000010291633,0.00007747134,0.000095007155,0.000010662513],"category_scores_gemma":[0.0003947702,0.000062734376,0.00005391968,0.00011577893,0.00004812121,0.0000018155106,0.00003441632,0.0000518061,1.3314644e-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":[0.00031268466,0.000010572064,0.0110924505,0.000056681958,0.00022385134,1.7837075e-7,0.00008361622,0.000556558,0.9864236,0.00019901732,0.00020038248,0.0008404235],"study_design_scores_gemma":[0.0019538586,0.0006490202,0.003961377,0.000017882,0.00034756612,0.000001892306,0.00027581435,0.059237383,0.9271025,0.0003134114,0.005903249,0.00023601379],"about_ca_topic_score_codex":0.000007662492,"about_ca_topic_score_gemma":0.000015163747,"teacher_disagreement_score":0.059321053,"about_ca_system_score_codex":0.0000065625663,"about_ca_system_score_gemma":0.000052707303,"threshold_uncertainty_score":0.25582337},"labels":[],"label_agreement":null},{"id":"W7017738390","doi":"","title":"Changes - 140819 - Canadian Political Spectrum Centre to Right","year":2014,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Politics; Sound (geography); Spectrum (functional analysis)","score_opus":0.0027408233929366492,"score_gpt":0.1810141613732955,"score_spread":0.17827333798035885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017738390","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":[0.00005646871,0.000059576956,0.0000025091451,0.001953264,0.00028286126,0.00037211418,0.0002801282,0.00005585246,0.9969372],"genre_scores_gemma":[0.0022776993,0.000035510344,0.0013398842,0.00258648,0.00047247764,0.0000073043257,0.0008365804,0.00013054984,0.9923135],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99836415,0.000061968814,0.00039788903,0.0002124692,0.00026847143,0.000695033],"domain_scores_gemma":[0.9985614,0.000019075205,0.00025904542,0.0005114961,0.00007735701,0.0005716219],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00018819771,0.00035113524,0.00032688855,0.00012546235,0.00006239957,0.000045589437,0.0003999582,0.0005601315,0.18193899],"category_scores_gemma":[0.0002195412,0.0003475673,0.00010908715,0.000007725236,0.00008616894,1.3714037e-8,0.00011950881,0.00022482785,0.013002],"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":[0.000021233573,0.000010823962,0.00001676136,0.00023515886,0.000050106464,0.00000495726,0.000034781162,0.000059212834,0.0000014988816,0.00022792451,0.9990645,0.00027306532],"study_design_scores_gemma":[0.00023933101,0.00020176756,0.000017528806,0.00011190646,0.000028647119,0.00004984126,0.00003297833,0.000022162987,0.00009848889,0.000004897109,0.9988031,0.00038939755],"about_ca_topic_score_codex":0.08004835,"about_ca_topic_score_gemma":0.37733927,"teacher_disagreement_score":0.29729092,"about_ca_system_score_codex":0.00006463808,"about_ca_system_score_gemma":0.00009278905,"threshold_uncertainty_score":0.99989766},"labels":[],"label_agreement":null},{"id":"W7017783262","doi":"","title":"From Cartier to Codification: Website-Blocking Injunctions and Third-Party Internet Service Provider Respondents","year":2023,"lang":"en","type":"article","venue":"eYLS (Yale Law School)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Appeal; Order (exchange); Copyright infringement; Anonymity; The Internet; Service provider; Internet service provider; Revenue","score_opus":0.014844733186808479,"score_gpt":0.27199557671111974,"score_spread":0.2571508435243113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017783262","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9937422,0.00009624258,0.00063937274,0.0015428294,0.00033858677,0.00027266503,0.00005171739,0.000109245375,0.0032070854],"genre_scores_gemma":[0.98252684,0.000021290492,0.0027205092,0.004493279,0.00046090476,0.00007315996,0.00053117133,0.00003663676,0.009136213],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99884987,0.0000790916,0.00027668595,0.00034764688,0.0001933022,0.0002534084],"domain_scores_gemma":[0.9990763,0.000029639075,0.000087019966,0.0005005529,0.00011609417,0.00019039192],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002485427,0.0001669714,0.00013655005,0.00006231861,0.0001454519,0.00013548057,0.00024425928,0.00015141701,0.000107892],"category_scores_gemma":[0.0002218794,0.00016417918,0.000040747505,0.00027490334,0.000039183546,0.000018292365,0.0003490616,0.00020456986,0.00095469813],"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":[0.0009938208,0.00018640964,0.15102483,0.00037268703,0.0005538586,0.000024163886,0.005861298,0.003922726,0.4931812,0.003929742,0.33676246,0.0031867956],"study_design_scores_gemma":[0.0008853507,0.00020756199,0.03741373,0.00009240347,0.000048888003,0.00001333129,0.0005564701,0.0039090132,0.028313123,0.00032331175,0.92773414,0.0005026731],"about_ca_topic_score_codex":0.000906807,"about_ca_topic_score_gemma":0.0013260369,"teacher_disagreement_score":0.5909717,"about_ca_system_score_codex":0.000022436814,"about_ca_system_score_gemma":0.00004601976,"threshold_uncertainty_score":0.99982315},"labels":[],"label_agreement":null},{"id":"W7017791310","doi":"","title":"Bird Sightings: May-june 1999 Summary","year":2023,"lang":"en","type":"article","venue":"Digital Commons - University of South Florida (University of South Florida)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Natural (archaeology); Selection (genetic algorithm); Identification (biology); Population","score_opus":0.01093757842642998,"score_gpt":0.19356848461767104,"score_spread":0.18263090619124106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017791310","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98278356,0.00006415369,0.0028282194,0.0003130708,0.00037550568,0.00026889495,0.0008089828,0.00035213155,0.012205511],"genre_scores_gemma":[0.9924439,0.00005147956,0.000982014,0.00002423576,0.0001019812,7.6002905e-8,0.00044198893,0.000054952594,0.005899344],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99820065,0.000059208163,0.00026626568,0.0004770708,0.0004856633,0.000511148],"domain_scores_gemma":[0.9982185,0.00006366979,0.00045129316,0.000762583,0.0002496293,0.00025433762],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002511747,0.0003415416,0.0004959656,0.0004307221,0.00047000215,0.00003906012,0.001111696,0.0003259929,0.000067960114],"category_scores_gemma":[0.00010331931,0.00046466262,0.00042490932,0.00080499495,0.0007022508,0.000095355375,0.0011942283,0.00034985435,0.00034152775],"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":[0.003760874,0.00042948112,0.8419501,0.001501291,0.0021267945,0.0004588546,0.058293443,0.0057265824,0.008424819,0.00243987,0.06889286,0.005995016],"study_design_scores_gemma":[0.01321615,0.0026228202,0.14649162,0.00082524377,0.0009448073,0.000054096974,0.28246185,0.009303602,0.0029613029,0.00036664525,0.5362504,0.0045014303],"about_ca_topic_score_codex":0.00023853629,"about_ca_topic_score_gemma":0.00017761922,"teacher_disagreement_score":0.6954585,"about_ca_system_score_codex":0.000045134093,"about_ca_system_score_gemma":0.00014786363,"threshold_uncertainty_score":0.99978054},"labels":[],"label_agreement":null},{"id":"W7017797023","doi":"","title":"\"Burria\", un nuevo sello anfórico hallado en el campamento romano de Castillejo (Garray, Soria)","year":2016,"lang":"en","type":"article","venue":"Deposito Adademico Digital Universidad De Navarra (University of Navarra)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Period (music); Vetting; Quarter (Canadian coin)","score_opus":0.003072316319847653,"score_gpt":0.20954759913334453,"score_spread":0.2064752828134969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017797023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9321636,0.00016491926,0.05286228,0.0005987104,0.00016986867,0.00027763288,0.00020153174,0.0001111363,0.013450313],"genre_scores_gemma":[0.99010533,0.00023407092,0.0042725806,0.00014181223,0.0001678435,5.48348e-7,0.00012138368,0.000052313913,0.004904088],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99775773,0.00015423697,0.00031524987,0.0005810999,0.00043084662,0.00076083036],"domain_scores_gemma":[0.99815124,0.00013145966,0.0003945603,0.0006581475,0.00020334267,0.0004612614],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026599827,0.0004241512,0.00041712288,0.00024506947,0.000306572,0.000071827606,0.0011033514,0.000631849,0.00009319993],"category_scores_gemma":[0.00023275889,0.00045866345,0.00032612996,0.00034790128,0.00031681033,0.0001531155,0.00053275336,0.00034269676,0.00006189041],"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":[0.0014872805,0.00049903453,0.119091205,0.00025609392,0.001130919,0.000570542,0.0054640803,0.0009984417,0.83147234,0.0017207911,0.01674651,0.02056279],"study_design_scores_gemma":[0.038556468,0.0069686566,0.12928033,0.0019351947,0.0019397337,0.004391994,0.04140089,0.01090272,0.21352002,0.0027434982,0.538418,0.009942514],"about_ca_topic_score_codex":0.00026912038,"about_ca_topic_score_gemma":0.00004288066,"teacher_disagreement_score":0.6179523,"about_ca_system_score_codex":0.00039263052,"about_ca_system_score_gemma":0.00035268176,"threshold_uncertainty_score":0.9997865},"labels":[],"label_agreement":null},{"id":"W7017800758","doi":"","title":"British Girls’ and Women’s Magazines at the University ofWaterloo","year":2020,"lang":"en","type":"article","venue":"Érudit documents and data repository (Érudit Consortium, University of Montreal)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"TRIPS architecture; Microform; Plan (archaeology); Work (physics); New england; Balance (ability); Club","score_opus":0.006830783334889297,"score_gpt":0.19281087320785656,"score_spread":0.18598008987296727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017800758","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99375176,0.0008987174,0.0001565786,0.0010938516,0.00007613951,0.00020243178,0.000313423,0.000023701345,0.0034833753],"genre_scores_gemma":[0.97959214,0.004347401,0.0006560397,0.00031506977,0.000114901835,3.419906e-7,0.000577658,0.000017707003,0.014378758],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989146,0.000084784755,0.00017361318,0.00044776962,0.0001623985,0.00021681281],"domain_scores_gemma":[0.99892694,0.000034450168,0.00021804686,0.00056377024,0.0000637254,0.00019305339],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001313399,0.00016090329,0.00021298074,0.00002296968,0.00041768447,0.000044480108,0.0005209517,0.000106126616,0.00009645132],"category_scores_gemma":[0.000057630583,0.00016628124,0.000039016155,0.00006146097,0.00043902668,0.00004933556,0.0014815509,0.000113543996,0.000005868109],"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":[0.0024617359,0.0002548778,0.21276757,0.0008255021,0.0015752,0.0011284202,0.0025003122,0.00017742233,0.036477074,0.00019405253,0.69329196,0.048345864],"study_design_scores_gemma":[0.0018106072,0.00029251986,0.035048082,0.00003414652,0.00014742903,0.00021288545,0.0010721424,0.0005813518,0.00058307993,0.000007157739,0.9598939,0.0003167261],"about_ca_topic_score_codex":0.002276672,"about_ca_topic_score_gemma":0.0034132556,"teacher_disagreement_score":0.26660192,"about_ca_system_score_codex":0.000061655635,"about_ca_system_score_gemma":0.000041727737,"threshold_uncertainty_score":0.67807525},"labels":[],"label_agreement":null},{"id":"W7017819342","doi":"","title":"Canadian Solar to Attend the 18th Annual Needham Growth Conference in New York City","year":2016,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Work (physics); China","score_opus":0.009013990904295579,"score_gpt":0.23989674289846466,"score_spread":0.23088275199416908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017819342","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":[0.0003894487,0.00013980726,0.0028427595,0.0035921268,0.0002448988,0.0004109119,0.000214959,0.000029736468,0.99213535],"genre_scores_gemma":[0.012717436,0.00006090501,0.0017567953,0.0034386239,0.00053854805,0.000009360325,0.00012693761,0.0001374175,0.981214],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989618,0.000048753995,0.00019466528,0.0002636922,0.00013063308,0.00040046737],"domain_scores_gemma":[0.99906886,0.000010182101,0.00009089958,0.0004946408,0.00003856236,0.0002968514],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015593803,0.00025908006,0.0001919865,0.00014506762,0.000042189957,0.000040463703,0.00057516084,0.00039230048,0.0033213748],"category_scores_gemma":[0.000111883455,0.00016497844,0.00005521252,0.000086117674,0.000050865514,0.0000015938901,0.00013914786,0.00022425194,0.0004152048],"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":[0.0000062623294,0.0000043141827,0.0032207232,0.000014149808,0.000028124969,0.0000016713471,0.00011498437,0.0000012452751,0.00011025972,0.0005208126,0.99426633,0.0017110921],"study_design_scores_gemma":[0.00019418463,0.000061330866,0.00076853466,0.000055640376,0.000006780484,0.000006225565,0.00008513414,0.000011310717,0.0002304076,0.000032817534,0.99826264,0.00028498902],"about_ca_topic_score_codex":0.23394333,"about_ca_topic_score_gemma":0.6924752,"teacher_disagreement_score":0.4585319,"about_ca_system_score_codex":0.000044228807,"about_ca_system_score_gemma":0.00084970455,"threshold_uncertainty_score":0.9975897},"labels":[],"label_agreement":null},{"id":"W7017861006","doi":"","title":"Brushing the surface: Edgar Degas’s La Coiffure as site of experimentation and corporal dissolution","year":2019,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"McGill University","keywords":"Photography; Subject matter; Repetition (rhetorical device); Subject (documents); Painting; Representation (politics)","score_opus":0.0074266036674435,"score_gpt":0.25576159077153837,"score_spread":0.24833498710409488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017861006","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9764478,0.00063019345,0.0000017860687,0.000013160683,0.00047057602,0.00053567986,0.0002925316,0.000032264386,0.021576006],"genre_scores_gemma":[0.9913904,0.00032943668,0.0006953327,0.00012378112,0.000035399644,0.00002092895,0.003094642,0.000092482114,0.0042175865],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99782485,0.00033849676,0.00059816334,0.00048697743,0.0004326464,0.0003188961],"domain_scores_gemma":[0.9981766,0.00009507429,0.00082020444,0.00057352317,0.00022936208,0.00010528444],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007027037,0.00044414712,0.00037848935,0.00007794708,0.00043831326,0.00007578221,0.0003311232,0.0007185354,0.000038452377],"category_scores_gemma":[0.00044774797,0.00039139795,0.00017192855,0.00014426162,0.00010151374,0.000043899086,0.00016125549,0.0007408586,0.000044286997],"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":[0.00046971126,0.00010444336,0.0014846111,0.00061322557,0.00025602744,0.0000048904903,0.00014937701,0.0005012169,0.9674875,0.012329738,0.000039879596,0.016559348],"study_design_scores_gemma":[0.0026111244,0.0010654212,0.022357006,0.00069989386,0.0004667999,0.000118445234,0.0029469645,0.0009935861,0.9010787,0.001549893,0.06430335,0.001808781],"about_ca_topic_score_codex":0.00021482482,"about_ca_topic_score_gemma":0.00019372291,"teacher_disagreement_score":0.066408806,"about_ca_system_score_codex":0.00007433228,"about_ca_system_score_gemma":0.000062109386,"threshold_uncertainty_score":0.9998538},"labels":[],"label_agreement":null},{"id":"W7017889293","doi":"","title":"Ban Conversion Therapy","year":2020,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Action (physics); Legislation; MEDLINE; Product (mathematics)","score_opus":0.0047433105418097305,"score_gpt":0.1887870671564841,"score_spread":0.18404375661467437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017889293","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":[0.0000662079,0.000421821,0.0000022839592,0.00020202668,0.00021148106,0.00032101903,0.00009307135,0.000083458785,0.99859864],"genre_scores_gemma":[0.0008164813,0.0010275347,0.001913399,0.0010156162,0.00022904576,0.0000066837297,0.0008519912,0.00012819318,0.99401104],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998865,0.000057102236,0.00042721705,0.00017429859,0.00026988474,0.00020646722],"domain_scores_gemma":[0.9989367,0.000016687494,0.0005007607,0.00036973855,0.000067261,0.00010881353],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00011156629,0.0003008718,0.00028707553,0.00003815493,0.000040900475,0.00002887675,0.0003458002,0.00047153985,0.18587433],"category_scores_gemma":[0.00010516535,0.00028905165,0.00015712675,0.0000053447548,0.0001011681,1.3098508e-8,0.00012888145,0.00022575026,0.006177476],"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":[0.00010449063,0.00001811686,0.000010154938,0.00028374846,0.00007714977,0.0000027526755,0.00005133538,0.00005848854,0.000014603306,0.000007740915,0.99801034,0.0013610915],"study_design_scores_gemma":[0.00062723644,0.00034018222,0.000007772544,0.00006777771,0.000017777345,0.000024396708,0.000033319688,0.00004047217,0.00025760755,7.681587e-7,0.9982813,0.00030140695],"about_ca_topic_score_codex":0.00071621727,"about_ca_topic_score_gemma":0.00009071629,"teacher_disagreement_score":0.17969684,"about_ca_system_score_codex":0.000010752768,"about_ca_system_score_gemma":0.000032943455,"threshold_uncertainty_score":0.9999562},"labels":[],"label_agreement":null},{"id":"W7017895344","doi":"","title":"1932 Chap. 0083. An Act Authorizing The City Of Brockton To Acquire By Gift And Maintain Certain Land In The Town Of Avon For Park Purposes.","year":2010,"lang":"en","type":"other","venue":"State Library's electronic repository (State Library of Massachusetts)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Government (linguistics); Payment; Legislation; Quarter (Canadian coin)","score_opus":0.0051166843362405335,"score_gpt":0.22642455134889813,"score_spread":0.2213078670126576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017895344","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87479967,0.00755213,0.0014699139,0.0046592113,0.00056289893,0.0065784436,0.0026429675,0.00023380147,0.10150099],"genre_scores_gemma":[0.7752701,0.0037517708,0.00654784,0.0016858953,0.0007477705,0.00034943924,0.004411307,0.0012951179,0.20594075],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967969,0.00051262294,0.0009637471,0.0006128867,0.00036601996,0.00074782094],"domain_scores_gemma":[0.99743706,0.0001747709,0.0010888829,0.0011305889,0.000025077567,0.00014361116],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005092947,0.00056758727,0.0007271292,0.00023202857,0.000117898264,0.00011324891,0.0013214187,0.0004641595,0.00007607841],"category_scores_gemma":[0.000052654606,0.00040349498,0.00019934874,0.00027429443,0.00032694635,0.000117227886,0.00036108962,0.0007250845,4.4018506e-7],"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":[0.0050730677,0.0009546731,0.093545,0.0040566665,0.0014421945,0.000031302934,0.0052281874,0.00032464156,0.19629134,0.0026630566,0.67269266,0.017697228],"study_design_scores_gemma":[0.0012227333,0.002539524,0.002341461,0.00023264017,0.00009230685,0.000038136743,0.00021587568,0.00028840583,0.12401016,0.0014689486,0.8668139,0.0007359378],"about_ca_topic_score_codex":0.00016093088,"about_ca_topic_score_gemma":0.00008174148,"teacher_disagreement_score":0.19412123,"about_ca_system_score_codex":0.00001261637,"about_ca_system_score_gemma":0.00039982423,"threshold_uncertainty_score":0.9998417},"labels":[],"label_agreement":null},{"id":"W7017970457","doi":"","title":"CanAlaska Uranium Ltd Invites You to Join Us at the VRIC Conference in Vancouver","year":2019,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Join (topology); Government (linguistics); Authorization; Uranium","score_opus":0.0054759680024346735,"score_gpt":0.22876518597967394,"score_spread":0.22328921797723927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017970457","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":[0.005462903,0.0003912805,0.00042148112,0.0005118798,0.00063841045,0.00061812054,0.00008397277,0.00003256859,0.9918394],"genre_scores_gemma":[0.008071994,0.0001293458,0.0007028253,0.002816917,0.00017769214,0.00002130224,0.00016868119,0.00015480025,0.98775643],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989122,0.0000621327,0.00024161827,0.00030793008,0.000179194,0.0002969288],"domain_scores_gemma":[0.9990094,0.000016744667,0.00014952196,0.0007164438,0.000035252204,0.000072641815],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015271368,0.00028593824,0.00024871095,0.00008815626,0.000028675382,0.00002893223,0.0004273196,0.00036558538,0.0019678788],"category_scores_gemma":[0.00009583219,0.0001922986,0.000072793206,0.000112643764,0.00005410364,0.0000012405999,0.00037206514,0.0002339309,0.0005926525],"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":[0.000012981325,0.000010333096,0.0034002352,0.00006263219,0.000036515732,0.0000012373341,0.000054009382,0.000118370495,0.002304244,0.00003353727,0.9937121,0.00025375397],"study_design_scores_gemma":[0.00023940505,0.00007669287,0.0005786847,0.000048272046,0.0000124163935,0.0000041810267,0.00005998262,0.00016704938,0.0017016327,0.0000028147638,0.996811,0.0002979158],"about_ca_topic_score_codex":0.0024805572,"about_ca_topic_score_gemma":0.10083373,"teacher_disagreement_score":0.09835317,"about_ca_system_score_codex":0.000042898206,"about_ca_system_score_gemma":0.00011851388,"threshold_uncertainty_score":0.99894446},"labels":[],"label_agreement":null},{"id":"W7017996476","doi":"","title":"CANADA STOCKS-TSX futures edge lower as coronavirus resurgence fears linger","year":2020,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Coronavirus; Futures contract; Coronavirus disease 2019 (COVID-19); Pandemic; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)","score_opus":0.007885729966198714,"score_gpt":0.25385644609696467,"score_spread":0.24597071613076596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017996476","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":[0.000504458,0.001370807,0.00022739235,0.00042986084,0.001465983,0.0003064945,0.00015449939,0.00007836386,0.9954621],"genre_scores_gemma":[0.007566228,0.00038181382,0.0018520918,0.004928574,0.0013324829,0.00001390127,0.0005159415,0.00035120334,0.98305774],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99862677,0.000047547484,0.0002695642,0.0004077308,0.00032072474,0.00032769385],"domain_scores_gemma":[0.99895334,0.000010976783,0.00022153818,0.00058309326,0.000035774276,0.00019528861],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00007727888,0.00037036504,0.00029030774,0.000041599957,0.00006186286,0.000032598597,0.00045953327,0.0004637238,0.0050449786],"category_scores_gemma":[0.00016711405,0.0003348568,0.00010290772,0.00007016997,0.00006151712,0.0000011690677,0.00024238238,0.0003622627,0.00018971536],"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":[0.00003510895,0.00001091881,0.00025175716,0.000076173965,0.00009891364,0.000017147111,0.000012796475,0.000021868664,0.0010057079,0.00006255217,0.9962185,0.0021885242],"study_design_scores_gemma":[0.0001782096,0.00011038259,0.00013254845,0.000035578672,0.000018869712,0.000012148972,0.000021589585,0.0000642593,0.00165284,0.0000029760095,0.9973366,0.00043397144],"about_ca_topic_score_codex":0.2949521,"about_ca_topic_score_gemma":0.52222276,"teacher_disagreement_score":0.22727065,"about_ca_system_score_codex":0.000031915355,"about_ca_system_score_gemma":0.0009905695,"threshold_uncertainty_score":0.99991035},"labels":[],"label_agreement":null},{"id":"W7018163589","doi":"","title":"Control of domain patterns in square shaped nickel rings","year":2003,"lang":"en","type":"article","venue":"eScholarship@McGill (McGill)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; McGill University; National Science Foundation","keywords":"Square (algebra); Magnetic domain; Magnetic field; Domain (mathematical analysis); Magnetic force microscope; Permalloy; Orientation (vector space); Plane (geometry); Nickel","score_opus":0.007134916718914002,"score_gpt":0.22408246608648058,"score_spread":0.21694754936756658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7018163589","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97881013,0.000078381876,0.000063416104,0.00001972065,0.00014373247,0.00036470057,0.0003203347,0.00003131088,0.020168293],"genre_scores_gemma":[0.9968639,0.000039510454,0.0020818023,0.0005331495,0.000016591694,0.00003691687,0.000077639954,0.0000611999,0.00028929085],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976126,0.0003543231,0.00073116244,0.0004519866,0.0003251119,0.0005248217],"domain_scores_gemma":[0.9986779,0.000065760476,0.00033127717,0.0006417728,0.00012108245,0.00016220291],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009473652,0.00034543374,0.00039534745,0.00015123894,0.00016963917,0.00002040939,0.0004120298,0.00035435596,0.00013206615],"category_scores_gemma":[0.00088749663,0.00035608726,0.00019019179,0.00022174725,0.00007549938,0.000025686082,0.00013425706,0.0005125723,0.00004728983],"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":[0.00028149222,0.00042647036,0.082379535,0.00042082576,0.00019879866,0.000034590896,0.000017123632,0.0006164481,0.8164809,0.09026647,0.00000719083,0.008870174],"study_design_scores_gemma":[0.015245956,0.0017410652,0.046504255,0.0004947871,0.00013543187,0.00022169907,0.00047232825,0.00088354666,0.68574035,0.011618061,0.23433657,0.0026059633],"about_ca_topic_score_codex":0.00008569344,"about_ca_topic_score_gemma":0.0002018166,"teacher_disagreement_score":0.23432939,"about_ca_system_score_codex":0.000084170526,"about_ca_system_score_gemma":0.000026850246,"threshold_uncertainty_score":0.99988914},"labels":[],"label_agreement":null},{"id":"W7018270938","doi":"","title":"Continuous sliding mode control of a Cartesian pneumatic robot","year":2002,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Diafiltration; Liquation; Emperipolesis; Triacetin; Durvalumab","score_opus":0.001868510370036028,"score_gpt":0.14664358331435934,"score_spread":0.14477507294432332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7018270938","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013757474,0.0011481956,0.0018101505,0.00041604345,0.00015027552,0.00028271542,0.00055403647,0.00001009431,0.99425274],"genre_scores_gemma":[0.74548686,0.0003272757,0.002221935,0.0004897789,0.00009719057,0.0000074023774,0.000048065507,0.00013446913,0.25118703],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99849916,0.000055294888,0.00032681867,0.0001873586,0.00070402736,0.00022736927],"domain_scores_gemma":[0.9991068,0.000045428747,0.00042105638,0.0002920342,5.508629e-7,0.00013409511],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000008281709,0.00023758369,0.00039370952,0.000027712242,0.000040615636,0.0000089924215,0.00023437984,0.00008479262,0.00009567423],"category_scores_gemma":[0.0000082577235,0.00023006625,0.000045487242,0.000029056746,0.000058129805,0.0000061616597,0.00009366032,0.00012389573,3.868717e-9],"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":[0.001419253,0.00033253708,0.057865914,0.011696014,0.0036972093,0.00021548789,0.0005842191,0.0070870793,0.40331566,0.038833313,0.43548474,0.039468598],"study_design_scores_gemma":[0.002804648,0.0006460248,0.0024896173,0.0015143605,0.00025622797,0.000049286184,0.0016152827,0.04212065,0.09880701,0.00013308953,0.8479933,0.0015704717],"about_ca_topic_score_codex":0.00268863,"about_ca_topic_score_gemma":0.0117982635,"teacher_disagreement_score":0.7441111,"about_ca_system_score_codex":0.0000022759432,"about_ca_system_score_gemma":0.00043791105,"threshold_uncertainty_score":0.9381829},"labels":[],"label_agreement":null},{"id":"W7018287229","doi":"","title":"Densification &amp; affordability : comparative real estate projects across Montreal","year":2014,"lang":"en","type":"other","venue":"Open MIND","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Real estate; Context (archaeology); Urban planning; Real estate development; Process (computing); Government (linguistics); Residential real estate","score_opus":0.047297534910776845,"score_gpt":0.37341046469839456,"score_spread":0.32611292978761774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7018287229","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":[0.10046425,0.000018541392,0.0005986461,0.00002692693,0.00011833781,0.00091963686,0.00019310838,0.00000573285,0.89765483],"genre_scores_gemma":[0.03824096,0.00026796543,0.04187663,0.000042090895,0.00042914323,0.000082548744,0.005491091,0.00023493374,0.9133346],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987216,0.00013322444,0.0002837863,0.00045142422,0.0001404309,0.0002695392],"domain_scores_gemma":[0.9986082,0.000015628902,0.0004137859,0.00081882684,0.00006526004,0.00007832159],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039147312,0.00027715036,0.00032911697,0.000030289455,0.00007558863,0.00012854324,0.00054687995,0.00035680478,0.00065299333],"category_scores_gemma":[0.00007824125,0.00024904744,0.000064123764,0.000057600828,0.00013606399,0.0000037961377,0.00037448903,0.00018354975,0.0007236624],"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":[0.00044338568,0.00032529788,0.0048661637,0.0002569575,0.00045097916,0.0000033808035,0.009358868,0.00020033144,0.007361609,0.000010503898,0.6643971,0.3123254],"study_design_scores_gemma":[0.00039294505,0.00011051032,0.0012225967,0.000037121183,0.000022375818,0.0000067913456,0.00018865286,0.00024326192,0.0014563879,0.0000024808935,0.9960008,0.00031606475],"about_ca_topic_score_codex":0.0016645561,"about_ca_topic_score_gemma":0.022515697,"teacher_disagreement_score":0.33160368,"about_ca_system_score_codex":0.00002148705,"about_ca_system_score_gemma":0.00011152159,"threshold_uncertainty_score":0.9999962},"labels":[],"label_agreement":null},{"id":"W7018394581","doi":"","title":"The Crustal Domains of the Newfoundland Margin: Implications for Rifting","year":2023,"lang":"en","type":"other","venue":"DIGITAL.CSIC (Spanish National Research Council (CSIC))","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rift; Rift zone; Precambrian; Margin (machine learning); Deformation (meteorology)","score_opus":0.09126424501112841,"score_gpt":0.3611027594089739,"score_spread":0.2698385143978455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7018394581","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":[0.00047376545,0.00086947804,0.0009122052,0.003148498,0.00046753403,0.0020259472,0.0037155612,0.00011641115,0.9882706],"genre_scores_gemma":[0.043735802,0.0014120432,0.000700664,0.00038869778,0.0022934112,0.0008818569,0.0011504644,0.0010625886,0.94837445],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950914,0.00010098309,0.0004768897,0.00043882857,0.0032769586,0.00061498076],"domain_scores_gemma":[0.9923267,0.0009771845,0.00039623343,0.0008221202,0.00535262,0.00012514497],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004120056,0.0002831526,0.0002342689,0.00011224905,0.000638737,0.00039348667,0.0012189007,0.00034686027,0.000037150417],"category_scores_gemma":[0.03095287,0.0001968303,0.00026168913,0.00043485427,0.00065597193,0.00001793055,0.000608435,0.0004822489,0.00005825319],"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":[0.000042241572,0.000051537852,0.0006671781,0.00013050986,0.00022885458,3.0117278e-7,0.00004658939,0.00005694768,0.00028984263,0.023577292,0.9715333,0.0033754024],"study_design_scores_gemma":[0.00044632502,0.00009955847,0.0015698825,0.000098175886,0.000013511671,0.0000069380662,0.000059546892,0.00021759435,0.0000350308,0.0039289184,0.99331033,0.00021417381],"about_ca_topic_score_codex":0.00016329701,"about_ca_topic_score_gemma":0.004301522,"teacher_disagreement_score":0.04326204,"about_ca_system_score_codex":0.0008201776,"about_ca_system_score_gemma":0.005438131,"threshold_uncertainty_score":0.9772098},"labels":[],"label_agreement":null},{"id":"W7018736212","doi":"","title":"Éduquer à la ville ou L'école montréalaise : propositions de l'Alliance des professeurs de Montréal pour une politique d'enseignement en milieu urbain","year":2015,"lang":"fr","type":"other","venue":"Bibliothèque et Archives nationales du Québec (Québec government)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Perspective (graphical); Meaning (existential); Identity (music); Relation (database)","score_opus":0.008008235564016286,"score_gpt":0.24433432561413937,"score_spread":0.2363260900501231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7018736212","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":[0.14559439,0.049118675,0.02259348,0.058920488,0.00018962075,0.0022072012,0.0014319534,0.00020971135,0.7197345],"genre_scores_gemma":[0.26118654,0.0069571156,0.0410702,0.0036302437,0.0009249052,0.0008020153,0.00043200143,0.0005194044,0.68447757],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957802,0.0010014934,0.0008109426,0.00070920563,0.0008283465,0.00086977513],"domain_scores_gemma":[0.9965633,0.0014147541,0.0006768086,0.0006605501,0.00017012663,0.00051443913],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007739928,0.0008227883,0.0005364359,0.0003878364,0.00037028032,0.00024087327,0.0009104506,0.00047260858,0.0015716775],"category_scores_gemma":[0.003033234,0.00084212597,0.00033470325,0.0004569983,0.00065553235,0.00005544155,0.00061575044,0.0007788331,0.00023768285],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00069731846,0.0022813978,0.074354276,0.0017194073,0.001505209,0.0001321986,0.0220649,0.008849176,0.018558685,0.04448345,0.8234071,0.0019468787],"study_design_scores_gemma":[0.0019448119,0.0004996071,0.05916118,0.00071620266,0.00022118154,0.00029236288,0.0010917361,0.007706663,0.0018653057,0.0014759704,0.9238775,0.0011474895],"about_ca_topic_score_codex":0.16443297,"about_ca_topic_score_gemma":0.92758507,"teacher_disagreement_score":0.7631521,"about_ca_system_score_codex":0.006338489,"about_ca_system_score_gemma":0.04922062,"threshold_uncertainty_score":0.99940294},"labels":[],"label_agreement":null},{"id":"W7024573695","doi":"","title":"Strategic Risk Management in the Municipal and Public Sector: An Exploration of Critical Success Factors and Barriers to Strategic Risk Management within the Province of Newfoundland and Labrador&#13;\\n","year":2010,"lang":"en","type":"report","venue":"Memorial University Research Repository (Memorial University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Risk management; Public sector; Enterprise risk management; Government (linguistics); Critical success factor; Strategic planning; Public policy; Local government","score_opus":0.04382230115732923,"score_gpt":0.30062058063134145,"score_spread":0.25679827947401224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024573695","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97245896,0.000065496875,0.00006932422,0.00005477866,0.0009877546,0.0011565275,0.00011576423,0.0000122435995,0.025079159],"genre_scores_gemma":[0.9969329,0.0013119025,0.00029237187,0.0000033218466,0.0005091321,0.0000013504641,0.000081080376,0.000021565433,0.00084632536],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9956944,0.001805859,0.0003805246,0.0006498072,0.00104932,0.0004200795],"domain_scores_gemma":[0.997701,0.00023877282,0.00042325992,0.0008073036,0.00047892763,0.00035077517],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0025881545,0.00033837243,0.0004112365,0.0006583564,0.0008829439,0.00023256108,0.0010454769,0.00045943956,0.000006528925],"category_scores_gemma":[0.0003519746,0.00027348916,0.00008342415,0.0005724107,0.0012062221,0.00015103948,0.0010384083,0.0012287846,2.6857768e-7],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03491297,0.0038453054,0.5512829,0.018842796,0.008914419,0.00692461,0.06047086,0.005636987,0.012020436,0.2865565,0.0027689203,0.007823298],"study_design_scores_gemma":[0.02127659,0.016339444,0.05256903,0.0009842525,0.0047438936,0.0002689797,0.76565415,0.0051375995,0.0030254377,0.0058430955,0.1193348,0.0048227357],"about_ca_topic_score_codex":0.013878784,"about_ca_topic_score_gemma":0.02664588,"teacher_disagreement_score":0.70518327,"about_ca_system_score_codex":0.00018758501,"about_ca_system_score_gemma":0.00077454024,"threshold_uncertainty_score":0.99997175},"labels":[],"label_agreement":null},{"id":"W7026743879","doi":"","title":"Are drugs too expensive in Canada?","year":2006,"lang":"en","type":"article","venue":"PubMed Central","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Drug; MEDLINE; Drug industry; Drug labeling","score_opus":0.004065951281630868,"score_gpt":0.18499770502968294,"score_spread":0.18093175374805207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7026743879","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99291515,0.00013397667,0.00005528414,0.00033816282,0.00027870748,0.00015048064,0.000014336116,0.000006640387,0.006107245],"genre_scores_gemma":[0.9978331,0.000008268911,0.00023428729,0.0008364642,0.0002543002,0.000027836742,0.000094879564,0.000010662775,0.0007002172],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988003,0.000025726547,0.00017694355,0.00013688764,0.00012686891,0.00073327275],"domain_scores_gemma":[0.99959624,0.000006570222,0.00010100417,0.00016926702,0.000019526882,0.000107397165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000087216096,0.00010178685,0.00009516993,0.000020406262,0.000025000492,0.000014498383,0.00012719657,0.000054719545,0.000013166959],"category_scores_gemma":[0.00009749187,0.00010157558,0.000028920918,0.00005286043,0.000019906092,0.0000026317725,0.000050115486,0.000098821096,0.0000026988853],"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":[0.000033189786,0.000028665718,0.9436704,0.000022043256,0.000013144,0.000022648834,0.00008259581,0.0029009795,0.0007043039,0.0001396128,0.04909619,0.0032862548],"study_design_scores_gemma":[0.00036672113,0.0000061607734,0.9129893,0.000003858324,0.0000028967925,0.000006946263,0.00023184647,0.0002964922,0.0070331017,0.000017077515,0.07889371,0.00015185805],"about_ca_topic_score_codex":0.2684559,"about_ca_topic_score_gemma":0.72456646,"teacher_disagreement_score":0.45611054,"about_ca_system_score_codex":0.00020893019,"about_ca_system_score_gemma":0.00029619766,"threshold_uncertainty_score":0.7364155},"labels":[],"label_agreement":null},{"id":"W7027385677","doi":"","title":"Comparing social norms for adolescent smoking and vaping behaviours using game theory based experiments and self-reports: insights from the MECHANISMS Study","year":2021,"lang":"en","type":"article","venue":"Research Portal (Queen's University Belfast)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Social norms approach; Construct (python library); Confirmatory factor analysis; Construct validity; Youth smoking; Social desirability; Structural equation modeling; Relevance (law); Social influence; Theory of planned behavior","score_opus":0.030969624711060934,"score_gpt":0.30892279003127276,"score_spread":0.27795316532021186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7027385677","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99305105,0.00006074449,0.0060343957,0.00009665813,0.000054492433,0.0005008596,0.000018428802,0.000020695408,0.00016266014],"genre_scores_gemma":[0.99788916,0.000017185233,0.00172677,0.000057968988,0.000070486196,0.0000027492604,0.00013306469,0.000020256406,0.00008233066],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998336,0.00035631756,0.00018893908,0.00039622132,0.00039293602,0.000329594],"domain_scores_gemma":[0.9991801,0.000081585706,0.00012464788,0.00027678267,0.00022189658,0.000114997405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060097035,0.00016368102,0.00018905992,0.000077087054,0.00081917475,0.00010478081,0.00017605169,0.00012402645,0.000009682861],"category_scores_gemma":[0.00009788234,0.0001504921,0.000064415806,0.0001345082,0.00013676003,0.000022699853,0.00062110904,0.00032814188,1.8929494e-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":[0.0015209299,0.0037924882,0.84243804,0.0004597639,0.0026430213,0.0021198269,0.027660666,0.0011191318,0.10376628,0.011415647,0.00093015237,0.0021340635],"study_design_scores_gemma":[0.018108994,0.0027533702,0.5519001,0.000743594,0.0014040933,0.00014881381,0.24495295,0.028243793,0.13704862,0.0018644148,0.009808614,0.003022679],"about_ca_topic_score_codex":0.00030841347,"about_ca_topic_score_gemma":0.000060051203,"teacher_disagreement_score":0.29053795,"about_ca_system_score_codex":0.00006306323,"about_ca_system_score_gemma":0.00019123331,"threshold_uncertainty_score":0.63005126},"labels":[],"label_agreement":null},{"id":"W7027921559","doi":"","title":"Detecting operons from RNA-seq data&#13;\\nusing a convolutional and recurrent neural&#13;\\nnetwork architecture","year":2023,"lang":"en","type":"dissertation","venue":"Memorial University Research Repository (Memorial University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Memorial University of Newfoundland","keywords":"Operon; Genome; Representation (politics); Gene; Function (biology); Convolutional neural network; Bacterial genome size; Model organism","score_opus":0.029421304934025956,"score_gpt":0.283524040901655,"score_spread":0.25410273596762906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7027921559","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97148645,0.0002614425,0.00028801116,0.00009789116,0.01289192,0.0008693525,0.0005917536,0.00016273644,0.013350459],"genre_scores_gemma":[0.77615476,0.0020092549,0.002942192,0.000043676562,0.041532293,0.0000035993878,0.04085694,0.0004191466,0.13603815],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99501175,0.0012192392,0.00040076245,0.0014410798,0.0010553026,0.0008718942],"domain_scores_gemma":[0.996845,0.0004147344,0.00041620684,0.0012750084,0.000605053,0.0004440137],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00092728453,0.0005556765,0.00057087396,0.0007958913,0.00202872,0.0002680356,0.0020727494,0.0010202233,0.000030613402],"category_scores_gemma":[0.0008011651,0.000683277,0.00021964623,0.0009736547,0.00044367177,0.000083455416,0.002161506,0.0021461034,0.000026229309],"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":[0.09742215,0.0016864996,0.013617211,0.0043408843,0.011097798,0.011576495,0.018874515,0.025447957,0.46869102,0.0015982621,0.22955535,0.11609183],"study_design_scores_gemma":[0.014434961,0.0028312744,0.008070864,0.0016910299,0.0017472862,0.00016614677,0.029424142,0.025081763,0.013783049,0.00027750005,0.8976865,0.0048054974],"about_ca_topic_score_codex":0.0054288604,"about_ca_topic_score_gemma":0.007593233,"teacher_disagreement_score":0.6681311,"about_ca_system_score_codex":0.00038815752,"about_ca_system_score_gemma":0.0011388584,"threshold_uncertainty_score":0.99956185},"labels":[],"label_agreement":null},{"id":"W7028370050","doi":"","title":"ESONET - European Seas Observatory NETwork. Network of Excellence (NoE). Periodic activity report : version #1 30 June 2009","year":2009,"lang":"en","type":"article","venue":"Institutional Archive of Ifremer (French Research Institute for Exploitation of the Sea)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Observatory; Excellence; Core (optical fiber); Subject (documents); Working group; Node (physics)","score_opus":0.04068113035033861,"score_gpt":0.3170984369902956,"score_spread":0.276417306639957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7028370050","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9123917,0.00080694875,0.061860677,0.0018318407,0.0013114618,0.0015953454,0.00058896304,0.000030288798,0.019582735],"genre_scores_gemma":[0.97960305,0.00015500005,0.018539056,0.00008947531,0.00037398955,0.000022104448,0.00066005596,0.000015546513,0.0005417442],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971166,0.00043500232,0.00067785167,0.00034911948,0.0009745524,0.00044687244],"domain_scores_gemma":[0.9975401,0.00012958849,0.00057175895,0.0006872324,0.0009439519,0.00012738106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023726523,0.00021023865,0.00028988082,0.00010065251,0.0005028899,0.000017145387,0.00077918626,0.00009730117,0.000021964155],"category_scores_gemma":[0.001797156,0.000179141,0.00027376815,0.0003944157,0.001313031,0.00006286775,0.00033244793,0.00036445897,0.00000622344],"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":[0.0014836602,0.00096754695,0.013492371,0.0008677808,0.00045073952,0.000025333666,0.0008827722,0.47240496,0.25142473,0.018759819,0.22489423,0.014346074],"study_design_scores_gemma":[0.003875876,0.003226615,0.27546817,0.0016218341,0.00012911375,0.00012251665,0.00017927076,0.025153758,0.063909404,0.012079731,0.6132884,0.0009452655],"about_ca_topic_score_codex":0.00016640805,"about_ca_topic_score_gemma":0.000082653496,"teacher_disagreement_score":0.4472512,"about_ca_system_score_codex":0.000054881428,"about_ca_system_score_gemma":0.00081915554,"threshold_uncertainty_score":0.73051584},"labels":[],"label_agreement":null},{"id":"W7028560940","doi":"","title":"Feasibility of Testing Client Preferences for Accessing Injectable Opioid Agonist Treatment (iOAT): A Pilot Study","year":2022,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Population; Respondent; Addiction; Health care; Test (biology); Conceptualization; Interview; Medical prescription; Outcome (game theory)","score_opus":0.35164006689265714,"score_gpt":0.5482598674812194,"score_spread":0.1966198005885622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7028560940","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9928596,0.0022603213,0.000434095,0.000018125585,0.00028909356,0.0016912704,0.00015865528,0.00001515582,0.0022736818],"genre_scores_gemma":[0.9968597,0.00024211341,0.0021006842,0.00006029414,0.000096314114,0.0002839535,0.00008642603,0.000036844092,0.00023364517],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971999,0.00039487123,0.0010549272,0.00047086834,0.00051612186,0.0003632922],"domain_scores_gemma":[0.9973018,0.00023434617,0.0013767962,0.000627859,0.0003274291,0.00013175038],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017208505,0.00031295954,0.00063685275,0.00025165998,0.00064949284,0.0005007548,0.0019559634,0.0000470545,0.00073446415],"category_scores_gemma":[0.00077827816,0.00027600303,0.00014510716,0.0005130394,0.00011044454,0.00008824109,0.0017902267,0.00024308282,6.644997e-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":[0.000762444,0.0019892487,0.8404241,0.00014510196,0.0002093739,0.0000020638897,0.00033597206,0.0026637835,0.14330521,0.0000047700555,0.0011958213,0.008962066],"study_design_scores_gemma":[0.0037113484,0.0051426236,0.891722,0.00017261918,0.00032605143,0.000028041135,0.0017878255,0.0016473656,0.08820896,0.0011249997,0.005260515,0.00086764543],"about_ca_topic_score_codex":0.0011451452,"about_ca_topic_score_gemma":0.00011610664,"teacher_disagreement_score":0.05509625,"about_ca_system_score_codex":0.00014227378,"about_ca_system_score_gemma":0.00041759302,"threshold_uncertainty_score":0.99996924},"labels":[],"label_agreement":null},{"id":"W7031201313","doi":"","title":"Art by the Yard","year":2015,"lang":"en","type":"other","venue":"Original","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Exhibition; Yard; Textile; Clothing; Feature (linguistics)","score_opus":0.005865756088933193,"score_gpt":0.25895840489378663,"score_spread":0.25309264880485344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7031201313","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":[0.000040872044,0.0009649114,0.00032415547,0.00019441506,0.0003026743,0.00010290379,0.000088695124,0.000031801796,0.9979496],"genre_scores_gemma":[0.00004397919,0.00007068403,0.00089708064,0.0004089912,0.00076929113,0.000007915752,0.0010272715,0.0001372004,0.9966376],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99943644,0.000028829969,0.000091074064,0.00013630603,0.00015457833,0.00015279601],"domain_scores_gemma":[0.9994356,0.000002728988,0.00010190622,0.00038819265,0.00002008705,0.00005147388],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00012400172,0.00015546281,0.0001034291,0.000019691664,0.00002532261,0.000022701226,0.00027224695,0.00021042186,0.0009161009],"category_scores_gemma":[0.000031443808,0.00010373178,0.000040563507,0.000034406643,0.00007036354,4.869088e-7,0.0000643119,0.00017347056,0.0012696336],"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":[0.000005692408,0.0000066630964,0.00006837149,0.000014130209,0.000033620705,6.199001e-7,0.0000061247492,0.0000015315841,0.00022368383,0.000051545197,0.9990696,0.00051844935],"study_design_scores_gemma":[0.00013095878,0.00006688089,0.0000018205687,0.00001269763,0.000014734767,0.000021064665,0.0000051173224,0.000013335425,0.00017071387,0.0000074292752,0.9994144,0.00014085897],"about_ca_topic_score_codex":0.000018784043,"about_ca_topic_score_gemma":0.000021421625,"teacher_disagreement_score":0.0013119847,"about_ca_system_score_codex":0.000008359771,"about_ca_system_score_gemma":0.00008433898,"threshold_uncertainty_score":0.9999972},"labels":[],"label_agreement":null},{"id":"W7032666996","doi":"","title":"Observation of Diffractive <i>J</i>/ψ Production at the Fermilab Tevatron","year":2001,"lang":"en","type":"article","venue":"Lincoln (University of Nebraska)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Istituto Nazionale di Fisica Nucleare; Korea Science and Engineering Foundation; National Science Council; Alfred P. Sloan Foundation; Fermilab; U.S. Department of Energy; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Tevatron; Pseudorapidity; Rapidity; Muon; Gluon; Fermilab; Production (economics)","score_opus":0.009537195231260572,"score_gpt":0.2114409235000774,"score_spread":0.20190372826881683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7032666996","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9945653,0.00007004189,0.0011150936,0.0011559838,0.000087215194,0.00017293422,0.000008625899,0.000008240967,0.0028165379],"genre_scores_gemma":[0.98601985,0.00015968981,0.0016479654,0.0000661824,0.000076283846,3.3776627e-7,0.00009612361,0.0000069101784,0.0119266445],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9994704,0.00004789962,0.00010402165,0.00013779431,0.00014283574,0.00009702198],"domain_scores_gemma":[0.99931794,0.00001723008,0.00023508817,0.00028411386,0.00012172056,0.000023928735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014558632,0.000074761,0.00009934616,0.000033792985,0.00013302115,0.000002858469,0.00018645186,0.00008766435,0.000058919002],"category_scores_gemma":[0.00008404198,0.00007138902,0.000068196314,0.000148349,0.00013157871,0.000012356922,0.00015414938,0.000080953265,0.000009635224],"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":[0.0012062652,0.0002833627,0.20443566,0.0001541664,0.00021173545,0.000003811295,0.002025422,0.004744586,0.7430648,0.0003100965,0.015699891,0.02786021],"study_design_scores_gemma":[0.0012310384,0.00062079664,0.6729877,0.000047638445,0.00010610793,0.000033865108,0.0026532714,0.0025211156,0.05868107,0.00011875136,0.26068527,0.0003134053],"about_ca_topic_score_codex":0.00010409398,"about_ca_topic_score_gemma":0.0002482328,"teacher_disagreement_score":0.68438375,"about_ca_system_score_codex":0.000026263386,"about_ca_system_score_gemma":0.00003750211,"threshold_uncertainty_score":0.29111597},"labels":[],"label_agreement":null},{"id":"W7033813243","doi":"","title":"Rising Together Webinar 5 Anti Oppression and the Green Economy","year":2020,"lang":"en","type":"other","venue":"York University Digital Library (York University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Oppression; Green economy; Indigenous; Human rights; Poverty; Civil rights","score_opus":0.004821944003526116,"score_gpt":0.1562847947855059,"score_spread":0.15146285078197977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7033813243","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":[0.0013044631,0.00037917233,0.00039643855,0.00077130564,0.000080666876,0.0003163994,0.00038604048,0.00018856741,0.99617696],"genre_scores_gemma":[0.015165442,0.00045654483,0.0008976839,0.00042422605,0.00028351942,8.160799e-8,0.0009334468,0.00019613311,0.9816429],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99900013,0.00008939659,0.00011683787,0.00043886778,0.00010577011,0.00024899814],"domain_scores_gemma":[0.9990851,0.000035981462,0.0002625502,0.00042724633,0.000009658791,0.00017945473],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00002789711,0.0003414206,0.00032599026,0.00021966649,0.00020872185,0.00017521658,0.0008114502,0.0004020223,0.00026387564],"category_scores_gemma":[0.000012881295,0.00032068082,0.00018423863,0.00027284774,0.00047174597,0.00007983152,0.0011858399,0.00032498135,0.000067909394],"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":[0.00070960633,0.000053816788,0.00545853,0.00021727731,0.0005192986,0.00013442083,0.00025699256,0.00003399879,0.000043452583,0.0074689337,0.9828042,0.0022994673],"study_design_scores_gemma":[0.0013727163,0.00007568746,0.000047273024,0.00009369115,0.00007573076,0.0000109783505,0.00083241705,0.000108022876,0.000044596385,0.00003309214,0.9969178,0.00038799224],"about_ca_topic_score_codex":0.00005310976,"about_ca_topic_score_gemma":0.0000072876874,"teacher_disagreement_score":0.014534024,"about_ca_system_score_codex":0.000017341123,"about_ca_system_score_gemma":0.00011076255,"threshold_uncertainty_score":0.99992454},"labels":[],"label_agreement":null},{"id":"W7034055149","doi":"","title":"St. John's (Asheboro)","year":2025,"lang":"en","type":"article","venue":"WakeSpace Scholarship (Wake Forest University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Ephemeral key; Period (music); Context (archaeology); Term (time); Data collection","score_opus":0.005175944214538451,"score_gpt":0.22592891253676595,"score_spread":0.2207529683222275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7034055149","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8497829,0.00019814586,0.0068770265,0.0011536563,0.00038417912,0.00030817956,0.000038227496,0.00012008668,0.14113763],"genre_scores_gemma":[0.9324834,0.00009723773,0.0028569542,0.0005766403,0.00009282415,0.0000013531578,0.000179408,0.000025726555,0.0636865],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987979,0.000097973854,0.00016306475,0.00036613774,0.00018481768,0.0003900931],"domain_scores_gemma":[0.9989214,0.00002892593,0.00010716541,0.0006510841,0.00015263121,0.00013877766],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029754685,0.00023734404,0.00017744287,0.00031591498,0.0002781853,0.00007377791,0.0006419017,0.0002968867,0.000061514016],"category_scores_gemma":[0.0003454078,0.00026559533,0.00014740504,0.00055750686,0.00013557557,0.000028834702,0.00034811822,0.00042903307,0.00007223986],"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":[0.0006071836,0.00023414263,0.80374587,0.00025325918,0.00045779697,0.000103506194,0.00021184831,0.0029646258,0.02414146,0.1280391,0.035232864,0.004008332],"study_design_scores_gemma":[0.0010384677,0.00014497055,0.04750448,0.000055784356,0.00005774924,0.0000080173,0.00020774608,0.00018479451,0.0036400044,0.00039075795,0.94642365,0.00034360035],"about_ca_topic_score_codex":0.000017379842,"about_ca_topic_score_gemma":0.00047232665,"teacher_disagreement_score":0.91119075,"about_ca_system_score_codex":0.000068241025,"about_ca_system_score_gemma":0.00019985513,"threshold_uncertainty_score":0.9999796},"labels":[],"label_agreement":null},{"id":"W7040668501","doi":"","title":"","year":2021,"lang":"","type":"other","venue":"Directory of Open access Books (OAPEN Foundation)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"World War II; First world war; George (robot); Period (music); Biography","score_opus":0.05648086449512517,"score_gpt":0.41654931837282627,"score_spread":0.3600684538777011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7040668501","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":[0.042474862,0.0022047241,0.0040296772,0.0005258191,0.0030405258,0.0062455866,0.000035128953,0.000068968744,0.9413747],"genre_scores_gemma":[0.20557232,0.006296685,0.016437702,0.0028057485,0.0018396867,0.0009885707,0.022163969,0.0017566595,0.7421386],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9875504,0.0017297219,0.0043230234,0.00314072,0.0016839086,0.0015722754],"domain_scores_gemma":[0.9846439,0.0003151889,0.007537907,0.0049694693,0.0017830867,0.00075048447],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaepi_narrow","open_science"],"category_scores_codex":[0.0025117237,0.0024444857,0.0034130758,0.0009046808,0.0010092476,0.008755337,0.017695377,0.0012207959,0.07755852],"category_scores_gemma":[0.0023245576,0.0027898115,0.001097943,0.0009778072,0.0015306562,0.00046143343,0.022239415,0.0014375444,0.00037500454],"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":[0.003316406,0.0034955882,0.16494487,0.010665117,0.012714044,0.00012156297,0.0012301856,0.0023491501,0.1353243,0.017657137,0.016105728,0.6320759],"study_design_scores_gemma":[0.003872267,0.00048678796,0.03014821,0.0021451784,0.0004614552,0.00006235429,0.00023467082,0.00057237403,0.040865473,0.00016390247,0.9180208,0.0029665127],"about_ca_topic_score_codex":0.0026332662,"about_ca_topic_score_gemma":0.0031808785,"teacher_disagreement_score":0.9019151,"about_ca_system_score_codex":0.00029859677,"about_ca_system_score_gemma":0.004158405,"threshold_uncertainty_score":0.9988292},"labels":[],"label_agreement":null},{"id":"W7044130981","doi":"","title":"USING MACHINE LEARNING TECHNIQUES FOR FINDING MEANINGFUL TRANSCRIPTS IN PROSTATE CANCER PROGRESSION","year":2015,"lang":"en","type":"dissertation","venue":"Scholarship at UWindsor (University of Windsor)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Prostate cancer; Feature selection; Support vector machine; Cancer; Feature (linguistics); Training set","score_opus":0.031428279729413706,"score_gpt":0.3246979044188795,"score_spread":0.2932696246894658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7044130981","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99618834,0.001301571,0.00013735415,0.00005168816,0.00021673716,0.0009719454,0.00014444707,0.000050237864,0.0009376517],"genre_scores_gemma":[0.95903873,0.0004149903,0.024785124,0.00003378914,0.00014851257,0.000013760548,0.0055370443,0.00014916284,0.009878855],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980504,0.00018063262,0.0003696186,0.0005286746,0.0004195435,0.0004511395],"domain_scores_gemma":[0.99846023,0.000022473356,0.00070631615,0.0003076423,0.00036771005,0.00013563047],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009677452,0.0004027275,0.0004983884,0.000403851,0.00035549997,0.000036900616,0.00050846324,0.00069954316,0.000041121413],"category_scores_gemma":[0.00024502128,0.0004871486,0.0002314429,0.00027063958,0.000080303456,0.000052880387,0.00013172385,0.00083315576,0.0000026396287],"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":[0.0049139448,0.00018748059,0.2578328,0.0024269095,0.00029848586,0.000025844272,0.010696878,0.0010021393,0.70745975,0.000027003243,0.00023391694,0.014894836],"study_design_scores_gemma":[0.014656465,0.0042336415,0.070311196,0.00976267,0.0014443651,0.00008946055,0.016907422,0.014505633,0.7155649,0.0006699001,0.14611197,0.0057423986],"about_ca_topic_score_codex":0.0002309413,"about_ca_topic_score_gemma":0.0026348175,"teacher_disagreement_score":0.18752159,"about_ca_system_score_codex":0.00019872769,"about_ca_system_score_gemma":0.0003492768,"threshold_uncertainty_score":0.999758},"labels":[],"label_agreement":null},{"id":"W7044320520","doi":"","title":"YORK:CC - York Harbour To Commence Trading on the Canadian...","year":2024,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Harbour; Government (linguistics); Legislation; Marine safety","score_opus":0.018110804624621772,"score_gpt":0.25905883799090723,"score_spread":0.24094803336628545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7044320520","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":[0.000056054894,0.00038708973,0.00017785319,0.0039655925,0.00048941094,0.00031316717,0.00006724607,0.000058260513,0.9944853],"genre_scores_gemma":[0.025377339,0.000019918634,0.0013986316,0.01312272,0.0005794373,0.000033263834,0.00009569192,0.00030884068,0.9590642],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99906796,0.000038043032,0.0001532425,0.00026879384,0.00015445091,0.00031752634],"domain_scores_gemma":[0.99914604,0.00001443072,0.000058471807,0.00058819813,0.000009925067,0.00018292565],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002030288,0.000255442,0.00014640992,0.00012879918,0.00008170676,0.000120177305,0.00048554948,0.0003305717,0.0015608723],"category_scores_gemma":[0.00008170272,0.00017345505,0.0000801918,0.00011049562,0.000042287804,3.6551745e-7,0.00008373488,0.00035484065,0.0018620993],"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":[0.000002377112,0.000009488616,0.0000132421055,0.000038684582,0.00005712254,0.0000021121195,0.00006836466,0.000004477782,0.00007580196,0.003194999,0.9961447,0.00038862714],"study_design_scores_gemma":[0.00008481483,0.00008589513,0.000005015227,0.0001392566,0.000015090437,0.0000053116164,0.000048898477,0.00019696231,0.0002965653,0.000030325175,0.99885064,0.00024119591],"about_ca_topic_score_codex":0.031320613,"about_ca_topic_score_gemma":0.1512596,"teacher_disagreement_score":0.11993899,"about_ca_system_score_codex":0.00004586735,"about_ca_system_score_gemma":0.0001469449,"threshold_uncertainty_score":0.99935186},"labels":[],"label_agreement":null},{"id":"W7065504113","doi":"","title":"The Effect of Introducing Mandatory Clauses on Procurement Documents: An Evaluation of the Perception of Procurement Professionals in Alberta, Canada","year":2024,"lang":"en","type":"article","venue":"Umsida Repository (Universitas Muhammadiyah Sidoarjo)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Procurement; Thematic analysis; Nonprobability sampling; Focus group; Flexibility (engineering); Population; Request for proposal; Reliability (semiconductor); Data collection","score_opus":0.004065312837216299,"score_gpt":0.25055680285053356,"score_spread":0.24649149001331724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7065504113","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9965482,0.00038601313,0.000013678573,0.0002065036,0.00047280116,0.00086994085,0.0000060717744,0.000004515262,0.0014922714],"genre_scores_gemma":[0.99939287,0.000010937648,0.000050297564,0.000019183748,0.00006986526,0.000022224785,0.000027663125,0.00001276964,0.00039418333],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978997,0.0005539152,0.00037589457,0.00025065578,0.00075850927,0.00016130233],"domain_scores_gemma":[0.9988641,0.00009788272,0.00030031518,0.00049663056,0.00020443022,0.00003660302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00121959,0.0001563619,0.00016551952,0.000078620644,0.00014860251,0.000015720856,0.00031075004,0.00009029228,0.000027153174],"category_scores_gemma":[0.00020573672,0.000101724756,0.00007990638,0.0001653497,0.00009782107,0.000028653096,0.00012327151,0.00017114848,5.479099e-7],"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":[0.001727226,0.0003874172,0.12045674,0.0032626945,0.00087815436,0.000008057626,0.0072269663,0.023634195,0.8035672,0.0008398709,0.02351011,0.014501421],"study_design_scores_gemma":[0.0020853656,0.0031449324,0.08604264,0.002380623,0.0006457463,0.00002000345,0.009649363,0.011501347,0.8801619,0.0000369673,0.0038550836,0.00047604184],"about_ca_topic_score_codex":0.01935744,"about_ca_topic_score_gemma":0.02034754,"teacher_disagreement_score":0.07659473,"about_ca_system_score_codex":0.00030543,"about_ca_system_score_gemma":0.0006757114,"threshold_uncertainty_score":0.99752855},"labels":[],"label_agreement":null},{"id":"W7066059085","doi":"","title":"ENVIRONMENTAL JUSTICE IN CANADA: THE STATISTICAL CORRELATION BETWEEN SOCIOECONOMIC STATUS AND POLLUTION IN FIVE MAJOR CANADIAN CITIES","year":2008,"lang":"en","type":"article","venue":"Scholarship@Western (Western University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Census; Environmental justice; Injustice; Metropolitan area; Socioeconomic status; Population; Pollution","score_opus":0.02155582049324311,"score_gpt":0.2438127858261866,"score_spread":0.22225696533294348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7066059085","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99913657,0.000065167806,0.000114126306,0.00017410012,0.000066377455,0.00015428312,0.00020394036,0.0000038028857,0.000081637954],"genre_scores_gemma":[0.9989097,0.00009805572,0.000029054558,0.00030290513,0.000034799687,7.011566e-7,0.00020227402,0.000011461068,0.0004110641],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99904335,0.0001475351,0.00017815751,0.00020222424,0.00010316876,0.00032555213],"domain_scores_gemma":[0.9995591,0.000041929863,0.000079555684,0.00015572956,0.000009039524,0.00015462907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013257828,0.00013666619,0.00012783379,0.00013781367,0.00017965179,0.000025176232,0.00014617834,0.00011510465,0.00001240125],"category_scores_gemma":[0.00003206728,0.00014602258,0.000017000988,0.000054667864,0.0001347966,0.000042182466,0.00010589379,0.0003307165,0.00001159593],"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":[0.0000244209,0.0000045586007,0.9988962,0.00001091607,0.000012866012,0.000038343424,0.00037650837,0.00043832135,0.00004119849,0.000018795516,0.0000030499118,0.00013483132],"study_design_scores_gemma":[0.000664721,0.000043416992,0.99698067,0.000010916379,0.000023731514,0.000019874704,0.0011055764,0.000018456343,0.000056000627,0.000010123731,0.0009067956,0.00015973224],"about_ca_topic_score_codex":0.2640801,"about_ca_topic_score_gemma":0.98668754,"teacher_disagreement_score":0.7226075,"about_ca_system_score_codex":0.00080817245,"about_ca_system_score_gemma":0.00071675004,"threshold_uncertainty_score":0.74082047},"labels":[],"label_agreement":null},{"id":"W7066065766","doi":"","title":"A Framework for Regulatory Excellence","year":2015,"lang":"en","type":"article","venue":"eYLS (Yale Law School)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Excellence; Regulator; Regulatory reform; Regulatory state; Master regulator","score_opus":0.017770219439803222,"score_gpt":0.2807085241965123,"score_spread":0.2629383047567091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7066065766","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7542324,0.0029633765,0.1874259,0.0016206783,0.0019276349,0.0012303338,0.00007302056,0.00022572794,0.05030092],"genre_scores_gemma":[0.8506531,0.000027017391,0.14131637,0.0024164354,0.0009185554,0.00007431059,0.000112930495,0.000047120357,0.004434131],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990216,0.000040563464,0.00022822763,0.0002443829,0.00018048254,0.00028476375],"domain_scores_gemma":[0.9988991,0.000030672767,0.000106902364,0.00059077813,0.00012397209,0.0002485999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000386769,0.0001559884,0.0001384579,0.00001975321,0.00009561305,0.000047379843,0.00030709358,0.0002358069,0.000039773528],"category_scores_gemma":[0.0007738817,0.00015105258,0.00008868788,0.000059244296,0.00009386751,0.000007640137,0.00012804772,0.00018910877,0.00013181915],"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":[0.0010517882,0.00037203764,0.022513328,0.0005831003,0.0003477967,0.000013182353,0.0010318274,0.0036376584,0.05820448,0.553723,0.34996083,0.008561006],"study_design_scores_gemma":[0.00085360074,0.00045741498,0.00055243075,0.000051942658,0.000020432031,0.000019079636,0.00014043336,0.0007789825,0.018087491,0.012787407,0.9658474,0.0004034323],"about_ca_topic_score_codex":0.000030807572,"about_ca_topic_score_gemma":0.000026212214,"teacher_disagreement_score":0.6158865,"about_ca_system_score_codex":0.000022574806,"about_ca_system_score_gemma":0.000107094005,"threshold_uncertainty_score":0.61597455},"labels":[],"label_agreement":null},{"id":"W7066175196","doi":"","title":"[Funeral Program for Earnest Sercy Henson, February 21, 2013]","year":2013,"lang":"en","type":"other","venue":"The Portal to Texas History (University of North Texas)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"George (robot); Government (linguistics); Year-ending; Quarter (Canadian coin)","score_opus":0.009959053728773927,"score_gpt":0.21305244677447313,"score_spread":0.2030933930456992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7066175196","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":[0.1455527,0.003160792,0.0030616813,0.0014390434,0.0021380822,0.0075683948,0.0007029191,0.00060063804,0.83577573],"genre_scores_gemma":[0.006574796,0.00017394127,0.008261709,0.00033165893,0.00034105085,0.0000061237038,0.0010434685,0.00023489477,0.98303235],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987081,0.00006098514,0.00022109953,0.00040232152,0.00023784692,0.00036961286],"domain_scores_gemma":[0.99837446,0.000014550652,0.00049828226,0.00082886626,0.00010538226,0.00017844533],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00014791032,0.00036315498,0.00039482082,0.00016959259,0.00011200741,0.0000098452265,0.0009065098,0.0003392327,0.0016278652],"category_scores_gemma":[0.000031722546,0.0003568033,0.00028456372,0.00009481438,0.00032008367,0.000008770753,0.00030604657,0.0002710426,0.00045041213],"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":[0.00006118988,0.000095041396,0.01027325,0.00018440072,0.00017220824,0.0000057466004,0.000091565904,0.000054514763,0.000014562004,0.00008492918,0.9855432,0.0034193743],"study_design_scores_gemma":[0.00039494512,0.00045160606,0.048039157,0.000041633582,0.00010963807,0.000010109024,0.000024038854,0.00010279225,0.000004837767,0.0000037313503,0.95041066,0.0004068285],"about_ca_topic_score_codex":0.002854515,"about_ca_topic_score_gemma":0.006073906,"teacher_disagreement_score":0.1472566,"about_ca_system_score_codex":0.00006925784,"about_ca_system_score_gemma":0.000181087,"threshold_uncertainty_score":0.9998884},"labels":[],"label_agreement":null},{"id":"W7066798191","doi":"","title":"The Legal Basis for the Application of the Uniform Customs and Practice for Documentary Credits (the UCP) in England &amp; Canada","year":2008,"lang":"en","type":"article","venue":"Research Output (Edinburgh Napier University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"English law; Common law; Legal culture; New england","score_opus":0.02352817097603541,"score_gpt":0.29263012474858463,"score_spread":0.2691019537725492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7066798191","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8872082,0.0017763245,0.022427464,0.06577266,0.0006168905,0.0074499506,0.00029294382,0.000019597628,0.014435947],"genre_scores_gemma":[0.9843059,0.001072826,0.000523579,0.00019984924,0.0002109622,0.000032221622,0.00004102131,0.000012251506,0.013601391],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99889696,0.00015435007,0.0001464011,0.00016017961,0.00035131563,0.00029079473],"domain_scores_gemma":[0.99724454,0.0018188538,0.0001122608,0.0004410213,0.00033376782,0.000049535687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015524871,0.00009200182,0.00008317104,0.000056093948,0.00094723725,0.000028456965,0.00064054044,0.000072577204,0.0000027145365],"category_scores_gemma":[0.0016236568,0.00004949341,0.000053884403,0.00032327574,0.00039815265,0.000021342563,0.00030733415,0.00027258502,2.1712636e-7],"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":[0.014443356,0.0007053246,0.05444477,0.0005951749,0.0026402276,0.000028766264,0.017012784,0.01083022,0.01940222,0.026632536,0.692253,0.16101162],"study_design_scores_gemma":[0.00062305987,0.000086538486,0.00087810203,0.000006351372,0.000022876062,0.000015068234,0.0013492032,0.001910125,0.00074006076,0.000024496781,0.99428046,0.00006364117],"about_ca_topic_score_codex":0.028850107,"about_ca_topic_score_gemma":0.1044907,"teacher_disagreement_score":0.30202746,"about_ca_system_score_codex":0.000110727924,"about_ca_system_score_gemma":0.00058161427,"threshold_uncertainty_score":0.97761685},"labels":[],"label_agreement":null},{"id":"W7066899386","doi":"","title":"Imagined transmigrations","year":2019,"lang":"en","type":"article","venue":"Oxford University Research Archive (ORA) (University of Oxford)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Polity; Population; Quarter (Canadian coin); Population growth; Kingdom","score_opus":0.012178941171008033,"score_gpt":0.2489766424284284,"score_spread":0.23679770125742036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7066899386","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.806617,0.00003676888,0.03574058,0.0010468697,0.0000708926,0.0006068731,0.00025087554,0.00004581347,0.1555843],"genre_scores_gemma":[0.95338434,0.0008653982,0.021002151,0.000045406265,0.000043597476,1.6290439e-7,0.00058340305,0.000025515657,0.024050033],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982353,0.0002718552,0.00012747588,0.00039260587,0.00045914899,0.0005136576],"domain_scores_gemma":[0.9986359,0.00009040634,0.00011399345,0.0006300006,0.00030850683,0.0002211823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004690834,0.00017590386,0.00023331317,0.0004466948,0.00044120714,0.000021372412,0.0010523931,0.00013694007,0.00040754862],"category_scores_gemma":[0.00006663748,0.00022467264,0.00021512092,0.0004888486,0.0005571714,0.000052130443,0.0006171744,0.00048796477,0.000048500617],"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":[0.0077896197,0.0014520606,0.36508498,0.001328793,0.00158687,0.00025374664,0.013151845,0.0050318446,0.41779056,0.06670904,0.08923575,0.030584889],"study_design_scores_gemma":[0.0021454885,0.0009617484,0.020519795,0.000046049227,0.0000360269,0.000013695182,0.0072904318,0.007497967,0.000936084,0.00040324038,0.95978665,0.00036281464],"about_ca_topic_score_codex":0.0003080686,"about_ca_topic_score_gemma":0.000710662,"teacher_disagreement_score":0.87055093,"about_ca_system_score_codex":0.000058960926,"about_ca_system_score_gemma":0.00030365164,"threshold_uncertainty_score":0.9161884},"labels":[],"label_agreement":null},{"id":"W7067054700","doi":"","title":"La consapevolezza dell’importanza del contesto sociale, culturale e politico del pensiero, dell’insegnamento e dell’apprendimento: Alcuni elementi del mio percorso","year":2017,"lang":"it","type":"article","venue":"View","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Politics; Initial training","score_opus":0.018212034732126545,"score_gpt":0.29991952409305733,"score_spread":0.28170748936093076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067054700","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8609263,0.06776269,0.0049893185,0.0030904983,0.0020992872,0.0035466847,0.0011608566,0.0002464134,0.056178007],"genre_scores_gemma":[0.9474637,0.024428189,0.0065456145,0.0033473528,0.0007574304,0.00013452492,0.001570497,0.00024158257,0.015511094],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9934397,0.0005600725,0.0019055548,0.0013085695,0.00086285494,0.0019232641],"domain_scores_gemma":[0.99379337,0.00013470567,0.0018810333,0.0026391905,0.00070570497,0.0008460061],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0013133776,0.0013401678,0.0012837915,0.00015098575,0.0017863943,0.00095554773,0.0020343293,0.001097724,0.0006816613],"category_scores_gemma":[0.0008289237,0.0013320956,0.0008260252,0.00016185925,0.0011377155,0.000115423056,0.0013847899,0.0010199032,0.000603968],"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":[0.0010793116,0.004809007,0.19618282,0.0075177355,0.009186504,0.0009486531,0.007988602,0.00058842124,0.12013771,0.020954475,0.49381003,0.13679674],"study_design_scores_gemma":[0.0042261095,0.0007174824,0.0046448493,0.000814508,0.0011306105,0.0004026395,0.0015316689,0.004559752,0.005512725,0.00023158031,0.9740107,0.0022173494],"about_ca_topic_score_codex":0.0013873767,"about_ca_topic_score_gemma":0.00065051665,"teacher_disagreement_score":0.4802007,"about_ca_system_score_codex":0.00028219653,"about_ca_system_score_gemma":0.000797674,"threshold_uncertainty_score":0.999935},"labels":[],"label_agreement":null},{"id":"W7067128146","doi":"","title":"Le bien-être psychologique à l'adolescence et l'implication dans des relations sexuelles non-romantiques chez les garçons et les filles","year":2018,"lang":"fr","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sexual behavior; Gender identity; Context (archaeology); Identity (music)","score_opus":0.009167581555133987,"score_gpt":0.28808119596438797,"score_spread":0.278913614409254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067128146","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08672401,0.001022,0.16735116,0.0031932273,0.0001967483,0.0006954011,0.00013718102,0.00016683419,0.74051344],"genre_scores_gemma":[0.4998244,0.0049159676,0.087044805,0.00076235493,0.0004169376,0.000104531464,0.0016400599,0.00030137933,0.40498957],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971568,0.0005862325,0.000718575,0.00080536073,0.00020595363,0.00052709784],"domain_scores_gemma":[0.99775845,0.00011455108,0.0006254251,0.0010826743,0.00025557808,0.00016335295],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006793723,0.00070062187,0.00044284924,0.00018941588,0.00051605504,0.00015095522,0.00075206364,0.0017242337,0.0021095118],"category_scores_gemma":[0.00049375783,0.0006600587,0.00024820463,0.00021763511,0.0013758667,0.000025061581,0.00034283992,0.0007052243,0.0005729829],"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":[0.0001094083,0.0010963053,0.37385055,0.0013923611,0.0007986714,0.0000091380225,0.0065131914,0.0007743076,0.19289577,0.14073241,0.26775002,0.01407786],"study_design_scores_gemma":[0.00080762047,0.00087611267,0.17736933,0.0010629849,0.00015237008,0.00015638031,0.0031451245,0.0020430125,0.030260248,0.0006714979,0.7817481,0.001707202],"about_ca_topic_score_codex":0.0010000987,"about_ca_topic_score_gemma":0.0064065494,"teacher_disagreement_score":0.5139981,"about_ca_system_score_codex":0.00005045467,"about_ca_system_score_gemma":0.0004565915,"threshold_uncertainty_score":0.9995851},"labels":[],"label_agreement":null},{"id":"W7067182552","doi":"","title":"A Life in Music from the Soviet Union to Canada [Sound Files]","year":2019,"lang":"en","type":"book","venue":"University of North Texas Digital Library (University of North Texas)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Portrait; Musical; Soviet union; Period (music); Popularity; Politics","score_opus":0.006273531443411063,"score_gpt":0.15518825824297147,"score_spread":0.14891472679956042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067182552","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9012824,0.00015716116,0.0003044446,0.00065729406,0.00021813504,0.0008007564,0.012047498,0.000040499337,0.08449175],"genre_scores_gemma":[0.548388,0.00025678487,0.00086251844,0.0012101064,0.00017823809,5.167401e-8,0.02322129,0.000090571026,0.42579243],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982881,0.00008697103,0.00029219233,0.00053420634,0.00044588215,0.00035263094],"domain_scores_gemma":[0.99800694,0.00013455012,0.000568306,0.0008851526,0.0001017741,0.0003032743],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00006113754,0.00041510205,0.00060231093,0.00019821321,0.00013807723,0.00003775093,0.0018358283,0.00028897414,0.00047987976],"category_scores_gemma":[0.00007078093,0.00048809545,0.00026854724,0.00029768827,0.00029212996,0.000107585045,0.0016533496,0.0004980973,0.00011009459],"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":[0.00020486522,0.000050504605,0.7635222,0.000115782794,0.00019258137,0.000043791882,0.00008649234,0.0011872662,9.071625e-8,0.000028821154,0.23304534,0.0015222619],"study_design_scores_gemma":[0.0004993453,0.00015786773,0.5019014,0.00009539627,0.000051136376,0.0000017671953,0.0000721815,0.00007483832,7.3285776e-7,0.000018562452,0.4967822,0.00034455193],"about_ca_topic_score_codex":0.0405378,"about_ca_topic_score_gemma":0.52864903,"teacher_disagreement_score":0.48811123,"about_ca_system_score_codex":0.000096235795,"about_ca_system_score_gemma":0.002727674,"threshold_uncertainty_score":0.99975705},"labels":[],"label_agreement":null},{"id":"W7067212098","doi":"","title":"&lt;em&gt;Painting the Map Red: Canada and the South African War, 1899â1902&lt;/em&gt; by Carmen Miller [Review]","year":2012,"lang":"en","type":"article","venue":"Scholars Commons (Wilfrid Laurier University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Diafiltration; Liquation; Emperipolesis; Triacetin; Fusible alloy","score_opus":0.005336662233808763,"score_gpt":0.1900307458523953,"score_spread":0.18469408361858652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067212098","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91612333,0.024290074,0.00036316158,0.009036789,0.0007124638,0.0013218225,0.00033008982,0.00008869685,0.047733564],"genre_scores_gemma":[0.9876942,0.0012511808,0.00051096274,0.0027032816,0.00015083094,0.0000059033387,0.00018311312,0.000045315723,0.007455233],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99777204,0.0006070385,0.0003057218,0.0003049766,0.0003819597,0.00062826055],"domain_scores_gemma":[0.998278,0.00011179095,0.0002912244,0.0009306937,0.0001343095,0.00025398214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012712496,0.00033209857,0.00032382147,0.00007342648,0.0008588149,0.00008244523,0.000920138,0.00015368128,0.000059182887],"category_scores_gemma":[0.0003666231,0.0002373191,0.00014544936,0.00034557612,0.0003271342,0.000042710846,0.0007750388,0.00066066504,0.0000103955135],"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":[0.00051109487,0.00018284227,0.076716065,0.0005993916,0.0013356798,0.00004910226,0.0069143097,0.00017358192,0.004558724,0.003914377,0.89791983,0.0071250196],"study_design_scores_gemma":[0.0009242471,0.000040904113,0.0015375161,0.00007053561,0.00017677789,0.00002327586,0.0018743338,0.00010898694,0.000342834,0.000009334758,0.9945331,0.0003581343],"about_ca_topic_score_codex":0.0029384699,"about_ca_topic_score_gemma":0.03714698,"teacher_disagreement_score":0.0966133,"about_ca_system_score_codex":0.00009750911,"about_ca_system_score_gemma":0.00022866181,"threshold_uncertainty_score":0.98042256},"labels":[],"label_agreement":null},{"id":"W7067222676","doi":"","title":"+91-9829791419#$ Love Vashikaran Specialist In Delhi, Goa","year":2021,"lang":"en","type":"other","venue":"OSF Preprints (OSF Preprints)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mantra; Spell; MAGIC (telescope); Curse; Unicorn; Reincarnation","score_opus":0.008651163274426178,"score_gpt":0.2595445499479819,"score_spread":0.2508933866735557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067222676","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":[0.0023694295,0.000033890556,0.0010695456,0.00014551944,0.00061290397,0.0007603675,0.00006359573,0.00006488521,0.99487984],"genre_scores_gemma":[0.0026450309,0.0006583386,0.0040015755,0.00034797017,0.0006972815,0.000058914055,0.00075992715,0.00041106678,0.9904199],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954913,0.00054324704,0.0007883621,0.0021205836,0.0004308191,0.0006256535],"domain_scores_gemma":[0.9945627,0.000060046335,0.0005393021,0.0045279656,0.000090070425,0.00021991425],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017947021,0.0006417951,0.0006905766,0.0002655747,0.00005105903,0.00012696402,0.001409677,0.0011344524,0.6028732],"category_scores_gemma":[0.0020582483,0.00075256947,0.0003336092,0.00023890474,0.00020768093,0.0000073612723,0.0020558117,0.00090296625,0.40995017],"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":[0.00011525518,0.00040681902,0.0135536175,0.00068960636,0.00047209693,0.00009937851,0.00056286517,0.0007305606,0.009288377,0.0003692934,0.9643538,0.009358326],"study_design_scores_gemma":[0.00074348104,0.0000025000297,0.002882149,0.00031066782,0.00004783773,0.000054031832,0.00007908698,0.00020772577,0.004587414,0.00011586656,0.9902069,0.0007623423],"about_ca_topic_score_codex":0.0006859418,"about_ca_topic_score_gemma":0.0017055977,"teacher_disagreement_score":0.19292301,"about_ca_system_score_codex":0.00014669217,"about_ca_system_score_gemma":0.0003253523,"threshold_uncertainty_score":0.9994925},"labels":[],"label_agreement":null},{"id":"W7067245499","doi":"","title":"Les motifs de migration pour études des universitaires internationaux en région intermédiaire au Québec","year":2016,"lang":"fr","type":"other","venue":"Knowledge UdeS (Institutional Deposit of the University of Sherbrooke)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Homogeneous; Context (archaeology); Local Development","score_opus":0.007695374263215269,"score_gpt":0.21900349883514508,"score_spread":0.21130812457192982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067245499","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6357188,0.0041846675,0.12495296,0.0011466953,0.0004108519,0.00035277472,0.000057915408,0.000028936498,0.23314637],"genre_scores_gemma":[0.87131166,0.00079144764,0.005401712,0.000013754771,0.00017817743,4.042329e-7,0.000040482395,0.000032974745,0.1222294],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99877447,0.00021116978,0.00028541154,0.00027654675,0.00021449005,0.00023788417],"domain_scores_gemma":[0.9989654,0.00006357724,0.0002993942,0.00034022238,0.00023805999,0.00009335262],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015965114,0.00031490214,0.00029011694,0.00016775179,0.00042799814,0.000012659709,0.0009787397,0.0004550921,0.00038862095],"category_scores_gemma":[0.0001701744,0.0002810247,0.00038234628,0.00009017529,0.0013294367,0.00003458237,0.0005695374,0.00021729118,0.00007175018],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009900689,0.0014340176,0.32535946,0.015248704,0.0034396832,0.00003982982,0.041743524,0.046770576,0.31186992,0.07353616,0.019526713,0.16004133],"study_design_scores_gemma":[0.0018488212,0.00036190153,0.22352193,0.012934622,0.00062414346,0.00011645127,0.001206483,0.019760147,0.061980408,0.00017841614,0.67666906,0.00079758774],"about_ca_topic_score_codex":0.037667166,"about_ca_topic_score_gemma":0.4516625,"teacher_disagreement_score":0.6571424,"about_ca_system_score_codex":0.0033772693,"about_ca_system_score_gemma":0.0012823995,"threshold_uncertainty_score":0.9999642},"labels":[],"label_agreement":null},{"id":"W7067326201","doi":"","title":"McGill Journal of Medicine","year":2020,"lang":"en","type":"other","venue":"Directory of Open Access Journals (EBSCO)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medical journal; MEDLINE; Feature (linguistics); Government (linguistics); Journal editor; Work (physics)","score_opus":0.0853912827468175,"score_gpt":0.4503607585362348,"score_spread":0.3649694757894173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067326201","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":[0.000965062,0.024908932,0.0010587093,0.001392288,0.0018712572,0.0005678108,0.00020755614,0.000021005755,0.9690074],"genre_scores_gemma":[0.0672268,0.087853335,0.023239877,0.011302293,0.015164173,0.000036080302,0.0005890578,0.0028986612,0.7916897],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99767303,0.0002230197,0.0011084778,0.00022930713,0.0005410995,0.00022505982],"domain_scores_gemma":[0.9956731,0.000037859634,0.0033496744,0.00045682114,0.00025271482,0.00022981687],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00091054797,0.00034831278,0.0009875378,0.00037339074,0.00005853772,0.00017881233,0.0035534697,0.00030556374,0.0058344016],"category_scores_gemma":[0.0009488818,0.0002730055,0.00021876555,0.00023414048,0.0002040499,0.000051438437,0.0011111877,0.0005591027,0.000009845906],"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":[0.00012214035,0.000051960003,0.0016064168,0.00028831887,0.00054460997,0.000022274393,0.000040811585,0.000030183879,0.014921677,0.000043436525,0.9765482,0.0057799476],"study_design_scores_gemma":[0.0010581698,0.0002912633,0.0008000351,0.0011799692,0.00013188028,0.0001091398,0.00002920866,0.000010017869,0.00790829,0.00006155676,0.9881348,0.0002856628],"about_ca_topic_score_codex":0.0001406734,"about_ca_topic_score_gemma":0.000033191212,"teacher_disagreement_score":0.17731766,"about_ca_system_score_codex":0.000018965888,"about_ca_system_score_gemma":0.00019255829,"threshold_uncertainty_score":0.9999722},"labels":[],"label_agreement":null},{"id":"W7067331280","doi":"","title":"L'Utilisation des ouvrages didactiques en langue anglaise dans les universités et collèges francophones du Québec : synthèse de la documentation /","year":2015,"lang":"fr","type":"other","venue":"Bibliothèque et Archives nationales du Québec (Québec government)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Documentation; Point (geometry); Conjunction (astronomy)","score_opus":0.0050724983446333366,"score_gpt":0.23372311098441953,"score_spread":0.2286506126397862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067331280","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60431194,0.012912296,0.008781482,0.0070572314,0.00028574676,0.0007690378,0.0007217106,0.00017835823,0.3649822],"genre_scores_gemma":[0.82649124,0.0057574613,0.0049124085,0.00068228395,0.00055098505,0.000100846075,0.0004986916,0.00025157197,0.16075453],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99592674,0.0016367364,0.0006193083,0.0006172463,0.0007609898,0.0004389679],"domain_scores_gemma":[0.9937984,0.004553615,0.0007714356,0.00045817395,0.00014857827,0.00026979827],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009545123,0.0007191734,0.0004804009,0.00060133246,0.00039385512,0.00039139966,0.0007612031,0.00044256065,0.0049913786],"category_scores_gemma":[0.0054306905,0.0007420753,0.0002733047,0.00041863852,0.0008290088,0.0001563256,0.0004934674,0.0006390372,0.00019856711],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0007203929,0.0008852715,0.57286054,0.0011196128,0.0012792802,0.000062554005,0.07583068,0.004583795,0.025926352,0.0073538027,0.30518344,0.0041942503],"study_design_scores_gemma":[0.001289875,0.00031742893,0.22443713,0.00036079538,0.00019108433,0.00011623868,0.0036012235,0.0014226591,0.0029693758,0.00011402261,0.76439196,0.00078819826],"about_ca_topic_score_codex":0.45104906,"about_ca_topic_score_gemma":0.97428924,"teacher_disagreement_score":0.52324015,"about_ca_system_score_codex":0.0046155886,"about_ca_system_score_gemma":0.034504715,"threshold_uncertainty_score":0.999503},"labels":[],"label_agreement":null},{"id":"W7067385959","doi":"","title":"Liepājas Muzikāli dramatiskā teātra baleta pedagoģiskā un mākslinieciskā vērtība Latvijas kultūrā","year":2014,"lang":"lv","type":"dissertation","venue":"E-resource repository of the University of Latvia (University of Latvia)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Derogation; Limiting; Pretext; State (computer science)","score_opus":0.004546989719673705,"score_gpt":0.18626932137035254,"score_spread":0.18172233165067883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067385959","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93820405,0.00074802135,0.0014402127,0.00040203752,0.0007330836,0.0008676546,0.00026527603,0.00006193954,0.057277713],"genre_scores_gemma":[0.93413985,0.00033881862,0.005423533,0.000043994238,0.00018493665,1.4457748e-7,0.0006649577,0.000096470096,0.059107304],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99505347,0.00088019954,0.0010095418,0.0010322336,0.0012920159,0.0007325185],"domain_scores_gemma":[0.99197847,0.0002309615,0.0042425054,0.0023853676,0.0007915891,0.000371127],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0008278021,0.000922993,0.0016655154,0.00044371161,0.0014688922,0.000036754554,0.003654878,0.0018093407,0.00036766907],"category_scores_gemma":[0.00020817184,0.0011066922,0.0017667745,0.0005448626,0.0018687319,0.000058519105,0.0013011371,0.0012797242,0.000049557555],"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":[0.017053353,0.004743903,0.15473774,0.025234766,0.020496724,0.000552535,0.1782779,0.02812084,0.46156016,0.0034126674,0.07111918,0.03469023],"study_design_scores_gemma":[0.012339214,0.0036103881,0.1760966,0.005541238,0.00808297,0.00025300513,0.07008612,0.013873453,0.059807464,0.00020356766,0.64528203,0.004823959],"about_ca_topic_score_codex":0.0019312544,"about_ca_topic_score_gemma":0.00049731886,"teacher_disagreement_score":0.57416284,"about_ca_system_score_codex":0.00016471889,"about_ca_system_score_gemma":0.0005754927,"threshold_uncertainty_score":0.9998311},"labels":[],"label_agreement":null},{"id":"W7067387997","doi":"","title":"L'innovation ouverte en aérospatiale - une comparaison Canada-Brésil","year":2014,"lang":"fr","type":"other","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Product (mathematics); Identification (biology); Interpretation (philosophy); Object (grammar)","score_opus":0.004929432761692173,"score_gpt":0.22080442768098738,"score_spread":0.2158749949192952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067387997","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":[0.024005296,0.003708803,0.8218605,0.014090221,0.0018076512,0.0022342664,0.0005265639,0.00039296964,0.13137373],"genre_scores_gemma":[0.48322803,0.0007486644,0.085699745,0.015123108,0.0026185133,0.00052546326,0.0038280413,0.0009639576,0.40726447],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99564266,0.00041735216,0.0012802064,0.00081930746,0.0006469929,0.001193483],"domain_scores_gemma":[0.99631786,0.00010320944,0.001219591,0.0016979002,0.00030500564,0.0003564449],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00079705444,0.0010349363,0.0009404232,0.00044411846,0.0003468646,0.00017535633,0.0011791575,0.0016384094,0.0009724747],"category_scores_gemma":[0.0007320009,0.0011400582,0.0002335412,0.00078038964,0.00024351942,0.000017882856,0.0005078767,0.0011569539,0.00013185492],"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":[0.00026635092,0.00043871903,0.05854766,0.0011466545,0.00078286603,0.00006011972,0.00037413294,0.020814847,0.031167911,0.06256505,0.7366227,0.087212995],"study_design_scores_gemma":[0.0007614035,0.00033519854,0.01722206,0.00021970643,0.00011114115,0.000102408965,0.000049838956,0.12151319,0.007124253,0.00013874905,0.8512669,0.0011551143],"about_ca_topic_score_codex":0.7225396,"about_ca_topic_score_gemma":0.8664432,"teacher_disagreement_score":0.73616076,"about_ca_system_score_codex":0.0010104883,"about_ca_system_score_gemma":0.0019960878,"threshold_uncertainty_score":0.99994075},"labels":[],"label_agreement":null},{"id":"W7067432597","doi":"","title":"$403.06 Million in Sales Expected for Enphase Energy, Inc. (NASDAQ:ENPH) This Quarter | Daily Political","year":2021,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Politics; Work (physics); Payment","score_opus":0.007812053139106663,"score_gpt":0.2688740471476653,"score_spread":0.2610619940085586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067432597","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":[0.0009825507,0.0028935312,0.020647343,0.00067221955,0.0005262702,0.0006411635,0.0003708334,0.00015373182,0.97311234],"genre_scores_gemma":[0.015467865,0.00028658877,0.019986367,0.0022262477,0.0013068074,0.00018067217,0.019049315,0.00051707716,0.94097906],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982324,0.0001044944,0.00044627316,0.0004844301,0.00018500754,0.00054737047],"domain_scores_gemma":[0.99895597,0.000040270847,0.00016140571,0.00061693316,0.000073892086,0.00015150977],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000120741985,0.00040823265,0.00040617783,0.0002254834,0.00003720797,0.000046183846,0.00029118042,0.00087747624,0.001945368],"category_scores_gemma":[0.00017101556,0.00037403355,0.00016544304,0.00011170946,0.00009284978,0.000002260708,0.0001571889,0.00020802855,0.00003555256],"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":[0.000049482423,0.00015986223,0.00039067102,0.00024540676,0.00012352302,0.000010352176,0.00004992913,0.0000032441696,0.00677558,0.005913684,0.9857635,0.0005147727],"study_design_scores_gemma":[0.0011096952,0.00021703275,0.000046977562,0.000113247326,0.000027134478,0.000019292173,0.00015012342,0.0006062505,0.0037920983,0.00005077891,0.99334675,0.00052062847],"about_ca_topic_score_codex":0.000592519,"about_ca_topic_score_gemma":0.0013773642,"teacher_disagreement_score":0.032133296,"about_ca_system_score_codex":0.00003688286,"about_ca_system_score_gemma":0.00015060617,"threshold_uncertainty_score":0.99987113},"labels":[],"label_agreement":null},{"id":"W7067486399","doi":"","title":"Legal environment and financial restatements : evidence from Canada and the U.S","year":2016,"lang":"en","type":"dissertation","venue":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Audit; Confidentiality; Work (physics)","score_opus":0.002924649501703272,"score_gpt":0.18214946110196223,"score_spread":0.17922481160025897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067486399","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9973387,0.00043421934,0.00005242601,0.0010505201,0.00014289982,0.00018339808,0.000026741349,0.000005231258,0.00076583494],"genre_scores_gemma":[0.99454945,0.002902909,0.00032139983,0.00003592036,0.00011137216,7.196559e-7,0.00002501966,0.000005545387,0.002047686],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99912274,0.000023057111,0.00012290936,0.0002877319,0.0002757034,0.00016784681],"domain_scores_gemma":[0.9993889,0.000032635013,0.00019833194,0.0002620192,0.00007737194,0.000040762432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027025185,0.00013225887,0.00016127607,0.00007442796,0.000608824,0.00002576507,0.00047131485,0.00015818646,0.000018017774],"category_scores_gemma":[0.00023080476,0.000090558446,0.000017748365,0.0001408162,0.002604675,0.000023490426,0.0003233393,0.00019005516,0.0000010005562],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003372812,0.0001130791,0.10450049,0.0004420897,0.00038910413,0.00015153999,0.009870085,0.000021314734,0.16844101,0.01151595,0.015202558,0.68597996],"study_design_scores_gemma":[0.00616008,0.0008823085,0.49619085,0.0013673985,0.000514758,0.000058708632,0.024277478,0.00027668139,0.058286812,0.0018064351,0.40848696,0.001691549],"about_ca_topic_score_codex":0.035505846,"about_ca_topic_score_gemma":0.10988394,"teacher_disagreement_score":0.68428844,"about_ca_system_score_codex":0.00004164067,"about_ca_system_score_gemma":0.0004903175,"threshold_uncertainty_score":0.9709168},"labels":[],"label_agreement":null},{"id":"W7067517709","doi":"","title":"Mapování starých zátěží na území ČR s využitím GIS","year":2015,"lang":"en","type":"dissertation","venue":"Digital Repository (National Repository of Grey Literature)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Czech; Work (physics); Locality; Geographic information system; Focus (optics)","score_opus":0.005722350120480527,"score_gpt":0.2556077240306425,"score_spread":0.249885373910162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067517709","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49614716,0.0050305403,0.00004613393,0.000024795352,0.003681238,0.0006025126,0.00047912798,0.000095787305,0.4938927],"genre_scores_gemma":[0.8113866,0.00003429687,0.00074691244,0.000084301144,0.0014763322,0.000053499465,0.018013492,0.00013633177,0.16806823],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99549884,0.00012303554,0.0013459668,0.00083041535,0.0017803253,0.0004214043],"domain_scores_gemma":[0.99414897,0.00007034826,0.0013059445,0.00080568856,0.0033773975,0.00029164436],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002909371,0.0007302148,0.0006107558,0.00032436635,0.00026905272,0.0007747751,0.00073478953,0.001121388,0.0000071105073],"category_scores_gemma":[0.00086265575,0.0007340268,0.00049749715,0.00029009738,0.00016744083,0.00012002479,0.00014569699,0.0007237058,0.000019458548],"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":[0.0072287866,0.0025982005,0.041603334,0.0077897906,0.0048140488,0.0007009192,0.008269516,0.0019572943,0.67053056,0.004936798,0.23675546,0.012815281],"study_design_scores_gemma":[0.0033595862,0.002962887,0.033639055,0.00318339,0.00046295588,0.002227102,0.00090234395,0.0009661519,0.32304114,0.0018492907,0.62276226,0.0046438416],"about_ca_topic_score_codex":0.000012861066,"about_ca_topic_score_gemma":0.000004591244,"teacher_disagreement_score":0.3860068,"about_ca_system_score_codex":0.00019251535,"about_ca_system_score_gemma":0.0011968312,"threshold_uncertainty_score":0.99951106},"labels":[],"label_agreement":null},{"id":"W7067526010","doi":"","title":"Nesting cackling Canada goose","year":2008,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nesting (process); Fishing; Goose; Natural (archaeology)","score_opus":0.004035274256994229,"score_gpt":0.20628162829981747,"score_spread":0.20224635404282323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067526010","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":[0.00039496997,0.0004253519,0.0007388561,0.000029547755,0.0002903284,0.00009998526,0.000017496594,0.00005118194,0.9979523],"genre_scores_gemma":[0.001482687,0.00017822118,0.00770626,0.0005689907,0.00063206453,0.000003806636,0.00034056773,0.0002671856,0.9888202],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999312,0.000015884738,0.00015569171,0.00017898325,0.00013640626,0.00020102729],"domain_scores_gemma":[0.9994422,0.000005835057,0.00013703803,0.00033065522,0.000018789195,0.00006546113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000036144604,0.00019414569,0.00014351272,0.000033231197,0.000041793184,0.000009183908,0.00018601293,0.00022811424,0.0005140811],"category_scores_gemma":[0.0000626841,0.00017907676,0.000038672966,0.000037153626,0.000026287214,3.3608714e-7,0.00009690408,0.00014476551,0.000027261483],"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":[0.0000013004938,0.0000031280078,0.00054430024,0.00004269008,0.000028746643,0.0000042213464,0.000008804602,0.00007058577,0.00018883453,0.000007805016,0.9982255,0.00087404443],"study_design_scores_gemma":[0.00010025215,0.000016713839,0.000030006478,0.00003103638,0.0000062515755,0.000040508017,0.000016226339,0.00024759292,0.00039010672,2.62511e-7,0.9988849,0.00023611258],"about_ca_topic_score_codex":0.56684667,"about_ca_topic_score_gemma":0.7785679,"teacher_disagreement_score":0.21172126,"about_ca_system_score_codex":0.000018421424,"about_ca_system_score_gemma":0.00041854655,"threshold_uncertainty_score":0.7302538},"labels":[],"label_agreement":null},{"id":"W7067549303","doi":"","title":"Miten tavallisuudesta poikkeava mainoskampanja tavoittaa paikallislehden tilaajan? : huomioarvotutkimus Kauhavan kaupungin mainoskampanjasta","year":2018,"lang":"fi","type":"other","venue":"Theseus (Ammattikorkeakoulujen)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Work (physics); Subject (documents); Data collection; Government (linguistics)","score_opus":0.010650509668921672,"score_gpt":0.25413820044292307,"score_spread":0.2434876907740014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067549303","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":[0.029949095,0.0029613452,0.0021137747,0.0012725748,0.002981672,0.0030854382,0.0011187735,0.00066695624,0.95585036],"genre_scores_gemma":[0.05261033,0.0022259166,0.008056975,0.0014829624,0.0066065593,0.0001380495,0.003638465,0.0021452727,0.92309546],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9856956,0.0016113636,0.003052528,0.0032506052,0.0020840554,0.0043058665],"domain_scores_gemma":[0.9882918,0.00040207346,0.0027958546,0.0061530634,0.000760389,0.0015968245],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.0030069898,0.0038106893,0.0031028376,0.0010981566,0.00088403997,0.0010451725,0.005830962,0.0042776396,0.017150342],"category_scores_gemma":[0.0014084935,0.0037308952,0.0016381743,0.0010037738,0.0021458336,0.00009563802,0.0030893218,0.0023165909,0.02230135],"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":[0.0053621964,0.0037654822,0.009735891,0.0080582,0.013068751,0.0010891154,0.010759551,0.0008844293,0.053956117,0.0072254655,0.2774813,0.60861355],"study_design_scores_gemma":[0.0029384238,0.0015242508,0.0011267122,0.0011575896,0.000855945,0.00038350874,0.00070624077,0.001761761,0.0036169603,0.0004444639,0.98136705,0.004117083],"about_ca_topic_score_codex":0.000396299,"about_ca_topic_score_gemma":0.0009496529,"teacher_disagreement_score":0.7038858,"about_ca_system_score_codex":0.0005477905,"about_ca_system_score_gemma":0.0010671023,"threshold_uncertainty_score":0.99999183},"labels":[],"label_agreement":null},{"id":"W7067567483","doi":"","title":"Microprogramme de troisième cycle en éducation (2-812-6-0), avec spécialisation en intégration pédagogique des technologies de l’information et de la communication (TIC), Programme spécialement conçu pour l'IIRCA-UNESCO","year":2003,"lang":"fr","type":"report","venue":"Érudit documents and data repository (Érudit Consortium, University of Montreal)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Context (archaeology); Order (exchange)","score_opus":0.013811348316170485,"score_gpt":0.27845933838025194,"score_spread":0.26464799006408146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067567483","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87988347,0.0069605354,0.080813736,0.0034919882,0.0006809005,0.0034080644,0.0012191262,0.0003193847,0.023222774],"genre_scores_gemma":[0.83917564,0.07159264,0.067484856,0.00013996472,0.0002445818,0.00003928187,0.01731242,0.00007465969,0.0039359797],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99568826,0.001767275,0.00093636266,0.0005696375,0.00043427316,0.0006042032],"domain_scores_gemma":[0.9957032,0.0003436765,0.0017897814,0.00143286,0.00054462627,0.00018584926],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0036865121,0.00051632774,0.0005407243,0.00024608744,0.00065427565,0.00030970533,0.0010522511,0.0011265972,0.000020306954],"category_scores_gemma":[0.0018728316,0.0006157922,0.0001517434,0.00016489431,0.0008808703,0.00032301355,0.00082322676,0.0006562637,0.000005298916],"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":[0.0013854795,0.0030789939,0.20820194,0.0069349427,0.0042668474,0.00023576547,0.027501881,0.0019614927,0.041037012,0.008600009,0.07418896,0.6226067],"study_design_scores_gemma":[0.0030287022,0.0006056067,0.021400953,0.0009272377,0.0013824403,0.0013872294,0.014043617,0.003893696,0.00788652,0.0011883995,0.9430512,0.0012044084],"about_ca_topic_score_codex":0.013020849,"about_ca_topic_score_gemma":0.008886634,"teacher_disagreement_score":0.8688622,"about_ca_system_score_codex":0.0024123,"about_ca_system_score_gemma":0.0023334594,"threshold_uncertainty_score":0.9996293},"labels":[],"label_agreement":null},{"id":"W7067572875","doi":"","title":"Manif d'art : Manifestation international d'art de Québec","year":2000,"lang":"fr","type":"book","venue":"E-Artexte (Artexte)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Government (linguistics); Set (abstract data type); Identification (biology); Relation (database)","score_opus":0.005762364972112354,"score_gpt":0.24005620906197123,"score_spread":0.23429384408985887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067572875","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":[0.009995381,0.00152944,0.006418824,0.00378165,0.0025016738,0.00088785763,0.00037251972,0.00015354951,0.9743591],"genre_scores_gemma":[0.019414965,0.002118906,0.0055231676,0.0030761922,0.0026936207,0.00008701993,0.008032911,0.00025956257,0.95879364],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995104,0.00034823405,0.0014340737,0.00112644,0.00082491274,0.0011623295],"domain_scores_gemma":[0.99694383,0.00013326298,0.0008377693,0.0012920713,0.00031223753,0.00048084222],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007970805,0.0011469013,0.00073351874,0.00028647183,0.00042718012,0.00031381467,0.0012842526,0.0014314888,0.020996343],"category_scores_gemma":[0.00027636188,0.0013305121,0.0006215233,0.00014502431,0.00054159865,0.00006297757,0.00037353378,0.0013331203,0.022287505],"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":[0.0003657093,0.0004228907,0.001230539,0.00056032086,0.0008983894,0.00018681234,0.0012002345,0.0018638265,0.0024189975,0.0058910768,0.91063136,0.07432984],"study_design_scores_gemma":[0.0012285371,0.00054362987,0.0031531565,0.00036312247,0.00023438004,0.0007444027,0.00008462769,0.0054683713,0.00047294123,0.00050990185,0.9859088,0.0012880992],"about_ca_topic_score_codex":0.00045939817,"about_ca_topic_score_gemma":0.002500662,"teacher_disagreement_score":0.07527746,"about_ca_system_score_codex":0.000707261,"about_ca_system_score_gemma":0.0020037591,"threshold_uncertainty_score":0.9998649},"labels":[],"label_agreement":null},{"id":"W7067575502","doi":"","title":"Monitoring signals for vaccine safety: the assessment of individual adverse event reports by an expert advisory committee","year":2000,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"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":"Adverse effect; Causality (physics); Advisory committee; Causation; Task (project management); Event (particle physics); Vaccine safety","score_opus":0.09408474432173544,"score_gpt":0.5186991693746825,"score_spread":0.4246144250529471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067575502","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98676205,0.0072208885,0.0026648515,0.00021303496,0.00036487804,0.00091433094,0.00011244024,0.00001560222,0.0017319333],"genre_scores_gemma":[0.99002934,0.006417363,0.0021898053,0.00032662513,0.00029027974,0.00008334627,0.00017388347,0.00005198054,0.00043741107],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9971509,0.00028807676,0.001279017,0.00033709384,0.00061290106,0.0003320025],"domain_scores_gemma":[0.99744844,0.00014238777,0.0012052055,0.00078908936,0.00024395515,0.00017093273],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023504451,0.00029810972,0.0005257044,0.00013805182,0.00027113574,0.00021851902,0.0018660795,0.00015374305,0.0020532398],"category_scores_gemma":[0.00019793752,0.00023358993,0.00022805925,0.00021361405,0.00007354832,0.0001240083,0.0005367561,0.00029811412,9.141264e-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":[0.00045602454,0.00060507114,0.41331512,0.00013678933,0.0006766669,0.0000101048845,0.0004519493,0.008280195,0.42289317,0.0000067581645,0.0742707,0.07889745],"study_design_scores_gemma":[0.0015233934,0.00023613631,0.5354184,0.00039540435,0.0001803609,0.00006237529,0.0004718575,0.0010191579,0.29014173,0.00032382773,0.16950603,0.00072136393],"about_ca_topic_score_codex":0.0001269936,"about_ca_topic_score_gemma":0.000007634631,"teacher_disagreement_score":0.13275145,"about_ca_system_score_codex":0.00003838021,"about_ca_system_score_gemma":0.00015102455,"threshold_uncertainty_score":0.99885905},"labels":[],"label_agreement":null},{"id":"W7067629313","doi":"","title":"“Mapping the Island”: Data Journalism Education through Coverage of Gentrification and Housing Issues in Montreal","year":2021,"lang":"en","type":"dissertation","venue":"Spectrum Research Repository (Concordia University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Journalism; Technical Journalism; Expansive; Set (abstract data type); Work (physics)","score_opus":0.02755785036589958,"score_gpt":0.3119890561465033,"score_spread":0.2844312057806037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067629313","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96179855,0.004104334,0.00022930045,0.00024223421,0.00030292067,0.00031799174,0.000022106102,0.000005726844,0.032976843],"genre_scores_gemma":[0.9720583,0.0073645883,0.000096625765,0.000011069267,0.00032295976,0.0000015719635,0.0017495562,0.00002105663,0.018374257],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99825114,0.00050270045,0.0002820306,0.00038292442,0.0003366185,0.00024456054],"domain_scores_gemma":[0.99855894,0.0000665878,0.00029149387,0.0008104448,0.000220729,0.00005180649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005554476,0.00015299783,0.00020927815,0.00028383386,0.0002796736,0.00010790644,0.0006365063,0.00024495515,0.000008691082],"category_scores_gemma":[0.00022623205,0.0001477094,0.000052023795,0.00043129546,0.00011904449,0.000037552058,0.00027142966,0.0006245581,9.2169176e-7],"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":[0.0027499911,0.001259553,0.48809788,0.004634134,0.0018254338,0.0005035627,0.039116643,0.0009051455,0.3655433,0.0035326343,0.03788581,0.05394591],"study_design_scores_gemma":[0.0018107294,0.00047171695,0.5835731,0.001308393,0.00015973127,0.00013508595,0.059665855,0.0023699873,0.0817191,0.00065938424,0.26713893,0.0009880086],"about_ca_topic_score_codex":0.016607305,"about_ca_topic_score_gemma":0.034246303,"teacher_disagreement_score":0.2838242,"about_ca_system_score_codex":0.00008757257,"about_ca_system_score_gemma":0.0008705952,"threshold_uncertainty_score":0.9899412},"labels":[],"label_agreement":null},{"id":"W7067635652","doi":"","title":"Nontraditional Students’ Perceptions and Experiences Using Technology in a Teacher Preparation Program","year":2022,"lang":"en","type":"article","venue":"ScholarWorks (Walden University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Andragogy; Perception; Educational technology; Technology education; Qualitative research; Perspective (graphical); Technology integration; Higher education; Lifelong learning; Information technology","score_opus":0.007356177701150697,"score_gpt":0.28884285743393695,"score_spread":0.28148667973278624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067635652","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99852806,0.000057947076,0.00043699436,0.00010162918,0.00004559054,0.00022773784,0.0000064442283,0.000027335285,0.0005682598],"genre_scores_gemma":[0.9953534,0.000009925374,0.0036359886,0.00003398716,0.00002629925,0.000011219928,0.00006743352,0.0000062879512,0.0008554323],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99932945,0.0000921271,0.00009510601,0.0001974287,0.0001456994,0.00014020302],"domain_scores_gemma":[0.9997437,0.0000040239984,0.000056001052,0.00013736008,0.000024415394,0.00003450978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013213829,0.00008044768,0.000069772395,0.00024808693,0.00034063653,0.000042117455,0.00023945226,0.000090610185,0.0001233587],"category_scores_gemma":[0.00002615151,0.000098520395,0.000023244871,0.00036232418,0.00009634047,0.000023728035,0.0003382892,0.0003142327,9.594377e-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":[0.00035111382,0.0009779586,0.93653184,0.000026010166,0.000118447824,0.000054786135,0.008614336,0.009561611,0.03479992,0.001651921,0.00053550565,0.0067765336],"study_design_scores_gemma":[0.010742686,0.00614939,0.28253415,0.00014113256,0.00025700932,0.0010294096,0.31899592,0.08687292,0.0029360773,0.0007207415,0.2864625,0.0031580417],"about_ca_topic_score_codex":0.0000105345325,"about_ca_topic_score_gemma":0.000034125896,"teacher_disagreement_score":0.6539977,"about_ca_system_score_codex":0.00007189357,"about_ca_system_score_gemma":0.0000502265,"threshold_uncertainty_score":0.40175453},"labels":[],"label_agreement":null},{"id":"W7067662905","doi":"","title":"Mobility of elements from cesium formate residue emplaced on pegmatite tailings, Bernic Lake, Manitoba, Canada","year":2012,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Residue (chemistry); Pegmatite; Caesium; Tailings; Leaching (pedology); Muscovite","score_opus":0.0075868263587462485,"score_gpt":0.2032540591313855,"score_spread":0.19566723277263925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067662905","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9928192,0.00011668424,0.00006793615,0.00006903899,0.0004166511,0.000370762,0.0006437878,0.00001495871,0.005480974],"genre_scores_gemma":[0.98811364,0.00011606952,0.0014028524,0.000039728104,0.00009815233,0.0000011658682,0.008433453,0.000037219103,0.0017577371],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984537,0.00010042453,0.00032640374,0.00030830698,0.00048220486,0.00032896997],"domain_scores_gemma":[0.99800783,0.000037564285,0.0009582366,0.00065152545,0.00023037576,0.000114437564],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002296589,0.00032452928,0.00042818175,0.00010421125,0.00015856135,0.000011034994,0.0005797452,0.00038828875,0.000053260243],"category_scores_gemma":[0.00007242578,0.0004046539,0.0001521521,0.00009690296,0.000061278115,0.000019215904,0.00015466702,0.00032950213,0.00001806554],"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":[0.0045317295,0.00084347394,0.80835694,0.00582042,0.0020920264,0.00003481831,0.0022746597,0.0012729949,0.08911257,0.00017916261,0.08223035,0.0032508732],"study_design_scores_gemma":[0.0013820418,0.00038382984,0.90723115,0.00030866175,0.00032925335,0.0000020533284,0.016901072,0.00036688813,0.026980314,0.000022002529,0.045366313,0.0007264052],"about_ca_topic_score_codex":0.3555582,"about_ca_topic_score_gemma":0.9976703,"teacher_disagreement_score":0.64211214,"about_ca_system_score_codex":0.00012930906,"about_ca_system_score_gemma":0.00035598368,"threshold_uncertainty_score":0.99984056},"labels":[],"label_agreement":null},{"id":"W7067667478","doi":"","title":"/123/ Mr Bunga Goes to Washington (2) ft. Nicholas Kiersey","year":2020,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Disappointment; George (robot); Expansive; Decorum; Presidential election","score_opus":0.0043690208808000374,"score_gpt":0.19599835137643803,"score_spread":0.191629330495638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067667478","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":[0.0001878234,0.00022374258,0.000008740738,0.00046487484,0.0003616644,0.00053590385,0.00020657768,0.00013728825,0.99787337],"genre_scores_gemma":[0.0008238835,0.00022544863,0.0069679427,0.0019267104,0.00040161188,0.000019088251,0.0008647118,0.0002019862,0.9885686],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99807453,0.000082202554,0.0007217685,0.00030659794,0.0004299062,0.00038500034],"domain_scores_gemma":[0.99837154,0.000031826145,0.00060229766,0.00060759275,0.00011968728,0.0002670513],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00022909707,0.00047208098,0.00045374595,0.00008128202,0.00007285622,0.00008261455,0.00063533784,0.0006440057,0.0746769],"category_scores_gemma":[0.0005504045,0.0004737032,0.00021236781,0.0000143564685,0.00009597949,4.7829964e-8,0.00034130513,0.00041479676,0.01347242],"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":[0.000101038364,0.000024881036,0.000011442105,0.00049167254,0.00010742765,0.0000049522255,0.00016586728,0.00043726902,0.000045081473,0.000013865263,0.9974316,0.0011649434],"study_design_scores_gemma":[0.00042910792,0.00042114255,0.000009468664,0.00016608369,0.0000508137,0.000037325975,0.00008631333,0.000039020473,0.0002903072,0.0000015210672,0.99795985,0.0005090602],"about_ca_topic_score_codex":0.001055718,"about_ca_topic_score_gemma":0.0006263882,"teacher_disagreement_score":0.061204482,"about_ca_system_score_codex":0.000029519217,"about_ca_system_score_gemma":0.0000554817,"threshold_uncertainty_score":0.9997715},"labels":[],"label_agreement":null},{"id":"W7067704070","doi":"","title":"Norton Live Support and Help? *+*18(00-750-6584 @@ Norton support phone number","year":2016,"lang":"en","type":"other","venue":"OSF Preprints (OSF Preprints)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Phone; The Internet; Mobile phone; Service (business); Mobile phone tracking; Smart phone","score_opus":0.007284182936529833,"score_gpt":0.26042911960268433,"score_spread":0.2531449366661545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067704070","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":[0.005510808,0.000006513049,0.00090615085,0.00012743405,0.00057912857,0.0010137552,0.00020472019,0.0001769469,0.99147457],"genre_scores_gemma":[0.008076196,0.0011263124,0.0023699484,0.0004149931,0.0006107641,0.00016683037,0.00076007255,0.0005280002,0.9859469],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99509454,0.00031520982,0.000864189,0.0023781622,0.00054639555,0.0008015112],"domain_scores_gemma":[0.9943827,0.00008249699,0.00085189973,0.0041009556,0.00015320077,0.00042878123],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017969282,0.00085979933,0.00078457425,0.00018385565,0.00014039739,0.00011760228,0.0011999533,0.0012461799,0.79217035],"category_scores_gemma":[0.00088926795,0.00083458726,0.00031056348,0.00009958386,0.00039654013,0.000020407062,0.0025460976,0.0006964609,0.7438432],"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":[0.00014345198,0.00018621303,0.043590255,0.00042581983,0.00053535076,0.000042435397,0.00034857358,0.000011808424,0.0052164462,0.0000779654,0.94069606,0.00872561],"study_design_scores_gemma":[0.0009712473,0.00000831366,0.0021085504,0.00015746744,0.0001230572,0.0002464942,0.000050518796,0.000030290534,0.006883245,0.00008232448,0.98836625,0.0009722577],"about_ca_topic_score_codex":0.0003254022,"about_ca_topic_score_gemma":0.0002232963,"teacher_disagreement_score":0.048327148,"about_ca_system_score_codex":0.00009822076,"about_ca_system_score_gemma":0.00033077996,"threshold_uncertainty_score":0.9994105},"labels":[],"label_agreement":null},{"id":"W7067712185","doi":"","title":"Montréal en 1919 : industries, travail et espaces résidentiels","year":2020,"lang":"fr","type":"other","venue":"Archipelago (Université du Québec à Montréal)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Dominion; Context (archaeology); Carpentry","score_opus":0.003989816862985182,"score_gpt":0.17668273775744675,"score_spread":0.17269292089446156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067712185","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56139994,0.08396093,0.015210433,0.0555642,0.00178303,0.0024296807,0.0009227778,0.0004785675,0.27825046],"genre_scores_gemma":[0.5061167,0.020237178,0.00613751,0.003990283,0.0019099144,0.000028257084,0.0014863062,0.0008419396,0.45925194],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964866,0.00061311206,0.000593709,0.00094694446,0.0005364511,0.00082320685],"domain_scores_gemma":[0.99741834,0.0001996361,0.00068645563,0.0009981148,0.000105152234,0.00059229],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00031883857,0.0010154231,0.0008719117,0.00028574234,0.00039401048,0.00013299807,0.0012919165,0.001222158,0.0027987307],"category_scores_gemma":[0.000489478,0.0011279747,0.00046761436,0.0003851134,0.0004984007,0.000038255086,0.0012578341,0.0015525947,0.0012008438],"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":[0.0010754116,0.0005398003,0.010020824,0.000891044,0.0034646338,0.00093390874,0.19862482,0.0029508208,0.005332578,0.0061352984,0.50481135,0.2652195],"study_design_scores_gemma":[0.0016587304,0.00072242785,0.0045380127,0.00017931595,0.0004076261,0.00015819419,0.015404361,0.0024583987,0.00028876093,0.00004426597,0.9729862,0.0011537094],"about_ca_topic_score_codex":0.27835754,"about_ca_topic_score_gemma":0.55914587,"teacher_disagreement_score":0.46817484,"about_ca_system_score_codex":0.00026702535,"about_ca_system_score_gemma":0.001500126,"threshold_uncertainty_score":0.9995768},"labels":[],"label_agreement":null},{"id":"W7067733984","doi":"","title":"Négociations collectives du secteur public au Québec (2015) : enjeux, stratégies et facteurs associés au pouvoir de négociation de la partie syndicale","year":2019,"lang":"fr","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Public policy; Public sector; Public discourse","score_opus":0.00826766732136471,"score_gpt":0.2742841732607837,"score_spread":0.266016505939419,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067733984","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15377825,0.00092932885,0.028434753,0.013990083,0.00075137144,0.0009894869,0.00037526237,0.00018954066,0.8005619],"genre_scores_gemma":[0.70097065,0.00066418335,0.003563009,0.0010554583,0.0006826871,0.000085101005,0.0008393499,0.00022049886,0.29191905],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99589616,0.0014543566,0.00065456284,0.00055594405,0.00039618093,0.001042778],"domain_scores_gemma":[0.9973002,0.0006519489,0.00083673286,0.0006080815,0.0002717444,0.00033130837],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014982455,0.0006409129,0.00057368673,0.00022388627,0.00043096306,0.0003603381,0.00057422207,0.0017362094,0.0020347529],"category_scores_gemma":[0.0046873847,0.0006491652,0.00034260433,0.00026636652,0.00035395398,0.000032203363,0.00027696174,0.00087770645,0.00030985833],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005796988,0.0007553395,0.82006836,0.0006405532,0.0018493318,0.000008306468,0.010334795,0.0016432626,0.00536071,0.026216812,0.12788244,0.0051821494],"study_design_scores_gemma":[0.0010142656,0.0004058958,0.2469375,0.000104736035,0.00020030147,0.000052724703,0.0014356376,0.0026192637,0.0009826254,0.0002268858,0.74509084,0.000929316],"about_ca_topic_score_codex":0.02262318,"about_ca_topic_score_gemma":0.11408882,"teacher_disagreement_score":0.6172084,"about_ca_system_score_codex":0.002095709,"about_ca_system_score_gemma":0.012901224,"threshold_uncertainty_score":0.99959594},"labels":[],"label_agreement":null},{"id":"W7067734747","doi":"","title":"Martyr for Mental Health John R. Seeley and the Forest Hill Village Project, 1948-1956 by Paul Roberts Bentley","year":2013,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mental health; Government (linguistics); Genius; Mental illness; Martyr; Biography","score_opus":0.003186828605974363,"score_gpt":0.19591057087535957,"score_spread":0.1927237422693852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067734747","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":[0.00009696913,0.0017491608,0.000012508353,0.0010743296,0.00021980266,0.0022040138,0.00077222247,0.000049419094,0.99382156],"genre_scores_gemma":[0.0005169138,0.0018305585,0.0017898888,0.0013917573,0.00019528884,0.00010116869,0.0032683078,0.00013184312,0.9907743],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982832,0.00013003459,0.0007044755,0.00023306833,0.00027210327,0.00037709414],"domain_scores_gemma":[0.9984248,0.000063393505,0.00088366505,0.00042569952,0.000090794114,0.00011163831],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00042862236,0.00039133898,0.00043685574,0.00004566255,0.00015378062,0.00008283501,0.00032018923,0.0003913056,0.010253524],"category_scores_gemma":[0.00016609159,0.00029772703,0.00016705884,0.0000065527693,0.00024320438,8.628024e-8,0.00018669714,0.00020975206,0.00031211253],"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":[0.00014973948,0.0000242896,0.000005007366,0.0006007198,0.00009755309,3.025341e-7,0.00015353214,0.00003613986,0.0000031425823,0.000028310229,0.997474,0.0014272635],"study_design_scores_gemma":[0.0016303789,0.00033772577,0.0000030646847,0.00012113591,0.000029398314,0.00007456692,0.0001026445,0.0005364474,0.000020917414,0.0000041638696,0.99682224,0.00031733868],"about_ca_topic_score_codex":0.004015242,"about_ca_topic_score_gemma":0.0017813778,"teacher_disagreement_score":0.009941412,"about_ca_system_score_codex":0.000027214404,"about_ca_system_score_gemma":0.00005645621,"threshold_uncertainty_score":0.9999475},"labels":[],"label_agreement":null},{"id":"W7067737442","doi":"","title":"Neo-‐Colonial Criminology: Quantifying Silence","year":2014,"lang":"en","type":"article","venue":"Digital Scholarship - Texas Southern University (Texas Southern University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Elite; Indigenous; Mainstream; Silence; Subject (documents); Criminal justice; State (computer science); Fourth World","score_opus":0.025770937274586122,"score_gpt":0.22484765409873328,"score_spread":0.19907671682414715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067737442","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96547496,0.000035686044,0.004695056,0.00016249178,0.00016717515,0.0002516916,0.0007294376,0.00021743345,0.028266089],"genre_scores_gemma":[0.9772434,0.000016698465,0.00081446214,0.00018233615,0.00017164001,1.02594065e-7,0.0004581307,0.000065832646,0.021047361],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974028,0.00031836945,0.00027719114,0.0007999595,0.0003992396,0.0008024478],"domain_scores_gemma":[0.9980866,0.000093373834,0.00034340483,0.0008504518,0.0002350503,0.00039117364],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038364725,0.0005094913,0.00038362652,0.00036863773,0.00052632764,0.00024222065,0.0015044643,0.00058886973,0.00011554053],"category_scores_gemma":[0.00034178825,0.0005985895,0.0003446584,0.00043819172,0.0004827557,0.00013481137,0.0008715435,0.0007267898,0.001376738],"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":[0.0021337317,0.0006186523,0.9553074,0.00025034152,0.0007739328,0.00032341373,0.004921376,0.0012529594,0.0064418367,0.011465813,0.0005203552,0.015990136],"study_design_scores_gemma":[0.0068689687,0.0015077922,0.028032653,0.0002369089,0.00048902957,0.00013472277,0.023648497,0.0014695976,0.0017344656,0.00073153095,0.93156844,0.0035773749],"about_ca_topic_score_codex":0.00016798441,"about_ca_topic_score_gemma":0.0001400167,"teacher_disagreement_score":0.9310481,"about_ca_system_score_codex":0.00016277075,"about_ca_system_score_gemma":0.00014236801,"threshold_uncertainty_score":0.99964654},"labels":[],"label_agreement":null},{"id":"W7067742510","doi":"","title":"New World Next Week: Episode149 - Korean War, Conspiracy Poll, Phone Tattoo","year":2013,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Phone; Ridiculous; Peninsula; Monarchy; Mobile phone; Sensationalism; Newspaper","score_opus":0.006042602255247363,"score_gpt":0.19720470565028975,"score_spread":0.1911621033950424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067742510","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":[0.000057128487,0.0010312177,0.000023275723,0.00026433368,0.0004141935,0.00059504935,0.00012440232,0.00013680107,0.9973536],"genre_scores_gemma":[0.00030485116,0.00062702614,0.011548928,0.0010099567,0.00048172957,0.000017654416,0.001144254,0.00022639912,0.9846392],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99774,0.000086862645,0.0009401219,0.00030415156,0.00043125486,0.0004976664],"domain_scores_gemma":[0.9976793,0.000049457914,0.001035164,0.00080948777,0.00014862117,0.00027798628],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00020354139,0.0005852836,0.00055571983,0.00014725006,0.00008161489,0.0000914802,0.0006244916,0.0006330541,0.344981],"category_scores_gemma":[0.00021606803,0.00057718385,0.00025523413,0.000018222618,0.00018842875,1.2199348e-7,0.00027010698,0.00044082044,0.023048995],"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":[0.00006413362,0.000043356235,0.00001184139,0.00038311546,0.00013993487,0.000004456514,0.000069181755,0.00017893713,0.000014420849,0.00003757605,0.99317974,0.005873293],"study_design_scores_gemma":[0.0008775448,0.00025073995,0.000010248885,0.00019051494,0.00006486497,0.00007107731,0.00005841172,0.00008301463,0.00016923818,0.00000612929,0.9976051,0.0006131366],"about_ca_topic_score_codex":0.007967517,"about_ca_topic_score_gemma":0.0018363264,"teacher_disagreement_score":0.32193202,"about_ca_system_score_codex":0.000032037777,"about_ca_system_score_gemma":0.00010873981,"threshold_uncertainty_score":0.99966794},"labels":[],"label_agreement":null},{"id":"W7067778267","doi":"","title":"Musculoskeletal radiology special issue: Guest editors","year":2001,"lang":"en","type":"other","venue":"National University of Singapore","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medical imaging; MEDLINE; Feature (linguistics); Computed tomography","score_opus":0.004504101940510873,"score_gpt":0.22903763415149528,"score_spread":0.2245335322109844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067778267","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":[0.00053592364,0.00007886351,0.0002530259,0.00018027793,0.0023771399,0.00011171255,0.00015391473,0.000027282358,0.99628186],"genre_scores_gemma":[0.00086422043,0.00031575642,0.0048840116,0.000084966734,0.08270726,1.7064419e-7,0.0034247297,0.00012522207,0.90759367],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992656,0.000037321388,0.00011015248,0.00019305329,0.0002654155,0.0001284228],"domain_scores_gemma":[0.99941534,0.0000113634715,0.0002569169,0.0001461835,0.00012273733,0.00004747571],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00010112722,0.0001516701,0.00017784601,0.00015941325,0.000056565583,0.000004052997,0.0002623673,0.00048764708,0.0041232053],"category_scores_gemma":[0.00009586387,0.000183441,0.0001163911,0.00007592686,0.00021851802,0.0000026544128,0.00010314416,0.00017022065,0.000090705245],"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":[0.000016044194,0.000028648594,0.0005459245,0.00004430125,0.00008209463,0.0000049586242,0.000024329216,0.000023437391,0.0001567237,0.00011484655,0.9982533,0.00070541695],"study_design_scores_gemma":[0.0003643911,0.000089647954,0.00017636358,0.000025776957,0.000024215104,0.00001797936,0.00007525364,0.000019575129,0.00005242568,0.000011764881,0.998972,0.00017059338],"about_ca_topic_score_codex":0.00010599475,"about_ca_topic_score_gemma":0.000096850985,"teacher_disagreement_score":0.0886882,"about_ca_system_score_codex":0.00003515088,"about_ca_system_score_gemma":0.00013843545,"threshold_uncertainty_score":0.9967872},"labels":[],"label_agreement":null},{"id":"W7067834078","doi":"","title":"2025 Milk Calendar Digital Download ONTARIO","year":2024,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; The Internet; Range (aeronautics); Thursday","score_opus":0.0038814830617278262,"score_gpt":0.18913221480683096,"score_spread":0.18525073174510312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067834078","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":[0.00006861898,0.0007266753,0.0000015998716,0.00008391643,0.00044982525,0.00030653318,0.0012033522,0.000104248364,0.99705523],"genre_scores_gemma":[0.00028084524,0.00014321641,0.00085745926,0.000267193,0.00016884228,0.000011333185,0.0016871378,0.00012226975,0.9964617],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99848145,0.000025064965,0.0006067826,0.0002467218,0.00033621446,0.0003037653],"domain_scores_gemma":[0.9988862,0.000014671359,0.00038455703,0.0005075274,0.00008978598,0.00011722],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00012685498,0.00040434778,0.00034163235,0.000074328025,0.0000340741,0.000080928236,0.00036497274,0.00060347945,0.18381782],"category_scores_gemma":[0.000106657164,0.0003887042,0.00023360446,0.0000066184816,0.0001326421,3.583689e-8,0.00023310285,0.00040602247,0.035721134],"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":[0.00004779444,0.000023684452,0.000010592196,0.00062681024,0.00014284046,0.000009734821,0.00011676464,0.000055260432,0.0000019150862,0.0000061507735,0.99790424,0.0010542372],"study_design_scores_gemma":[0.00030811594,0.00020612027,0.0000033813785,0.00021137437,0.000059033777,0.000060429502,0.000037731374,0.000007979253,0.000035901852,0.000006763699,0.998657,0.00040618016],"about_ca_topic_score_codex":0.012998008,"about_ca_topic_score_gemma":0.016685834,"teacher_disagreement_score":0.14809668,"about_ca_system_score_codex":0.000048561644,"about_ca_system_score_gemma":0.00010115286,"threshold_uncertainty_score":0.9998565},"labels":[],"label_agreement":null},{"id":"W7067930843","doi":"","title":"+++1 888 879 0163 Norton antivirus tech support phone number Norton 360 customer service number","year":2016,"lang":"en","type":"other","venue":"OSF Preprints (OSF Preprints)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Phone; The Internet; Service (business); Mobile phone; Smart phone; Internet appliance","score_opus":0.007138034622868587,"score_gpt":0.26691313273768724,"score_spread":0.25977509811481864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067930843","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":[0.0059951437,0.0000031090833,0.0013072991,0.00018536804,0.0007907049,0.0010667357,0.00021600246,0.00028741034,0.99014825],"genre_scores_gemma":[0.007015286,0.000497135,0.0026591127,0.0007890293,0.0006911859,0.00021603378,0.0007376119,0.00071757066,0.98667705],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943901,0.00042334356,0.0010128634,0.0024558448,0.00073706574,0.0009807894],"domain_scores_gemma":[0.99300563,0.00008397251,0.0010269384,0.005246291,0.0002641271,0.00037301183],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018657035,0.0010190206,0.0008623995,0.00018923139,0.0001685324,0.00012586913,0.0019142689,0.0016191844,0.82094777],"category_scores_gemma":[0.0006290417,0.0009989535,0.00042104124,0.00027187634,0.0002702715,0.000028225944,0.002686761,0.00095111504,0.9603614],"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":[0.00016117151,0.00030064888,0.0389563,0.00055172475,0.0006270205,0.000034949077,0.00021600889,0.00003183239,0.013168442,0.00008625156,0.9400945,0.0057711643],"study_design_scores_gemma":[0.00096948777,0.0000017986606,0.0011496574,0.00021804708,0.00014357026,0.00019429672,0.000027123415,0.000039547587,0.017412031,0.000058816477,0.97863454,0.0011510649],"about_ca_topic_score_codex":0.0007670484,"about_ca_topic_score_gemma":0.0005342051,"teacher_disagreement_score":0.13941368,"about_ca_system_score_codex":0.00014953961,"about_ca_system_score_gemma":0.00038715257,"threshold_uncertainty_score":0.99967694},"labels":[],"label_agreement":null},{"id":"W7068028953","doi":"","title":"NYS Poet Jean Valentine to read works at Alfred University, November 04, 2008","year":2008,"lang":"en","type":"other","venue":"Alfred University Research and Archives (AURA) (Alfred University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"New York Foundation for the Arts; York University; Yale University; National Endowment for the Arts","keywords":"Poetry; Consciousness; Subliminal stimuli; Camouflage","score_opus":0.016499977071289994,"score_gpt":0.24117044842755253,"score_spread":0.22467047135626253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068028953","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":[0.020780493,0.00071481505,0.002976475,0.0015112718,0.00032205577,0.0014672304,0.0036144564,0.00032817753,0.968285],"genre_scores_gemma":[0.003124058,0.010985263,0.005068837,0.000081149126,0.0003052628,3.7490813e-7,0.0034957596,0.0002538635,0.9766854],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99538875,0.00072240364,0.00027888623,0.0014158848,0.0007254369,0.0014686548],"domain_scores_gemma":[0.9966673,0.00030696052,0.00032000936,0.001392704,0.00017563983,0.001137341],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00022141922,0.0007925442,0.0007333553,0.002632802,0.0013541841,0.000080769685,0.0020452845,0.0008233066,0.0008962645],"category_scores_gemma":[0.00017184553,0.0009912215,0.0003348119,0.0014821148,0.002009518,0.00006381471,0.00397352,0.0012779296,0.00017399143],"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":[0.0034064124,0.00039876645,0.0026437894,0.00030757705,0.0011379911,0.001578464,0.00095073273,0.00017274388,0.00801822,0.0028186599,0.9752362,0.0033304857],"study_design_scores_gemma":[0.0031160424,0.00076897716,0.00058218045,0.00037004167,0.00011640217,0.00006763571,0.002382849,0.00018403969,0.00035760898,0.00001970904,0.9909993,0.0010352553],"about_ca_topic_score_codex":0.0024786987,"about_ca_topic_score_gemma":0.0046036337,"teacher_disagreement_score":0.017656434,"about_ca_system_score_codex":0.00020768067,"about_ca_system_score_gemma":0.00040519977,"threshold_uncertainty_score":0.99994594},"labels":[],"label_agreement":null},{"id":"W7068070391","doi":"","title":"Les auteurs","year":2017,"lang":"fr","type":"book-chapter","venue":"OpenEdition (OpenEdition)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Identity (music); Focus (optics); Subject (documents); Term (time)","score_opus":0.02244075860806971,"score_gpt":0.2729645628610384,"score_spread":0.25052380425296866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068070391","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":[0.0006053143,0.00178567,0.0050626583,0.019198876,0.00557589,0.0011350447,0.0017858803,0.000096922944,0.96475375],"genre_scores_gemma":[0.1563045,0.005323894,0.011098276,0.019419752,0.006564339,0.00028608632,0.032088637,0.0004117706,0.7685028],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.995919,0.00016639773,0.0011987408,0.0011152602,0.0008152782,0.0007853278],"domain_scores_gemma":[0.9950519,0.00009302672,0.0016697622,0.0020558313,0.0006534424,0.00047604626],"candidate_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00072158634,0.0011398122,0.00085681194,0.00021518942,0.001646465,0.00061989616,0.0015544313,0.0017956657,0.01264588],"category_scores_gemma":[0.000522387,0.0012628052,0.0006130641,0.000035214805,0.0011051889,0.0006396621,0.00087591086,0.0011710917,0.0053631854],"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":[0.00019566904,0.00016920138,0.0002710372,0.0005479723,0.00058453146,0.00009924807,0.000049032627,0.0004075557,0.0013423448,0.8966852,0.038765512,0.060882695],"study_design_scores_gemma":[0.0011592929,0.00069727073,0.0037850405,0.0007135524,0.00028969676,0.00026020754,0.000028066439,0.00032764496,0.0023407815,0.0021524793,0.986803,0.0014429636],"about_ca_topic_score_codex":0.00013584744,"about_ca_topic_score_gemma":0.0011428144,"teacher_disagreement_score":0.9480375,"about_ca_system_score_codex":0.00018657101,"about_ca_system_score_gemma":0.00034070507,"threshold_uncertainty_score":0.9996533},"labels":[],"label_agreement":null},{"id":"W7068080071","doi":"","title":"In the Name of Energy Sovereignty","year":2022,"lang":"en","type":"article","venue":"eYLS (Yale Law School)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sovereignty; Energy policy; Government (linguistics); Subsidy; Energy security; Energy (signal processing); Treaty; Renewable energy; Environmental impact of the energy industry; Energy law","score_opus":0.006588224873594606,"score_gpt":0.23502683244607395,"score_spread":0.22843860757247933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068080071","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82357764,0.001301027,0.00045997312,0.0008694111,0.00035127677,0.0002180778,0.000073842166,0.000018190613,0.17313054],"genre_scores_gemma":[0.99498695,0.000026908243,0.00046256246,0.0031969934,0.000094551266,0.0000337721,0.00008158155,0.000011100223,0.0011055943],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99910593,0.00016424764,0.00021783671,0.00013133719,0.0002161264,0.00016450378],"domain_scores_gemma":[0.9994179,0.00002153778,0.00010162229,0.00040740013,0.000020062049,0.000031476877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003738486,0.00009119333,0.0001011924,0.000023053486,0.00010529502,0.000013363059,0.00043034615,0.00004929193,0.00064586656],"category_scores_gemma":[0.00006821214,0.00007504373,0.00006610766,0.000102297665,0.00005642,0.00000435135,0.00024306877,0.00021125817,0.000009669112],"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":[0.00032017016,0.00053432956,0.017210204,0.00012629536,0.00013650823,0.000034373606,0.0008499467,0.013695423,0.044982012,0.8506881,0.06907552,0.0023471324],"study_design_scores_gemma":[0.0005727769,0.00033172758,0.0010349356,0.0000047299022,0.0000081886055,0.000043339372,0.00033912135,0.0005017059,0.010520265,0.0028170676,0.983647,0.00017913041],"about_ca_topic_score_codex":0.0003052257,"about_ca_topic_score_gemma":0.000106134445,"teacher_disagreement_score":0.9145715,"about_ca_system_score_codex":0.000015246403,"about_ca_system_score_gemma":0.000045982433,"threshold_uncertainty_score":0.7071786},"labels":[],"label_agreement":null},{"id":"W7068092177","doi":"","title":"The Sonika Album","year":2010,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nothing; Feeling; Lyrics; Globe; Musical","score_opus":0.002837649350459473,"score_gpt":0.18693509022252686,"score_spread":0.1840974408720674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068092177","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":[0.00004017924,0.00041199266,0.0000017538896,0.00019520654,0.00046013523,0.00029854104,0.000064208616,0.000061012557,0.99846697],"genre_scores_gemma":[0.00021824779,0.0005512773,0.0017216777,0.00030885777,0.0003127266,0.000014064598,0.0003223809,0.00012331668,0.9964275],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987237,0.0000531675,0.00049107196,0.00014805127,0.0002912527,0.00029275662],"domain_scores_gemma":[0.99851483,0.00004498588,0.0005967952,0.0006477121,0.0001096079,0.00008604198],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00028291033,0.00029333337,0.0002232224,0.000029232056,0.00012459839,0.000067402674,0.00054259127,0.0006369455,0.070311844],"category_scores_gemma":[0.00029989975,0.00022726785,0.00015671704,0.0000042246056,0.0002172324,1.0381245e-8,0.00018329288,0.00043072802,0.004775099],"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":[0.000036952282,0.00001219394,0.0000042424062,0.00013542036,0.0000602525,0.000001117913,0.00002370917,0.000037960075,0.000007804923,0.00003528545,0.99625003,0.0033950473],"study_design_scores_gemma":[0.0002660478,0.0001235929,0.0000060808848,0.00004870988,0.000025877605,0.000049641567,0.000033336608,0.000025101173,0.00008807998,0.0000038298103,0.99906784,0.00026187647],"about_ca_topic_score_codex":0.00095869944,"about_ca_topic_score_gemma":0.0025775728,"teacher_disagreement_score":0.065536745,"about_ca_system_score_codex":0.000008947536,"about_ca_system_score_gemma":0.000043208725,"threshold_uncertainty_score":0.9959998},"labels":[],"label_agreement":null},{"id":"W7068159485","doi":"","title":"7 Must-Buy Nasdaq Stocks to Kick Off the First Quarter","year":2023,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Stock (firearms); Forecast period","score_opus":0.0051029926746909504,"score_gpt":0.24361079382159517,"score_spread":0.23850780114690423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068159485","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":[0.00019006245,0.00022840803,0.0018532563,0.0026353355,0.0007516327,0.00064812816,0.00007530137,0.00031193683,0.9933059],"genre_scores_gemma":[0.0008081764,0.00011234687,0.001101597,0.0034714474,0.0008949792,0.00006379478,0.00011648581,0.0006054905,0.9928257],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99897176,0.00002715538,0.00022149704,0.00029205045,0.00019124865,0.0002962615],"domain_scores_gemma":[0.99889475,0.000019587229,0.00012035403,0.00085616,0.000028169825,0.000080984864],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00015370268,0.00028667744,0.0001911384,0.000081796265,0.00007402189,0.00004663723,0.0005203387,0.00040739492,0.0013101911],"category_scores_gemma":[0.000103297454,0.00018923094,0.00012296111,0.000110201814,0.00005210751,8.5784785e-7,0.0002641176,0.00022421763,0.0019611267],"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":[0.000007004283,0.000009834196,0.00016784856,0.000036443485,0.000078478675,0.000001233751,0.00009093635,0.00004304386,0.000054902997,0.000060288978,0.99753654,0.0019134304],"study_design_scores_gemma":[0.00014792333,0.00014235184,0.00018538818,0.000043558328,0.000018008353,0.0000054998004,0.000083853665,0.00013342647,0.0001216935,0.0000032768203,0.9988349,0.00028011124],"about_ca_topic_score_codex":0.00017107188,"about_ca_topic_score_gemma":0.0051642684,"teacher_disagreement_score":0.004993196,"about_ca_system_score_codex":0.000012562796,"about_ca_system_score_gemma":0.000037573813,"threshold_uncertainty_score":0.99960274},"labels":[],"label_agreement":null},{"id":"W7068173273","doi":"","title":"Q&amp;A","year":2012,"lang":"en","type":"article","venue":"WBI Studies Repository","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Selection (genetic algorithm); Action (physics); Relation (database); Natural (archaeology)","score_opus":0.024880256688166204,"score_gpt":0.3225941779979605,"score_spread":0.2977139213097943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068173273","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9034152,0.013042608,0.00044757492,0.000092224225,0.0015041536,0.000111416615,0.0000016621038,0.000046425615,0.08133875],"genre_scores_gemma":[0.98302674,0.0002194291,0.0033421104,0.00029780492,0.0010639579,0.000016338468,0.000016794073,0.000015105262,0.012001703],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99936795,0.000038265633,0.00016198613,0.000100516896,0.00010258035,0.00022867405],"domain_scores_gemma":[0.9995079,0.000012961769,0.00007208751,0.0002909819,0.00005597678,0.00006007479],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001437047,0.00010615957,0.00010317195,0.000017673485,0.00014808685,0.000009277569,0.000098728204,0.00006599703,0.0000050256026],"category_scores_gemma":[0.00014877327,0.00009012139,0.00005605294,0.00003505972,0.0000802478,0.0000038302887,0.00017193466,0.00007743363,0.00006155127],"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":[0.000072367875,0.00019350465,0.35746485,0.00024283178,0.00091332104,0.0000035890919,0.0044019246,0.00010156895,0.35096723,0.0006726111,0.28071508,0.0042511174],"study_design_scores_gemma":[0.00017700682,0.000075905074,0.015374534,0.000011537371,0.000028459805,0.00007660928,0.0004159406,0.000009663881,0.033094123,0.000007811925,0.9505124,0.00021600856],"about_ca_topic_score_codex":0.000003678796,"about_ca_topic_score_gemma":0.0000021767999,"teacher_disagreement_score":0.6697973,"about_ca_system_score_codex":0.00001594482,"about_ca_system_score_gemma":0.000011445829,"threshold_uncertainty_score":0.36750436},"labels":[],"label_agreement":null},{"id":"W7068187691","doi":"","title":"New GPS Time Series Analysis and a Simplified Model to Compute an Accurate Seasonal Amplitude of Tropospheric Delay","year":2017,"lang":"en","type":"article","venue":"Scholarship@Western (Western University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Natural Resources Canada; Natural Sciences and Engineering Research Council of Canada; National Oceanic and Atmospheric Administration; New York State Department of Transportation; U.S. Department of Transportation","keywords":"Global Positioning System; Noise (video); Interferometric synthetic aperture radar; Zenith; Time series; Satellite geodesy; Geodetic datum; Data processing; Post-glacial rebound","score_opus":0.04312481052106654,"score_gpt":0.3199014061902114,"score_spread":0.27677659566914486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068187691","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8911863,0.000017111008,0.1083105,0.000110267225,0.000028461121,0.00014950405,0.00004976985,0.000026366688,0.000121754914],"genre_scores_gemma":[0.9866868,0.000021401105,0.008211124,0.00016133607,0.00005145341,4.600922e-7,0.00010843867,0.000025499232,0.004733432],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987064,0.00009875595,0.00023640133,0.00043396317,0.0002186139,0.000305879],"domain_scores_gemma":[0.9981874,0.000013604211,0.00032892445,0.00094138505,0.0001493916,0.00037928825],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002083378,0.00026509806,0.00036052507,0.00015371645,0.00030583845,0.00031491145,0.0009101605,0.00018597729,0.000012804665],"category_scores_gemma":[0.00005879386,0.00029014074,0.00013481342,0.00019168243,0.00011665813,0.00016688435,0.00077564776,0.00020136332,0.000017214488],"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":[0.00038616933,0.000043471166,0.9686388,0.000037556812,0.00048313555,0.000017179036,0.00027082665,0.011698219,0.01736604,0.00005753159,0.0000035208338,0.0009975567],"study_design_scores_gemma":[0.00091287814,0.00047528654,0.99106324,0.000031127536,0.00040737077,0.000021677537,0.000052085084,0.0010368959,0.0047107227,0.00004951668,0.00076343154,0.00047577245],"about_ca_topic_score_codex":0.000015693482,"about_ca_topic_score_gemma":0.00091367087,"teacher_disagreement_score":0.10009937,"about_ca_system_score_codex":0.000027888924,"about_ca_system_score_gemma":0.00011946644,"threshold_uncertainty_score":0.99995506},"labels":[],"label_agreement":null},{"id":"W7068233968","doi":"","title":"JumpTV","year":2005,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"The Internet; Selection (genetic algorithm); Internet access; Variety (cybernetics); Digital subscriber line; IPTV; Quality (philosophy); Interactive television","score_opus":0.003446665809099926,"score_gpt":0.19196519104602683,"score_spread":0.18851852523692691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068233968","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":[0.00003581639,0.00046943064,0.0000025778777,0.00008639212,0.00020893462,0.0002684515,0.00010714208,0.00008684683,0.9987344],"genre_scores_gemma":[0.0002572279,0.00041725123,0.0044509666,0.0004836265,0.00042378058,0.000009813788,0.00068739906,0.00014769116,0.9931222],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987089,0.00004449635,0.0005270401,0.00017091101,0.00028321447,0.0002654292],"domain_scores_gemma":[0.99874043,0.00001576716,0.0005544302,0.0005031307,0.00008902746,0.00009718214],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00015933569,0.00032145338,0.00029168456,0.000058368518,0.00004004143,0.000031060245,0.00036908616,0.00056764815,0.33623284],"category_scores_gemma":[0.00013983253,0.00032167492,0.00016386854,0.000004480001,0.00010954016,1.0960821e-8,0.00014744491,0.00023412022,0.011345297],"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":[0.00003581802,0.00002373252,0.000005985359,0.0002759838,0.000068779846,0.0000017108044,0.00002750703,0.00025134685,0.000003130245,0.000013642458,0.995902,0.00339038],"study_design_scores_gemma":[0.00037948543,0.00015391184,0.00000917346,0.0000938591,0.00003276359,0.000053196964,0.00002032001,0.000031811956,0.00005573272,8.300872e-7,0.9988311,0.0003378377],"about_ca_topic_score_codex":0.00083500246,"about_ca_topic_score_gemma":0.00070347096,"teacher_disagreement_score":0.32488754,"about_ca_system_score_codex":0.000015606212,"about_ca_system_score_gemma":0.000033249093,"threshold_uncertainty_score":0.9999235},"labels":[],"label_agreement":null},{"id":"W7068307178","doi":"","title":"Artchatpodcast 094","year":2013,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"George (robot); Photography; Publishing; Happening; Publication; Space (punctuation); Mindset","score_opus":0.0037572417536956043,"score_gpt":0.18537992935414174,"score_spread":0.18162268760044614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068307178","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":[0.00007370937,0.0003297111,0.0000045763118,0.00007891034,0.00026721891,0.00038702175,0.00009776969,0.00008830055,0.9986728],"genre_scores_gemma":[0.00032165274,0.0003059984,0.0033137572,0.0004195533,0.00027811548,0.000019466364,0.000740163,0.0001612248,0.9944401],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986218,0.000051724757,0.00055476144,0.00018564405,0.00029164966,0.00029439322],"domain_scores_gemma":[0.9985822,0.00001845316,0.0006172483,0.00055178464,0.000114521186,0.00011580311],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00014450849,0.00035348246,0.00032139188,0.000059603357,0.000044194134,0.000048636142,0.0003797936,0.00058886886,0.27559793],"category_scores_gemma":[0.00014597143,0.00034311434,0.00016182962,0.0000049423993,0.00012791202,1.7228624e-8,0.00017649686,0.00024543342,0.021426598],"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":[0.000023795943,0.000022933344,0.000006835271,0.00035414493,0.00007409757,0.0000018889328,0.00003204074,0.00012486798,0.000005398703,0.000026781901,0.9976102,0.0017170277],"study_design_scores_gemma":[0.00035126743,0.00018790006,0.0000081779535,0.000109376415,0.000028923461,0.000058760117,0.00003778889,0.00005940107,0.00005918364,0.000002058049,0.9987372,0.00035994573],"about_ca_topic_score_codex":0.0015187829,"about_ca_topic_score_gemma":0.0003345782,"teacher_disagreement_score":0.25417134,"about_ca_system_score_codex":0.000013886755,"about_ca_system_score_gemma":0.00003063635,"threshold_uncertainty_score":0.99990207},"labels":[],"label_agreement":null},{"id":"W7068339821","doi":"","title":"CANADA","year":2014,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.0026033567455160155,"score_gpt":0.17231578401343142,"score_spread":0.1697124272679154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068339821","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":[0.000028873535,0.00016886956,0.0000028562768,0.000098202414,0.00026620307,0.00019696266,0.0001373557,0.000038586488,0.99906206],"genre_scores_gemma":[0.00075266336,0.00009970773,0.001314264,0.00091795495,0.00022735818,0.0000066453567,0.0006883589,0.0001134985,0.99587953],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998826,0.000048457237,0.00044951204,0.0001424832,0.00029964888,0.00023385571],"domain_scores_gemma":[0.99883467,0.000019997055,0.0005134286,0.00044884323,0.00008660646,0.00009647885],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001363568,0.000272788,0.0002705505,0.000029604713,0.000036197333,0.000020834917,0.00033435808,0.00036655302,0.10245722],"category_scores_gemma":[0.00018214285,0.0002718004,0.00009057717,0.0000032458015,0.00006909822,4.9404703e-9,0.00011500934,0.00018570319,0.0017876909],"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":[0.000020981768,0.00000770269,0.0000068720087,0.00033221647,0.00005268988,0.0000018087359,0.000007467516,0.00025559164,0.0000013319885,0.000012195838,0.9986313,0.0006698442],"study_design_scores_gemma":[0.0002700603,0.000103571714,0.000008555078,0.00007649212,0.000022832543,0.000035153924,0.00001235195,0.000035792054,0.0000374197,7.199842e-7,0.9991055,0.0002915395],"about_ca_topic_score_codex":0.4895822,"about_ca_topic_score_gemma":0.5665276,"teacher_disagreement_score":0.100669526,"about_ca_system_score_codex":0.00002423676,"about_ca_system_score_gemma":0.00015420257,"threshold_uncertainty_score":0.9999734},"labels":[],"label_agreement":null},{"id":"W7068351442","doi":"","title":"Building Movements","year":2013,"lang":"en","type":"other","venue":"RMIT Research Repository (RMIT University Library)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Exhibition; General partnership; Politics; Work (physics); Leverage (statistics); Research council; Framing (construction)","score_opus":0.01182580031663647,"score_gpt":0.2589641097857735,"score_spread":0.24713830946913704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068351442","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":[0.005819022,0.00046136737,0.00038118087,0.00010992579,0.00027831295,0.0005535622,0.000032619188,0.00018817013,0.9921758],"genre_scores_gemma":[0.0018025797,0.00035718732,0.005819293,0.00006795945,0.00071500597,0.0000036645574,0.00020432661,0.0003216267,0.99070835],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975724,0.00040222777,0.00020593192,0.0005784993,0.00061511726,0.00062581495],"domain_scores_gemma":[0.99840975,0.000034300778,0.00019832033,0.0009875152,0.00007467312,0.00029546086],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017655134,0.00032296553,0.00026442352,0.00056094164,0.00030561298,0.00016993785,0.0012206053,0.0006716649,0.00095669634],"category_scores_gemma":[0.00006053664,0.00035107398,0.0001632559,0.00030657506,0.00028398377,0.00003417989,0.0013574746,0.00078133395,0.00031269895],"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":[0.0000327411,0.000055559514,0.0022987407,0.0001690868,0.00019151976,0.00008172297,0.000019238061,0.0000071754544,0.0053567127,0.001552632,0.98961705,0.0006178455],"study_design_scores_gemma":[0.00037058754,0.00017182413,0.0002861272,0.00013927663,0.000013182955,0.00000972463,0.00007085156,0.00013560452,0.008515271,0.00001697914,0.98991334,0.00035721215],"about_ca_topic_score_codex":0.00049662776,"about_ca_topic_score_gemma":0.000011363333,"teacher_disagreement_score":0.005438112,"about_ca_system_score_codex":0.00006109023,"about_ca_system_score_gemma":0.00029579847,"threshold_uncertainty_score":0.99995655},"labels":[],"label_agreement":null},{"id":"W7068368859","doi":"","title":"The Road to Apollo","year":2009,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Apollo; Marketing buzz; Excursion; Moon landing; Quarter (Canadian coin); Meteorite","score_opus":0.0032818773650518454,"score_gpt":0.19569205601560094,"score_spread":0.1924101786505491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068368859","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":[0.000037701277,0.00043660233,0.0000023021005,0.000374061,0.00022417598,0.00040189817,0.000053036492,0.000060414022,0.9984098],"genre_scores_gemma":[0.00023780829,0.00040330616,0.0018553046,0.0009753389,0.00024258805,0.000012459093,0.00021541542,0.000089467336,0.99596834],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986891,0.00005639609,0.00049909245,0.00015477583,0.00030234805,0.00029825227],"domain_scores_gemma":[0.99875265,0.000023499751,0.00041851753,0.0005910957,0.000097796066,0.00011643639],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00024786513,0.0002900644,0.00023481253,0.000032154177,0.000099966746,0.00006342246,0.0005181002,0.00038111047,0.030187512],"category_scores_gemma":[0.00027908004,0.00023018537,0.00014151653,0.0000068745403,0.000086478954,9.78477e-9,0.00014280612,0.00020891345,0.0067765024],"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":[0.000056415596,0.000012448005,0.0000015097015,0.00007704094,0.000046666002,0.0000011830609,0.00003493312,0.00021814638,0.0000034407647,0.000016923002,0.9877896,0.011741693],"study_design_scores_gemma":[0.00022802239,0.00027482826,0.000017274577,0.00007162049,0.000020397341,0.000030398529,0.00003489525,0.000016870677,0.000045701927,0.0000025359398,0.99898845,0.00026897943],"about_ca_topic_score_codex":0.0008368287,"about_ca_topic_score_gemma":0.0010325832,"teacher_disagreement_score":0.02341101,"about_ca_system_score_codex":0.000015749925,"about_ca_system_score_gemma":0.000033088632,"threshold_uncertainty_score":0.99399686},"labels":[],"label_agreement":null},{"id":"W7068375853","doi":"","title":"LGS 20131012 IM","year":2013,"lang":"fr","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Term (time); Context (archaeology); The Internet","score_opus":0.003485089971676244,"score_gpt":0.18247819499474738,"score_spread":0.17899310502307114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068375853","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":[0.000690517,0.0016184613,0.000008623745,0.00049582525,0.00076529925,0.000733275,0.00017499622,0.000057531994,0.99545544],"genre_scores_gemma":[0.0016686966,0.0012029785,0.005662119,0.00085247244,0.00048782787,0.000032450724,0.0007544127,0.00014432601,0.9891947],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971499,0.00016168579,0.0012670867,0.000328328,0.000463333,0.00062967744],"domain_scores_gemma":[0.99723047,0.00008197186,0.0011873422,0.0008522004,0.00037770672,0.00027031158],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00033301872,0.00068815064,0.00059795013,0.000077027566,0.00013808435,0.00011853083,0.00071934995,0.0012390022,0.7348897],"category_scores_gemma":[0.0004116034,0.00069718575,0.00036073753,0.00000936975,0.00040911857,7.360207e-8,0.00035824982,0.00057299255,0.09252389],"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":[0.00006930921,0.00007785361,0.000050097613,0.0017601133,0.00020300044,0.0000048743973,0.00017138002,0.00094892434,0.000015795824,0.00023062831,0.9888075,0.0076605077],"study_design_scores_gemma":[0.00071132916,0.00047733795,0.00008534724,0.0002862928,0.00011877443,0.00015902024,0.00010131151,0.00041164987,0.00013569121,0.000006361276,0.9967875,0.0007193811],"about_ca_topic_score_codex":0.002656504,"about_ca_topic_score_gemma":0.00045665877,"teacher_disagreement_score":0.6423658,"about_ca_system_score_codex":0.00006261554,"about_ca_system_score_gemma":0.000089273344,"threshold_uncertainty_score":0.99954796},"labels":[],"label_agreement":null},{"id":"W7068378832","doi":"","title":"The Lies We Tell","year":2020,"lang":"en","type":"dissertation","venue":"The Atrium (University of Guelph)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Narrative; Consciousness; Power (physics); Accident (philosophy); Meditation","score_opus":0.007734928674877252,"score_gpt":0.21785540581604992,"score_spread":0.21012047714117268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068378832","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7811821,0.0120315,0.0012011739,0.016819417,0.001799404,0.0011993053,0.00012843094,0.000113148744,0.18552549],"genre_scores_gemma":[0.9407815,0.0046803816,0.00054825575,0.000090000845,0.00019622577,2.9196784e-7,0.00080439204,0.000024788716,0.052874215],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99937344,0.000064175845,0.00011481365,0.00013960674,0.00016768787,0.00014026166],"domain_scores_gemma":[0.99913216,0.0000443764,0.00028274817,0.00041194903,0.00009059224,0.00003815717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015393815,0.00014258176,0.00014529913,0.000022833372,0.0003601529,0.000018655135,0.0008165367,0.00019249186,0.000037185964],"category_scores_gemma":[0.00008392146,0.00010705013,0.00017029325,0.00009210467,0.00013196957,0.0000032081916,0.00016145302,0.0002693673,0.000066080866],"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":[0.0027126467,0.00009061751,0.0007390919,0.0014049147,0.0015220484,0.000018197114,0.022121143,0.0004112081,0.6288545,0.004111324,0.30297184,0.035042472],"study_design_scores_gemma":[0.00030341477,0.00021230959,0.00873914,0.000037741684,0.00017682003,0.0000043908385,0.014900852,0.0005248647,0.0036440815,0.00012864276,0.9710811,0.00024668133],"about_ca_topic_score_codex":0.00006270307,"about_ca_topic_score_gemma":0.00026148252,"teacher_disagreement_score":0.66810924,"about_ca_system_score_codex":0.000008538473,"about_ca_system_score_gemma":0.00009173556,"threshold_uncertainty_score":0.43653777},"labels":[],"label_agreement":null},{"id":"W7068543469","doi":"","title":"Village-life.com","year":2002,"lang":"en","type":"other","venue":"CGSPace A Repository of Agricultural Research Outputs (Consultative Group for International Agricultural Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Raja; Government (linguistics); Tamil; Navy; Officer; Plan (archaeology); Position (finance); Fishing; Stress (linguistics); Loudspeaker","score_opus":0.034800653216270225,"score_gpt":0.3387025609561194,"score_spread":0.30390190773984915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068543469","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":[0.060943693,0.00779002,0.000493323,0.008450846,0.0034773273,0.008715918,0.0024066758,0.00036620183,0.907356],"genre_scores_gemma":[0.07225618,0.0011000916,0.0024517346,0.00004841474,0.00297363,0.00053176674,0.0031495627,0.00027412843,0.9172145],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9922286,0.0010929458,0.0009504574,0.0012153903,0.0031668586,0.0013457154],"domain_scores_gemma":[0.9904219,0.00087764754,0.00078183686,0.0006434131,0.00667785,0.0005973523],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018618043,0.00073226524,0.0007378509,0.0007279549,0.00065772585,0.00034864893,0.0021694633,0.0009203489,0.0002866942],"category_scores_gemma":[0.009820854,0.00046466122,0.000564227,0.0008732783,0.0014197218,0.000053811516,0.0011606488,0.001687418,0.00021141517],"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":[0.00020941692,0.00024567594,0.00015460017,0.00033055144,0.00075369625,0.00000784383,0.00048650184,0.000040286206,0.104437,0.0015630081,0.89127094,0.0005004812],"study_design_scores_gemma":[0.0016767585,0.001543251,0.010695551,0.00071000477,0.000045516386,0.00007530888,0.0035432584,0.000060856255,0.013657787,0.000049938408,0.96708214,0.00085964426],"about_ca_topic_score_codex":0.0005793547,"about_ca_topic_score_gemma":0.0002686334,"teacher_disagreement_score":0.090779215,"about_ca_system_score_codex":0.00036321665,"about_ca_system_score_gemma":0.00018441069,"threshold_uncertainty_score":0.99978054},"labels":[],"label_agreement":null},{"id":"W7068657348","doi":"","title":"","year":2024,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Human sexuality; Variety (cybernetics); Discipline; Politics; Lesbian; Human immunodeficiency virus (HIV)","score_opus":0.0038864138529168908,"score_gpt":0.25583684685846003,"score_spread":0.25195043300554315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068657348","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":[0.000056337263,0.0038943123,0.0033797217,0.000216942,0.0005856196,0.00031491948,0.00004909618,0.0004247713,0.99107826],"genre_scores_gemma":[0.00038313612,0.0003761141,0.01173291,0.00096436404,0.0013963259,0.0000360168,0.00060409907,0.0018115308,0.9826955],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985672,0.000035498386,0.00029134788,0.0005441181,0.00021260719,0.00034921957],"domain_scores_gemma":[0.9987707,0.000002522919,0.00015114556,0.00094235473,0.000017551307,0.00011570471],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001512544,0.000473926,0.0002787441,0.00019890093,0.000016922626,0.00008009323,0.00043132954,0.00083770277,0.0006601339],"category_scores_gemma":[0.00008379021,0.0003933478,0.00019705981,0.0000934935,0.00008651674,3.8684848e-7,0.00046990573,0.0003244246,0.00082970737],"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":[0.000008087388,0.000014023568,0.00009322577,0.0004382885,0.00024292116,0.000006055581,0.000020006637,0.000006688799,0.001766168,0.00041498756,0.99644905,0.0005405196],"study_design_scores_gemma":[0.00019380475,0.0001790646,0.0000073593897,0.00015183493,0.000050094048,0.00004277914,0.000030247787,0.000072897914,0.0011206239,0.000047341244,0.9975892,0.00051476376],"about_ca_topic_score_codex":0.00014744214,"about_ca_topic_score_gemma":0.0005142968,"teacher_disagreement_score":0.008382777,"about_ca_system_score_codex":0.0000071257127,"about_ca_system_score_gemma":0.000052028758,"threshold_uncertainty_score":0.99994826},"labels":[],"label_agreement":null},{"id":"W7068741219","doi":"","title":"Leaky Condo 2.0","year":2019,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Negotiation; Rhetoric; Process (computing); Narrative; Sustainability; Status quo; Agency (philosophy); Product (mathematics); Contingency; Foundation (evidence); Face (sociological concept)","score_opus":0.003408860032081901,"score_gpt":0.1692215091462147,"score_spread":0.1658126491141328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068741219","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9830172,0.00007939141,0.00040183438,0.000030723375,0.000100804406,0.00012776208,0.000040595074,0.000018073215,0.016183604],"genre_scores_gemma":[0.9913196,0.000055680415,0.0009813651,0.00008628578,0.00002284959,1.0364055e-7,0.00007173364,0.000009363902,0.0074530174],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99945545,0.000024331419,0.00007784579,0.00018394006,0.00011226953,0.00014618336],"domain_scores_gemma":[0.9994923,0.0000071384816,0.00008789497,0.00027732045,0.0000802777,0.000055063174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009874329,0.000029290311,0.00012455252,0.000014089691,0.000060967395,0.000029937251,0.00024330437,0.00010663099,0.00024494168],"category_scores_gemma":[0.000024611347,0.00011105735,0.000080999365,0.00006743476,0.000098349075,0.000008798911,0.00014872577,0.000084080704,0.00012534314],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000062128485,0.000188064,0.41587934,0.00038368275,0.00020604553,0.000043978045,0.00025622404,0.00027508612,0.0643834,0.000013796594,0.052206356,0.4661019],"study_design_scores_gemma":[0.00093387073,0.00018671363,0.970924,0.00003540467,0.000013026389,0.00005025786,0.0004113034,0.00038632154,0.000035269033,0.000024137213,0.02682674,0.00017296255],"about_ca_topic_score_codex":0.0075379503,"about_ca_topic_score_gemma":0.02071273,"teacher_disagreement_score":0.55504465,"about_ca_system_score_codex":0.000009583676,"about_ca_system_score_gemma":0.00004312733,"threshold_uncertainty_score":0.99907094},"labels":[],"label_agreement":null},{"id":"W7068751245","doi":"","title":"","year":2023,"lang":"en","type":"other","venue":"Directory of Open access Books (OAPEN Foundation)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Invisibility; Visibility; Air pollution; Natural (archaeology); Environmental pollution","score_opus":0.05049954590625032,"score_gpt":0.41211436077754204,"score_spread":0.3616148148712917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068751245","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":[0.0034934864,0.00016659425,0.0010829617,0.00016892239,0.0013668961,0.0027852808,0.000029706178,0.0004846349,0.99042153],"genre_scores_gemma":[0.008560707,0.0009561462,0.0034814447,0.0006241835,0.00074314454,0.0004911751,0.0034523385,0.0027580482,0.9789328],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963168,0.0002733123,0.0011528583,0.0010295014,0.0006588827,0.0005686826],"domain_scores_gemma":[0.9954098,0.000097806995,0.0021525458,0.0018900092,0.00023880372,0.00021103332],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009201984,0.0007949878,0.0010313414,0.00059062685,0.00022501615,0.0014866773,0.00677545,0.00042605863,0.0036886088],"category_scores_gemma":[0.0008303098,0.0008347785,0.00028428267,0.0003770279,0.00039536672,0.00012628724,0.0057654814,0.00039950272,0.00054767187],"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":[0.00092159456,0.00058954145,0.0854944,0.002281123,0.0040017967,0.000030007624,0.00031198366,0.000589935,0.013019723,0.011175249,0.57170117,0.3098835],"study_design_scores_gemma":[0.0011639049,0.0001410268,0.011001896,0.00043539822,0.00009205619,0.0000066546704,0.000034046712,0.00008252448,0.0042475094,0.00010416313,0.9817191,0.00097172265],"about_ca_topic_score_codex":0.0039404356,"about_ca_topic_score_gemma":0.00800636,"teacher_disagreement_score":0.41001797,"about_ca_system_score_codex":0.000068608526,"about_ca_system_score_gemma":0.0005333668,"threshold_uncertainty_score":0.99954987},"labels":[],"label_agreement":null},{"id":"W7068754931","doi":"","title":"","year":2022,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"University of Oxford; Associated Medical Services; Canada Council for the Arts; Alberta Health Services; Government of Alberta; Cumming School of Medicine, University of Calgary; University of Calgary; Government of Canada","keywords":"Outreach; Excellence; Context (archaeology); Health care; Indigenous; Community health","score_opus":0.0034227800711472646,"score_gpt":0.2323740084629772,"score_spread":0.22895122839182994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068754931","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":[0.0002806573,0.00067996955,0.0014726878,0.0001352805,0.0002725312,0.00041840418,0.00007303296,0.00023441247,0.996433],"genre_scores_gemma":[0.00028522857,0.0002554617,0.010417808,0.0021362812,0.0006042319,0.00010719774,0.003342344,0.001114343,0.9817371],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984302,0.00010738926,0.0002865831,0.00047875606,0.00032541706,0.00037168892],"domain_scores_gemma":[0.9983658,0.0000056753306,0.00032838777,0.001178353,0.000013392515,0.00010838185],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00020447222,0.00041988207,0.0002846444,0.00017487117,0.000097303964,0.00002899907,0.0007249859,0.00042533004,0.022240318],"category_scores_gemma":[0.00012740486,0.00040458422,0.0001733903,0.00010157203,0.000071127084,4.0754205e-7,0.0010617797,0.00037292662,0.000029651588],"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":[0.000019477287,0.00003603854,0.0029987777,0.000072691066,0.00015009097,0.000003381068,0.000018074465,0.00008525265,0.00089342816,0.00017410221,0.99491274,0.00063595327],"study_design_scores_gemma":[0.00046954825,0.00034064296,0.00008501293,0.000007616596,0.000021161457,0.000037875532,0.00009316723,0.000046350648,0.00025213676,0.0000046400305,0.9981108,0.00053110404],"about_ca_topic_score_codex":0.00021322758,"about_ca_topic_score_gemma":0.0005026964,"teacher_disagreement_score":0.022210667,"about_ca_system_score_codex":0.000017616803,"about_ca_system_score_gemma":0.00007732648,"threshold_uncertainty_score":0.9998406},"labels":[],"label_agreement":null},{"id":"W7068762735","doi":"","title":"Remerciements","year":2018,"lang":"fr","type":"book-chapter","venue":"OpenEdition (OpenEdition)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Subject (documents); Order (exchange); Maxim","score_opus":0.016166879416490188,"score_gpt":0.2570284186130328,"score_spread":0.24086153919654263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068762735","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":[0.0020248636,0.0011585837,0.006831461,0.01391836,0.006514078,0.0016066271,0.0017447725,0.00010763099,0.9660936],"genre_scores_gemma":[0.07618993,0.0047551296,0.024521438,0.07018801,0.011515363,0.00036381365,0.049876787,0.00052280916,0.7620667],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953728,0.00018120439,0.0014332272,0.0011783898,0.0009891299,0.00084530335],"domain_scores_gemma":[0.99585354,0.000066894885,0.0011796664,0.0015065033,0.00091004604,0.0004833186],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00084092055,0.0011012299,0.00075729727,0.00024062462,0.00078758795,0.00031548587,0.0010749431,0.0014624189,0.047600765],"category_scores_gemma":[0.0003274218,0.001232827,0.0005042876,0.00011404527,0.0009840736,0.0005372039,0.0008555237,0.00081463926,0.018213589],"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":[0.0005242192,0.00045805864,0.0003313122,0.00094692915,0.001349984,0.00009220855,0.00014454876,0.00027854944,0.0055571687,0.6869838,0.2824926,0.02084057],"study_design_scores_gemma":[0.001275735,0.0012448529,0.0011292935,0.0006372746,0.0002843786,0.00015970829,0.000046298293,0.00031763397,0.005140407,0.0021741146,0.98621076,0.001379544],"about_ca_topic_score_codex":0.000026988819,"about_ca_topic_score_gemma":0.00046637887,"teacher_disagreement_score":0.7037181,"about_ca_system_score_codex":0.00021880836,"about_ca_system_score_gemma":0.00032300115,"threshold_uncertainty_score":0.9998339},"labels":[],"label_agreement":null},{"id":"W7068783534","doi":"","title":"Cleveland, Ohio","year":2009,"lang":"en","type":"other","venue":"OhioLink ETD Center (Ohio Library and Information Network)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"George (robot); Quarter (Canadian coin); Period (music); Settlement (finance)","score_opus":0.004963350062164315,"score_gpt":0.20374006334956643,"score_spread":0.19877671328740212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068783534","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":[0.000024788955,0.00097402727,0.0017933962,0.00028823168,0.000514225,0.0003705338,0.00017270897,0.00019594283,0.99566615],"genre_scores_gemma":[0.0074556405,0.029345445,0.023989817,0.03453078,0.009116364,0.00007102708,0.04103842,0.0007574424,0.85369503],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99845546,0.00007666502,0.00057623495,0.00024069534,0.00018572484,0.00046521894],"domain_scores_gemma":[0.99879265,0.000011663054,0.00049702753,0.00049771485,0.000015229502,0.00018574632],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001133911,0.00044905324,0.00033734684,0.00016946728,0.000111498564,0.00020111968,0.00035202483,0.00070774084,0.0011131393],"category_scores_gemma":[0.000015346519,0.0004126103,0.00012717911,0.000147809,0.00007316362,0.00020400481,0.000276654,0.00040916674,0.00016459684],"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":[0.00006942955,0.00002180224,0.00024815593,0.00015854966,0.00008401035,0.000001124783,0.000038778602,0.00011677781,0.0000032153341,0.047149926,0.93612444,0.015983803],"study_design_scores_gemma":[0.0007533982,0.00015583131,0.00056368136,0.00022988261,0.000019957555,0.000033119566,0.0000023013456,0.00062297937,0.000033682445,0.00007956524,0.99703306,0.0004725574],"about_ca_topic_score_codex":8.484173e-8,"about_ca_topic_score_gemma":0.0000015196924,"teacher_disagreement_score":0.14197108,"about_ca_system_score_codex":0.000004423773,"about_ca_system_score_gemma":0.000059163816,"threshold_uncertainty_score":0.9998326},"labels":[],"label_agreement":null},{"id":"W7068792481","doi":"","title":"Galion, Ohio","year":2009,"lang":"en","type":"other","venue":"OhioLink ETD Center (Ohio Library and Information Network)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Poor relief; Poorhouse; New england","score_opus":0.0045210608742189875,"score_gpt":0.2034524057581705,"score_spread":0.1989313448839515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068792481","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":[0.000018117782,0.0011536889,0.001455516,0.00037953278,0.0005428306,0.0003802376,0.0001327736,0.00022336104,0.99571395],"genre_scores_gemma":[0.0062117386,0.031764545,0.017519435,0.03712083,0.009321652,0.00007309128,0.04002629,0.00076124974,0.85720116],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998394,0.00008364536,0.0006079392,0.00024815713,0.00019695098,0.00046929877],"domain_scores_gemma":[0.9987136,0.000010587543,0.000532974,0.0005334693,0.000018713727,0.00019063028],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00011972128,0.00046022912,0.00033727332,0.00019463932,0.00011325138,0.00021269023,0.00036167036,0.0007053838,0.0012413227],"category_scores_gemma":[0.000017165394,0.00042897245,0.00013153732,0.00017698263,0.00007885936,0.00022236833,0.00027285487,0.0003970364,0.00015816191],"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":[0.000054071097,0.000021469752,0.00016778668,0.000160082,0.00007376819,9.925847e-7,0.000038881586,0.00015349155,0.00000462201,0.046164572,0.9441658,0.008994442],"study_design_scores_gemma":[0.00064069376,0.00015282826,0.00038217276,0.00025249153,0.000020518808,0.000033287728,0.0000023616392,0.00068027485,0.000044813474,0.000074722986,0.99723876,0.00047707508],"about_ca_topic_score_codex":8.4882e-8,"about_ca_topic_score_gemma":0.0000011481428,"teacher_disagreement_score":0.13851278,"about_ca_system_score_codex":0.000004682498,"about_ca_system_score_gemma":0.00006113828,"threshold_uncertainty_score":0.9998162},"labels":[],"label_agreement":null},{"id":"W7068849174","doi":"","title":"After resettlement","year":2013,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Subject (documents); Cover (algebra); Photography; Narrative","score_opus":0.003607357326466888,"score_gpt":0.23837656659882678,"score_spread":0.2347692092723599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068849174","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":[0.00005398122,0.00046449286,0.0012308825,0.00008259843,0.00014746092,0.00018896608,0.000021927237,0.000041344298,0.99776834],"genre_scores_gemma":[0.00024545987,0.000120919336,0.007974173,0.0006892695,0.00041841995,0.000052679636,0.0003008531,0.00021330679,0.9899849],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99946815,0.00001606848,0.000113402035,0.00015365105,0.00009915219,0.00014959737],"domain_scores_gemma":[0.99944705,0.0000013191661,0.0000694561,0.00042508869,0.000012128862,0.00004496418],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000043037846,0.00015005968,0.00009466784,0.000046239496,0.000008389322,0.000018866098,0.00014747179,0.00025421177,0.021876656],"category_scores_gemma":[0.00001796499,0.000120412325,0.000049561255,0.0000181341,0.000028803795,3.153468e-7,0.0001466174,0.000086304826,0.0017557237],"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":[0.0000029598107,0.0000070042297,0.00022434161,0.000036294114,0.000036703797,5.1013166e-7,0.0000031624093,5.555531e-7,0.00014930444,0.00007875371,0.998639,0.00082144747],"study_design_scores_gemma":[0.000096695454,0.000049404647,0.00007186798,0.000018357514,0.0000064608384,0.0000019794693,0.0000042054285,0.000026278889,0.000300571,0.0000035342139,0.999255,0.00016565312],"about_ca_topic_score_codex":0.00005749654,"about_ca_topic_score_gemma":0.000055457764,"teacher_disagreement_score":0.02012093,"about_ca_system_score_codex":0.0000040101786,"about_ca_system_score_gemma":0.000016998816,"threshold_uncertainty_score":0.99902153},"labels":[],"label_agreement":null},{"id":"W7068858082","doi":"","title":"Toledo, Ohio","year":2009,"lang":"en","type":"other","venue":"OhioLink ETD Center (Ohio Library and Information Network)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Eagle; Orange (colour); Globe; Natural (archaeology)","score_opus":0.004684022224796671,"score_gpt":0.20427965951058435,"score_spread":0.1995956372857877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068858082","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":[0.000024556599,0.0011428022,0.0013271505,0.00030309163,0.0005526607,0.00039166436,0.00013729684,0.00022298389,0.99589777],"genre_scores_gemma":[0.00832637,0.02813003,0.021320181,0.039642844,0.010095522,0.0000838049,0.03951662,0.00083465123,0.85204995],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983936,0.00007849105,0.0005996273,0.00025158422,0.0001932765,0.00048343308],"domain_scores_gemma":[0.9987206,0.000011317899,0.0005171693,0.00054163794,0.000016295038,0.00019301362],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00011029049,0.00047010725,0.00035592285,0.00017569678,0.00011195822,0.00021524778,0.00037671614,0.0007161876,0.0012364378],"category_scores_gemma":[0.000016144813,0.00043904354,0.00013766895,0.00015844026,0.00007822111,0.00021755333,0.00029852963,0.00041398898,0.00016278763],"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":[0.000059236776,0.00002360329,0.0001861585,0.00017042473,0.00008105641,0.0000011628549,0.000037663867,0.00017726657,0.000004419935,0.053842146,0.93121743,0.014199456],"study_design_scores_gemma":[0.00067048427,0.000164861,0.00042686576,0.00025100663,0.00002119929,0.000031717955,0.0000024034628,0.000864997,0.00004108918,0.00006813302,0.9969693,0.00048798352],"about_ca_topic_score_codex":8.720326e-8,"about_ca_topic_score_gemma":0.0000013726974,"teacher_disagreement_score":0.14384782,"about_ca_system_score_codex":0.0000047853327,"about_ca_system_score_gemma":0.00006211355,"threshold_uncertainty_score":0.9998061},"labels":[],"label_agreement":null},{"id":"W7068873293","doi":"","title":"Muséomix 2014","year":2015,"lang":"fr","type":"other","venue":"OpenEdition (OpenEdition)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; Diafiltration; TSG101; Dysgeusia; Liquation; Fusible alloy; Hyporeflexia; Demotion","score_opus":0.008675477478086847,"score_gpt":0.24528846920362576,"score_spread":0.23661299172553893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068873293","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":[0.00043867817,0.0039052353,0.0049791285,0.015896693,0.0063186367,0.0013251312,0.001912358,0.0001217788,0.9651024],"genre_scores_gemma":[0.0084201405,0.0018606932,0.010650149,0.031632435,0.007408073,0.00035179305,0.036991015,0.00056325604,0.90212244],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957002,0.0004516433,0.0010834178,0.0010370712,0.00085167476,0.0008760314],"domain_scores_gemma":[0.9962051,0.00006475894,0.0009989787,0.0014029178,0.0006835159,0.00064470834],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009275042,0.0010166288,0.00081835425,0.00027785703,0.00035149988,0.00032908708,0.0010668595,0.0015771249,0.06819215],"category_scores_gemma":[0.0006061941,0.0010821051,0.00034251527,0.00027746212,0.0004778811,0.00037851487,0.00064548233,0.00083128776,0.031327832],"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":[0.00011384685,0.00025730464,0.00011046067,0.00032415966,0.00029909675,0.000028145529,0.00006509378,0.0004526806,0.0010099582,0.022653095,0.96850026,0.006185907],"study_design_scores_gemma":[0.0017151091,0.0007026981,0.00088466675,0.00035717056,0.00020938166,0.00016902422,0.00010340374,0.00052574236,0.0015058991,0.000352147,0.9922071,0.0012676395],"about_ca_topic_score_codex":0.00007861231,"about_ca_topic_score_gemma":0.0015320876,"teacher_disagreement_score":0.062979914,"about_ca_system_score_codex":0.000238397,"about_ca_system_score_gemma":0.00073558046,"threshold_uncertainty_score":0.999719},"labels":[],"label_agreement":null},{"id":"W7068880837","doi":"","title":"","year":2023,"lang":"en","type":"other","venue":"Directory of Open access Books (OAPEN Foundation)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Direktorat Riset dan Pengabdian Masyarakat; Natural Sciences and Engineering Research Council of Canada","keywords":"Propulsion; Diesel fuel; Thermal efficiency; Fuel efficiency; Efficient energy use; Nitrogen oxides; Carbon oxide; Energy consumption","score_opus":0.05049954590625032,"score_gpt":0.41211436077754204,"score_spread":0.3616148148712917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068880837","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":[0.0034934864,0.00016659425,0.0010829617,0.00016892239,0.0013668961,0.0027852808,0.000029706178,0.0004846349,0.99042153],"genre_scores_gemma":[0.008560707,0.0009561462,0.0034814447,0.0006241835,0.00074314454,0.0004911751,0.0034523385,0.0027580482,0.9789328],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963168,0.0002733123,0.0011528583,0.0010295014,0.0006588827,0.0005686826],"domain_scores_gemma":[0.9954098,0.000097806995,0.0021525458,0.0018900092,0.00023880372,0.00021103332],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009201984,0.0007949878,0.0010313414,0.00059062685,0.00022501615,0.0014866773,0.00677545,0.00042605863,0.0036886088],"category_scores_gemma":[0.0008303098,0.0008347785,0.00028428267,0.0003770279,0.00039536672,0.00012628724,0.0057654814,0.00039950272,0.00054767187],"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":[0.00092159456,0.00058954145,0.0854944,0.002281123,0.0040017967,0.000030007624,0.00031198366,0.000589935,0.013019723,0.011175249,0.57170117,0.3098835],"study_design_scores_gemma":[0.0011639049,0.0001410268,0.011001896,0.00043539822,0.00009205619,0.0000066546704,0.000034046712,0.00008252448,0.0042475094,0.00010416313,0.9817191,0.00097172265],"about_ca_topic_score_codex":0.0039404356,"about_ca_topic_score_gemma":0.00800636,"teacher_disagreement_score":0.41001797,"about_ca_system_score_codex":0.000068608526,"about_ca_system_score_gemma":0.0005333668,"threshold_uncertainty_score":0.99954987},"labels":[],"label_agreement":null},{"id":"W7068936849","doi":"","title":"","year":2023,"lang":"en","type":"other","venue":"Directory of Open access Books (OAPEN Foundation)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Poetics; Poetry; Meaning (existential); Hegemony; Cultural hegemony","score_opus":0.05049954590625032,"score_gpt":0.41211436077754204,"score_spread":0.3616148148712917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7068936849","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":[0.0034934864,0.00016659425,0.0010829617,0.00016892239,0.0013668961,0.0027852808,0.000029706178,0.0004846349,0.99042153],"genre_scores_gemma":[0.008560707,0.0009561462,0.0034814447,0.0006241835,0.00074314454,0.0004911751,0.0034523385,0.0027580482,0.9789328],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963168,0.0002733123,0.0011528583,0.0010295014,0.0006588827,0.0005686826],"domain_scores_gemma":[0.9954098,0.000097806995,0.0021525458,0.0018900092,0.00023880372,0.00021103332],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009201984,0.0007949878,0.0010313414,0.00059062685,0.00022501615,0.0014866773,0.00677545,0.00042605863,0.0036886088],"category_scores_gemma":[0.0008303098,0.0008347785,0.00028428267,0.0003770279,0.00039536672,0.00012628724,0.0057654814,0.00039950272,0.00054767187],"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":[0.00092159456,0.00058954145,0.0854944,0.002281123,0.0040017967,0.000030007624,0.00031198366,0.000589935,0.013019723,0.011175249,0.57170117,0.3098835],"study_design_scores_gemma":[0.0011639049,0.0001410268,0.011001896,0.00043539822,0.00009205619,0.0000066546704,0.000034046712,0.00008252448,0.0042475094,0.00010416313,0.9817191,0.00097172265],"about_ca_topic_score_codex":0.0039404356,"about_ca_topic_score_gemma":0.00800636,"teacher_disagreement_score":0.41001797,"about_ca_system_score_codex":0.000068608526,"about_ca_system_score_gemma":0.0005333668,"threshold_uncertainty_score":0.99954987},"labels":[],"label_agreement":null},{"id":"W7069001018","doi":"","title":"Canada Connections","year":2013,"lang":"en","type":"other","venue":"University of Huddersfield Repository (University of Huddersfield)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Miller; Performance art; George (robot); Gloom; Subject (documents); Wright; Performing arts","score_opus":0.0026909913653231686,"score_gpt":0.14845378173418458,"score_spread":0.14576279036886142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069001018","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":[0.00034338355,0.0004770593,0.0032397562,0.00031205788,0.00043292018,0.00025810552,0.000055781373,0.0000422925,0.99483865],"genre_scores_gemma":[0.1285165,0.00047924332,0.0033053826,0.00008924709,0.00013523937,6.6987106e-8,0.00010256342,0.000086427295,0.8672853],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99889725,0.0000820301,0.00016369461,0.0003462687,0.0002671034,0.00024364266],"domain_scores_gemma":[0.9985183,0.000037214315,0.000539046,0.00064339634,0.00013035677,0.00013168303],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000054008084,0.00025877822,0.0004006762,0.00015469336,0.00021565461,0.000007600247,0.0006652441,0.0006452415,0.03941729],"category_scores_gemma":[0.000027310436,0.00035765776,0.0002303016,0.000106823856,0.0003153639,0.000011434519,0.0002689637,0.0003228221,0.000014170561],"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":[0.000040141713,0.000041501637,0.0002835334,0.00018230182,0.00035920355,0.00003322672,0.00021602331,0.0000681142,0.0012281364,0.00015769349,0.9972011,0.00018903193],"study_design_scores_gemma":[0.0012790438,0.0003567019,0.000035428846,0.00022110218,0.00032057526,0.000042776708,0.31348014,0.00031022084,0.0015396203,0.00000728496,0.6816808,0.00072632],"about_ca_topic_score_codex":0.4872423,"about_ca_topic_score_gemma":0.26714507,"teacher_disagreement_score":0.31552032,"about_ca_system_score_codex":0.0000016338618,"about_ca_system_score_gemma":0.0006532834,"threshold_uncertainty_score":0.9998875},"labels":[],"label_agreement":null},{"id":"W7069022032","doi":"","title":"","year":2021,"lang":"fr","type":"other","venue":"Directory of Open access Books (OAPEN Foundation)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Derogation; ESPACE; Context (archaeology); Power (physics)","score_opus":0.046777564815686457,"score_gpt":0.3969640010454515,"score_spread":0.35018643622976503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069022032","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":[0.0490101,0.0025879242,0.004314676,0.001005665,0.0027804007,0.0036799682,0.000024901208,0.000051547562,0.93654484],"genre_scores_gemma":[0.09240611,0.0025721767,0.017979791,0.0022404252,0.0013063243,0.0005353845,0.012335287,0.0008761806,0.8697483],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9919385,0.0012682151,0.0026865525,0.0019765147,0.0010107048,0.0011195674],"domain_scores_gemma":[0.9908204,0.00028025868,0.0041072015,0.003087968,0.0011840846,0.0005200503],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaepi_narrow","open_science"],"category_scores_codex":[0.0015719389,0.0015959563,0.0022180863,0.0005144631,0.00063845626,0.0048906207,0.010704526,0.0008821253,0.09107414],"category_scores_gemma":[0.0018846082,0.0018193993,0.00071373815,0.00061558554,0.00117526,0.00032368823,0.012608832,0.0009948728,0.00040430532],"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":[0.0010865309,0.0017064973,0.16308078,0.0062752897,0.0055576344,0.000075803844,0.00087455445,0.0021863803,0.07952174,0.060547285,0.007693061,0.67139447],"study_design_scores_gemma":[0.0023126348,0.00030118437,0.048021734,0.0015511233,0.00030702553,0.00005604978,0.000150167,0.0006116073,0.029741693,0.00020971756,0.9148891,0.0018479694],"about_ca_topic_score_codex":0.0031667121,"about_ca_topic_score_gemma":0.005411392,"teacher_disagreement_score":0.90719604,"about_ca_system_score_codex":0.00028743412,"about_ca_system_score_gemma":0.002578551,"threshold_uncertainty_score":0.99967885},"labels":[],"label_agreement":null},{"id":"W7069079856","doi":"","title":"","year":2022,"lang":"en","type":"other","venue":"Directory of Open access Books (OAPEN Foundation)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Service (business); Work (physics); Settlement (finance); Community service","score_opus":0.039229850953230214,"score_gpt":0.39530203424264726,"score_spread":0.35607218328941703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069079856","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":[0.003927144,0.00027707499,0.00054672605,0.00013357976,0.0008233276,0.0025227778,0.00003331521,0.00012410911,0.99161196],"genre_scores_gemma":[0.009508117,0.0005312283,0.0046883016,0.0013574755,0.00053600327,0.00081348856,0.012022496,0.0012589337,0.96928394],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960163,0.00047599894,0.001121324,0.0010614452,0.00079719943,0.0005276952],"domain_scores_gemma":[0.995034,0.00006619877,0.0024623747,0.0020761532,0.00016653458,0.00019478076],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0009693988,0.0007807364,0.0010042434,0.00055954483,0.0003835972,0.0013131843,0.0085565,0.0002778769,0.054517075],"category_scores_gemma":[0.00048536411,0.0008584725,0.00029310692,0.0003216423,0.000354461,0.00010859643,0.010347359,0.0005507848,0.00013571978],"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":[0.0012043226,0.0009141525,0.10546539,0.0019111518,0.0032879666,0.00002527244,0.00035406076,0.00085541024,0.011732687,0.01160883,0.69800365,0.16463712],"study_design_scores_gemma":[0.0012676248,0.00020762449,0.005034311,0.00010965904,0.00009206685,0.000012980781,0.00006514082,0.00005331424,0.0019801415,0.0000824165,0.99013454,0.0009601891],"about_ca_topic_score_codex":0.0024361224,"about_ca_topic_score_gemma":0.0017275726,"teacher_disagreement_score":0.2921309,"about_ca_system_score_codex":0.000110125424,"about_ca_system_score_gemma":0.00068809633,"threshold_uncertainty_score":0.99972355},"labels":[],"label_agreement":null},{"id":"W7069100976","doi":"","title":"Queer Ecofeminism","year":2025,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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","funders":"","keywords":"","score_opus":0.10171448199097598,"score_gpt":0.5448518354309736,"score_spread":0.4431373534399976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069100976","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8166796,0.014435123,0.0058045248,0.00056347664,0.0012956281,0.00058421295,0.000048947775,0.000041229407,0.16054726],"genre_scores_gemma":[0.98491067,0.005277741,0.0014982396,0.0016252457,0.00020303755,0.000028204573,0.00006122655,0.000038919792,0.0063567064],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99823076,0.00014189174,0.00069453253,0.00031220244,0.00030477456,0.0003158356],"domain_scores_gemma":[0.9984387,0.000075294694,0.0004899195,0.0006417633,0.00021958165,0.00013474835],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008569105,0.00025922412,0.00041820467,0.00035991028,0.00017475136,0.000545175,0.002290224,0.00020049165,0.0028304623],"category_scores_gemma":[0.00054034276,0.0002395673,0.00017698159,0.0004299868,0.00011711865,0.000063771746,0.0014286271,0.0003468639,0.000022648579],"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":[0.00016518189,0.00014276357,0.36001304,0.0001696335,0.00035368872,0.000008275424,0.000094392955,0.000442094,0.27415183,0.0004646353,0.34836096,0.01563353],"study_design_scores_gemma":[0.0008437767,0.000027853888,0.3289886,0.0003117953,0.00009454401,0.000018137258,0.00007970868,0.00036539728,0.21120757,0.0031886357,0.45429397,0.0005799843],"about_ca_topic_score_codex":0.00015704821,"about_ca_topic_score_gemma":0.00002146737,"teacher_disagreement_score":0.16823108,"about_ca_system_score_codex":0.000030322428,"about_ca_system_score_gemma":0.00019661976,"threshold_uncertainty_score":0.9980811},"labels":[],"label_agreement":null},{"id":"W7069148095","doi":"","title":"Generator sample","year":2011,"lang":"en","type":"other","venue":"International Linear Collider","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Phone; Join (topology); Password; Service (business); Generator (circuit theory); Permission","score_opus":0.011660619029818275,"score_gpt":0.2673380727362106,"score_spread":0.2556774537063923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069148095","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":[0.00012777063,0.00028242785,0.012516512,0.00009714639,0.0015020147,0.00017656162,0.00047000512,0.00006893762,0.9847586],"genre_scores_gemma":[0.00042572073,0.00017141226,0.06336091,0.0007822045,0.0022881276,0.000022966737,0.0018734152,0.00030770747,0.93076754],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992663,0.000019617008,0.00018667227,0.0002146873,0.00018106903,0.00013160931],"domain_scores_gemma":[0.9994125,0.000008478024,0.0001679886,0.00029734327,0.000060730432,0.00005295842],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000063400475,0.0001836196,0.00012272701,0.00009128796,0.000020526199,0.000021669095,0.00035823532,0.00028650856,0.0067314925],"category_scores_gemma":[0.0001935242,0.00017641639,0.000087766406,0.0000321266,0.000039291273,0.000001350061,0.00015126952,0.00012674197,0.00059150317],"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":[0.000015535466,0.000027906275,0.0010077741,0.000015063128,0.00019436558,0.000002253881,0.000014337308,0.000051382558,0.00038122304,0.00043655565,0.99748033,0.00037324958],"study_design_scores_gemma":[0.00019757758,0.000039097293,0.00003907493,0.000021760412,0.000010855337,0.000008539621,0.0000026684415,0.0006075652,0.0009971835,0.00002223559,0.99785316,0.00020029015],"about_ca_topic_score_codex":0.00015485754,"about_ca_topic_score_gemma":0.00011165322,"teacher_disagreement_score":0.05399109,"about_ca_system_score_codex":0.000013318691,"about_ca_system_score_gemma":0.00006420486,"threshold_uncertainty_score":0.9941765},"labels":[],"label_agreement":null},{"id":"W7069161512","doi":"","title":"Canton, Ohio","year":2009,"lang":"en","type":"other","venue":"OhioLink ETD Center (Ohio Library and Information Network)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Knight; Government (linguistics); Quarter (Canadian coin); Netting","score_opus":0.00436965886673802,"score_gpt":0.20204056477528518,"score_spread":0.19767090590854716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069161512","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":[0.000023371962,0.001215244,0.0010115885,0.00032167308,0.0005510163,0.00038301857,0.00016797602,0.00020873047,0.99611735],"genre_scores_gemma":[0.007239567,0.03318871,0.015747074,0.03746698,0.009018601,0.00007443658,0.03939823,0.0007737807,0.8570926],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99840087,0.0000768447,0.0005921499,0.00024729111,0.00019153257,0.00049132534],"domain_scores_gemma":[0.9987247,0.000010605197,0.00052160694,0.00052623916,0.000017471064,0.00019937311],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000111048044,0.0004642492,0.00034582955,0.00017640372,0.00011493073,0.00020219474,0.00036803697,0.00069087726,0.0011030992],"category_scores_gemma":[0.000015940343,0.00043247428,0.00012397561,0.00016155237,0.00008044002,0.00020574412,0.00027470684,0.00040547695,0.00012405701],"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":[0.00005401718,0.000019941057,0.00018012644,0.00016571804,0.000080679354,0.0000012171565,0.000043450975,0.0001645905,0.000004929786,0.04198784,0.9456618,0.011635731],"study_design_scores_gemma":[0.0006303397,0.0001462546,0.00037235342,0.00023985523,0.000020918098,0.000033035052,0.000002497719,0.0007497588,0.00004585547,0.00005484085,0.9972213,0.00048302786],"about_ca_topic_score_codex":2.015795e-7,"about_ca_topic_score_gemma":0.000003199332,"teacher_disagreement_score":0.13902476,"about_ca_system_score_codex":0.000005504813,"about_ca_system_score_gemma":0.00007894713,"threshold_uncertainty_score":0.9998127},"labels":[],"label_agreement":null},{"id":"W7069174811","doi":"","title":"Hong Kong’s Future","year":2016,"lang":"en","type":"other","venue":"The HKU Scholars Hub (University of Hong Kong)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.0034124589714175308,"score_gpt":0.20144553036998486,"score_spread":0.19803307139856732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069174811","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":[0.046539783,0.0028105911,0.0028707,0.002441969,0.0014910682,0.00078614074,0.00041016878,0.00021823379,0.94243133],"genre_scores_gemma":[0.014162313,0.0016296507,0.0034467424,0.00022237842,0.0009935582,4.763008e-7,0.00023524596,0.00024987658,0.97905976],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99876416,0.00014547119,0.00014866695,0.00032640927,0.00030019958,0.00031511742],"domain_scores_gemma":[0.99837446,0.000016433722,0.00043998827,0.0009907753,0.0000772434,0.000101108715],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00031761228,0.00031492385,0.00031832137,0.00014801984,0.00022056466,0.00003115191,0.0011991035,0.0006006337,0.0018058094],"category_scores_gemma":[0.000046624227,0.0002573773,0.00024237226,0.00011005444,0.00032180076,0.000014215831,0.000523748,0.00051774416,0.00044571597],"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":[0.000094249386,0.00004746337,0.0020201572,0.0001711701,0.00045669283,0.000018161534,0.0002708914,0.000010975005,0.0067119873,0.0004743282,0.98285794,0.0068659964],"study_design_scores_gemma":[0.0006899663,0.000098196644,0.0022288426,0.0001559624,0.000106771746,0.00001802491,0.00055891933,0.000018794844,0.00037748684,0.000029758623,0.9953265,0.00039073042],"about_ca_topic_score_codex":0.00008731757,"about_ca_topic_score_gemma":0.00018707788,"teacher_disagreement_score":0.036628414,"about_ca_system_score_codex":0.000024717361,"about_ca_system_score_gemma":0.00009526624,"threshold_uncertainty_score":0.99998784},"labels":[],"label_agreement":null},{"id":"W7069177368","doi":"","title":"9780472904396.pdf","year":2024,"lang":"en","type":"other","venue":"OAPEN (The OAPEN Foundation)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Defence Research and Development Canada; Innovationsfonden; University of Minnesota; University of Cambridge; Yale University; Northwestern University; U.S. Department of State","keywords":"Geopolitics; Securitization; Politics; Arctic; Security studies; Identity (music); The arctic; International security","score_opus":0.006137055880492946,"score_gpt":0.2635969665918195,"score_spread":0.25745991071132657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069177368","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":[0.00003296089,0.000024903225,0.00096563227,0.0007424742,0.0011337819,0.00048513777,4.1122693e-8,0.000114966555,0.9965001],"genre_scores_gemma":[0.0006387893,0.00023848993,0.0016652159,0.0008397492,0.0014585791,0.000071998125,0.001522098,0.00053805014,0.99302703],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985224,0.00008701757,0.000333476,0.00044391764,0.0003033967,0.00030978263],"domain_scores_gemma":[0.99861234,0.000019120576,0.00027877974,0.0009694077,0.000044276447,0.000076100856],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003041591,0.00038782138,0.0002478058,0.00011420972,0.0001044475,0.000252476,0.0007084765,0.0003451688,0.5122437],"category_scores_gemma":[0.00012155619,0.0002943315,0.00017652284,0.00015936507,0.00015515173,0.0000053507706,0.00039089745,0.00040559596,0.9485556],"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":[0.000014349297,0.000024472192,0.000067027104,0.00018628662,0.0003183781,0.000003570271,0.000047748556,0.000013493002,0.00044768507,0.0007821024,0.1291664,0.8689285],"study_design_scores_gemma":[0.00018030866,0.00006795326,0.000040188082,0.00009927517,0.000100990066,0.000032339103,0.00002729124,0.00012714404,0.00016021589,0.00020919123,0.9985825,0.0003726248],"about_ca_topic_score_codex":0.00007577853,"about_ca_topic_score_gemma":0.00012372911,"teacher_disagreement_score":0.86941606,"about_ca_system_score_codex":0.00003046439,"about_ca_system_score_gemma":0.00012879467,"threshold_uncertainty_score":0.9999509},"labels":[],"label_agreement":null},{"id":"W7069194611","doi":"","title":"English Report","year":2003,"lang":"en","type":"article","venue":"Érudit (Université de Montréal)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Exhibition; Painting; Subject (documents); Irish; Event (particle physics); SAINT; The Imaginary","score_opus":0.0025319506399594234,"score_gpt":0.16334217616767435,"score_spread":0.16081022552771493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069194611","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81428593,0.0033719193,0.0038062227,0.0008993244,0.00034397253,0.00017158745,0.000009783971,0.00008895593,0.17702231],"genre_scores_gemma":[0.88117677,0.0009261331,0.010187175,0.00050598686,0.000207293,0.0000046642917,0.00019401916,0.000042782267,0.106755145],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993359,0.00004162999,0.00011589294,0.00017851483,0.00011043115,0.00021764077],"domain_scores_gemma":[0.99933046,0.000008120057,0.000098749995,0.0003869551,0.00007763173,0.00009809753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018174086,0.00011276742,0.00009618159,0.000038368005,0.0001633666,0.000008086163,0.00014092853,0.00012602657,0.00008228925],"category_scores_gemma":[0.00027967116,0.00012446087,0.00007796245,0.00008112626,0.000032822558,0.000004215328,0.000102231395,0.000098543525,0.00003406138],"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":[0.00024921136,0.00021267457,0.057879355,0.00010460804,0.00045327444,0.0038453336,0.001276899,0.0025905226,0.06486286,0.035994638,0.8189376,0.013593042],"study_design_scores_gemma":[0.00034390725,0.00006419691,0.0005106572,0.0000032831683,0.000017783394,0.0008469222,0.00015203099,0.00009671559,0.0070521543,0.000056478802,0.9907034,0.00015247938],"about_ca_topic_score_codex":0.00008614159,"about_ca_topic_score_gemma":0.0008760587,"teacher_disagreement_score":0.1717658,"about_ca_system_score_codex":0.00034308527,"about_ca_system_score_gemma":0.00003497719,"threshold_uncertainty_score":0.5075367},"labels":[],"label_agreement":null},{"id":"W7069237244","doi":"","title":"Novembre 2020","year":2020,"lang":"fr","type":"other","venue":"OpenEdition (OpenEdition)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Center (category theory); Context (archaeology); Government (linguistics); George (robot); Work (physics); State (computer science); Public policy","score_opus":0.007224015466982509,"score_gpt":0.23310824241411768,"score_spread":0.22588422694713517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069237244","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":[0.00027092543,0.0032891438,0.0111764185,0.077159084,0.0050448705,0.0015704506,0.0020100793,0.00015443635,0.8993246],"genre_scores_gemma":[0.023216465,0.0033989293,0.02136733,0.1691554,0.013901404,0.00050732645,0.039940886,0.00090360775,0.7276087],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958883,0.00032238316,0.0010964678,0.0011794625,0.0007227427,0.00079064496],"domain_scores_gemma":[0.99697775,0.00007076324,0.0009766271,0.0010873015,0.00027234072,0.0006151927],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00034609353,0.0010441173,0.00084525143,0.00014490845,0.00039354232,0.00036261583,0.0011305155,0.0013970671,0.07321245],"category_scores_gemma":[0.00059295143,0.0011460583,0.00047020873,0.0004027551,0.00039776583,0.00032590676,0.0007462229,0.001007482,0.018880427],"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":[0.00021277968,0.00034376737,0.00020789272,0.0009761294,0.00062263303,0.000106547726,0.000106811574,0.0005289432,0.006187007,0.055927232,0.91923785,0.015542435],"study_design_scores_gemma":[0.0014354037,0.0007554746,0.0017663299,0.0004118194,0.00021515836,0.00015766248,0.00008993496,0.000996945,0.003802564,0.00015882586,0.9889279,0.0012820077],"about_ca_topic_score_codex":0.000052143885,"about_ca_topic_score_gemma":0.0007710597,"teacher_disagreement_score":0.17171595,"about_ca_system_score_codex":0.00013940333,"about_ca_system_score_gemma":0.00048506257,"threshold_uncertainty_score":0.9998993},"labels":[],"label_agreement":null},{"id":"W7069241317","doi":"","title":"Kapak-İçindekiler","year":2013,"lang":"tr","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Technical university; Research method; Middle East; Statistical analysis","score_opus":0.12813175943181968,"score_gpt":0.5257339484587434,"score_spread":0.3976021890269238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069241317","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9074143,0.027753312,0.00087186217,0.00064706535,0.0015921828,0.0013386304,0.00011238719,0.000038760816,0.06023145],"genre_scores_gemma":[0.97248894,0.016811442,0.0017770386,0.001423816,0.00082509936,0.000073278556,0.00013122239,0.00015131744,0.0063178344],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9953934,0.0003552028,0.0017343466,0.0007211501,0.0008911727,0.0009047528],"domain_scores_gemma":[0.995332,0.00013749825,0.0018746296,0.0012079346,0.00083275815,0.0006151601],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013153559,0.0007525596,0.0010828363,0.00058856927,0.000385298,0.0028485106,0.0051573752,0.00060104334,0.03994745],"category_scores_gemma":[0.0007880486,0.0007046333,0.000469241,0.00074672553,0.00036014072,0.00035175483,0.0033607066,0.0010076193,0.00053703226],"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":[0.00014815565,0.00039125807,0.3749809,0.0003721604,0.0007240814,0.000012574426,0.00021423229,0.00030139566,0.19837,0.00012375046,0.40252313,0.021838343],"study_design_scores_gemma":[0.0015552478,0.00010211486,0.644029,0.0007308949,0.00026413106,0.00008429709,0.00022935052,0.0014588158,0.07648542,0.0021055131,0.27125323,0.0017019567],"about_ca_topic_score_codex":0.0009589201,"about_ca_topic_score_gemma":0.000035542125,"teacher_disagreement_score":0.26904812,"about_ca_system_score_codex":0.000082085186,"about_ca_system_score_gemma":0.00031035085,"threshold_uncertainty_score":0.9995405},"labels":[],"label_agreement":null},{"id":"W7069242723","doi":"","title":"Svěřenské fondy","year":2014,"lang":"en","type":"dissertation","venue":"Digital Repository (National Repository of Grey Literature)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Czech; Civil code; Negotiation; Subject (documents); Convention; Legal research; Civil law (Civil law); CLARITY","score_opus":0.0035186366763083647,"score_gpt":0.23497684859943596,"score_spread":0.2314582119231276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069242723","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36106044,0.0024145823,0.00011874445,0.000019100815,0.0031475641,0.0004266436,0.00015395523,0.000072000395,0.63258696],"genre_scores_gemma":[0.844795,0.000021879396,0.00048826291,0.00008575136,0.001485058,0.000037017096,0.009850995,0.00009565103,0.1431404],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99682295,0.000088877045,0.0010508273,0.00063117925,0.0011054071,0.00030076836],"domain_scores_gemma":[0.9962754,0.000071395894,0.0010789039,0.0006317972,0.001782043,0.00016045806],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017491488,0.00054282544,0.0004706377,0.000239073,0.00023557874,0.00055307156,0.0005459508,0.0008656605,0.000004211982],"category_scores_gemma":[0.00068583636,0.00054095587,0.00046213836,0.00017965342,0.000119905715,0.000057571728,0.00008619254,0.0005118285,0.000013954587],"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":[0.0036242644,0.0010935583,0.03070994,0.007001419,0.0029638794,0.00021015324,0.003597105,0.0010945691,0.8011705,0.010185723,0.12887937,0.009469529],"study_design_scores_gemma":[0.0015612041,0.0015246243,0.02465217,0.0020633147,0.00022960671,0.0010517393,0.00022630166,0.0005819542,0.4363419,0.0008799483,0.5284097,0.002477485],"about_ca_topic_score_codex":0.000004033947,"about_ca_topic_score_gemma":0.0000024214585,"teacher_disagreement_score":0.48944658,"about_ca_system_score_codex":0.00006971762,"about_ca_system_score_gemma":0.0004493869,"threshold_uncertainty_score":0.9997042},"labels":[],"label_agreement":null},{"id":"W7069246991","doi":"","title":"","year":2021,"lang":"fr","type":"other","venue":"Directory of Open access Books (OAPEN Foundation)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Subject (documents); Identity (music); State (computer science); Interpretation (philosophy); Context (archaeology)","score_opus":0.046777564815686457,"score_gpt":0.3969640010454515,"score_spread":0.35018643622976503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069246991","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":[0.0490101,0.0025879242,0.004314676,0.001005665,0.0027804007,0.0036799682,0.000024901208,0.000051547562,0.93654484],"genre_scores_gemma":[0.09240611,0.0025721767,0.017979791,0.0022404252,0.0013063243,0.0005353845,0.012335287,0.0008761806,0.8697483],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9919385,0.0012682151,0.0026865525,0.0019765147,0.0010107048,0.0011195674],"domain_scores_gemma":[0.9908204,0.00028025868,0.0041072015,0.003087968,0.0011840846,0.0005200503],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaepi_narrow","open_science"],"category_scores_codex":[0.0015719389,0.0015959563,0.0022180863,0.0005144631,0.00063845626,0.0048906207,0.010704526,0.0008821253,0.09107414],"category_scores_gemma":[0.0018846082,0.0018193993,0.00071373815,0.00061558554,0.00117526,0.00032368823,0.012608832,0.0009948728,0.00040430532],"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":[0.0010865309,0.0017064973,0.16308078,0.0062752897,0.0055576344,0.000075803844,0.00087455445,0.0021863803,0.07952174,0.060547285,0.007693061,0.67139447],"study_design_scores_gemma":[0.0023126348,0.00030118437,0.048021734,0.0015511233,0.00030702553,0.00005604978,0.000150167,0.0006116073,0.029741693,0.00020971756,0.9148891,0.0018479694],"about_ca_topic_score_codex":0.0031667121,"about_ca_topic_score_gemma":0.005411392,"teacher_disagreement_score":0.90719604,"about_ca_system_score_codex":0.00028743412,"about_ca_system_score_gemma":0.002578551,"threshold_uncertainty_score":0.99967885},"labels":[],"label_agreement":null},{"id":"W7069476526","doi":"","title":"McLuhan’s galaxy","year":2011,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Galaxy; Focus (optics); Staring; Mode (computer interface); Feature (linguistics)","score_opus":0.20011212488407903,"score_gpt":0.5250586202335529,"score_spread":0.32494649534947384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069476526","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9006015,0.006017068,0.0024602895,0.000059189508,0.0006639899,0.0004104534,0.000033118133,0.000033915705,0.08972047],"genre_scores_gemma":[0.9910175,0.0036210795,0.0032707804,0.00051283377,0.00024446164,0.000023107737,0.000045200406,0.000058080666,0.0012069478],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980683,0.00015309824,0.00069648674,0.00032198604,0.0003826729,0.00037750733],"domain_scores_gemma":[0.9981407,0.00003546954,0.0006629517,0.00068774144,0.00024260467,0.00023054614],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007293659,0.00028732143,0.00041737218,0.00028018586,0.0001622979,0.00033629002,0.0025542048,0.00018696455,0.0077614286],"category_scores_gemma":[0.0003975543,0.0002605319,0.00018680464,0.00031069227,0.00013860312,0.0000953309,0.001284932,0.00033222773,0.000052895946],"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":[0.00024156037,0.00021097274,0.5497777,0.00011564386,0.00028549007,0.000016563183,0.00033241944,0.00007071337,0.3458731,0.00018139342,0.092435636,0.010458856],"study_design_scores_gemma":[0.0006049032,0.00005468764,0.6602183,0.00013613729,0.00006860937,0.00004950238,0.00007477264,0.00011939613,0.2602213,0.0019208118,0.07592752,0.0006040294],"about_ca_topic_score_codex":0.00028011564,"about_ca_topic_score_gemma":0.00002793088,"teacher_disagreement_score":0.110440664,"about_ca_system_score_codex":0.00002374366,"about_ca_system_score_gemma":0.00011411395,"threshold_uncertainty_score":0.9999847},"labels":[],"label_agreement":null},{"id":"W7069765784","doi":"","title":"Pig cognition","year":2010,"lang":"en","type":"article","venue":"Bristol Research (University of Bristol)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Institute of Infection and Immunity","funders":"","keywords":"Cognition; Perception; Disease","score_opus":0.019794395652524804,"score_gpt":0.29851371010344147,"score_spread":0.2787193144509167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069765784","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.948882,0.00006460271,0.0034980972,0.00054560875,0.00010833904,0.00021251621,0.000036404657,0.000023436713,0.046628986],"genre_scores_gemma":[0.99018365,0.00006244876,0.0050551184,0.000029350456,0.00009482609,4.1815395e-7,0.00014896852,0.000013225983,0.0044119875],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988369,0.00012032726,0.000114478375,0.00023072334,0.0004072962,0.00029032797],"domain_scores_gemma":[0.9988306,0.00003751915,0.00009715441,0.00043846437,0.0004556787,0.00014057408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008027084,0.000091139824,0.00012857743,0.00016089504,0.0002935091,0.000018932527,0.00050311454,0.00018680599,0.00022305115],"category_scores_gemma":[0.0004583482,0.00011853925,0.0000872204,0.00021010976,0.0005636513,0.000012362332,0.00032394184,0.0005284136,0.0001505893],"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":[0.00045349574,0.0003142845,0.008332989,0.00021054072,0.0001144794,0.000046350695,0.00066283555,0.00002700148,0.8284179,0.0017750625,0.1245461,0.035098977],"study_design_scores_gemma":[0.0016130118,0.00074266543,0.022359286,0.000038935228,0.000034779536,0.000086749234,0.0022685917,0.0020541665,0.018863112,0.0005202283,0.9509811,0.00043738386],"about_ca_topic_score_codex":0.0003189305,"about_ca_topic_score_gemma":0.0006450737,"teacher_disagreement_score":0.82643497,"about_ca_system_score_codex":0.000017932123,"about_ca_system_score_gemma":0.00016211715,"threshold_uncertainty_score":0.48338902},"labels":[],"label_agreement":null},{"id":"W7069839687","doi":"","title":"Sobrevivir y amar","year":2022,"lang":"es","type":"other","venue":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Population; Statistical analysis; Quarter (Canadian coin)","score_opus":0.01200883843233039,"score_gpt":0.24387441157802678,"score_spread":0.2318655731456964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069839687","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025474448,0.0022626661,0.001625964,0.008311805,0.0018557529,0.0010637873,0.00038984456,0.00030829897,0.98163444],"genre_scores_gemma":[0.88211733,0.0041584102,0.015182027,0.0016561743,0.004853963,0.0007819624,0.0065199356,0.0009856041,0.08374458],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99397314,0.00097361114,0.0012361484,0.0013742276,0.001212984,0.0012298708],"domain_scores_gemma":[0.9959363,0.00014008614,0.0012603054,0.0017166558,0.0003040131,0.00064265996],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001012323,0.0011761542,0.00096392975,0.0006325608,0.0009971084,0.00035686532,0.0017170772,0.0016745324,0.0029583988],"category_scores_gemma":[0.0010595111,0.0012288038,0.0006667857,0.0006287483,0.00006137621,0.00003959352,0.0014318266,0.001852988,0.00017136325],"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":[0.00055516296,0.0013361898,0.0018966736,0.0013934708,0.001643773,0.0003222667,0.0010715295,0.00041806142,0.006453325,0.854953,0.120936416,0.00902012],"study_design_scores_gemma":[0.0012793605,0.00029576477,0.000979917,0.00020046889,0.0002143042,0.0013331964,0.00024083629,0.00040982198,0.00043603356,0.00006885846,0.9932529,0.0012885373],"about_ca_topic_score_codex":0.0000018780466,"about_ca_topic_score_gemma":0.0000973448,"teacher_disagreement_score":0.89788985,"about_ca_system_score_codex":0.0006986835,"about_ca_system_score_gemma":0.0015198227,"threshold_uncertainty_score":0.9996215},"labels":[],"label_agreement":null},{"id":"W7069884507","doi":"","title":"Emergency","year":2005,"lang":"en","type":"report","venue":"Library, Museums and Press - UDSpace (University of Delaware)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Hyporeflexia; Articular cartilage damage; Fusible alloy","score_opus":0.013743464250778135,"score_gpt":0.2284435229206778,"score_spread":0.21470005866989966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069884507","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":[0.08364406,0.025732026,0.004843849,0.0028904092,0.0017356635,0.0010427218,0.0012248829,0.00024745765,0.8786389],"genre_scores_gemma":[0.21463394,0.29486305,0.027581647,0.00024296364,0.002136048,0.0000032757753,0.005356967,0.00031456622,0.45486754],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99866474,0.00006675589,0.00023646202,0.00040929162,0.00034627868,0.00027646704],"domain_scores_gemma":[0.9986624,0.00001323196,0.00047193232,0.0005830568,0.00010341301,0.00016594831],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001368255,0.0003195278,0.00040115733,0.00009837707,0.0001513748,0.000027577878,0.00049840036,0.00062270206,0.00075135275],"category_scores_gemma":[0.000036721798,0.00037242027,0.00021253324,0.00008216623,0.00014044288,0.000046097408,0.0007085631,0.00034553243,0.0000082840725],"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":[0.00019602444,0.00013597237,0.0143882735,0.0017983648,0.00075187144,0.000030525767,0.0011926369,0.0003507766,0.0005860756,0.00039044252,0.95996636,0.020212667],"study_design_scores_gemma":[0.00033478873,0.00017745669,0.004336843,0.00008942113,0.00012133216,0.00003126715,0.00023899059,0.0003854463,0.00015478057,0.000011888552,0.9936931,0.00042465463],"about_ca_topic_score_codex":0.00074079557,"about_ca_topic_score_gemma":0.00018792672,"teacher_disagreement_score":0.42377138,"about_ca_system_score_codex":0.000010584975,"about_ca_system_score_gemma":0.00026228864,"threshold_uncertainty_score":0.9998728},"labels":[],"label_agreement":null},{"id":"W7069886623","doi":"","title":"English Anxieties","year":2009,"lang":"en","type":"other","venue":"Sunderland Repository (University of Sunderland)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Commission; Period (music); Suite; Everyday life; Adversary; Mode (computer interface); Key (lock); Work (physics)","score_opus":0.0038987361068150823,"score_gpt":0.18261777547033126,"score_spread":0.17871903936351619,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069886623","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":[0.0034979645,0.0015865223,0.0012514513,0.000066172324,0.000615522,0.00025686767,0.000038111462,0.0001529817,0.9925344],"genre_scores_gemma":[0.0320774,0.0011249718,0.001969482,0.0000685726,0.0007106058,2.911547e-7,0.00041786727,0.00016947319,0.96346134],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998813,0.00008456922,0.00018789947,0.00037271617,0.000268861,0.00027295965],"domain_scores_gemma":[0.9987657,0.000012212197,0.0004060566,0.00060115947,0.0000966182,0.00011825034],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00010261977,0.0003153932,0.00039513645,0.00015301669,0.00016043807,0.000027369291,0.00046168818,0.0007169844,0.00021586457],"category_scores_gemma":[0.000021302745,0.00034232181,0.00022321478,0.00009050193,0.0002593702,0.000006442478,0.00014870652,0.00026739918,0.000016612992],"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":[0.0001260952,0.00010376458,0.004223339,0.00036309165,0.0003966565,0.000036086916,0.0007319424,0.00004264019,0.0012248785,0.00016645354,0.99128807,0.0012970124],"study_design_scores_gemma":[0.0009424015,0.00035604901,0.0011174732,0.00015270321,0.000113306036,0.000041205058,0.0013035947,0.000048618906,0.0002553127,0.00004466288,0.99510044,0.0005242173],"about_ca_topic_score_codex":0.00039377017,"about_ca_topic_score_gemma":0.00053281704,"teacher_disagreement_score":0.029073067,"about_ca_system_score_codex":0.00002381633,"about_ca_system_score_gemma":0.00013638152,"threshold_uncertainty_score":0.9999029},"labels":[],"label_agreement":null},{"id":"W7069982975","doi":"","title":"Ormat Technologies, Inc. to Host Conference Call Announcing Second Quarter 2016 Financial Results","year":2016,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Host (biology); Financial services; Term (time)","score_opus":0.005863420517276256,"score_gpt":0.23649897772702128,"score_spread":0.23063555720974502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069982975","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":[0.00018453767,0.00020372854,0.008658951,0.00088645477,0.00042429665,0.00047746504,0.0009635875,0.00032160323,0.9878794],"genre_scores_gemma":[0.0020702614,0.00019846785,0.0080927415,0.00086809206,0.00043511717,0.000035695608,0.0005043111,0.00016581439,0.9876295],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99847305,0.000033387965,0.0004172025,0.00044775344,0.00019198543,0.00043661313],"domain_scores_gemma":[0.99863565,0.000014454909,0.00028075508,0.00087494124,0.000105947925,0.00008822628],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00020159606,0.00039651585,0.00031713647,0.00017565384,0.000053599466,0.000050416602,0.0005968324,0.00097357336,0.0010054265],"category_scores_gemma":[0.0003759431,0.0002853224,0.00006677635,0.000066152235,0.00010495453,0.0000039547,0.00042907547,0.00027479173,0.0015173297],"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":[0.000053618154,0.000011641701,0.000022899307,0.000062764826,0.000027612556,0.0000029547757,0.000038042912,3.4046803e-7,0.006731523,0.00013633657,0.9898583,0.003053938],"study_design_scores_gemma":[0.00054932025,0.00025002123,0.000030798914,0.00017483695,0.000007900724,0.000012910546,0.000035799145,0.000015248487,0.0039234515,0.000013187038,0.9944972,0.00048932503],"about_ca_topic_score_codex":0.00008027106,"about_ca_topic_score_gemma":0.001104834,"teacher_disagreement_score":0.0046388726,"about_ca_system_score_codex":0.000034056728,"about_ca_system_score_gemma":0.00027902125,"threshold_uncertainty_score":0.9999599},"labels":[],"label_agreement":null},{"id":"W7070032944","doi":"","title":"untitled","year":2013,"lang":"en","type":"article","venue":"Sound Ideas (University of Puget Sound)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Object (grammar); Focus (optics); Face (sociological concept); Work (physics); Process (computing)","score_opus":0.0050963481830002075,"score_gpt":0.1996683877571084,"score_spread":0.1945720395741082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070032944","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96850383,0.00006972016,0.01101338,0.00013391842,0.00008013058,0.00012765796,0.000008170357,0.000023657078,0.020039514],"genre_scores_gemma":[0.98826844,0.000022940187,0.0045594475,0.0001052463,0.000055267577,2.8616427e-7,0.00008165326,0.000010674682,0.006896062],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99940765,0.000032813157,0.00009921251,0.00015173614,0.00013007931,0.00017853496],"domain_scores_gemma":[0.9993747,0.0000111434765,0.00011367405,0.00031345125,0.00011174503,0.000075303906],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00010038587,0.000103188795,0.00012332058,0.000054595363,0.00012734148,0.000022338925,0.000280383,0.0001208343,0.0015314728],"category_scores_gemma":[0.00005903034,0.00012059283,0.000100164485,0.00008706733,0.00015365942,0.0000138545265,0.00016786014,0.0000959718,0.0006464943],"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":[0.00025868998,0.0004752358,0.25534925,0.0005834907,0.0009294045,0.00001764659,0.004437483,0.0016059052,0.024572078,0.51463616,0.19587293,0.0012617372],"study_design_scores_gemma":[0.0011674167,0.000292359,0.018531926,0.000015912123,0.000051882693,0.000018486873,0.0024714577,0.0016089537,0.00010568865,0.94722766,0.028069386,0.00043889575],"about_ca_topic_score_codex":0.0002751417,"about_ca_topic_score_gemma":0.00012102652,"teacher_disagreement_score":0.4325915,"about_ca_system_score_codex":0.0000149121415,"about_ca_system_score_gemma":0.00003498366,"threshold_uncertainty_score":0.99938124},"labels":[],"label_agreement":null},{"id":"W7070071659","doi":"","title":"PNC Reports First Quarter 2017 Net Income of $1.1 Billion, $1.96 Diluted EPS","year":2017,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Net income; Consumption (sociology); Population","score_opus":0.006145788834247947,"score_gpt":0.25099141516765316,"score_spread":0.24484562633340523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070071659","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":[0.00083356345,0.0007579562,0.0016684645,0.00019148282,0.00079589686,0.0004019291,0.00007706084,0.0000782871,0.9951954],"genre_scores_gemma":[0.021251759,0.0006248663,0.0048583397,0.00015085647,0.000685268,0.000022010136,0.0011426597,0.00030053643,0.9709637],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986163,0.000033850134,0.00047810437,0.00037726553,0.0002247837,0.0002697172],"domain_scores_gemma":[0.9966262,0.000009834679,0.0012394942,0.0019503032,0.000078321886,0.00009585039],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022700337,0.0003553583,0.00043445078,0.0001484967,0.0000832942,0.000039351595,0.00047433324,0.0007230703,0.000962881],"category_scores_gemma":[0.0002229537,0.00028791724,0.00017322117,0.000043859574,0.00016926571,0.0000031542454,0.0002706955,0.00020339986,0.00006677197],"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":[0.000010810009,0.000029465566,0.006185807,0.0002469951,0.00014495883,0.000016317437,0.00002352758,0.000010162438,0.00048959104,0.000020241161,0.9925045,0.00031764395],"study_design_scores_gemma":[0.00024270927,0.00015863679,0.0012442295,0.00020295163,0.00003772725,0.00008775111,0.000006788925,0.00007568914,0.0010512728,0.000016414368,0.99649954,0.00037629085],"about_ca_topic_score_codex":0.0005231392,"about_ca_topic_score_gemma":0.00065883534,"teacher_disagreement_score":0.024231654,"about_ca_system_score_codex":0.000009394358,"about_ca_system_score_gemma":0.00008226143,"threshold_uncertainty_score":0.9999573},"labels":[],"label_agreement":null},{"id":"W7070097280","doi":"","title":"Elopement","year":2021,"lang":"en","type":"other","venue":"OSF Preprints (OSF Preprints)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scientific literature; Identification (biology); Perspective (graphical); Scientific evidence; Medical literature; Autism","score_opus":0.008365303200963022,"score_gpt":0.2604875827217986,"score_spread":0.2521222795208356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070097280","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":[0.00034138229,0.00002283201,0.0023699424,0.00010642537,0.00047153118,0.0005617675,0.000029934257,0.00009016035,0.996006],"genre_scores_gemma":[0.0004662294,0.00059371855,0.0070361407,0.00035531344,0.00039115697,0.00011622944,0.0007528632,0.00034445853,0.98994386],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967529,0.00032705584,0.00048225038,0.0016593044,0.00035856335,0.0004199011],"domain_scores_gemma":[0.99488765,0.000031916625,0.00040727286,0.00441241,0.00008135273,0.00017942331],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013523854,0.0004553483,0.00041940945,0.00012451834,0.00007452655,0.000084121915,0.0010787783,0.00070280937,0.76156455],"category_scores_gemma":[0.0013541003,0.00051043666,0.00024877922,0.00010792426,0.000118062926,0.0000027936985,0.002313084,0.00048716387,0.48739767],"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":[0.000023755185,0.00013181588,0.0019102311,0.0003139693,0.00040190248,0.000014886188,0.00009159638,0.00015737631,0.008149717,0.00018764383,0.9829852,0.00563189],"study_design_scores_gemma":[0.00035548626,0.0000014073445,0.0005246426,0.00016740004,0.000049956372,0.00003310287,0.000029277955,0.000083731844,0.006665175,0.0000451498,0.991547,0.00049770187],"about_ca_topic_score_codex":0.00013171531,"about_ca_topic_score_gemma":0.00013404115,"teacher_disagreement_score":0.27416685,"about_ca_system_score_codex":0.00006446283,"about_ca_system_score_gemma":0.00022905391,"threshold_uncertainty_score":0.9997347},"labels":[],"label_agreement":null},{"id":"W7070144110","doi":"","title":"Pepco Holdings Reports Fourth Quarter and Full Year 2012 Financial Results; Announces 2013 Earnings Guidance\\n| Reuters","year":2013,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Earnings; Quarter (Canadian coin); Financial analysis; Financial ratio","score_opus":0.004505576095497216,"score_gpt":0.219055428770093,"score_spread":0.2145498526745958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070144110","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":[0.01068214,0.0025689013,0.001499635,0.0010518105,0.0010970682,0.0008030933,0.00011544356,0.00021101188,0.9819709],"genre_scores_gemma":[0.0011143242,0.0012010086,0.020669235,0.0005461325,0.0011622718,0.000036858826,0.0006281266,0.0002321778,0.9744099],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980312,0.000055665114,0.0005796998,0.00062901,0.00027350505,0.00043089822],"domain_scores_gemma":[0.9981937,0.000013250726,0.0007929254,0.0007677211,0.00008338669,0.00014904064],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000390563,0.0004504253,0.00037928156,0.00013816018,0.00007895872,0.0001113661,0.00024770966,0.00072909147,0.00057273963],"category_scores_gemma":[0.0002706535,0.0003865354,0.00011445548,0.000072906354,0.00017431339,0.000013530186,0.00022914627,0.00034957874,0.00020075376],"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":[0.000039024428,0.000014118272,0.000914372,0.00008439268,0.00005084066,0.000008583628,0.00009203801,0.000006173873,0.0009805048,0.00004094135,0.99749327,0.00027575693],"study_design_scores_gemma":[0.00042303168,0.00035177747,0.0010390423,0.00011458444,0.000028652406,0.00009146515,0.000050708386,0.00007714724,0.000106691485,0.000013388191,0.99716944,0.0005340743],"about_ca_topic_score_codex":0.00041174813,"about_ca_topic_score_gemma":0.00025146033,"teacher_disagreement_score":0.0191696,"about_ca_system_score_codex":0.000012178339,"about_ca_system_score_gemma":0.00008109769,"threshold_uncertainty_score":0.9998587},"labels":[],"label_agreement":null},{"id":"W7070170076","doi":"","title":"OM Group To Issue 2013 Third Quarter Results On November 1, 2013","year":2013,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Group (periodic table); Work (physics); Period (music)","score_opus":0.005361564845240182,"score_gpt":0.2450141972957439,"score_spread":0.23965263245050372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070170076","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":[0.00016219365,0.00015095733,0.0013939444,0.002731134,0.00070752954,0.0006982811,0.0001140541,0.00012225108,0.9939197],"genre_scores_gemma":[0.00020771465,0.00020599546,0.0101482365,0.0053178146,0.0014808818,0.00005818653,0.00095913786,0.00031937222,0.9813027],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982531,0.000056962763,0.0004240712,0.0005597882,0.00027607518,0.0004299672],"domain_scores_gemma":[0.9982702,0.000017086139,0.00024796024,0.0012080697,0.000051931063,0.0002047594],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00016335977,0.00049366563,0.0003392566,0.00015997177,0.0000410185,0.00007615297,0.00048403966,0.0008092018,0.0052656727],"category_scores_gemma":[0.00007182904,0.00039136253,0.00013375841,0.00007666814,0.00004762974,0.0000028452157,0.00021641598,0.0003204011,0.021236168],"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":[0.000046885278,0.0000490085,0.000016232307,0.00004851022,0.00007904726,0.0000010583348,0.000042960663,0.00003548412,0.00077831716,0.00013299381,0.99805874,0.0007107557],"study_design_scores_gemma":[0.00051944336,0.0005842368,0.000065616514,0.00008407352,0.000015045489,0.0000048652205,0.000027724642,0.00019134207,0.00043754553,0.0000046367472,0.9975178,0.0005476245],"about_ca_topic_score_codex":0.0016135228,"about_ca_topic_score_gemma":0.00088834896,"teacher_disagreement_score":0.015970496,"about_ca_system_score_codex":0.000015214549,"about_ca_system_score_gemma":0.000024125391,"threshold_uncertainty_score":0.99985385},"labels":[],"label_agreement":null},{"id":"W7070182414","doi":"","title":"Ojibwa: a language of Canada","year":2018,"lang":"en","type":"article","venue":"Americanae (AECID Library)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Natural language; Constructed language; Language industry; On Language; Universal Networking Language","score_opus":0.00177542866586241,"score_gpt":0.19753106877920726,"score_spread":0.19575564011334484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070182414","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96639806,0.00013613832,0.0003399617,0.00042293043,0.00012506534,0.00006861342,0.000028175078,0.000019228044,0.032461844],"genre_scores_gemma":[0.98736787,0.000017219745,0.005719418,0.0017815396,0.00023789318,0.0000035996168,0.000081712235,0.000023653254,0.0047671054],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99930143,0.000030972886,0.00018846929,0.00014166057,0.00013148003,0.00020596995],"domain_scores_gemma":[0.99936897,0.000012255818,0.00013632262,0.00037057587,0.000026028876,0.000085858606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000037518825,0.00010855774,0.00013338604,0.000030739928,0.000042272528,0.000005033758,0.00026560563,0.00004223325,0.00041462787],"category_scores_gemma":[0.00008246626,0.00010058233,0.000039857197,0.00016294961,0.00017385784,0.000007798386,0.00013767903,0.000064328095,0.0000090960975],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012294069,0.00006348039,0.2797117,0.0000648023,0.00019124168,0.00001677789,0.0006526206,0.00005555091,0.074628875,0.00070359587,0.6238313,0.019957185],"study_design_scores_gemma":[0.00068053283,0.0012890935,0.20543382,0.000028829372,0.000027554708,0.00002419681,0.0010016748,0.00091682695,0.47319013,0.00003280295,0.3167349,0.0006396393],"about_ca_topic_score_codex":0.29974225,"about_ca_topic_score_gemma":0.023867141,"teacher_disagreement_score":0.39856124,"about_ca_system_score_codex":0.0000067796745,"about_ca_system_score_gemma":0.0003609474,"threshold_uncertainty_score":0.99394476},"labels":[],"label_agreement":null},{"id":"W7070195410","doi":"","title":"Operationalizing longitudinal approaches to climate change vulnerability assessment in the Arctic","year":2016,"lang":"en","type":"other","venue":"USC Research Bank (University of the Sunshine Coast)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Vulnerability (computing); Operationalization; Climate change; Dynamism; Adaptive capacity; Vulnerability assessment; Psychological resilience; Adaptation (eye)","score_opus":0.16196054080362127,"score_gpt":0.35544504509580627,"score_spread":0.193484504292185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070195410","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08178459,0.0019854004,0.0073813726,0.10675431,0.0007351475,0.011113229,0.001415426,0.00011394623,0.78871655],"genre_scores_gemma":[0.8401833,0.0006607217,0.0049067046,0.00039421668,0.000667669,0.00004543067,0.00029109995,0.0001785224,0.15267232],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975138,0.0009367765,0.00014851167,0.00034820585,0.00066027377,0.00039246355],"domain_scores_gemma":[0.9986763,0.00010755227,0.00013300999,0.0009161666,0.000100958474,0.00006603736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002687011,0.00019172435,0.00025943865,0.00019463694,0.0002753296,0.000037621976,0.0013817268,0.00019420047,0.0008099056],"category_scores_gemma":[0.00023700533,0.00012058122,0.00017495174,0.00026274245,0.0003119651,0.000010615461,0.001336465,0.0006108817,0.000030475027],"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":[0.0005722898,0.0009433269,0.17241874,0.0031283873,0.0017234059,0.000037901336,0.006111492,0.0006622274,0.0016261786,0.023958653,0.77686507,0.011952358],"study_design_scores_gemma":[0.0016664616,0.0006369179,0.16688156,0.0007159925,0.00023950828,0.000024114657,0.0023248007,0.0012064524,0.00010429934,0.00049618474,0.8249118,0.0007919288],"about_ca_topic_score_codex":0.002164999,"about_ca_topic_score_gemma":0.011969225,"teacher_disagreement_score":0.7583987,"about_ca_system_score_codex":0.000083043116,"about_ca_system_score_gemma":0.00013780042,"threshold_uncertainty_score":0.8867898},"labels":[],"label_agreement":null},{"id":"W7070209749","doi":"","title":"In Peril, In Prospect","year":2019,"lang":"en","type":"book","venue":"eScholarship (California Digital Library)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; Yale University","keywords":"Energy (signal processing); Health care; Test (biology); Modern medicine; Disease; Wonder","score_opus":0.005955644401923103,"score_gpt":0.21226436083938768,"score_spread":0.20630871643746457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070209749","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":[0.024258623,0.00075941725,0.000017556587,0.00024942734,0.00025873753,0.00085913955,0.001960824,0.00007332969,0.9715629],"genre_scores_gemma":[0.056685947,0.00013828122,0.00064495584,0.0014366076,0.0005438512,0.00004679942,0.010751632,0.00029931913,0.9294526],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99768364,0.000058924372,0.0007453897,0.00063845614,0.00032697443,0.00054659985],"domain_scores_gemma":[0.99876803,0.000038638256,0.0002637958,0.00076175807,0.00002292046,0.00014486564],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00020043584,0.00055963604,0.0005154364,0.00031845976,0.00002928303,0.0005219984,0.00074472575,0.0008733293,0.00053673564],"category_scores_gemma":[0.000265897,0.00056044647,0.00021777808,0.0001816125,0.000094004594,0.00013535195,0.0006215696,0.0012824048,0.0029710091],"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":[0.0011157811,0.00070029654,0.56241024,0.0025928826,0.0002488363,0.00039813723,0.00014496893,0.00047642362,0.0008343212,0.006898739,0.41759104,0.0065883417],"study_design_scores_gemma":[0.00072900107,0.0001885256,0.0012973929,0.00027141217,0.000006439035,0.000022798506,0.000005296821,0.00008986979,0.00046342402,0.002815845,0.9933999,0.0007100685],"about_ca_topic_score_codex":0.0000013799029,"about_ca_topic_score_gemma":0.0000065868203,"teacher_disagreement_score":0.5758089,"about_ca_system_score_codex":0.0000846335,"about_ca_system_score_gemma":0.0005726314,"threshold_uncertainty_score":0.9996847},"labels":[],"label_agreement":null},{"id":"W7070222327","doi":"","title":"Où va l'analyse des politiques publiques au 21e siècle?","year":2019,"lang":"fr","type":"article","venue":"Digital Access to Libraries (Université catholique de Louvain (UCL), l'Université de Namur (UNamur) and the Université Saint-Louis (USL-B))","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Politics; Context (archaeology); Public opinion","score_opus":0.008859909161401102,"score_gpt":0.21897501708091438,"score_spread":0.21011510791951327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070222327","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7376731,0.0029386745,0.004237067,0.01676537,0.00038601764,0.0012284009,0.0007111524,0.00027868134,0.23578154],"genre_scores_gemma":[0.892117,0.0025166874,0.002228349,0.003265786,0.00035937334,0.0000067831993,0.0008412195,0.00019157452,0.09847321],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99399626,0.00078836904,0.00068937824,0.0014498904,0.00067567796,0.0024004278],"domain_scores_gemma":[0.99481964,0.00050008355,0.0007710647,0.001570141,0.0007889374,0.0015501064],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0009294947,0.0013266335,0.0012439416,0.0011005373,0.0020739175,0.002143617,0.0034864892,0.0012378067,0.0006989639],"category_scores_gemma":[0.00052397046,0.0014137116,0.0008801301,0.0016903703,0.002527654,0.0008059721,0.006113998,0.0011766773,0.00021135832],"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":[0.009135826,0.00068407453,0.16929825,0.001747928,0.003393977,0.0014090058,0.150655,0.0029168376,0.0015854669,0.6154441,0.015943723,0.027785795],"study_design_scores_gemma":[0.0060921214,0.0011673662,0.027010065,0.00051639625,0.0009098542,0.0008386079,0.012438918,0.003895352,0.0031480636,0.005123158,0.9363807,0.0024794175],"about_ca_topic_score_codex":0.0045966012,"about_ca_topic_score_gemma":0.00052288064,"teacher_disagreement_score":0.920437,"about_ca_system_score_codex":0.0030233767,"about_ca_system_score_gemma":0.0016316739,"threshold_uncertainty_score":0.9999485},"labels":[],"label_agreement":null},{"id":"W7070227410","doi":"","title":"Ocean Healing Yoga Nidra: Soothe Your Body &amp; Mind | YWM 642","year":2023,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Feeling; Meditation; Bathing; Anxiety; Body position; Relaxation (psychology)","score_opus":0.007817377266752823,"score_gpt":0.22127153582268771,"score_spread":0.2134541585559349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070227410","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":[0.00036669767,0.00028023767,0.000009574621,0.00014231713,0.00045638386,0.00040738966,0.00027471318,0.00018923321,0.9978734],"genre_scores_gemma":[0.00040126644,0.00045258898,0.0040901876,0.00029322016,0.00042629798,0.00000854624,0.001024055,0.00037337444,0.9929305],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979292,0.00008133812,0.00082017755,0.00028653286,0.0004331911,0.00044954775],"domain_scores_gemma":[0.9981501,0.000047668207,0.0008181456,0.00069512136,0.00013808039,0.00015087874],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003716674,0.00047455987,0.00044539495,0.00010821055,0.000100307254,0.00006617242,0.00049398735,0.00076138065,0.08240343],"category_scores_gemma":[0.00039647432,0.00047295415,0.00024254105,0.000014104874,0.00014459835,5.2286826e-8,0.00023077238,0.00039403056,0.011887812],"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":[0.000060543778,0.000028798418,0.000021216822,0.00040745348,0.00013155465,0.00000530874,0.00012843817,0.00075413386,0.0000070200626,0.0000072603466,0.9971585,0.0012897309],"study_design_scores_gemma":[0.00050462846,0.00016378763,0.000009122758,0.00020737796,0.000058334266,0.00007161275,0.000091426125,0.00005542794,0.00006341333,0.0000029419139,0.9982888,0.0004831245],"about_ca_topic_score_codex":0.001735751,"about_ca_topic_score_gemma":0.0014736436,"teacher_disagreement_score":0.07051562,"about_ca_system_score_codex":0.000032639837,"about_ca_system_score_gemma":0.000062363986,"threshold_uncertainty_score":0.9997722},"labels":[],"label_agreement":null},{"id":"W7070233581","doi":"","title":"Ontario’s Renewable Energy Plans: A Staggered Approach Towards a Greener Future","year":2023,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Renewable energy; Production (economics); Energy (signal processing); Sustainability","score_opus":0.007803451549223336,"score_gpt":0.21963006322625883,"score_spread":0.21182661167703548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070233581","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":[0.000015474316,0.0003537903,0.009788768,0.000061896506,0.00056028925,0.0001745004,0.00013926702,0.00033437827,0.98857164],"genre_scores_gemma":[0.0000768993,0.00041653417,0.012576055,0.00048181528,0.0015543803,0.00006214693,0.0020145993,0.0008008778,0.9820167],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984813,0.00004508138,0.00029114494,0.00049300364,0.0002822328,0.00040728107],"domain_scores_gemma":[0.99878967,0.0000039857396,0.00021749546,0.00083326997,0.00003353177,0.00012204495],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012776734,0.0004515485,0.0003711844,0.00015378646,0.0000478024,0.000046782574,0.0004485258,0.0009873294,0.0019029421],"category_scores_gemma":[0.000024349856,0.0003747496,0.00017570282,0.00012013376,0.0000502123,0.000001990945,0.0002589185,0.0002496292,0.00007988821],"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":[0.00002821356,0.000035702986,0.00021946414,0.0000866653,0.0002485851,0.0000045788092,0.000069718946,0.00016426532,0.00009016448,0.0001557582,0.99612355,0.0027733336],"study_design_scores_gemma":[0.0004238452,0.000110264686,0.000063707084,0.000035585694,0.000034191704,0.000017740054,0.00007243658,0.00024032517,0.0002407583,0.0000132958785,0.9982551,0.0004927805],"about_ca_topic_score_codex":0.15832011,"about_ca_topic_score_gemma":0.55460835,"teacher_disagreement_score":0.39628822,"about_ca_system_score_codex":0.00005261633,"about_ca_system_score_gemma":0.00031715818,"threshold_uncertainty_score":0.9998704},"labels":[],"label_agreement":null},{"id":"W7070241997","doi":"","title":"~1-888-879-016.3++Phone Number,norton 360 phone number norton Support Phone Number!!@~1-888-879-0163++ norton support phone number","year":2016,"lang":"en","type":"other","venue":"OSF Preprints (OSF Preprints)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Phone; Toll; Service (business); The Internet; Mobile phone","score_opus":0.007380480357252584,"score_gpt":0.26523400732607794,"score_spread":0.25785352696882535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070241997","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":[0.04409304,0.0000142512945,0.0023889926,0.00038214363,0.0033538996,0.0028228003,0.0010434365,0.00084199203,0.9450594],"genre_scores_gemma":[0.025027808,0.0020129194,0.006386868,0.0010354378,0.0023488284,0.00077906414,0.0050074323,0.0019270176,0.9554746],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9832335,0.0012151141,0.0036874504,0.0062082564,0.0024420642,0.0032136065],"domain_scores_gemma":[0.98366684,0.00033253798,0.0034758742,0.010164057,0.00076297205,0.0015977029],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.0045094304,0.003246764,0.0029730578,0.00040633028,0.0006048746,0.00046369768,0.004400012,0.0040497524,0.8777072],"category_scores_gemma":[0.0019088145,0.0033772665,0.001703495,0.00079841353,0.001212011,0.00015319913,0.005296931,0.002967924,0.9354552],"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":[0.0008369151,0.00143087,0.08961527,0.0010954051,0.0019482535,0.00026824465,0.0008977508,0.0000727313,0.015090116,0.000118794414,0.88330483,0.0053207986],"study_design_scores_gemma":[0.0044757505,0.000015916363,0.0029831633,0.0005822184,0.0005942332,0.0015123509,0.0001560765,0.00008668761,0.03742603,0.00026485772,0.9480962,0.003806528],"about_ca_topic_score_codex":0.0029355246,"about_ca_topic_score_gemma":0.0013649473,"teacher_disagreement_score":0.0866321,"about_ca_system_score_codex":0.00076043437,"about_ca_system_score_gemma":0.0015131567,"threshold_uncertainty_score":0.99933225},"labels":[],"label_agreement":null},{"id":"W7070252483","doi":"","title":"The Ottawa Charter Twenty Years On: an International Nursing Student Exchange Program Perspective&#13;\\n&#13;\\n&#13;\\n&#13;\\n","year":2007,"lang":"en","type":"other","venue":"Bournemouth University Research Online (Bournemouth University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Charter; MEDLINE; Study abroad; Nurse education; Government (linguistics); Licensure; Field (mathematics)","score_opus":0.026613234420921825,"score_gpt":0.35864567781546997,"score_spread":0.3320324433945481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070252483","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":[0.06935576,0.00048263988,0.0005017107,0.0020521167,0.0015652417,0.0027848305,0.0014888518,0.00055388577,0.92121494],"genre_scores_gemma":[0.024080077,0.0028151635,0.0012246508,0.00020245569,0.0026078068,0.0000026652012,0.0019377881,0.0005130871,0.96661633],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9925051,0.0012066603,0.0005268636,0.0016043747,0.0022436369,0.0019133957],"domain_scores_gemma":[0.99510306,0.00015471311,0.00073790614,0.0019233684,0.0011049787,0.0009759447],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0019128403,0.00095949,0.0007083073,0.002912346,0.0013133205,0.00043685,0.0042985957,0.0012565106,0.0008339656],"category_scores_gemma":[0.00032877713,0.0009879238,0.0005643765,0.0014803588,0.0016061625,0.000097451906,0.0014670966,0.0029480879,0.0002635067],"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":[0.008433312,0.013807653,0.022429945,0.000589501,0.006330747,0.004229218,0.018957876,0.00070373004,0.00031526203,0.017279666,0.72949505,0.17742805],"study_design_scores_gemma":[0.0033796763,0.0015105277,0.008504079,0.00041860802,0.00016449128,0.00004321574,0.02826585,0.00049220567,0.000026997155,0.000045498273,0.95606774,0.0010810975],"about_ca_topic_score_codex":0.0016402997,"about_ca_topic_score_gemma":0.009068462,"teacher_disagreement_score":0.22657272,"about_ca_system_score_codex":0.001406708,"about_ca_system_score_gemma":0.00086108304,"threshold_uncertainty_score":0.9999868},"labels":[],"label_agreement":null},{"id":"W7070253295","doi":"","title":"Editorial","year":2007,"lang":"en","type":"article","venue":"Open ULeth Scholarship (OPUS) (University of Lethbridge)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Reading (process); Front (military); Government (linguistics); Period (music); Closing (real estate)","score_opus":0.012915141359108427,"score_gpt":0.2709487446016577,"score_spread":0.25803360324254926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070253295","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9154472,0.00011188213,0.01384673,0.0007042985,0.0113341,0.00059788337,0.000053278574,0.000044829274,0.057859845],"genre_scores_gemma":[0.9560775,0.00006833246,0.02836533,0.0004829871,0.007979869,4.007488e-7,0.0002468495,0.000040017323,0.0067387135],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985998,0.00011651632,0.00022450763,0.0003273094,0.00037011324,0.00036174653],"domain_scores_gemma":[0.9986821,0.00004763067,0.00026500653,0.0005882781,0.00023529137,0.0001817273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021342337,0.00018233943,0.00023852344,0.000095614225,0.00028130322,0.00007472803,0.0013882171,0.0003467856,0.00012009995],"category_scores_gemma":[0.00031182874,0.00022518118,0.00013023548,0.00019213649,0.00018115566,0.000062920735,0.0008879522,0.0004941991,0.00011110465],"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":[0.0024032164,0.00038363415,0.08233234,0.00020895101,0.00037910655,0.000053520875,0.0013787987,0.00014300205,0.34538427,0.0028396074,0.5342233,0.03027021],"study_design_scores_gemma":[0.0018660257,0.00035351756,0.032538872,0.000043707965,0.000042421296,0.000017369508,0.00057233433,0.000029765692,0.019959493,0.00008995946,0.94407225,0.00041428243],"about_ca_topic_score_codex":0.00029339176,"about_ca_topic_score_gemma":0.0001354296,"teacher_disagreement_score":0.40984893,"about_ca_system_score_codex":0.000034980443,"about_ca_system_score_gemma":0.00013077995,"threshold_uncertainty_score":0.9182622},"labels":[],"label_agreement":null},{"id":"W7070254495","doi":"","title":"Perceived Knowledge, Guidelines Concordance, and Practices of Physicians for Management of Recurrent Urinary Tract Infections in Women","year":2024,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Specialty; Health care; Concordance; Obstetrics and gynaecology; Infectious disease (medical specialty)","score_opus":0.16031229472673178,"score_gpt":0.5737566150471877,"score_spread":0.41344432032045586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070254495","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9755331,0.019508684,0.0005503689,0.00010668708,0.00028893352,0.00046757906,0.000053773045,0.0000075663283,0.003483264],"genre_scores_gemma":[0.9682923,0.029562626,0.0016053173,0.00004605195,0.000096875265,0.00008024533,0.000023638866,0.000023813185,0.0002691418],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99860764,0.000096337004,0.0007409872,0.00022509678,0.00015284665,0.0001770984],"domain_scores_gemma":[0.9985415,0.00013245236,0.00079227326,0.00022803643,0.00025812042,0.00004761567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084511697,0.00016650329,0.00037189957,0.0003033931,0.00005232937,0.00013197878,0.0005395266,0.00006939559,0.00011502809],"category_scores_gemma":[0.00027334018,0.00015322187,0.00009835482,0.00034221995,0.000095698415,0.00010089125,0.00040225202,0.00016000918,6.6025075e-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":[0.0012579436,0.0042678835,0.27672532,0.008230049,0.0017073684,0.00002341977,0.0023376301,0.0015787701,0.30671763,0.00039342628,0.04790162,0.34885895],"study_design_scores_gemma":[0.0017831987,0.00073916395,0.73975563,0.0048871543,0.00027743698,0.000059186666,0.0014757595,0.005327304,0.019085746,0.0009888088,0.22491115,0.00070945476],"about_ca_topic_score_codex":0.00006261751,"about_ca_topic_score_gemma":0.000019752259,"teacher_disagreement_score":0.4630303,"about_ca_system_score_codex":0.000037878137,"about_ca_system_score_gemma":0.000081349404,"threshold_uncertainty_score":0.6248207},"labels":[],"label_agreement":null},{"id":"W7070269370","doi":"","title":"Patterns in the &lt;i&gt;Jordan&lt;/i&gt; Case Law One Year After &lt;i&gt;Cody&lt;/i&gt;","year":2018,"lang":"en","type":"article","venue":"eYLS (Yale Law School)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Supreme court; Obligation; Common law; Section (typography); Economic Justice; High Court","score_opus":0.008665007678480907,"score_gpt":0.24063601197085266,"score_spread":0.23197100429237175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070269370","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9421635,0.0012240742,0.0007014644,0.000787114,0.000639301,0.00080807746,0.00025708583,0.000107237116,0.05331214],"genre_scores_gemma":[0.98633784,0.00018273063,0.002990792,0.0048193564,0.0016093032,0.0001575802,0.00033230998,0.00012881059,0.0034413063],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959364,0.00045907588,0.0009280473,0.0008519471,0.00070470583,0.0011198339],"domain_scores_gemma":[0.9969202,0.00010070868,0.00034085603,0.0020048283,0.00025013863,0.00038323324],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011643287,0.00067165954,0.00053729594,0.0001231585,0.0004357794,0.00029583139,0.0010973118,0.00061481,0.00096053095],"category_scores_gemma":[0.00029223546,0.0005811801,0.00031142336,0.00033075147,0.0005522809,0.00006135944,0.00061314605,0.00070238113,0.0013115912],"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":[0.0015194714,0.0020376553,0.014059208,0.00093725306,0.0011321547,0.0020256285,0.004547566,0.00033492508,0.71395844,0.17282854,0.08219478,0.0044243415],"study_design_scores_gemma":[0.0021407944,0.00086654787,0.006360716,0.00017327453,0.00013981853,0.00051532924,0.00008949965,0.00047762718,0.01203062,0.00046590218,0.97558725,0.0011525968],"about_ca_topic_score_codex":0.00016818667,"about_ca_topic_score_gemma":0.014684918,"teacher_disagreement_score":0.8933925,"about_ca_system_score_codex":0.00009262938,"about_ca_system_score_gemma":0.00013469209,"threshold_uncertainty_score":0.99995273},"labels":[],"label_agreement":null},{"id":"W7070278752","doi":"","title":"Outlier detection methods for meta-analyses of site-specific effect estimates from a multi-site network","year":2023,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"Canadian Institutes of Health Research","keywords":"Outlier; Residual; Variance (accounting); Studentized residual; Anomaly detection; Standard deviation; Estimation; Pairwise comparison","score_opus":0.0524143185288902,"score_gpt":0.33991663005491557,"score_spread":0.28750231152602534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070278752","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":[0.7657274,0.002150448,0.23007771,0.000029356677,0.00063275493,0.0008083098,0.00027290315,0.0000647109,0.00023640682],"genre_scores_gemma":[0.15468472,0.0007775509,0.8222389,0.000025568737,0.0003894271,0.000023919762,0.015708614,0.00020240543,0.005948856],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987746,0.0002276415,0.00023591485,0.00037453903,0.00016759647,0.00021972384],"domain_scores_gemma":[0.9982148,0.00031740905,0.00072823965,0.00046057854,0.00022504485,0.000053961805],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005479892,0.0003157953,0.00080644526,0.0001528008,0.00016214598,0.000018187382,0.0003067397,0.00046127127,0.000015197302],"category_scores_gemma":[0.0002456515,0.00033525578,0.0007714155,0.00018782257,0.0000620519,0.000007894668,0.00010754113,0.00020164612,0.000019182944],"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":[0.0024665936,0.00013481361,0.012082521,0.0018886235,0.014847671,0.000006580173,0.001161215,0.018990478,0.9211774,0.000011637927,0.008687912,0.01854459],"study_design_scores_gemma":[0.004515359,0.0024412205,0.1525843,0.0003278231,0.03449585,0.000003980227,0.008160443,0.09791381,0.64500153,0.00015663971,0.052373495,0.0020255554],"about_ca_topic_score_codex":0.0014994886,"about_ca_topic_score_gemma":0.07321877,"teacher_disagreement_score":0.6110427,"about_ca_system_score_codex":0.000026803098,"about_ca_system_score_gemma":0.00002918013,"threshold_uncertainty_score":0.99990994},"labels":[],"label_agreement":null},{"id":"W7070280727","doi":"","title":"Oklahoma Firefighter (Oklahoma City, Okla.), Vol. 19, No. 5, Ed. 1 Thursday, August 1, 2002","year":2002,"lang":"en","type":"other","venue":"The Gateway to Oklahoma History","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"State (computer science); Information system; Association (psychology); Quarter (Canadian coin)","score_opus":0.010969001802913611,"score_gpt":0.22078485157824446,"score_spread":0.20981584977533085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070280727","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":[0.0010804207,0.01942603,0.000282696,0.0005182266,0.0061537917,0.0014434701,0.00029303404,0.0005326098,0.97026974],"genre_scores_gemma":[0.000821911,0.00135113,0.0019855248,0.0042571425,0.0048854104,0.00021327,0.0005638046,0.0011982287,0.98472357],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951139,0.0003376395,0.0009794865,0.0013157061,0.00093687576,0.0013163927],"domain_scores_gemma":[0.99476224,0.00007561147,0.00086930115,0.0033527554,0.00029835998,0.00064173853],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.00060251786,0.0014070304,0.001024357,0.00046128168,0.0003388576,0.000100342324,0.0023903605,0.0014412492,0.0482778],"category_scores_gemma":[0.0006589567,0.0011660533,0.00062777137,0.0002507545,0.0006708428,0.0000143587895,0.0011204919,0.0011462463,0.014406447],"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":[0.00010928137,0.00016879478,0.00018116031,0.00022896763,0.0002644945,0.000031486918,0.00035590143,0.00003700236,0.0011143846,0.0000438639,0.99546206,0.0020025987],"study_design_scores_gemma":[0.00087804714,0.0004654285,0.00028633612,0.0002040993,0.00017530762,0.00009828112,0.000025256566,0.00016717079,0.00030597925,0.000011679014,0.9958604,0.0015220254],"about_ca_topic_score_codex":0.0008308015,"about_ca_topic_score_gemma":0.00051659415,"teacher_disagreement_score":0.033871353,"about_ca_system_score_codex":0.00057683676,"about_ca_system_score_gemma":0.0003156062,"threshold_uncertainty_score":0.999868},"labels":[],"label_agreement":null},{"id":"W7070283709","doi":"","title":"Organización de Eventos Deportivos - DT50 - 202101","year":2021,"lang":"es","type":"report","venue":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Subject (documents); Quarter (Canadian coin); Kingdom","score_opus":0.01639599769143287,"score_gpt":0.26381895645462144,"score_spread":0.24742295876318857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070283709","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1457707,0.019196797,0.02949948,0.021205714,0.010428817,0.004133633,0.0013139476,0.0011348295,0.7673161],"genre_scores_gemma":[0.9638708,0.007530792,0.010354061,0.0005400732,0.00412219,0.0003145734,0.0065573296,0.00035724297,0.006352911],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9904638,0.001070875,0.0024899738,0.0019458017,0.0020850657,0.0019444886],"domain_scores_gemma":[0.9919692,0.00020233353,0.0022598226,0.0022396739,0.0021078207,0.0012211241],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.002000031,0.0016059332,0.0015345264,0.0005949088,0.0011142945,0.00073590525,0.0016312979,0.003432949,0.00033337297],"category_scores_gemma":[0.0052052583,0.0017128125,0.0009988813,0.0010880395,0.00008089075,0.00008592803,0.0014569,0.0025458464,0.00006002867],"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":[0.002217208,0.010385932,0.050770603,0.014810004,0.014583037,0.012103706,0.008018409,0.002597479,0.24470371,0.48180908,0.115356654,0.042644188],"study_design_scores_gemma":[0.0012393048,0.00025470855,0.004095895,0.0008679712,0.00052471826,0.012890075,0.00042285907,0.00049417856,0.011128005,0.000059385748,0.9663142,0.0017087028],"about_ca_topic_score_codex":0.000008554356,"about_ca_topic_score_gemma":0.00024233395,"teacher_disagreement_score":0.8509576,"about_ca_system_score_codex":0.0016650867,"about_ca_system_score_gemma":0.008893245,"threshold_uncertainty_score":0.9997553},"labels":[],"label_agreement":null},{"id":"W7070287968","doi":"","title":"Observation of B0âÏc0K*0 and evidence for B+âÏc0K*+","year":2008,"lang":"en","type":"article","venue":"eScholarship (California Digital Library)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"SLAC National Accelerator Laboratory; Institut National de Physique Nucléaire et de Physique des Particules; Centre National de la Recherche Scientifique; Bundesministerium für Bildung und Forschung; Science and Technology Facilities Council; Alfred P. Sloan Foundation; Natural Sciences and Engineering Research Council of Canada; U.S. Department of Energy; European Commission; Deutsche Forschungsgemeinschaft; Ministerio de Economía y Competitividad; National Science Foundation","keywords":"Branching fraction; Detector; Standard deviation; Particle decay; Branching (polymer chemistry); Electron–positron annihilation; B meson; Meson","score_opus":0.03352418969237961,"score_gpt":0.2563689875083426,"score_spread":0.22284479781596297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070287968","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99443066,0.00069503795,0.0026187396,0.00024804228,0.000043623433,0.0002733327,0.00038431803,0.000039603172,0.0012666276],"genre_scores_gemma":[0.9865473,0.00014736975,0.011158392,0.00037182285,0.000104367326,0.000018608529,0.00060380006,0.000034668876,0.0010136905],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990701,0.000026418127,0.0003360711,0.00022596701,0.00014674243,0.00019469718],"domain_scores_gemma":[0.99930614,0.00009297978,0.00016733688,0.00027563336,0.000056553803,0.0001013724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012788558,0.000157091,0.00015662998,0.000048861035,0.00009178311,0.00009443088,0.00021819294,0.0001339125,0.000017708675],"category_scores_gemma":[0.0010508243,0.0001468986,0.000088797904,0.000111210946,0.00012265205,0.00015067354,0.00016404246,0.00011350494,0.00002631203],"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":[0.0004302927,0.00008960127,0.9645349,0.00042565668,0.00005874044,0.0000023989578,0.00005180776,0.000046904403,0.021166947,0.0007196981,0.0056313383,0.0068417555],"study_design_scores_gemma":[0.0023599186,0.0015861165,0.22111548,0.00042298267,0.000052774103,0.0001370271,0.000051655585,0.0022152066,0.1883998,0.0026405363,0.5798985,0.0011200442],"about_ca_topic_score_codex":9.898517e-7,"about_ca_topic_score_gemma":2.756538e-7,"teacher_disagreement_score":0.74341935,"about_ca_system_score_codex":0.000004288309,"about_ca_system_score_gemma":0.00007593333,"threshold_uncertainty_score":0.5990351},"labels":[],"label_agreement":null},{"id":"W7070289231","doi":"","title":"Only speaking out against Quebec's controversial Bill-21 after election &amp; Sports Talk with Don Robertson","year":2021,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Blame; Politics; Test (biology); Head (geology); Beijing; Government (linguistics)","score_opus":0.002966684088368586,"score_gpt":0.1852169298791103,"score_spread":0.1822502457907417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070289231","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":[0.002324312,0.00036184836,0.000024917457,0.00010070317,0.00035819394,0.0004311007,0.00006320971,0.00007197601,0.99626374],"genre_scores_gemma":[0.0068028946,0.0002817443,0.0024801246,0.0005467724,0.0003964378,0.000015082461,0.0019537397,0.00015489718,0.9873683],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99816006,0.000074986354,0.0006109384,0.00030406375,0.0004806893,0.00036927944],"domain_scores_gemma":[0.9983198,0.00002146844,0.00081389013,0.0005340707,0.00019410935,0.000116640316],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017602307,0.0004709783,0.00044454736,0.00008553326,0.00007084383,0.00008717558,0.00022199098,0.0006252061,0.16764067],"category_scores_gemma":[0.00011807295,0.0003952705,0.00019619851,0.000010871971,0.00011709195,1.1016067e-7,0.00012099944,0.00034901197,0.00017696884],"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":[0.00038900363,0.00004415172,0.00007451201,0.00042945848,0.00014787313,0.0000302509,0.000115526505,0.0008269861,0.00002838105,0.0000021917158,0.99482673,0.0030849595],"study_design_scores_gemma":[0.00079349364,0.00018562817,0.000056504363,0.00043779105,0.00007367756,0.00013756148,0.0000713895,0.000037057423,0.00011097996,3.7305102e-7,0.9975839,0.00051158847],"about_ca_topic_score_codex":0.026040185,"about_ca_topic_score_gemma":0.20656666,"teacher_disagreement_score":0.18052648,"about_ca_system_score_codex":0.00006293693,"about_ca_system_score_gemma":0.000104950734,"threshold_uncertainty_score":0.9998499},"labels":[],"label_agreement":null},{"id":"W7070318237","doi":"","title":"Red Cloud","year":2013,"lang":"en","type":"other","venue":"ThinkTech (Texas Tech University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"TSG101; Liquation; Limiting; Gloom; Circumstantial evidence; Buckle","score_opus":0.004450924681999022,"score_gpt":0.1927879455822812,"score_spread":0.1883370209002822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070318237","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":[0.00025220835,0.0001819454,0.004640299,0.00012507928,0.00031985051,0.00041573014,0.000040095747,0.00042579378,0.993599],"genre_scores_gemma":[0.0005263077,0.00044933587,0.009792434,0.00015844824,0.00042476738,9.0975664e-7,0.00034706865,0.00028692713,0.9880138],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998849,0.00006461164,0.00015530593,0.00039512134,0.00020123228,0.00033473314],"domain_scores_gemma":[0.9986268,0.000007719478,0.00026824506,0.0009269812,0.00005049215,0.00011974474],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00010298834,0.00035967308,0.00028091704,0.00039492402,0.00007235065,0.000030248735,0.00086014654,0.00096074713,0.001789546],"category_scores_gemma":[0.00005565786,0.00038380458,0.0001444829,0.00024788146,0.00013555674,0.0000043060554,0.00049244973,0.0004405111,0.00085541676],"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":[0.000016606324,0.000029922854,0.00012533022,0.000079015816,0.00013990258,0.00001649283,0.000012246125,0.000005461292,0.0015299029,0.0019468952,0.99520725,0.0008909718],"study_design_scores_gemma":[0.00039955004,0.00013181998,0.000022525128,0.00006742456,0.00005039943,0.000012102199,0.000025706664,0.000054700893,0.0016009248,0.000040396186,0.9971482,0.00044620628],"about_ca_topic_score_codex":0.00014557574,"about_ca_topic_score_gemma":0.00004558604,"teacher_disagreement_score":0.0055851964,"about_ca_system_score_codex":0.0000476463,"about_ca_system_score_gemma":0.00008934178,"threshold_uncertainty_score":0.9999225},"labels":[],"label_agreement":null},{"id":"W7070335116","doi":"","title":"One-Person Households in Canada and the Implications for Health: A Health Geography Perspective","year":2023,"lang":"en","type":"dissertation","venue":"QSpace (Queen's University Library)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Microdata (statistics); Census; Public health; Socioeconomic status; Marital status; Population; Context (archaeology); Population health; Life course approach; Perspective (graphical)","score_opus":0.007992884518654837,"score_gpt":0.2286437924617479,"score_spread":0.22065090794309306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070335116","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3243425,0.0009945781,0.00036467504,0.66282785,0.0004802058,0.0039840727,0.0015957844,0.00019137662,0.005218932],"genre_scores_gemma":[0.8361248,0.016858237,0.007952637,0.009434703,0.0004014362,0.0000987233,0.019736042,0.00038957095,0.10900384],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9988956,0.00014171208,0.00016799374,0.00035310077,0.000110400026,0.00033117877],"domain_scores_gemma":[0.99908555,0.00008011587,0.00031504728,0.0003365872,0.00004939892,0.00013328061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009966082,0.00021018076,0.0003139171,0.00015972192,0.00030159482,0.00003556147,0.0003128729,0.00015723924,0.0000036763163],"category_scores_gemma":[0.000051702693,0.00021674408,0.00010950113,0.00031424375,0.000067386805,0.00001856858,0.000070167924,0.0002985656,7.0497754e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023487082,0.00013873061,0.10134017,0.0019309641,0.00079293933,0.0000053918748,0.013837281,0.00043667658,0.000012606036,0.019939926,0.85507804,0.0041385954],"study_design_scores_gemma":[0.003758237,0.00058135705,0.8079538,0.00031688652,0.0000829471,8.4935465e-7,0.05405091,0.00007905994,0.00012066052,0.00053733704,0.1315944,0.00092356716],"about_ca_topic_score_codex":0.9085565,"about_ca_topic_score_gemma":0.8336889,"teacher_disagreement_score":0.7234836,"about_ca_system_score_codex":0.00022561234,"about_ca_system_score_gemma":0.0027352476,"threshold_uncertainty_score":0.8838567},"labels":[],"label_agreement":null},{"id":"W7070340494","doi":"","title":"Première partie, Synthèse énantiosélective d'amines Ã-tertiaires, Deuxième partie, Synthèse d'halogénocyclopropylméthanols","year":2000,"lang":"fr","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Liquation; Diafiltration; Emperipolesis; Triacetin; Fusible alloy","score_opus":0.003335400482015859,"score_gpt":0.1632766946353424,"score_spread":0.15994129415332653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070340494","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062809095,0.006439739,0.00030911487,0.0030178356,0.00084793917,0.0010347671,0.0019701952,0.00004022675,0.9235311],"genre_scores_gemma":[0.6962285,0.0036829056,0.0020438677,0.0018382127,0.0005595799,0.0000797078,0.00035655074,0.00028811485,0.29492256],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947288,0.00033765382,0.0010783116,0.0009469444,0.0017713715,0.0011368935],"domain_scores_gemma":[0.9972619,0.00026152705,0.0008469148,0.0009346569,0.000003918157,0.00069111545],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000034566772,0.0010559595,0.0009810034,0.00007945113,0.0003737421,0.000098720135,0.0008327077,0.00043140378,0.002289695],"category_scores_gemma":[0.00004847711,0.0010394314,0.0001890063,0.00016474434,0.00049142796,0.00007759162,0.00054659194,0.00062141963,2.4260592e-7],"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":[0.009311333,0.0014676813,0.21047474,0.013775466,0.00800269,0.0014519955,0.0024035221,0.004522912,0.25995287,0.029457413,0.21454069,0.24463868],"study_design_scores_gemma":[0.00085508934,0.00049351295,0.014860737,0.0012361632,0.00025507424,0.00007600708,0.0008758641,0.0040680375,0.18512593,0.00018928398,0.7904936,0.0014707166],"about_ca_topic_score_codex":0.004449742,"about_ca_topic_score_gemma":0.07643161,"teacher_disagreement_score":0.6334194,"about_ca_system_score_codex":0.000026896663,"about_ca_system_score_gemma":0.0023188293,"threshold_uncertainty_score":0.9992056},"labels":[],"label_agreement":null},{"id":"W7070341526","doi":"","title":"Onderzoek naar het terugdringen van korte detenties met behulp van instrumenten:Changing justice gears - Empirische fase","year":2024,"lang":"nl","type":"book","venue":"Digital Academic REpository of VU University Amsterdam (Vrije Universiteit Amsterdam)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"L'Alliance Boviteq","funders":"","keywords":"Post hoc; European union; Automatism (medicine)","score_opus":0.010127081149628176,"score_gpt":0.22389018603858676,"score_spread":0.21376310488895858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070341526","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6206408,0.002290215,0.0016325938,0.00028588358,0.0027472908,0.001625437,0.0021541237,0.00036042745,0.3682632],"genre_scores_gemma":[0.44029656,0.0011984534,0.0006021958,0.0002589247,0.0007687761,0.0000017101116,0.0023795194,0.00025684506,0.554237],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99235845,0.00040013393,0.0017725456,0.002221116,0.0014859664,0.0017618019],"domain_scores_gemma":[0.9941567,0.0001856319,0.002309501,0.001827157,0.0006220281,0.0008989789],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.0005554279,0.0019740576,0.0017856992,0.0021090447,0.0011560334,0.0004948596,0.003165988,0.0027344262,0.00014547486],"category_scores_gemma":[0.00013049727,0.0024030867,0.0016118172,0.0008373884,0.0016939039,0.0006343574,0.0050595906,0.003400433,0.0004609446],"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":[0.022150595,0.004422889,0.046234332,0.07576091,0.06843531,0.0293392,0.108212195,0.015885092,0.19371325,0.009871088,0.33068728,0.095287874],"study_design_scores_gemma":[0.0039055112,0.002337376,0.00021846243,0.0038151515,0.0063107302,0.0009803724,0.03211628,0.002311108,0.0078287795,0.00014129764,0.93622667,0.0038082784],"about_ca_topic_score_codex":0.00004871972,"about_ca_topic_score_gemma":0.000009640884,"teacher_disagreement_score":0.6055394,"about_ca_system_score_codex":0.0011260733,"about_ca_system_score_gemma":0.0010316,"threshold_uncertainty_score":0.99930024},"labels":[],"label_agreement":null},{"id":"W7070352690","doi":"","title":"Paul Martin - Sept 14","year":2021,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Paraphernalia","score_opus":0.004179551979302814,"score_gpt":0.19578399758839773,"score_spread":0.19160444560909493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070352690","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":[0.00008178509,0.0008381027,0.0000032295231,0.00011221073,0.00029832043,0.00025436602,0.000108874105,0.00006462773,0.9982385],"genre_scores_gemma":[0.00028442586,0.00033532942,0.0032710778,0.0004966964,0.00025307218,0.0000122371675,0.001926102,0.00013922276,0.99328184],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99848706,0.000081434446,0.00060104934,0.00021133795,0.00032320054,0.00029590479],"domain_scores_gemma":[0.9985541,0.00002012123,0.0005939412,0.00057688187,0.00014610024,0.000108859625],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00019943168,0.00034659114,0.00035026888,0.000048222453,0.0000471204,0.00004596419,0.000336314,0.00061618997,0.32885748],"category_scores_gemma":[0.0002530214,0.0003541365,0.00020193573,0.000007182781,0.00010443116,1.2129302e-8,0.00021637924,0.00027847444,0.0036260828],"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":[0.00003283406,0.000028222821,0.000013379559,0.00057768525,0.000095889256,0.00000838354,0.00003131758,0.00015133826,0.000009586206,0.000007063617,0.9981129,0.0009314036],"study_design_scores_gemma":[0.0003970634,0.00014744938,0.000008871834,0.00017937779,0.0000361947,0.00009170241,0.000041741092,0.00003814113,0.00013296683,0.0000018715075,0.9985543,0.00037034796],"about_ca_topic_score_codex":0.00061113236,"about_ca_topic_score_gemma":0.00065823924,"teacher_disagreement_score":0.3252314,"about_ca_system_score_codex":0.000015927411,"about_ca_system_score_gemma":0.000051995998,"threshold_uncertainty_score":0.99989104},"labels":[],"label_agreement":null},{"id":"W7070357374","doi":"","title":"Popular sovereignty, constitutionalism and the Indian constitution","year":2019,"lang":"en","type":"article","venue":"Oxford University Research Archive (ORA) (University of Oxford)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Trinity College","funders":"","keywords":"Constitution; Sovereignty; Constitutionalism; Popular sovereignty; Legitimacy; Democracy; Constitution of India; Politics","score_opus":0.011959532721025427,"score_gpt":0.24146789341531877,"score_spread":0.22950836069429334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070357374","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7970763,0.0000976053,0.006686362,0.0011289741,0.000086234155,0.0008023504,0.0002434788,0.000024086676,0.19385462],"genre_scores_gemma":[0.9922466,0.0010398384,0.0031378143,0.000059749204,0.00002939401,1.3600153e-7,0.0002693456,0.000006912713,0.0032101574],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99837834,0.00038910855,0.00011525557,0.00032003524,0.00042113013,0.00037615022],"domain_scores_gemma":[0.9989103,0.0001237666,0.00013331854,0.0004554075,0.00021688246,0.00016032996],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00081951625,0.00015090055,0.00022645088,0.00026502233,0.00071460597,0.000027729327,0.000707657,0.00014362777,0.00017335666],"category_scores_gemma":[0.00014348478,0.00015211072,0.0001348983,0.00026940723,0.003026299,0.000046596,0.0010391076,0.0004695988,0.00001689196],"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":[0.0025561296,0.00009408603,0.0498512,0.00019535642,0.00029881755,0.000060143193,0.0019652983,0.00044110414,0.0033077518,0.93556964,0.0036418666,0.0020186258],"study_design_scores_gemma":[0.007424998,0.00056395365,0.010722543,0.000095186144,0.00006243325,0.00009689182,0.014240672,0.0032246278,0.00020227335,0.0062312325,0.9567205,0.00041473235],"about_ca_topic_score_codex":0.00042133802,"about_ca_topic_score_gemma":0.00028997957,"teacher_disagreement_score":0.95307857,"about_ca_system_score_codex":0.000053179177,"about_ca_system_score_gemma":0.00034254164,"threshold_uncertainty_score":0.9996869},"labels":[],"label_agreement":null},{"id":"W7070365608","doi":"","title":"Ownership transformation and firm&#13;\\nperformance in the successor states of the&#13;\\nformer Yugoslavia","year":2016,"lang":"en","type":"dissertation","venue":"Staffordshire Online Repository (Staffordshire University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Oxford; York University","keywords":"Successor cardinal; Empirical research; Context (archaeology); Variety (cybernetics); Frontier; Politics; Panel data; Set (abstract data type); Consolidation (business); Imputation (statistics)","score_opus":0.004744935439778682,"score_gpt":0.2206355455046937,"score_spread":0.215890610064915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070365608","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9751486,0.0003850925,0.000084723804,0.00029673273,0.0005252105,0.00082933984,0.0002708184,0.000029728013,0.02242975],"genre_scores_gemma":[0.9792683,0.0011757159,0.00014986334,0.00007763452,0.00020314113,0.00000780895,0.0020178317,0.000060189166,0.017039524],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.997414,0.00023944263,0.0007756765,0.00046467132,0.00058925065,0.00051698147],"domain_scores_gemma":[0.9978224,0.00008265051,0.0008916401,0.00083158055,0.00027168877,0.000100013116],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040143257,0.0005636806,0.00047594108,0.00033521093,0.00047045632,0.00006944758,0.001146895,0.00061608903,0.000012296678],"category_scores_gemma":[0.0000845313,0.0003662936,0.00029093184,0.0005253577,0.0002971451,0.00009931999,0.0001332115,0.0006056507,0.0000021302894],"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":[0.021885594,0.0053227306,0.48808354,0.029567951,0.004234225,0.0003332242,0.12751411,0.0042473343,0.105451345,0.011723043,0.013839006,0.18779789],"study_design_scores_gemma":[0.012520406,0.0044799633,0.26022062,0.005796298,0.0015858533,0.00038175104,0.09723539,0.0047739325,0.09922488,0.00063026854,0.50755024,0.0056003975],"about_ca_topic_score_codex":0.0003325938,"about_ca_topic_score_gemma":0.0054808804,"teacher_disagreement_score":0.49371123,"about_ca_system_score_codex":0.000103987724,"about_ca_system_score_gemma":0.00041086308,"threshold_uncertainty_score":0.9998789},"labels":[],"label_agreement":null},{"id":"W7070374440","doi":"","title":"The Philosophy and Physics of Relationality and Inherent Nature: ??nyat? and Svabh?va in Madhyamaka Buddhist Philosophy, Western Analytic Metaphysics, Philosophy of Science and Physics","year":2013,"lang":"en","type":"dissertation","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interpretation (philosophy); Metaphysics; Buddhism; Meaning (existential); Western philosophy; Philosophy of science; Focus (optics); Philosophy of religion; Buddhist philosophy","score_opus":0.003917936504459268,"score_gpt":0.1863753454303276,"score_spread":0.18245740892586834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070374440","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9626622,0.0038760947,0.000021900805,0.0012636128,0.00014078712,0.0004632098,0.00032850463,0.0000030849271,0.031240605],"genre_scores_gemma":[0.99746424,0.0013073526,0.00048007575,0.00020202924,0.000087818575,0.000007988459,0.00010464745,0.000021147238,0.00032471915],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99788976,0.000060946946,0.00044791528,0.00035189517,0.0010486876,0.00020081627],"domain_scores_gemma":[0.9988883,0.00013322895,0.000553285,0.00027489164,0.000011285103,0.00013897067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000057953122,0.00028691304,0.00039416895,0.000024982379,0.00019105067,0.000035525176,0.00021504224,0.00009962665,8.3280236e-7],"category_scores_gemma":[0.000024541157,0.00024450087,0.000029613102,0.00012468119,0.00084932963,0.00007360064,0.00022835108,0.00031516902,9.886255e-10],"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":[0.0015511937,0.0002112411,0.17306343,0.008477578,0.0009013469,0.000009829704,0.0013398356,0.00015092861,0.095573604,0.6847746,0.0002523152,0.033694133],"study_design_scores_gemma":[0.0028277913,0.000914448,0.5944055,0.0017757278,0.00041818412,0.00001892011,0.0035936765,0.013959489,0.1629493,0.21521366,0.0021202574,0.0018031052],"about_ca_topic_score_codex":0.0005253131,"about_ca_topic_score_gemma":0.0022342782,"teacher_disagreement_score":0.4695609,"about_ca_system_score_codex":0.000006745814,"about_ca_system_score_gemma":0.0007145205,"threshold_uncertainty_score":0.99704564},"labels":[],"label_agreement":null},{"id":"W7070378507","doi":"","title":"The Paradox of the Assisted User: Guidance Leads to more Shallow Behavior","year":2005,"lang":"en","type":"article","venue":"DSpace (Open University in the Netherlands)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Term (time); Work (physics); Perspective (graphical); Focus (optics)","score_opus":0.010259353415175011,"score_gpt":0.26822287017544977,"score_spread":0.25796351676027474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070378507","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9824076,0.00007126948,0.00010294355,0.0080213165,0.00006259251,0.0005295649,0.00001855975,0.000006182144,0.008779918],"genre_scores_gemma":[0.9889454,0.000051869996,0.0007933391,0.00080374937,0.000048808964,0.000004291371,0.000012408947,0.000010298023,0.009329832],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99906874,0.00023908695,0.00014139358,0.00015458098,0.00018791758,0.00020829716],"domain_scores_gemma":[0.9989604,0.000059573627,0.00014134884,0.00074957375,0.00005201138,0.000037124355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055445055,0.00012436522,0.0001180875,0.00002356478,0.00025098657,0.00004981847,0.0020693974,0.00009883967,0.000015026126],"category_scores_gemma":[0.000091331014,0.00007152738,0.000076399796,0.00022497335,0.00013142626,0.000011003524,0.00054460496,0.000201785,0.000012927657],"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":[0.0012435586,0.00056448876,0.8049659,0.00005148162,0.00018067431,0.000019277968,0.015193023,0.015963277,0.041609164,0.0031135553,0.0946517,0.022443863],"study_design_scores_gemma":[0.0009187347,0.00015836315,0.26834583,0.000033263375,0.000037270347,0.000017542294,0.0031566957,0.00050465745,0.0030026603,0.0000053801446,0.72361284,0.00020678845],"about_ca_topic_score_codex":0.00016845539,"about_ca_topic_score_gemma":0.0036772692,"teacher_disagreement_score":0.62896115,"about_ca_system_score_codex":0.000031480642,"about_ca_system_score_gemma":0.00005293647,"threshold_uncertainty_score":0.38454896},"labels":[],"label_agreement":null},{"id":"W7070382729","doi":"","title":"Wholly Quantum","year":2020,"lang":"en","type":"other","venue":"York University Digital Library (York University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University","keywords":"Multitude; Universe; Face (sociological concept); Physicist; Quantum; Exhibition; Parallel universe","score_opus":0.005592145383774592,"score_gpt":0.156902164092564,"score_spread":0.1513100187087894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070382729","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":[0.00034779613,0.00018043934,0.00087533635,0.0002514585,0.0002041309,0.0002563654,0.0017276268,0.00052371604,0.9956331],"genre_scores_gemma":[0.00449457,0.0002717928,0.0015354636,0.00028916134,0.00035637766,5.1167078e-8,0.0039640605,0.00030694788,0.9887816],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99858105,0.00007092455,0.0001442481,0.0005965129,0.00022097256,0.00038626898],"domain_scores_gemma":[0.99874365,0.000018681538,0.0002938936,0.00058731355,0.000014111297,0.0003423622],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000015003911,0.0004679963,0.0003696343,0.00044211943,0.00014601354,0.0001660792,0.0012819716,0.0006345155,0.00086896616],"category_scores_gemma":[0.000022807255,0.00058992207,0.00030949066,0.00065129687,0.00024526252,0.00007066757,0.0010700269,0.00040565198,0.00059940596],"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":[0.0001907521,0.000057024416,0.0016440675,0.000102322374,0.0002501313,0.00020611516,0.000040505343,0.000017807542,0.000039325234,0.004544629,0.9922987,0.00060859544],"study_design_scores_gemma":[0.0006716628,0.0002151326,0.00004755368,0.00008894496,0.00006715241,0.000010732568,0.0006369292,0.00005459802,0.00005009116,0.000013799639,0.99749196,0.0006514678],"about_ca_topic_score_codex":0.000023649693,"about_ca_topic_score_gemma":0.000012089348,"teacher_disagreement_score":0.0068515562,"about_ca_system_score_codex":0.00003399352,"about_ca_system_score_gemma":0.00028689796,"threshold_uncertainty_score":0.99965525},"labels":[],"label_agreement":null},{"id":"W7070392621","doi":"","title":"Post to Post Podcast - Cannon Goes BOOM","year":2016,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Boom; Equating; Administration (probate law); Football","score_opus":0.0028455345658790652,"score_gpt":0.19603459562378878,"score_spread":0.1931890610579097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070392621","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":[0.0003629963,0.00015322622,0.0000039634606,0.00052865787,0.00032920387,0.0004699597,0.00086633855,0.000085140666,0.9972005],"genre_scores_gemma":[0.0007957811,0.00010433422,0.0019908557,0.001526127,0.00030572436,0.000015858119,0.0009643914,0.00017118665,0.9941257],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983628,0.000059391627,0.0006117429,0.00024024784,0.0003446303,0.00038122264],"domain_scores_gemma":[0.998373,0.000027676278,0.0005311962,0.0005987528,0.00027515757,0.00019425558],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001813477,0.00041778403,0.0003571435,0.00010119269,0.00006307495,0.000050574457,0.0004895422,0.00053958816,0.17086612],"category_scores_gemma":[0.00029505318,0.000359762,0.00016999051,0.0000062160675,0.00010450802,3.6053795e-8,0.0002524151,0.00019739023,0.020446135],"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":[0.00010733615,0.000023238144,0.000011044111,0.00029973383,0.00007930381,0.000004679515,0.00006912159,0.00004903178,0.000105168736,0.000014223047,0.9968484,0.0023886985],"study_design_scores_gemma":[0.00040544302,0.00046557447,0.000026074065,0.00020315875,0.000030624586,0.00006660573,0.000065684275,0.0000036689066,0.00019665106,8.5238025e-7,0.9980793,0.00045639026],"about_ca_topic_score_codex":0.0033758709,"about_ca_topic_score_gemma":0.0023206514,"teacher_disagreement_score":0.15041998,"about_ca_system_score_codex":0.000030911877,"about_ca_system_score_gemma":0.00006747982,"threshold_uncertainty_score":0.99988544},"labels":[],"label_agreement":null},{"id":"W7070392904","doi":"","title":"Observation of new resonances decaying to Dπ and D*π in inclusive e+e- collisions near √s=10.58  GeV","year":2010,"lang":"en","type":"article","venue":"Digital Academic REpository of VU University Amsterdam (Vrije Universiteit Amsterdam)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"SLAC National Accelerator Laboratory; Institut National de Physique Nucléaire et de Physique des Particules; Centre National de la Recherche Scientifique; Bundesministerium für Bildung und Forschung; Science and Technology Facilities Council; Natural Sciences and Engineering Research Council of Canada; European Commission; Alfred P. Sloan Foundation; Deutsche Forschungsgemeinschaft; U.S. Department of Energy; National Science Foundation","keywords":"Resonance (particle physics); Field (mathematics); Interval (graph theory); Spectrum (functional analysis); Limit (mathematics)","score_opus":0.008013728620432486,"score_gpt":0.23335461736301757,"score_spread":0.2253408887425851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070392904","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99008095,0.00007090933,0.00034121724,0.00028044547,0.00013367915,0.0003006631,0.000049946128,0.00001971727,0.008722475],"genre_scores_gemma":[0.9882973,0.000053355314,0.0027784628,0.00007417465,0.00006471698,2.3541529e-7,0.000072000534,0.000017390137,0.008642364],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856967,0.000054424738,0.00042105338,0.00039767794,0.00028496905,0.0002722362],"domain_scores_gemma":[0.99871,0.00007061017,0.0004215384,0.00038132927,0.00018924935,0.00022727235],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015826066,0.00023782713,0.00032676623,0.00028746043,0.00019570139,0.000040134335,0.00059863395,0.0003886584,0.000010814671],"category_scores_gemma":[0.00016667295,0.00028003298,0.00010724149,0.00045481315,0.00031940916,0.00016630383,0.0008670203,0.0004356865,0.0000046692885],"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":[0.0024968039,0.000194336,0.4119247,0.0002826667,0.00019166256,0.000081893086,0.009230771,0.0024121932,0.5560969,0.00064535293,0.004638897,0.011803831],"study_design_scores_gemma":[0.006507046,0.0019037423,0.2034026,0.0008435528,0.00020050567,0.0001750232,0.012613618,0.0040267245,0.1413566,0.000111896494,0.6271381,0.0017206426],"about_ca_topic_score_codex":0.00014561329,"about_ca_topic_score_gemma":0.000053916297,"teacher_disagreement_score":0.62249917,"about_ca_system_score_codex":0.00006467622,"about_ca_system_score_gemma":0.00020129426,"threshold_uncertainty_score":0.9999652},"labels":[],"label_agreement":null},{"id":"W7070414562","doi":"","title":"Objectif Numérique S01E53 - Le syndrôme de Stéphane","year":2014,"lang":"fr","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Panorama; Photography; Digital photography","score_opus":0.0028291082207271188,"score_gpt":0.18257241558064646,"score_spread":0.17974330735991934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070414562","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":[0.0018250097,0.0007969172,0.00009225599,0.0005615356,0.0005071595,0.00055382523,0.0001177836,0.000073139265,0.9954724],"genre_scores_gemma":[0.024019135,0.0006198769,0.005781501,0.00089438824,0.00047019764,0.000025395368,0.00064373325,0.00015572144,0.96739006],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99715775,0.00030426553,0.0011574364,0.00034223514,0.00034700995,0.0006912715],"domain_scores_gemma":[0.99737,0.000116456096,0.0011185623,0.00080797425,0.0003015312,0.0002854517],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006760175,0.0006614375,0.0006596996,0.00008963213,0.00015678693,0.00010628816,0.00069355854,0.0013036407,0.22847596],"category_scores_gemma":[0.00073085545,0.0007214487,0.00035812025,0.000012987766,0.00033950445,8.052108e-8,0.00028222363,0.0006210096,0.0144351395],"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":[0.00013972462,0.00009951512,0.00005803174,0.0016539532,0.0002077553,0.0000124670405,0.0003128139,0.0047399476,0.000045879355,0.0003328096,0.98882556,0.0035715268],"study_design_scores_gemma":[0.00092449045,0.00061357435,0.00005941474,0.00034137862,0.00006038507,0.0005313828,0.0001865571,0.0008455937,0.0005125698,0.000023434164,0.9951796,0.0007215973],"about_ca_topic_score_codex":0.0039144475,"about_ca_topic_score_gemma":0.0022350722,"teacher_disagreement_score":0.21404082,"about_ca_system_score_codex":0.00009370273,"about_ca_system_score_gemma":0.00023311796,"threshold_uncertainty_score":0.99999285},"labels":[],"label_agreement":null},{"id":"W7070432592","doi":"","title":"Organic matter quality in cryosols : effect on soil nitrogen dynamics and greenhouse gas emissions","year":2011,"lang":"en","type":"article","venue":"University Library - University of Saskatchewan (University of Saskatchewan)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Natural Sciences and Engineering Research Council of Canada; Churchill Northern Studies Centre","keywords":"Greenhouse gas; Soil organic matter; Nitrogen; Organic matter; Quality (philosophy); Soil water","score_opus":0.005474743839916236,"score_gpt":0.17646728013808238,"score_spread":0.17099253629816616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070432592","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9930794,0.000028612925,0.0014145335,0.00037542943,0.000041298597,0.00031264898,0.0002456676,0.00006869647,0.004433682],"genre_scores_gemma":[0.9851656,0.00009238011,0.0048416965,0.0000822033,0.000015967986,1.900461e-8,0.00021845964,0.000033997432,0.009549685],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.998121,0.00035755886,0.00022845117,0.00058705476,0.00027888213,0.0004270241],"domain_scores_gemma":[0.99838656,0.00009344146,0.0004498908,0.00068737124,0.00007662476,0.00030610352],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002591182,0.00038168358,0.0005929759,0.00041892737,0.00030238528,0.000010899877,0.0009645789,0.00046936248,0.0009923732],"category_scores_gemma":[0.000016265058,0.00052121194,0.00027421647,0.00046440988,0.00073656027,0.00017775406,0.0009834603,0.00044346857,0.000039294817],"study_design_candidate":"qualitative","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":[0.008078556,0.0012817858,0.73958635,0.0010827166,0.0008709489,0.00045938257,0.21000098,0.00017371133,0.030617146,0.00015463494,0.0027032197,0.0049905623],"study_design_scores_gemma":[0.007896968,0.0027197234,0.09242873,0.00032854147,0.0003831132,0.00003044434,0.8763026,0.00065684604,0.014833128,0.00025243266,0.0026240747,0.0015434145],"about_ca_topic_score_codex":0.008870761,"about_ca_topic_score_gemma":0.014146965,"teacher_disagreement_score":0.6663016,"about_ca_system_score_codex":0.00009384734,"about_ca_system_score_gemma":0.00036313874,"threshold_uncertainty_score":0.99992085},"labels":[],"label_agreement":null},{"id":"W7070434328","doi":"","title":"582 Philip Cross Caddo History","year":2024,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Soul; Jazz; Attendance; Comedy; Style (visual arts); Order (exchange)","score_opus":0.005257183090194701,"score_gpt":0.20461807082943106,"score_spread":0.19936088773923635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070434328","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":[0.00003861139,0.0028812063,0.0000011136393,0.000060295246,0.0008367254,0.00027706014,0.00015533002,0.00013271764,0.9956169],"genre_scores_gemma":[0.00026683384,0.0004088351,0.0009424189,0.0004399076,0.00039174323,0.000015147327,0.0006276835,0.00022829117,0.9966791],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99846756,0.000049038586,0.00061126257,0.0002529559,0.00032696064,0.00029221212],"domain_scores_gemma":[0.9986929,0.00001626472,0.00048271252,0.0005913616,0.00010824454,0.00010847815],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000245152,0.000376822,0.00032394056,0.00007689105,0.000029036813,0.00004204505,0.00041224438,0.0006811941,0.30333334],"category_scores_gemma":[0.00018296544,0.000378408,0.00021968802,0.0000048551724,0.0002120357,2.1488422e-8,0.00020973904,0.00036574338,0.03553677],"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":[0.00004292422,0.000019336332,0.00000505163,0.0010995835,0.00010503252,0.000007677948,0.00008634795,0.0001231594,0.0000049644664,0.000026446649,0.9980028,0.00047666472],"study_design_scores_gemma":[0.000288683,0.00012530823,0.0000039439715,0.00017371264,0.00005106192,0.00008206664,0.000021381029,0.000028133463,0.00003516559,0.00000428615,0.99879575,0.0003905287],"about_ca_topic_score_codex":0.0013706331,"about_ca_topic_score_gemma":0.00045107497,"teacher_disagreement_score":0.26779658,"about_ca_system_score_codex":0.00007029645,"about_ca_system_score_gemma":0.000070450034,"threshold_uncertainty_score":0.9998668},"labels":[],"label_agreement":null},{"id":"W7070448077","doi":"","title":"Perpetual Industries Announces Strong First Quarter 2021","year":2021,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Government (linguistics); Work (physics)","score_opus":0.008097161705414323,"score_gpt":0.24468953125421275,"score_spread":0.23659236954879842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070448077","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":[0.0002568737,0.0017790465,0.0008816554,0.0002759836,0.0003774645,0.00013395974,0.000072766314,0.000032458738,0.9961898],"genre_scores_gemma":[0.0016718963,0.00039677403,0.0022153975,0.00020472557,0.0013107724,0.000015058118,0.002253322,0.00016578444,0.9917663],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989998,0.000038126567,0.00021121817,0.00031046293,0.0001849506,0.00025547063],"domain_scores_gemma":[0.99923086,0.0000088599545,0.00015040132,0.00049571774,0.00004600024,0.00006816503],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000076041964,0.0002881427,0.00023594836,0.00006383613,0.00005671679,0.000072390016,0.00025150992,0.00063600007,0.012577947],"category_scores_gemma":[0.000091147675,0.00025309023,0.00008810345,0.00008088135,0.00009645361,0.000001379256,0.0001716095,0.00027399225,0.0001059861],"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":[0.0000042206366,0.000020223357,0.0012566729,0.000071605275,0.000117763855,0.0000037199047,0.00003976158,0.000011193154,0.00011954248,0.000099149074,0.99751836,0.0007377599],"study_design_scores_gemma":[0.00017697725,0.0001081584,0.000072501796,0.00008878148,0.00001760259,0.000012388606,0.0004064912,0.00005345406,0.00041604319,0.0000010309437,0.99832416,0.0003224312],"about_ca_topic_score_codex":0.00011787387,"about_ca_topic_score_gemma":0.0008660719,"teacher_disagreement_score":0.012471961,"about_ca_system_score_codex":0.000009599083,"about_ca_system_score_gemma":0.00014680836,"threshold_uncertainty_score":0.99999213},"labels":[],"label_agreement":null},{"id":"W7070450217","doi":"","title":"Précision du positionnement implantaire : chirurgie guidée dynamique VS chirurgie guidée statique et chirurgie à main levée","year":2022,"lang":"en","type":"dissertation","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Implant; Randomized controlled trial; Mean difference; MEDLINE; Prospective cohort study; Meta-analysis; Clinical trial; Clinical Practice; Navigation system","score_opus":0.005564278057864978,"score_gpt":0.24908183478246068,"score_spread":0.2435175567245957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070450217","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61323303,0.0025631892,0.05549152,0.016327867,0.0016725033,0.0032421572,0.0018476454,0.0005824878,0.3050396],"genre_scores_gemma":[0.74456465,0.005738886,0.0431403,0.0017091992,0.00020959927,0.00073935406,0.13278438,0.00044398775,0.070669666],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99210596,0.0040697,0.0012365113,0.0010588199,0.0008417771,0.0006872531],"domain_scores_gemma":[0.99463904,0.0004295866,0.0012324743,0.0022443966,0.0011679343,0.00028655757],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0052094334,0.00077204616,0.00060674024,0.00033509772,0.0009519162,0.00037261395,0.0016257073,0.00060782774,0.00087283703],"category_scores_gemma":[0.0015862064,0.0008429495,0.00041329343,0.00042296553,0.00013488432,0.000045421093,0.00084444473,0.0010477179,0.000047932874],"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":[0.0029866097,0.007370352,0.008264333,0.0047804667,0.0028170242,0.00027007816,0.058934208,0.0055074627,0.23929752,0.33349147,0.1904099,0.14587057],"study_design_scores_gemma":[0.0055890167,0.000068117835,0.023081917,0.0037477459,0.0004438309,0.00051939534,0.0037308969,0.022535002,0.18966046,0.0030305025,0.7430649,0.004528229],"about_ca_topic_score_codex":0.00082230486,"about_ca_topic_score_gemma":0.0056970213,"teacher_disagreement_score":0.552655,"about_ca_system_score_codex":0.00026291262,"about_ca_system_score_gemma":0.00090570387,"threshold_uncertainty_score":0.9994021},"labels":[],"label_agreement":null},{"id":"W7070455488","doi":"","title":"26-Point First Quarter Ignites No. 21 UMD to 54-23 Win Over Golden Eagle on Senior Day","year":2016,"lang":"en","type":"other","venue":"University of Minnesota Digital Conservancy (University of Minnesota)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Eagle; Period (music); Feature (linguistics)","score_opus":0.004605915078279183,"score_gpt":0.18682194616569786,"score_spread":0.18221603108741868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070455488","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":[0.1882039,0.00038640667,0.0038979768,0.0037272978,0.0009684569,0.0019430228,0.00874562,0.00035184674,0.79177547],"genre_scores_gemma":[0.031573124,0.00046883622,0.0038234335,0.0002572688,0.00029064584,3.5021898e-7,0.00095526286,0.00032154098,0.96230954],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978431,0.000097956225,0.00030124525,0.0007642259,0.0004697013,0.00052381156],"domain_scores_gemma":[0.9974192,0.00014379784,0.0007091358,0.0010969603,0.00031399532,0.0003169463],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00017844155,0.00061046425,0.000787646,0.0005026808,0.0001885372,0.00003062023,0.0012056011,0.0006816196,0.0024387296],"category_scores_gemma":[0.00017264733,0.00072110887,0.00048702536,0.00023194058,0.00066605007,0.000075765514,0.0007450619,0.00025863652,0.0017068933],"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":[0.0006103104,0.00025015362,0.0039915494,0.00039986635,0.00042300235,0.00008090942,0.0008601011,0.000011374841,0.0013448735,0.00009472189,0.99093467,0.0009984754],"study_design_scores_gemma":[0.0020098193,0.00083816476,0.001679889,0.0007432382,0.00013439386,0.0000121081575,0.0015909015,0.000054992153,0.00023917553,0.000009873046,0.9918531,0.0008343543],"about_ca_topic_score_codex":0.0004984706,"about_ca_topic_score_gemma":0.0015933693,"teacher_disagreement_score":0.17053406,"about_ca_system_score_codex":0.0000839893,"about_ca_system_score_gemma":0.00017631154,"threshold_uncertainty_score":0.999524},"labels":[],"label_agreement":null},{"id":"W7070458753","doi":"","title":"Parcours d'insertion d'immigrants travailleurs qualifiés et transitions professionnelles vers de nouveaux domaines de formation","year":2014,"lang":"fr","type":"other","venue":"Archipelago (Université du Québec à Montréal)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sociological research; Identity (music); Immigration; Ethnography","score_opus":0.005283856780251312,"score_gpt":0.20241842638366314,"score_spread":0.19713456960341183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070458753","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78594536,0.0028612423,0.18576498,0.00930872,0.0003304553,0.0007779812,0.00016056179,0.00012458832,0.014726107],"genre_scores_gemma":[0.97058153,0.0030725386,0.007992665,0.0013094584,0.00033190762,0.00003147021,0.0009530437,0.00022729086,0.0155000985],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969784,0.00093725655,0.0005094065,0.00049030344,0.0003195935,0.00076504354],"domain_scores_gemma":[0.9981861,0.00014301384,0.00055376854,0.000635902,0.00011419656,0.00036702256],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00065741444,0.0006342105,0.00049748516,0.000323545,0.0006593658,0.000058557376,0.0005975379,0.000729821,0.0005848044],"category_scores_gemma":[0.0001942363,0.00067858817,0.0004152115,0.00019003637,0.000342133,0.000047930604,0.00015529651,0.00064513815,0.00023066984],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002735263,0.0014541561,0.0096468115,0.0035961636,0.0016832722,0.00019504827,0.6370689,0.028050113,0.070554204,0.016592024,0.116592735,0.111831255],"study_design_scores_gemma":[0.0066535086,0.0014325704,0.026421156,0.0015068018,0.0011559323,0.000619362,0.12695579,0.08268329,0.0018009525,0.00084659184,0.747201,0.0027230259],"about_ca_topic_score_codex":0.044514645,"about_ca_topic_score_gemma":0.37122366,"teacher_disagreement_score":0.63060826,"about_ca_system_score_codex":0.00037691664,"about_ca_system_score_gemma":0.00092773687,"threshold_uncertainty_score":0.99956656},"labels":[],"label_agreement":null},{"id":"W7070477026","doi":"","title":"@PumpUpThaVolume: Episode067 - Temporary Paradise","year":2013,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Paradise; Sound (geography); Patron saint; Adventure","score_opus":0.004111113898900889,"score_gpt":0.1883900663295342,"score_spread":0.1842789524306333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070477026","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":[0.00016320749,0.0006778056,0.00000460841,0.00009444188,0.00027683616,0.0005308959,0.0001504673,0.00011568163,0.9979861],"genre_scores_gemma":[0.0006054382,0.0004321492,0.0030586296,0.00042407098,0.00026973794,0.000030963954,0.0013222598,0.00019571352,0.99366105],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998274,0.000080171834,0.0007170445,0.00024111259,0.0003428461,0.00034482332],"domain_scores_gemma":[0.9982159,0.000024581888,0.00079302926,0.0007015689,0.00010659775,0.00015833751],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00018096878,0.0004360698,0.00040865465,0.00007325462,0.00005822532,0.000057330813,0.0004922908,0.0007006849,0.2108528],"category_scores_gemma":[0.00015909495,0.00043044324,0.00020565424,0.000007108961,0.00017350182,3.8355058e-8,0.00020854372,0.00030596365,0.015019734],"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":[0.00003615192,0.000035656612,0.000055917928,0.0004971889,0.00009549421,0.0000039677184,0.000027875923,0.00014727845,0.0000035746323,0.000018408622,0.9978222,0.0012562876],"study_design_scores_gemma":[0.00044317337,0.00020975633,0.000022604669,0.00012944207,0.000038532467,0.00006824262,0.00003432503,0.00010723535,0.000040362847,0.0000036054444,0.9984415,0.0004611737],"about_ca_topic_score_codex":0.0030036427,"about_ca_topic_score_gemma":0.00027615382,"teacher_disagreement_score":0.19583307,"about_ca_system_score_codex":0.000018164603,"about_ca_system_score_gemma":0.00004898375,"threshold_uncertainty_score":0.99981475},"labels":[],"label_agreement":null},{"id":"W7070479385","doi":"","title":"Patiëntenvoorkeuren om de waarde van gentherapie te bepalen","year":2020,"lang":"en","type":"article","venue":"Lirias (KU Leuven)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Orphan drug; Health technology; Value (mathematics); Quality of life (healthcare); Preference","score_opus":0.011947348015823357,"score_gpt":0.2418595530003709,"score_spread":0.22991220498454754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070479385","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94944584,0.001311443,0.016012227,0.010222131,0.00043041378,0.00051137345,0.00008732167,0.00020004,0.021779213],"genre_scores_gemma":[0.9837463,0.00012166735,0.005127226,0.008657863,0.00082245766,0.000018013627,0.00021808146,0.000054272292,0.001234113],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987723,0.00009276599,0.00029061435,0.00029231946,0.00018310672,0.00036885758],"domain_scores_gemma":[0.9991937,0.000018321427,0.0001317555,0.00039035224,0.0000501415,0.0002157222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017616921,0.00022157599,0.00019696333,0.000026673286,0.000093603965,0.000047133064,0.00038827962,0.00020627295,0.00025020173],"category_scores_gemma":[0.00020047546,0.00021062903,0.00013839533,0.0000927064,0.000060340586,0.000006881435,0.00018055082,0.00024991165,0.00024112985],"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":[0.0012654394,0.0004490713,0.14468382,0.00074354844,0.0015342714,0.000105893574,0.014885816,0.009690241,0.39168173,0.0018753937,0.20962878,0.223456],"study_design_scores_gemma":[0.001088234,0.0005847843,0.0037695891,0.000024324512,0.000049506863,0.000025145053,0.00025502592,0.0060381354,0.030121291,0.00014880994,0.9574055,0.0004896706],"about_ca_topic_score_codex":0.000023910501,"about_ca_topic_score_gemma":0.000017791026,"teacher_disagreement_score":0.7477767,"about_ca_system_score_codex":0.000019868141,"about_ca_system_score_gemma":0.00008275047,"threshold_uncertainty_score":0.8589203},"labels":[],"label_agreement":null},{"id":"W7070479650","doi":"","title":"The organization and use of documentary deposits in the near east from ancient to medieval times : libraries, archives, book collections and genizas","year":2002,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Research Foundation; McGill University","keywords":"Context (archaeology); Ancient city; Middle East; Hebrew; Ideal (ethics); Ancient literature","score_opus":0.00681044615912221,"score_gpt":0.20430060765683344,"score_spread":0.19749016149771123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070479650","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9926225,0.0019578086,0.0000020684197,0.00007520271,0.00019923381,0.00063783047,0.00044917356,0.000017457623,0.004038726],"genre_scores_gemma":[0.9674849,0.0049942215,0.006014126,0.0016844023,0.000102184655,0.00009825074,0.0058841445,0.00017117319,0.013566598],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99838316,0.0002771849,0.00042752508,0.00037429467,0.00028487257,0.0002529743],"domain_scores_gemma":[0.998922,0.0002060535,0.0002548404,0.00041318813,0.000093488416,0.00011043967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020202533,0.00029513604,0.00022805858,0.00010103731,0.0010504371,0.00025528556,0.00032412136,0.00024751286,0.000034029876],"category_scores_gemma":[0.0007517518,0.00022447099,0.000048836184,0.00037950525,0.000109881126,0.000049485447,0.000191096,0.00043982553,0.000004187688],"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":[0.0034185322,0.0012744373,0.021587757,0.0014797269,0.0027643563,0.00008682737,0.0055686347,0.0020702605,0.7140647,0.024302963,0.009210884,0.21417092],"study_design_scores_gemma":[0.0017656455,0.00090697815,0.05397578,0.00040494298,0.00042845987,0.000119886994,0.002091898,0.0009369703,0.11990796,0.0011426532,0.81697613,0.001342705],"about_ca_topic_score_codex":0.00019314529,"about_ca_topic_score_gemma":0.0014772083,"teacher_disagreement_score":0.80776525,"about_ca_system_score_codex":0.00003148204,"about_ca_system_score_gemma":0.000050546198,"threshold_uncertainty_score":0.9153661},"labels":[],"label_agreement":null},{"id":"W7070481770","doi":"","title":"Persévérance scolaire des élèves inuit: Influence de la perception, de l'attitude et de l'approche pédagogique des enseignants inuit et qallunaat (non inuit)","year":2015,"lang":"fr","type":"other","venue":"Bibliothèque et Archives nationales du Québec (Québec government)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Public policy; Context (archaeology); Subject (documents); Ethnic group","score_opus":0.008322133361181613,"score_gpt":0.2536683590261826,"score_spread":0.245346225665001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070481770","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9150984,0.004599724,0.006021054,0.0010099689,0.000044486816,0.0006801885,0.0005404303,0.000110636,0.0718951],"genre_scores_gemma":[0.8645027,0.005755221,0.028361239,0.0037051553,0.00033595873,0.00024203898,0.0000967955,0.0003231777,0.09667768],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9943838,0.0018381904,0.0009008799,0.00091000175,0.0009766133,0.0009904782],"domain_scores_gemma":[0.99546903,0.0021356614,0.0008640464,0.00071899215,0.00024569704,0.0005665465],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023865902,0.0010327201,0.000667463,0.00065166183,0.00040492197,0.0006523649,0.001417257,0.0007588636,0.0017358693],"category_scores_gemma":[0.009132134,0.0010677266,0.00035465768,0.00060922507,0.0020840375,0.00017502654,0.00088794087,0.0013213308,0.00014629084],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00063113007,0.0010216833,0.3234104,0.0029915175,0.0009697051,0.00006455704,0.5190393,0.013816666,0.083957724,0.0032430703,0.046846244,0.0040080436],"study_design_scores_gemma":[0.0019322386,0.00068465614,0.7965847,0.002072095,0.00024119305,0.000695757,0.0036958605,0.0029102983,0.0017816167,0.0014916634,0.18611215,0.0017977541],"about_ca_topic_score_codex":0.044699427,"about_ca_topic_score_gemma":0.90621114,"teacher_disagreement_score":0.8615117,"about_ca_system_score_codex":0.011596177,"about_ca_system_score_gemma":0.13128693,"threshold_uncertainty_score":0.99921435},"labels":[],"label_agreement":null},{"id":"W7070482327","doi":"","title":"Quebec lobster fisheries: Management, fishing boats, equipment and working processes","year":2015,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Fishing; Work (physics); Production (economics); Netting; Government (linguistics)","score_opus":0.02089359172146459,"score_gpt":0.24939294341873683,"score_spread":0.22849935169727223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070482327","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6607944,0.0009409334,0.018747797,0.001620273,0.00032692013,0.00048030898,0.0000035652215,0.000113351976,0.3169725],"genre_scores_gemma":[0.9596017,0.00013712965,0.016626531,0.001399134,0.0001330677,0.000020546458,0.00007050579,0.000021858168,0.021989511],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99931985,0.000018266588,0.00016349902,0.0001807601,0.00012785,0.00018976274],"domain_scores_gemma":[0.9995984,0.000008447165,0.00006262513,0.00019404569,0.000048582147,0.000087926586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001688763,0.00012413716,0.00008521001,0.000025710116,0.00005238331,0.00013309073,0.00013694807,0.000068932335,0.000022274062],"category_scores_gemma":[0.00009917573,0.0001065279,0.000016769827,0.00006571936,0.000043448952,0.000010593892,0.00028432132,0.00006480437,0.000010510643],"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":[0.0004549198,0.00027913426,0.35960227,0.0028426365,0.00075291644,0.000048559414,0.008480711,0.0007595734,0.004117732,0.0026564742,0.4536178,0.16638725],"study_design_scores_gemma":[0.0007981146,0.00016146708,0.00401352,0.00007862038,0.000025810898,0.000019749903,0.0021078216,0.0005128407,0.0040881815,0.000112522175,0.9877013,0.0003800433],"about_ca_topic_score_codex":0.00014796732,"about_ca_topic_score_gemma":0.00096871116,"teacher_disagreement_score":0.5340835,"about_ca_system_score_codex":0.000015893102,"about_ca_system_score_gemma":0.00003736484,"threshold_uncertainty_score":0.43440816},"labels":[],"label_agreement":null},{"id":"W7070487050","doi":"","title":"Person-centred Care Coordination in Ontario: A Multimethod Evaluation of Implementation and Impact","year":2021,"lang":"en","type":"dissertation","venue":"TSpace (University of Toronto)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Operationalization; Health care; Quality (philosophy); Needs assessment; Social support; Program evaluation; Data collection; Health care quality","score_opus":0.0206006995575152,"score_gpt":0.32673205504124736,"score_spread":0.30613135548373216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070487050","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9893391,0.002130453,0.000056114117,0.000016411977,0.00006263397,0.00032688628,0.000025199299,0.0000028530253,0.008040342],"genre_scores_gemma":[0.9900087,0.00006412191,0.0037471897,0.0000015546217,0.0000075265802,6.535012e-7,0.0047252094,0.000008836564,0.0014362182],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9992276,0.00013753142,0.00011335009,0.0001799667,0.0002423942,0.00009915568],"domain_scores_gemma":[0.9990404,0.000009881725,0.00034104116,0.00015525191,0.00042204713,0.000031354062],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016926906,0.00012742013,0.00020581491,0.00004975019,0.00003982517,0.0000063648727,0.000086406,0.00019942147,0.0023849027],"category_scores_gemma":[0.000046116966,0.00016517975,0.000087627544,0.000033315846,0.000020112855,0.00001840755,0.000029703866,0.0000918807,2.8915608e-7],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009144422,0.00015114211,0.0835439,0.0010341213,0.0006438919,0.0000030622716,0.50077355,0.00082511426,0.121747255,0.000026788048,0.00042106217,0.28991565],"study_design_scores_gemma":[0.0014819824,0.00017567127,0.6971594,0.00006716831,0.00019807485,8.9114775e-7,0.29733002,0.0015416379,0.001840666,7.9500626e-7,0.00006705907,0.0001365927],"about_ca_topic_score_codex":0.5996385,"about_ca_topic_score_gemma":0.9341886,"teacher_disagreement_score":0.6136155,"about_ca_system_score_codex":0.00040025765,"about_ca_system_score_gemma":0.0004635468,"threshold_uncertainty_score":0.99852705},"labels":[],"label_agreement":null},{"id":"W7070487897","doi":"","title":"The Ozone Layer: Ozone Depletion, Recovery in a Changing Climate, and the \"World Avoided\"","year":2008,"lang":"en","type":"article","venue":"University of North Texas Digital Library (University of North Texas)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Ozone; Pollutant; Ozone layer; Montreal Protocol; Ultraviolet; Ultraviolet radiation","score_opus":0.006174206061720531,"score_gpt":0.16807464739229167,"score_spread":0.16190044133057113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070487897","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9911923,0.00018622931,0.00034151357,0.0005735271,0.000042447784,0.00026130764,0.00022661652,0.000031028125,0.007145052],"genre_scores_gemma":[0.9878249,0.0019328946,0.0006566295,0.000095822885,0.000027668977,4.293048e-8,0.00034476022,0.000015830032,0.0091014365],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988697,0.00009468242,0.00020542595,0.00026430702,0.00020746696,0.00035839961],"domain_scores_gemma":[0.9989821,0.0001414196,0.00031834014,0.00040286253,0.00006319619,0.00009211462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015789918,0.00019235496,0.00028251705,0.00027794033,0.00057252386,0.000030900646,0.0006646335,0.00007807042,0.000033756114],"category_scores_gemma":[0.00004779673,0.00018090494,0.00016707278,0.00063885265,0.0009504651,0.00019362441,0.0010220242,0.00023310611,0.000019504812],"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":[0.00070568844,0.00005928934,0.99451363,0.00005169,0.00007642497,0.0000291256,0.00011835117,0.0003156466,4.7111573e-7,0.00027067657,0.0021258125,0.0017331971],"study_design_scores_gemma":[0.0015934038,0.00014937407,0.92875576,0.00003379437,0.000028424625,0.000027355029,0.00015328672,0.00049734226,0.000011260887,0.000025675292,0.068512134,0.0002122137],"about_ca_topic_score_codex":0.00010287856,"about_ca_topic_score_gemma":0.0024133583,"teacher_disagreement_score":0.06638632,"about_ca_system_score_codex":0.000016625001,"about_ca_system_score_gemma":0.00009126839,"threshold_uncertainty_score":0.7377089},"labels":[],"label_agreement":null},{"id":"W7070495740","doi":"","title":"Provident Bancorp, Inc. Reports Earnings for the March 31, 2022 Quarter and Continues Payment of Quarterly Cash Dividends of $0.04 per Share","year":2022,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Earnings; Quarter (Canadian coin); Payment; Cash; Dividend","score_opus":0.005341921865133203,"score_gpt":0.24595312794981466,"score_spread":0.24061120608468145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070495740","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":[0.15249169,0.036724295,0.012869441,0.006374469,0.004426495,0.02362254,0.0058554774,0.00041844766,0.75721717],"genre_scores_gemma":[0.09327392,0.00042467992,0.0038167043,0.00038356692,0.0004659928,0.0007737244,0.0023057978,0.00040459775,0.89815104],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99843955,0.000072994706,0.0005887227,0.00035230463,0.0003236422,0.00022275592],"domain_scores_gemma":[0.99823123,0.000066479035,0.00090191467,0.0006587977,0.000093831404,0.000047757585],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00052791275,0.00026872513,0.0003814861,0.000095778385,0.000072011884,0.000026914035,0.00027435433,0.00020686816,0.0031138144],"category_scores_gemma":[0.0001009363,0.00019225509,0.00015130574,0.000047727233,0.0001281756,0.000003472687,0.0002641568,0.00021833621,0.0000016207531],"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":[0.00007650675,0.000056739176,0.015531783,0.0009201831,0.0003757964,0.0000040822515,0.00076614623,0.0000071575587,0.0035037757,0.00004013278,0.97429734,0.004420353],"study_design_scores_gemma":[0.0004020014,0.0013439506,0.00256819,0.00006713332,0.00010169037,0.000047492747,0.0010012412,0.00013012982,0.000480679,0.000013075474,0.9935747,0.000269746],"about_ca_topic_score_codex":0.00037767642,"about_ca_topic_score_gemma":0.00030713555,"teacher_disagreement_score":0.14093387,"about_ca_system_score_codex":0.00001624425,"about_ca_system_score_gemma":0.000092519964,"threshold_uncertainty_score":0.9977975},"labels":[],"label_agreement":null},{"id":"W7070501020","doi":"","title":"(PR) Peter Pesce, Founder of Reunion Coffee Roasters, Wins Lifetime Achievement Award from the Coffee Association of Canada","year":2024,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Association (psychology); Government (linguistics)","score_opus":0.003762376872154805,"score_gpt":0.2102781421669804,"score_spread":0.2065157652948256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070501020","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":[0.0062511833,0.0017244344,0.0019209766,0.00499902,0.0022120583,0.0010510008,0.001650836,0.000061905936,0.9801286],"genre_scores_gemma":[0.017710356,0.00020770919,0.0022129663,0.0012946615,0.00062912045,0.00001353028,0.0015010156,0.00027303657,0.9761576],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99855274,0.000110521716,0.00042739764,0.00024052942,0.00045789592,0.0002109133],"domain_scores_gemma":[0.99869806,0.000047143913,0.0005802296,0.00055483775,0.00007274343,0.00004698814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028982462,0.00025674285,0.00031164882,0.00004553231,0.000029510464,0.000021283191,0.0003535312,0.0004471867,0.0006573415],"category_scores_gemma":[0.00011253508,0.0001839345,0.00012063355,0.00006681485,0.000043073556,0.0000016888291,0.00023575139,0.0003036615,0.000022048122],"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":[0.000018273959,0.000022775674,0.0031314327,0.00015414844,0.00062786945,5.4059404e-7,0.00008090429,0.000025152287,0.0012772684,0.00005833734,0.99446833,0.00013495206],"study_design_scores_gemma":[0.00030545946,0.000118870674,0.0020463085,0.00017495312,0.00014316608,8.249051e-7,0.000102564394,0.00018894771,0.0011716015,0.000023577293,0.99549985,0.00022386311],"about_ca_topic_score_codex":0.0991191,"about_ca_topic_score_gemma":0.30808818,"teacher_disagreement_score":0.2089691,"about_ca_system_score_codex":0.00009804556,"about_ca_system_score_gemma":0.00033637704,"threshold_uncertainty_score":0.90687996},"labels":[],"label_agreement":null},{"id":"W7070505144","doi":"","title":"Oral health and olfactory function : what can they tell us about cognitive ageing?","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Masticatory force; Cognition; Tooth loss; Dementia; Cognitive decline; Ageing; Olfaction; Brain size; Montreal Cognitive Assessment","score_opus":0.036990064839754186,"score_gpt":0.27256076596254714,"score_spread":0.23557070112279294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070505144","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8609962,0.0148854,0.00022681708,0.0022688447,0.00039835676,0.0017016802,0.11170534,0.0002802086,0.0075371647],"genre_scores_gemma":[0.91021997,0.00012095091,0.00007013128,0.010721161,0.00017923412,0.000020220656,0.07854714,0.000021323802,0.000099853634],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99938434,0.00004855016,0.00012953952,0.00018091887,0.00008619407,0.00017047081],"domain_scores_gemma":[0.9995505,0.000016819198,0.00010326362,0.000096969954,0.000055308185,0.00017713575],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000032264896,0.00012065031,0.00010581525,0.000014000132,0.0000920322,0.00008090387,0.00007515551,0.00009012028,0.002840067],"category_scores_gemma":[0.000577531,0.000113213784,0.000034196844,0.000034640085,0.000008369175,0.000010925438,0.0001143272,0.00015095361,0.000114539216],"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":[0.0006631042,0.000113699636,0.020434244,0.003331783,0.00039796068,0.000037307324,0.012653078,0.0002773969,0.004965011,0.000013778977,0.70920616,0.24790648],"study_design_scores_gemma":[0.0013489503,0.0021011182,0.06962268,0.0013569783,0.00002485549,0.000023882585,0.0018850398,0.0022408168,0.0032562502,0.000008277778,0.91748494,0.0006462291],"about_ca_topic_score_codex":0.000016009068,"about_ca_topic_score_gemma":0.000064622436,"teacher_disagreement_score":0.24726024,"about_ca_system_score_codex":0.000008430574,"about_ca_system_score_gemma":0.00009160847,"threshold_uncertainty_score":0.9980715},"labels":[],"label_agreement":null},{"id":"W7070509191","doi":"","title":"Plan directeur des infrastructures vertes de gestion des eaux pluviales pour un secteur de la ville de Magog","year":2022,"lang":"fr","type":"other","venue":"Knowledge UdeS (Institutional Deposit of the University of Sherbrooke)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); European union; Prospection; Transportation infrastructure","score_opus":0.007089917802787876,"score_gpt":0.19941284952493807,"score_spread":0.1923229317221502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070509191","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75045407,0.011963445,0.041482665,0.00005215788,0.00022088918,0.0002606544,0.00011220341,0.000037508195,0.19541644],"genre_scores_gemma":[0.93482894,0.0028080612,0.045328684,0.000034392273,0.00016944224,0.0000015056875,0.00012123391,0.00005923203,0.016648524],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99821264,0.0006457462,0.00026440682,0.00028335763,0.00022182087,0.00037205793],"domain_scores_gemma":[0.999065,0.000121967234,0.00021978898,0.00034548534,0.000111407826,0.0001363677],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003680611,0.00035093175,0.00033022213,0.00014166196,0.0007458459,0.000025146774,0.00090752286,0.0005308652,0.0016904367],"category_scores_gemma":[0.00041858605,0.0003576172,0.00031833292,0.00016989329,0.001967201,0.000019112449,0.00065971626,0.0005021003,0.00001632772],"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":[0.0006475358,0.0007163118,0.30007857,0.009796266,0.0013677638,0.000049786435,0.022251904,0.1658794,0.45588443,0.009000872,0.009019313,0.025307849],"study_design_scores_gemma":[0.0017956968,0.00035700918,0.5705935,0.0030534926,0.0006904307,0.0006850277,0.00080044457,0.023364771,0.11898566,0.0021835854,0.27669528,0.0007951017],"about_ca_topic_score_codex":0.0026091912,"about_ca_topic_score_gemma":0.010962882,"teacher_disagreement_score":0.33689874,"about_ca_system_score_codex":0.0014743161,"about_ca_system_score_gemma":0.00073872664,"threshold_uncertainty_score":0.9998876},"labels":[],"label_agreement":null},{"id":"W7070513458","doi":"","title":"PArasites of th lake sturgeon, Acipenser fulvescens, systematics and biogeography","year":2007,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Biogeography; Monophyly; Acipenser; Biological dispersal; Subspecies; Systematics; Actinopterygii; Fauna; Cypriniformes","score_opus":0.0019153447151418587,"score_gpt":0.155947769406717,"score_spread":0.15403242469157516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070513458","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019274196,0.0037991991,0.00016616585,0.00025439728,0.00021592916,0.00042591762,0.0012796264,0.000012923848,0.97457165],"genre_scores_gemma":[0.6048514,0.004628959,0.013824438,0.001957159,0.00035898678,0.000015107947,0.00055912556,0.0004344805,0.37337032],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99842143,0.000046079334,0.00036065397,0.00020084991,0.0007507953,0.00022018593],"domain_scores_gemma":[0.99905676,0.000055884408,0.00044070862,0.00029431016,9.152553e-7,0.0001514364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000020647778,0.00025485214,0.00036469128,0.00006182114,0.000043714812,0.0000109007005,0.00018391138,0.00010812811,0.000050205865],"category_scores_gemma":[0.0000071253494,0.00022740033,0.00003995816,0.000060064525,0.00013310723,0.0000061323753,0.00016165418,0.000117245996,2.6048912e-9],"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":[0.0009093219,0.00015935293,0.64780694,0.021778736,0.0025559268,0.00009705118,0.00021964105,0.00006345356,0.038619865,0.031547707,0.24818574,0.008056278],"study_design_scores_gemma":[0.0006136992,0.00027165003,0.02133422,0.0011997122,0.00012733776,0.0000272365,0.0011464102,0.000302008,0.038435835,0.00007534833,0.93573374,0.0007327934],"about_ca_topic_score_codex":0.0008804561,"about_ca_topic_score_gemma":0.03521301,"teacher_disagreement_score":0.687548,"about_ca_system_score_codex":8.3893923e-7,"about_ca_system_score_gemma":0.0003410216,"threshold_uncertainty_score":0.98239183},"labels":[],"label_agreement":null},{"id":"W7070523651","doi":"","title":"Patient safety management system in pediatric ICUs","year":2006,"lang":"en","type":"book-chapter","venue":"Data Archiving and Networked Services (DANS)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Pediatric Oncology Group","funders":"","keywords":"Patient safety; MEDLINE; Management system; Quality management; Risk management; System safety; Patient care","score_opus":0.005056157282411876,"score_gpt":0.20102688518846498,"score_spread":0.1959707279060531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070523651","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020605879,0.0039986023,0.0032964926,0.000030671985,0.00055372104,0.00097203354,0.0014761423,0.00011400922,0.9689525],"genre_scores_gemma":[0.6150224,0.030919392,0.023600303,0.0012178604,0.006231009,0.00010808557,0.17266195,0.00077863224,0.14946033],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99804425,0.000058792026,0.00061884645,0.0006650797,0.00024576296,0.00036727756],"domain_scores_gemma":[0.9982009,0.00003349161,0.0003542449,0.0013009674,0.00001805389,0.00009234339],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003306704,0.00043161758,0.00034677752,0.00013811543,0.00013316721,0.000064684544,0.00083934405,0.0002375002,0.000005155114],"category_scores_gemma":[0.0000023388493,0.00040233717,0.00005934158,0.000046044268,0.00004479608,0.000009622717,0.0018415543,0.00035845468,0.00001652883],"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":[0.0025812085,0.0005902688,0.13782723,0.074016996,0.0028319014,0.0012436981,0.00573944,0.12677129,0.00025852863,0.026622446,0.08729981,0.5342172],"study_design_scores_gemma":[0.0010680773,0.00022697455,0.017392619,0.0017969324,0.0003959306,0.00008868862,0.00025779702,0.10111374,0.0000052610517,0.00018321938,0.87597185,0.0014989235],"about_ca_topic_score_codex":0.00011294672,"about_ca_topic_score_gemma":0.00061502,"teacher_disagreement_score":0.8194921,"about_ca_system_score_codex":0.00003059124,"about_ca_system_score_gemma":0.000020329864,"threshold_uncertainty_score":0.9998428},"labels":[],"label_agreement":null},{"id":"W7070529723","doi":"","title":"Pulling together : a guide for leaders and administrators","year":2018,"lang":"en","type":"other","venue":"Bibliothèque et Archives nationales du Québec (Québec government)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Ministry of Advanced Education","keywords":"Work (physics); Government (linguistics); Key (lock); Agency (philosophy)","score_opus":0.009972373898730968,"score_gpt":0.25578698176742193,"score_spread":0.24581460786869097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070529723","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":[0.013525774,0.0055684308,0.008925834,0.0034209965,0.000196859,0.0009829813,0.00043515058,0.00014313911,0.9668008],"genre_scores_gemma":[0.018121453,0.00089230994,0.015390886,0.0017927389,0.001119625,0.00019215555,0.00019540226,0.0005071622,0.96178824],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99841684,0.00006593731,0.00038499126,0.00047800175,0.00036889827,0.000285325],"domain_scores_gemma":[0.9984513,0.00061529636,0.00041055528,0.00035859784,0.00003403279,0.00013021873],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00023074193,0.00039688428,0.00027715947,0.00033611283,0.000113431706,0.00012964489,0.00042006286,0.00019994404,0.0011667135],"category_scores_gemma":[0.0017729091,0.00038356747,0.00016539638,0.00012210081,0.00039750294,0.000010837987,0.00023928248,0.00015274536,0.00007340911],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009259205,0.000056331723,0.008906806,0.00025626665,0.00027549744,0.0000011920763,0.0004113096,0.00001078333,0.0014007016,0.0008025567,0.9874739,0.00031207185],"study_design_scores_gemma":[0.0006089863,0.00027195745,0.0010164069,0.000122062826,0.000051010837,0.000021440714,0.000107502136,0.00027258042,0.00070555124,0.000029910525,0.9963598,0.00043277233],"about_ca_topic_score_codex":0.006999039,"about_ca_topic_score_gemma":0.56129575,"teacher_disagreement_score":0.5542967,"about_ca_system_score_codex":0.00026021633,"about_ca_system_score_gemma":0.009391644,"threshold_uncertainty_score":0.9998616},"labels":[],"label_agreement":null},{"id":"W7070533586","doi":"","title":"Rapid evidence profile #45: What is known from evidence and from experiences in other jurisdictions about how to effectively and efficiently improve wait times for scheduled (elective) surgical services?","year":2022,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Diafiltration; Dysgeusia; Liquation; Triacetin; Fusible alloy; Emperipolesis","score_opus":0.00897254357277364,"score_gpt":0.2707529550502579,"score_spread":0.26178041147748426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070533586","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.893593,0.08418776,0.0019385902,0.0008965964,0.0007440458,0.0052344655,0.00089362916,0.00015633288,0.01235557],"genre_scores_gemma":[0.55314606,0.026697656,0.052844666,0.0047117164,0.002718178,0.010171469,0.001480604,0.0014134021,0.34681627],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979398,0.00023021892,0.00028043037,0.000944226,0.0002583996,0.00034692514],"domain_scores_gemma":[0.9987076,0.00037634574,0.0002548491,0.00044857906,0.00006642891,0.00014622994],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003764385,0.00042661192,0.0004505187,0.00016556763,0.00014047706,0.00029917594,0.00036326252,0.00039601958,0.0030753587],"category_scores_gemma":[0.00019542903,0.00036770277,0.000091069356,0.00017764063,0.00013849884,0.00004509259,0.00045047523,0.00027914962,0.000011954231],"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":[0.00809584,0.002078254,0.08566577,0.007482443,0.0047902577,0.000062240724,0.15104976,0.00017468017,0.16379029,0.00047674327,0.25655457,0.31977916],"study_design_scores_gemma":[0.0031629577,0.0032962146,0.007890535,0.0038121988,0.0002370065,0.000015137848,0.010280381,0.014426289,0.03406888,0.00004021575,0.9205491,0.00222111],"about_ca_topic_score_codex":0.0011722244,"about_ca_topic_score_gemma":0.0004750608,"teacher_disagreement_score":0.6639945,"about_ca_system_score_codex":0.000042704374,"about_ca_system_score_gemma":0.000090944566,"threshold_uncertainty_score":0.9998775},"labels":[],"label_agreement":null},{"id":"W7070536382","doi":"","title":"Ontario budget 2001","year":2016,"lang":"en","type":"other","venue":"Brock University Digital Repository (Brock University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Work (physics); Agency (philosophy); Production (economics); Quality (philosophy)","score_opus":0.005043617001228132,"score_gpt":0.18360281784284344,"score_spread":0.1785592008416153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070536382","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":[0.0015742759,0.00004949067,0.0022223552,0.0000031704046,0.0004033495,0.00025230675,0.00017898284,0.00019025356,0.99512583],"genre_scores_gemma":[0.00044041767,0.0000970183,0.00033068072,0.00003678703,0.00029063,1.04494326e-7,0.0002723717,0.00016656746,0.9983654],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983434,0.000062884814,0.00018044896,0.000623416,0.0002892964,0.00050054584],"domain_scores_gemma":[0.99845046,0.000018749264,0.00038292995,0.0007185081,0.0001088921,0.00032044694],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0000020950613,0.0004922097,0.0003483612,0.0004599909,0.00020006586,0.00008397797,0.00094122294,0.0007349656,0.00021741429],"category_scores_gemma":[0.000028687571,0.0005537176,0.00031681432,0.00016203073,0.00017810754,0.00004758335,0.0007924759,0.00032463222,0.00044332264],"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":[0.00015327212,0.000071806324,0.014292306,0.000055571934,0.0002670277,0.000084964624,0.000005816301,0.00000925665,0.004027381,0.000021230244,0.98072875,0.00028264368],"study_design_scores_gemma":[0.0008647162,0.0001829173,0.00037619966,0.00011999997,0.00009448221,0.00007618382,0.00039007966,5.069851e-7,0.00020069418,0.0000032751982,0.99701434,0.00067660905],"about_ca_topic_score_codex":0.0011723207,"about_ca_topic_score_gemma":0.016613856,"teacher_disagreement_score":0.016285613,"about_ca_system_score_codex":0.00041413435,"about_ca_system_score_gemma":0.00047324298,"threshold_uncertainty_score":0.9996914},"labels":[],"label_agreement":null},{"id":"W7070542045","doi":"","title":"Pour une éducation en vue du développement durable en hôtellerie, restauration et tourisme","year":2012,"lang":"fr","type":"other","venue":"Knowledge UdeS (Institutional Deposit of the University of Sherbrooke)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Obstacle; Armed conflict; Pilotage","score_opus":0.009290235849468762,"score_gpt":0.22736696085945618,"score_spread":0.21807672500998743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070542045","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09410704,0.006538896,0.15945172,0.0071689733,0.0022480693,0.0010127696,0.00006733471,0.00003388646,0.7293713],"genre_scores_gemma":[0.7758768,0.005538169,0.02265727,0.000062345425,0.000512241,0.000001636888,0.00030102057,0.00005709659,0.19499338],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99843943,0.0003531917,0.00038873524,0.00027916307,0.00028396424,0.000255539],"domain_scores_gemma":[0.99879265,0.00006560076,0.0003724988,0.00047465452,0.00019406507,0.000100561265],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004045787,0.00033110846,0.00032876644,0.00015127902,0.00030865156,0.000015942587,0.00071013713,0.0005295001,0.0007816761],"category_scores_gemma":[0.00017563194,0.00032663892,0.00026353294,0.00021416611,0.0004231825,0.00003406254,0.00047670823,0.00031830487,0.000116061994],"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":[0.00079965696,0.00308792,0.030412912,0.019855192,0.002432267,0.000012981301,0.066127114,0.10876386,0.405253,0.097450756,0.24228905,0.02351531],"study_design_scores_gemma":[0.00096173066,0.0001511973,0.042174626,0.0023942832,0.0003244421,0.000042716532,0.0006160944,0.005386643,0.04118881,0.0001087399,0.9062065,0.00044422343],"about_ca_topic_score_codex":0.00074826146,"about_ca_topic_score_gemma":0.007883234,"teacher_disagreement_score":0.6817698,"about_ca_system_score_codex":0.0009607518,"about_ca_system_score_gemma":0.0006038002,"threshold_uncertainty_score":0.9999186},"labels":[],"label_agreement":null},{"id":"W7070548394","doi":"","title":"Ontario PublicAccounts 1415 Vol1","year":2019,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.004067289663228114,"score_gpt":0.183502356087893,"score_spread":0.1794350664246649,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070548394","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":[0.00014565601,0.00017044977,0.0000018490533,0.00007805097,0.0004214142,0.00044522842,0.00012763355,0.00006525447,0.99854445],"genre_scores_gemma":[0.00035257151,0.00009623037,0.0016283239,0.0005206984,0.00019202624,0.000011795162,0.0011918007,0.00013852109,0.995868],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984144,0.000044010558,0.000597911,0.00022732514,0.0003883854,0.00032798693],"domain_scores_gemma":[0.9983013,0.000019154371,0.0007094715,0.0007071458,0.00015763669,0.00010528438],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00020952446,0.00038083183,0.00037450268,0.000074806536,0.00004101278,0.00006816205,0.00050405273,0.00070776267,0.24888791],"category_scores_gemma":[0.00014815996,0.00037935504,0.00018608528,0.0000059042145,0.00009309015,3.2869224e-8,0.00021765928,0.00035307667,0.020904398],"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":[0.000051964707,0.000028805845,0.00007658065,0.00034427596,0.00010024829,0.0000016697852,0.00007136666,0.0001170831,0.0000016370828,0.000016308592,0.99847317,0.0007169093],"study_design_scores_gemma":[0.0005289116,0.00020646321,0.000030565512,0.0001077717,0.000036343114,0.000046543213,0.000027911457,0.000017185683,0.000019898636,0.0000018640771,0.9985742,0.0004023271],"about_ca_topic_score_codex":0.025546651,"about_ca_topic_score_gemma":0.031529836,"teacher_disagreement_score":0.22798352,"about_ca_system_score_codex":0.000051491388,"about_ca_system_score_gemma":0.00012964268,"threshold_uncertainty_score":0.99986583},"labels":[],"label_agreement":null},{"id":"W7070555528","doi":"","title":"Panel Summary: Modernizing the Oversight of the Health Workforce in Ontario","year":2017,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Workforce; Workforce development; Workforce planning; Key (lock); Government (linguistics); Public health","score_opus":0.027291349460126065,"score_gpt":0.2668241057634282,"score_spread":0.23953275630330212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070555528","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":[0.0005081972,0.0009112876,0.00041918803,0.0005486759,0.00023383272,0.00033967145,0.00001117746,0.0000096501135,0.99701834],"genre_scores_gemma":[0.007083095,0.00028184208,0.0006469659,0.00083315093,0.00008675369,0.000005042675,0.000060713635,0.000084294974,0.99091816],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992581,0.00006264836,0.00018460948,0.0001532327,0.00014664348,0.00019476745],"domain_scores_gemma":[0.99852836,0.0000096362855,0.0004591663,0.00096469716,0.00001144853,0.000026718593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021709711,0.00016865734,0.0001989655,0.000030767143,0.00008089055,0.00001815142,0.00070416176,0.0002277786,0.00014992006],"category_scores_gemma":[0.000047712983,0.000091588445,0.00009698828,0.000024110788,0.000104897175,0.0000011488875,0.00031315684,0.00034363198,0.0000046596024],"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":[0.000024533638,0.00002666825,0.017963646,0.00011157662,0.00008000797,4.4520425e-7,0.00046798046,0.0002227452,0.00012151486,0.0005168481,0.9774388,0.0030252438],"study_design_scores_gemma":[0.00018570834,0.00003784067,0.0016415436,0.00023649217,0.0000065961967,0.0000023982589,0.000026955799,0.00018627665,0.00010488455,0.000016555647,0.9974386,0.000116125266],"about_ca_topic_score_codex":0.062221464,"about_ca_topic_score_gemma":0.42846054,"teacher_disagreement_score":0.36623907,"about_ca_system_score_codex":0.00004294056,"about_ca_system_score_gemma":0.00034814925,"threshold_uncertainty_score":0.9440233},"labels":[],"label_agreement":null},{"id":"W7070571963","doi":"","title":"Raconter et construire son récit pour obtenir le statut de réfugié : contexte, exigences et résistances des femmes","year":2024,"lang":"fr","type":"article","venue":"Digital Access to Libraries (Université catholique de Louvain (UCL), l'Université de Namur (UNamur) and the Université Saint-Louis (USL-B))","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Democratic legitimacy; European union","score_opus":0.012009309055181022,"score_gpt":0.23488571930417518,"score_spread":0.22287641024899416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070571963","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68854254,0.019032326,0.034963004,0.036523417,0.00053532375,0.0011715423,0.0015905207,0.000387162,0.21725413],"genre_scores_gemma":[0.91609114,0.0055912323,0.003160769,0.0033664168,0.00019223162,0.000008687243,0.0005116161,0.00014324991,0.07093468],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952588,0.0008488445,0.0005561496,0.0012233496,0.0005071994,0.0016056743],"domain_scores_gemma":[0.99668217,0.0007959827,0.0004530787,0.0008060186,0.00036059713,0.00090216583],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.0009932987,0.0010828126,0.00093090883,0.000698604,0.0017134782,0.0028251007,0.002258216,0.0008572573,0.00030454007],"category_scores_gemma":[0.00032748698,0.0011187745,0.00066881435,0.0011515159,0.0027835937,0.0008211213,0.0031485702,0.0011242069,0.00006605069],"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":[0.004952427,0.00032580364,0.01506088,0.0013583337,0.0020323524,0.0024079115,0.1733059,0.0018463135,0.0014311781,0.7371093,0.018322937,0.041846674],"study_design_scores_gemma":[0.004181489,0.0006002784,0.0047856434,0.00097303,0.00058466144,0.0011164612,0.026365738,0.005326169,0.0020558205,0.008086175,0.9441573,0.0017672253],"about_ca_topic_score_codex":0.002619427,"about_ca_topic_score_gemma":0.0009644409,"teacher_disagreement_score":0.92583436,"about_ca_system_score_codex":0.0011908979,"about_ca_system_score_gemma":0.0026708418,"threshold_uncertainty_score":0.99993026},"labels":[],"label_agreement":null},{"id":"W7070574235","doi":"","title":"Portrait des entrepreneurs forestiers du Québec 2020-2021","year":2023,"lang":"fr","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Portrait; Context (archaeology); Work (physics)","score_opus":0.004276712000334803,"score_gpt":0.21388985335148603,"score_spread":0.20961314135115122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070574235","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":[0.011675537,0.003980511,0.0054572313,0.0023449003,0.0016399461,0.0005576874,0.00009777999,0.00021542353,0.974031],"genre_scores_gemma":[0.017664142,0.0035710179,0.0060718153,0.00046048223,0.0014426729,0.000037998176,0.00035061716,0.0006874602,0.9697138],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978968,0.000093733535,0.0005483949,0.00059236283,0.0002397116,0.0006289782],"domain_scores_gemma":[0.99849087,0.00006828873,0.00032345767,0.0007494119,0.000099487115,0.00026846072],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002218288,0.0005807811,0.00041643085,0.000096069845,0.00014506187,0.00007913726,0.000505225,0.00076911657,0.029260477],"category_scores_gemma":[0.00094663486,0.000553206,0.00034347092,0.00018848592,0.0005637258,0.00000513728,0.00037387028,0.0003627564,0.0028705348],"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":[0.000066145374,0.00016937112,0.21392839,0.0006673344,0.0010798355,0.00013085653,0.0005630311,0.0021446855,0.0013130821,0.002231661,0.5846575,0.19304812],"study_design_scores_gemma":[0.00041826902,0.0002522407,0.006347357,0.00014574605,0.00012568425,0.00009141714,0.00015215977,0.0016298259,0.0007602122,0.00006612504,0.9893598,0.0006511638],"about_ca_topic_score_codex":0.010963688,"about_ca_topic_score_gemma":0.107145615,"teacher_disagreement_score":0.4047023,"about_ca_system_score_codex":0.000117442454,"about_ca_system_score_gemma":0.00084650464,"threshold_uncertainty_score":0.99969196},"labels":[],"label_agreement":null},{"id":"W7070580457","doi":"","title":"Protocol for the Brain Health Support Program Study of the Canadian Therapeutic Platform Trial for Multidomain Interventions to Prevent Dementia (CAN-THUMBS UP): A Prospective 12-Month Intervention Study.","year":2023,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Dementia; Intervention (counseling); Protocol (science); Psychological intervention; Randomized controlled trial; Clinical trial","score_opus":0.049544462212720436,"score_gpt":0.4144543329662294,"score_spread":0.364909870753509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070580457","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":[0.0007704544,0.000015869564,0.0025277636,0.0009417032,0.00073803175,0.9918169,0.00037272155,0.0001280937,0.0026884745],"genre_scores_gemma":[0.033435345,7.290725e-7,0.00075766345,0.00018982313,0.00021054815,0.82044286,0.00014189135,0.00042273867,0.14439842],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976311,0.00020653519,0.00095364556,0.00045528915,0.00029709266,0.00045638997],"domain_scores_gemma":[0.9980382,0.00006501281,0.0008509404,0.0008147032,0.00011172576,0.00011944295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018009914,0.00036560453,0.00041359727,0.0001704073,0.00034217062,0.00008178406,0.00071847317,0.00019204078,0.00011569377],"category_scores_gemma":[0.00027858262,0.00022154741,0.0005912911,0.00016656925,0.000062617146,0.000003980725,0.00023846178,0.00020573352,0.0000026767236],"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":[0.018800348,0.033351287,0.0101908,0.006717179,0.016487602,0.0000013457791,0.018964402,0.00028169953,0.000029083087,0.0010741506,0.6769872,0.21711493],"study_design_scores_gemma":[0.12999253,0.12892003,0.00669336,0.0010350256,0.00092183263,0.0000044860376,0.014082307,0.0008657714,0.00016151142,0.00021460843,0.71599704,0.0011115272],"about_ca_topic_score_codex":0.035315327,"about_ca_topic_score_gemma":0.9377767,"teacher_disagreement_score":0.90246135,"about_ca_system_score_codex":0.00017029169,"about_ca_system_score_gemma":0.00050456234,"threshold_uncertainty_score":0.9711086},"labels":[],"label_agreement":null},{"id":"W7070593973","doi":"","title":"Ontario chooses FP as CMA's president-elect","year":2003,"lang":"en","type":"article","venue":"Europe PMC (PubMed Central)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.007797076452290326,"score_gpt":0.21573305288278516,"score_spread":0.20793597643049483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070593973","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86053634,0.0005116686,0.0004062429,0.00013753524,0.00059010217,0.00041608285,0.000005349876,0.000051911506,0.13734476],"genre_scores_gemma":[0.9471909,0.00025258283,0.0015538521,0.0007847995,0.00025268478,0.000039984014,0.00008691614,0.00006013323,0.04977819],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99791896,0.00017920235,0.0003323772,0.0003749579,0.00025642462,0.00093809876],"domain_scores_gemma":[0.99887466,0.000016372062,0.0001438993,0.0005752772,0.00007848021,0.00031131817],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031791176,0.00028049783,0.00018430759,0.000046066074,0.000113717855,0.00009874569,0.0003589688,0.00012607737,0.00046985614],"category_scores_gemma":[0.0009955355,0.0002561889,0.00010773854,0.00014846417,0.00006504229,0.00001117297,0.00010926188,0.00030732117,0.00026911034],"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":[0.00043142366,0.00059802143,0.8121506,0.00020574828,0.00067612686,0.0001484336,0.0077940635,0.0011229004,0.048436966,0.004588956,0.101692595,0.02215415],"study_design_scores_gemma":[0.00053901185,0.00013647065,0.09337767,0.000010360184,0.000027849572,0.0000802672,0.000023232373,0.000009060174,0.060841627,0.00004358616,0.844598,0.0003128886],"about_ca_topic_score_codex":0.0005052438,"about_ca_topic_score_gemma":0.0012402217,"teacher_disagreement_score":0.7429054,"about_ca_system_score_codex":0.00007762506,"about_ca_system_score_gemma":0.00032493315,"threshold_uncertainty_score":0.99998903},"labels":[],"label_agreement":null},{"id":"W7070598072","doi":"","title":"The pastoral history, biological and cultural significance of the Scotia country, far Western New South Wales","year":2012,"lang":"en","type":"article","venue":"FedUni ResearchOnline (Federation University Australia)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Vegetation (pathology); Nova scotia; Grazing; Stocking; Fauna","score_opus":0.06437490089306978,"score_gpt":0.30375597234131524,"score_spread":0.23938107144824544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070598072","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9972478,0.00021210664,0.0005142277,0.0011912032,0.00019235344,0.00025238263,0.000035997742,0.000008886391,0.00034502125],"genre_scores_gemma":[0.9793523,0.0001205097,0.00061566546,0.000058222304,0.0002149159,4.088786e-7,0.00009064134,0.0000060619695,0.019541286],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.998973,0.000224567,0.00014793442,0.00014417215,0.00023091323,0.00027940996],"domain_scores_gemma":[0.99933463,0.0000383201,0.00013243932,0.00025411288,0.00011009593,0.00013038961],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003067856,0.00011761816,0.00010051146,0.000024508658,0.00037479587,0.00004669535,0.00032266256,0.00013215531,0.000037546793],"category_scores_gemma":[0.00021994681,0.000076555494,0.000055356653,0.000075048476,0.00048569703,0.00002492995,0.00022933414,0.00022204466,0.000007556067],"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":[0.0007671277,0.00018387975,0.79918545,0.00009438332,0.0001984045,0.0000024582646,0.0033289283,0.0004383048,0.113947496,0.0036722836,0.076300465,0.00188083],"study_design_scores_gemma":[0.00059600757,0.0002052798,0.15080883,0.00001695414,0.000018602253,0.000011689007,0.0016408517,0.00034633584,0.0027032006,0.0000074044347,0.84345335,0.00019147628],"about_ca_topic_score_codex":0.0002435315,"about_ca_topic_score_gemma":0.00065941527,"teacher_disagreement_score":0.7671529,"about_ca_system_score_codex":0.00007230464,"about_ca_system_score_gemma":0.00014081947,"threshold_uncertainty_score":0.31218424},"labels":[],"label_agreement":null},{"id":"W7070600733","doi":"","title":"Quelques résultats sur la modélisation et la couverture de portefeuilles exposés au risque de longévité","year":2017,"lang":"fr","type":"other","venue":"Knowledge UdeS (Institutional Deposit of the University of Sherbrooke)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Diafiltration; Dysgeusia; Hyporeflexia; Liquation; Fusible alloy","score_opus":0.007594674971248397,"score_gpt":0.22731067908135233,"score_spread":0.21971600411010395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070600733","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17684719,0.011606487,0.09961602,0.00023673361,0.00049451104,0.0004794511,0.00012771924,0.000033545723,0.71055835],"genre_scores_gemma":[0.8979606,0.003150513,0.009155921,0.000054426848,0.00015532046,9.913875e-7,0.00012547965,0.00005033141,0.08934639],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984246,0.00044713967,0.0002748392,0.00030661278,0.0002528814,0.0002939423],"domain_scores_gemma":[0.9984773,0.000092178176,0.00046076387,0.0006030226,0.00023846471,0.00012828968],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00050428126,0.00036754104,0.00039869576,0.00010652607,0.00042160114,0.000035325073,0.0010745553,0.0009193237,0.00008420971],"category_scores_gemma":[0.00048366305,0.00035763087,0.00038222657,0.000068700436,0.0013422548,0.000038366394,0.0004952925,0.0004637505,0.00001475823],"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":[0.0012387602,0.0023208838,0.09876404,0.02841167,0.003791896,0.00015549132,0.03660797,0.44533974,0.20840625,0.06463149,0.07378549,0.036546305],"study_design_scores_gemma":[0.0016092162,0.00018835081,0.068172455,0.0077572777,0.000514093,0.0002256889,0.00019498635,0.051437538,0.029461266,0.0001930751,0.83957714,0.00066893786],"about_ca_topic_score_codex":0.004687354,"about_ca_topic_score_gemma":0.033126898,"teacher_disagreement_score":0.7657916,"about_ca_system_score_codex":0.0008238736,"about_ca_system_score_gemma":0.001545145,"threshold_uncertainty_score":0.9998876},"labels":[],"label_agreement":null},{"id":"W7070604005","doi":"","title":"Preterm bebeklerde nöromotor gelişimin farklı hareket analizleri ile değerlendirilmesi","year":2016,"lang":"tr","type":"other","venue":"Marmara University Open Access System","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Motor activity; Population; Gross motor skill; Pregnancy","score_opus":0.019569281479562287,"score_gpt":0.3116435153165278,"score_spread":0.2920742338369655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070604005","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":[0.012513867,0.00039325585,0.0027827641,0.00029594125,0.0015017636,0.0034281153,0.002474831,0.00016190457,0.9764476],"genre_scores_gemma":[0.0928366,0.0007296712,0.0021137968,0.00025793107,0.00080417295,0.000022451071,0.0015452708,0.00043399844,0.9012561],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99551624,0.00066113286,0.0007929765,0.0014120333,0.0005864516,0.001031189],"domain_scores_gemma":[0.99569845,0.00005609324,0.0016273173,0.0017983093,0.00029426845,0.0005255693],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.00068604853,0.0011150872,0.0012539921,0.00047202097,0.00060925365,0.0015420597,0.008876704,0.0010889902,0.008804353],"category_scores_gemma":[0.000067525274,0.0011000102,0.0004630563,0.0003080377,0.00032107922,0.00019662449,0.008995391,0.00055265124,0.0019101956],"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":[0.0015298065,0.00027281087,0.03364064,0.005746671,0.0024881773,0.00047601567,0.0003046564,0.00004653379,0.0015734802,0.0013471755,0.94618857,0.0063854354],"study_design_scores_gemma":[0.0026912591,0.00022245392,0.0029433193,0.0015639819,0.00034931928,0.00010674374,0.00059694,0.0006436275,0.0005876898,0.0000014467626,0.9888022,0.0014910022],"about_ca_topic_score_codex":0.00085414835,"about_ca_topic_score_gemma":0.00040151723,"teacher_disagreement_score":0.080322735,"about_ca_system_score_codex":0.0006422159,"about_ca_system_score_gemma":0.00054342765,"threshold_uncertainty_score":0.99949443},"labels":[],"label_agreement":null},{"id":"W7070608973","doi":"","title":"Peruskoulun 3.-6. luokan suomen kielen ja kirjallisuuden tehtävien sähköistettävyys","year":2021,"lang":"fi","type":"other","venue":"UTUPub (University of Turku)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Loin; Work (physics); Quarter (Canadian coin)","score_opus":0.0062114918624021865,"score_gpt":0.2045642011858605,"score_spread":0.1983527093234583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070608973","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":[0.029826725,0.0047430145,0.000942909,0.00095172005,0.0008383314,0.0006508952,0.00037981747,0.00006279981,0.96160376],"genre_scores_gemma":[0.0427271,0.003722098,0.009262465,0.00030970303,0.0006152112,0.0000010263637,0.0027826023,0.00022464202,0.9403551],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971126,0.00026509928,0.00043006524,0.0008899181,0.00056517456,0.00073716696],"domain_scores_gemma":[0.99705344,0.00004628567,0.0008381595,0.0014312583,0.0002798499,0.0003510047],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00034380416,0.00071306556,0.00093420624,0.00031394255,0.00028413982,0.000073111536,0.0015853362,0.0014164725,0.011140456],"category_scores_gemma":[0.00014626529,0.0008899487,0.00065756135,0.00033523148,0.00051036075,0.00001874667,0.0013643433,0.0007645562,0.00036730894],"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":[0.0011029125,0.0019132007,0.025385523,0.011885207,0.009481359,0.0007340792,0.017505622,0.0010205724,0.06544878,0.0028904555,0.72682196,0.1358103],"study_design_scores_gemma":[0.0012182008,0.0003502365,0.0014768132,0.00039167525,0.0002983012,0.000052063006,0.0028934046,0.0007959609,0.0005298428,0.000012673423,0.99105895,0.00092191197],"about_ca_topic_score_codex":0.0008034727,"about_ca_topic_score_gemma":0.0008914469,"teacher_disagreement_score":0.26423693,"about_ca_system_score_codex":0.00013840805,"about_ca_system_score_gemma":0.00040672542,"threshold_uncertainty_score":0.9998799},"labels":[],"label_agreement":null},{"id":"W7070637671","doi":"","title":"Press Release (1961-02-21) Spring quarter registration for all currently enrolled UMD students will be held","year":2018,"lang":"en","type":"other","venue":"University of Minnesota Digital Conservancy (University of Minnesota)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Spring (device); Quarter (Canadian coin); Press release","score_opus":0.011159694482729958,"score_gpt":0.22675034030516622,"score_spread":0.21559064582243626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070637671","genre_codex":"empirical","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":[0.5445512,0.0019074096,0.031036824,0.002248434,0.0014322306,0.005571828,0.0069816243,0.00039636705,0.4058741],"genre_scores_gemma":[0.10976904,0.0019486449,0.012976162,0.00015501406,0.00041463223,0.000001312903,0.0037675432,0.0003918238,0.87057585],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99805,0.00007720207,0.00032208159,0.0006545632,0.0004810171,0.00041513564],"domain_scores_gemma":[0.99743736,0.000064077605,0.0010831333,0.0008566614,0.00036033965,0.00019844968],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019136553,0.0004793299,0.00066900696,0.0002570921,0.00016814182,0.00004214115,0.0012533109,0.0006177806,0.00026991073],"category_scores_gemma":[0.000118458855,0.000659583,0.00045178825,0.00012868417,0.00057086523,0.00010099627,0.00054644764,0.0001903611,0.000031658878],"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":[0.0018110208,0.00065439026,0.008002089,0.0015807037,0.0012270812,0.000046491827,0.0010334144,0.000022906426,0.0011150063,0.00023585097,0.9829769,0.0012941187],"study_design_scores_gemma":[0.0035802238,0.0007970652,0.0005079879,0.00038714864,0.00032436725,0.000009842207,0.001740889,0.00032271788,0.00021941717,0.000012015838,0.9914367,0.00066159567],"about_ca_topic_score_codex":0.0006603092,"about_ca_topic_score_gemma":0.0015058151,"teacher_disagreement_score":0.4647017,"about_ca_system_score_codex":0.000053070635,"about_ca_system_score_gemma":0.00016779553,"threshold_uncertainty_score":0.99958557},"labels":[],"label_agreement":null},{"id":"W7070640302","doi":"","title":"PNR and SWIFT agreements : external relations of the EU on data protection matters","year":2012,"lang":"en","type":"other","venue":"Dipòsit Digital de Documents de la UAB (Universitat Autònoma de Barcelona)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Swift; European union; Context (archaeology); Directive; Negotiation; Terrorism; Order (exchange)","score_opus":0.006408121972952618,"score_gpt":0.2328160522988053,"score_spread":0.22640793032585269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070640302","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15857598,0.00061977335,0.010912463,0.0013950688,0.00033494236,0.0014077593,0.0012851433,0.00011542122,0.82535344],"genre_scores_gemma":[0.66506934,0.000104920415,0.0043126056,0.0006678453,0.00017283221,0.000012604699,0.0010697122,0.0002517287,0.3283384],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99887025,0.00011389409,0.00015835442,0.0002916894,0.0002391722,0.000326643],"domain_scores_gemma":[0.9988267,0.000024738232,0.00029959154,0.0007079442,0.000019952093,0.00012108441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018858825,0.00025310396,0.00016922322,0.00014105975,0.00010758612,0.00011489095,0.00067101716,0.00032191066,0.00021044553],"category_scores_gemma":[0.00006331768,0.00024096998,0.00008281305,0.000098100594,0.00018103348,0.000051618284,0.0007503016,0.00028830228,0.000035365167],"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":[0.0006137787,0.0008851561,0.17418563,0.0011738931,0.0026567136,0.00007925404,0.0022802514,0.00036675265,0.015805291,0.007394365,0.7374853,0.057073653],"study_design_scores_gemma":[0.001152467,0.00018347488,0.051124804,0.0003730695,0.00018201281,0.00011546726,0.0002803483,0.0006963557,0.000307718,0.00027199983,0.94481283,0.00049946643],"about_ca_topic_score_codex":0.00009850082,"about_ca_topic_score_gemma":0.00002157562,"teacher_disagreement_score":0.50649333,"about_ca_system_score_codex":0.00010509582,"about_ca_system_score_gemma":0.000083226,"threshold_uncertainty_score":0.9826471},"labels":[],"label_agreement":null},{"id":"W7070641734","doi":"","title":"Put People First, Demand Over 150 Canadian Organizations with the Launch of Six Principles for a Just Recovery","year":2020,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Work (physics); Agency (philosophy)","score_opus":0.006178296678189975,"score_gpt":0.21546915020900945,"score_spread":0.20929085353081947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070641734","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":[0.002335862,0.00060101616,0.04254268,0.0043141544,0.00025911265,0.00223733,0.0015756079,0.0000816793,0.94605255],"genre_scores_gemma":[0.022145253,0.00019998814,0.01490289,0.0017053102,0.00048266925,0.00006823026,0.002459254,0.00047736755,0.95755905],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99936193,0.000015911173,0.00016397494,0.00018393743,0.0000948124,0.00017940998],"domain_scores_gemma":[0.99924916,0.00002410766,0.00018989165,0.00035697734,0.00008877786,0.00009111383],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000068387344,0.00018240238,0.00018422502,0.00005558542,0.000081548154,0.000025519577,0.0002613559,0.0002330816,0.0009800604],"category_scores_gemma":[0.00023489578,0.0001194745,0.000045604025,0.00018159562,0.00004600384,0.0000014497784,0.000072047194,0.000093209,0.000010154387],"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":[0.000015937274,0.000012638532,0.0045093275,0.00039943878,0.0002329743,4.0698367e-7,0.00018351553,0.0006898498,0.00012717172,0.0006127436,0.99316084,0.00005513457],"study_design_scores_gemma":[0.00023707919,0.00015966334,0.0007222808,0.00003375871,0.00006022562,0.0000035070254,0.00006948301,0.0006223399,0.00025856806,0.0000016678912,0.9976516,0.00017986754],"about_ca_topic_score_codex":0.013118837,"about_ca_topic_score_gemma":0.63110137,"teacher_disagreement_score":0.6179825,"about_ca_system_score_codex":0.00001530611,"about_ca_system_score_gemma":0.00047463283,"threshold_uncertainty_score":0.9999332},"labels":[],"label_agreement":null},{"id":"W7070644711","doi":"","title":"Primary characterization of a panel of monoclonal antibodies raised against the fungal pathogen Candida albicans","year":2014,"lang":"en","type":"article","venue":"NPARC","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Candida albicans; Monoclonal antibody; Pathogen; Corpus albicans; Antibody; Immunofluorescence; Candida tropicalis; Glycoprotein; Yeast","score_opus":0.007546454541587085,"score_gpt":0.21309097033474125,"score_spread":0.20554451579315416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070644711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98229575,0.000013732215,0.0031680842,0.00013864189,0.000050543393,0.00011049414,0.000074604366,0.0000056090043,0.014142559],"genre_scores_gemma":[0.99752563,0.00004847185,0.0014255486,0.00027625964,0.00008234585,0.0000054241677,0.00045305098,0.000010091029,0.0001731582],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993607,0.00007014986,0.00023433325,0.00009458932,0.00012823839,0.000112004476],"domain_scores_gemma":[0.99941826,0.00001976498,0.00020862799,0.00025595547,0.00007218412,0.000025207073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022148027,0.0000880365,0.0001352029,0.00002211183,0.000041392625,0.0000062091217,0.00016832755,0.00006800942,0.000025864769],"category_scores_gemma":[0.000100299454,0.00006400865,0.000057934147,0.000045810226,0.00010378988,0.0000030102844,0.000078614336,0.00006525337,0.0000014878487],"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":[0.000039956096,0.000020168292,0.018215599,0.000058674603,0.000026760119,1.377809e-7,0.00019116083,0.000031976535,0.9769756,0.00013698036,0.00011621838,0.004186722],"study_design_scores_gemma":[0.0009491657,0.00039277907,0.40878025,0.000054523538,0.000041000058,0.000011171892,0.00006735499,0.008845282,0.5541589,0.00012829917,0.026290227,0.0002810453],"about_ca_topic_score_codex":0.000004823838,"about_ca_topic_score_gemma":0.000002034875,"teacher_disagreement_score":0.42281675,"about_ca_system_score_codex":0.0000043605537,"about_ca_system_score_gemma":0.000048658607,"threshold_uncertainty_score":0.2610197},"labels":[],"label_agreement":null},{"id":"W7070657051","doi":"","title":"Parliamentary corruption as developed in its connection with Jesuit incorporation and the Quebec Jesuits estates Act.","year":2014,"lang":"en","type":"article","venue":"QSpace (Queen's University Library)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Protestantism; Conscience; Power (physics); Language change; Brother; Duty; Patron saint; Governor; Independence (probability theory)","score_opus":0.0040613015574543394,"score_gpt":0.1838288382378483,"score_spread":0.17976753668039394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070657051","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97990835,0.000009520313,0.0023312108,0.014236685,0.000044635482,0.0002995288,0.000004407236,0.000041530497,0.0031241197],"genre_scores_gemma":[0.9864132,0.00016976846,0.0018293916,0.0004682639,0.00003668712,0.0000016700736,0.00026308376,0.0000147881965,0.010803146],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.999236,0.00019926309,0.00010862198,0.00020124576,0.000107881715,0.00014698572],"domain_scores_gemma":[0.999536,0.000054464086,0.00014782963,0.0001710287,0.00003339277,0.00005732241],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000119671386,0.00014078476,0.00012435367,0.000085295025,0.00013264452,0.000059679747,0.000143809,0.00010733868,0.000024899477],"category_scores_gemma":[0.000064038206,0.00011375104,0.000023221473,0.00017147964,0.00012139706,0.00010110008,0.0001433479,0.00014900645,0.000010964338],"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":[0.010924148,0.0003149414,0.85386944,0.00046169022,0.00040237888,0.000060683782,0.0064458977,0.008193617,0.0029087984,0.03761289,0.054333273,0.024472248],"study_design_scores_gemma":[0.018619914,0.0024051326,0.36019862,0.0003310677,0.00020691562,0.000024459083,0.009607569,0.008466627,0.062649146,0.0009803085,0.53448486,0.0020253486],"about_ca_topic_score_codex":0.0063734287,"about_ca_topic_score_gemma":0.0030957242,"teacher_disagreement_score":0.49367082,"about_ca_system_score_codex":0.000028215163,"about_ca_system_score_gemma":0.000109566696,"threshold_uncertainty_score":0.96347606},"labels":[],"label_agreement":null},{"id":"W7070663955","doi":"","title":"Phibro Animal Health Corporation Reports First Quarter","year":2017,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corporation; Quarter (Canadian coin); Animal health; Public health","score_opus":0.008530448784602256,"score_gpt":0.27202745998480166,"score_spread":0.2634970112001994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070663955","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":[0.00006050243,0.00050052366,0.0027684306,0.0007851203,0.00045904564,0.0003281642,0.000021634112,0.00008427536,0.9949923],"genre_scores_gemma":[0.011199129,0.00026463444,0.005664043,0.0005916892,0.0009169017,0.000014897236,0.0016129826,0.00022341202,0.97951233],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99910897,0.000023549026,0.00025227992,0.0002807196,0.00013965499,0.00019481777],"domain_scores_gemma":[0.9981109,0.000002136996,0.00090986176,0.0008727579,0.000024519844,0.00007982343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001700671,0.0002166619,0.00021673288,0.000056192435,0.000107028165,0.0000602349,0.00016304813,0.00034236783,0.0005661311],"category_scores_gemma":[0.00006258125,0.00019271432,0.00007516301,0.0000151447675,0.00005346967,0.0000021294636,0.000084138956,0.0001304241,0.000069911024],"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":[0.0000073032834,0.0000137191455,0.00063105224,0.00011522001,0.000032683332,0.000004967555,0.000012983113,0.000002021659,0.000132177,0.000061749866,0.99842185,0.000564289],"study_design_scores_gemma":[0.00011686566,0.00028477825,0.00023074895,0.00007329713,0.000006444872,0.00006229439,0.000005157707,0.00008057561,0.00013560234,0.0000062323193,0.99878,0.00021797388],"about_ca_topic_score_codex":0.0003677315,"about_ca_topic_score_gemma":0.0014771114,"teacher_disagreement_score":0.015479992,"about_ca_system_score_codex":0.000013033322,"about_ca_system_score_gemma":0.00012588395,"threshold_uncertainty_score":0.78586614},"labels":[],"label_agreement":null},{"id":"W7070668328","doi":"","title":"From practicum to practice, two beginning teachers' perceptions of the quality of their preservice preparation","year":2000,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Practicum; Quality (philosophy); Perception; Qualitative research","score_opus":0.00355527619574616,"score_gpt":0.22280064182315473,"score_spread":0.21924536562740857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070668328","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05800679,0.00023573232,0.0002032877,0.0019218542,0.0001382663,0.00037072858,0.0010954858,0.000005350352,0.9380225],"genre_scores_gemma":[0.7531841,0.00029145816,0.013516943,0.0018748775,0.00029985502,0.000019716095,0.00024550187,0.0001396504,0.23042792],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99842906,0.00020369851,0.00033940308,0.00017902815,0.0007229564,0.00012582805],"domain_scores_gemma":[0.99869645,0.00014144553,0.0006314029,0.00044986152,0.0000013009048,0.00007952949],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000024948144,0.00016445406,0.00022604526,0.000015882611,0.00005063822,0.000008436763,0.00030449303,0.00006249244,0.00010660265],"category_scores_gemma":[0.00003209508,0.00013167124,0.000040235504,0.00004912512,0.00006378523,0.000019117084,0.00020316419,0.00014598327,3.8463837e-9],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032718512,0.0003527317,0.06635901,0.001588269,0.00198088,0.000004492752,0.0052262736,0.0036426173,0.52914476,0.0037150807,0.370959,0.013755035],"study_design_scores_gemma":[0.0003690603,0.00012272756,0.014781587,0.00026798053,0.00006958423,0.0000025654006,0.005622949,0.00040938286,0.053539116,0.00004992627,0.92447937,0.00028574534],"about_ca_topic_score_codex":0.021641968,"about_ca_topic_score_gemma":0.06094552,"teacher_disagreement_score":0.7075946,"about_ca_system_score_codex":0.0000025772208,"about_ca_system_score_gemma":0.00081321615,"threshold_uncertainty_score":0.984873},"labels":[],"label_agreement":null},{"id":"W7070677564","doi":"","title":"Reclaiming digital sovereignty: A roadmap to build a digital stack for people and the planet","year":2024,"lang":"en","type":"article","venue":"UCL Discovery (University College London)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Universidade Federal do Paraná; Instituto Tecnológico y de Estudios Superiores de Monterrey; Universidad de Córdoba; Università degli Studi di Siena; Consejo Nacional de Investigaciones Científicas y Técnicas; Universidade Federal do Rio de Janeiro; Universidade Federal de Minas Gerais; Universiteit van Amsterdam; London School of Economics and Political Science; University College London; University of Toronto; Universitat Pompeu Fabra; Vrije Universiteit Amsterdam; Universiteit Utrecht; Politecnico di Torino; Universidad Nacional de Córdoba","keywords":"Sovereignty; Agency (philosophy); Civil society; Government (linguistics); The Internet; State (computer science); Misappropriation; Democracy","score_opus":0.0038941571472545173,"score_gpt":0.19694210597912978,"score_spread":0.19304794883187526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070677564","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95382744,0.00035085646,0.019095294,0.0021025897,0.0002886028,0.0011172006,0.008465328,0.00007912906,0.01467357],"genre_scores_gemma":[0.98055565,0.000034639277,0.0004974753,0.0002470639,0.0001151924,0.0000039341917,0.0007127145,0.000023902312,0.017809438],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911517,0.000022293021,0.00012923164,0.00031995,0.00014645762,0.00026689892],"domain_scores_gemma":[0.9994157,0.00013368198,0.000047471814,0.00027409094,0.000030231335,0.00009885665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012050092,0.00018545284,0.00019557889,0.00008570651,0.00027349428,0.00041899484,0.00027050212,0.00010163009,0.000016225782],"category_scores_gemma":[0.000113342256,0.00015739925,0.00011092869,0.0001878294,0.00010694267,0.000119370794,0.00040399126,0.00012952158,0.000025443831],"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":[0.01954979,0.0004080307,0.014938403,0.0021008588,0.0024487337,0.00028984903,0.0091229025,0.0043653045,0.0030232323,0.4455703,0.46653333,0.03164926],"study_design_scores_gemma":[0.003546822,0.0006460297,0.0008373941,0.000096791155,0.00011745262,0.00014266511,0.0044221417,0.023189794,0.00017986135,0.0010646413,0.96509075,0.0006656424],"about_ca_topic_score_codex":0.000028824574,"about_ca_topic_score_gemma":0.00007845227,"teacher_disagreement_score":0.49855742,"about_ca_system_score_codex":0.000036250032,"about_ca_system_score_gemma":0.00010598348,"threshold_uncertainty_score":0.64185554},"labels":[],"label_agreement":null},{"id":"W7070685520","doi":"","title":"Photographs - Two photographs of the drawing room at 32 Church Street, 13 June 1954","year":2024,"lang":"en","type":"other","venue":"Brock University Digital Repository (Brock University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Photography; White (mutation); Line drawings; Doors","score_opus":0.004789902085497092,"score_gpt":0.1913222523904206,"score_spread":0.18653235030492352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070685520","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":[0.041794796,0.00047397285,0.00024201926,0.0000026028345,0.0010152957,0.0005747103,0.0004494756,0.00023156144,0.9552156],"genre_scores_gemma":[0.04216774,0.00013706429,0.00011950216,0.000022603288,0.00015442936,2.6360718e-7,0.00017974671,0.00020714117,0.9570115],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979272,0.00010553336,0.00029400087,0.00074264884,0.00047093074,0.0004596833],"domain_scores_gemma":[0.99805,0.00002667831,0.0005509364,0.001034277,0.0001245085,0.0002136363],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0000055733763,0.000576612,0.00045423245,0.00072521396,0.0002839842,0.00008801259,0.0013671918,0.00061051326,0.00003602504],"category_scores_gemma":[0.00003129814,0.000590393,0.00080242805,0.0008477018,0.00034560898,0.00004065645,0.0019433277,0.0005074735,0.000043685053],"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":[0.00020724135,0.00013411972,0.028515132,0.00045872247,0.00088734605,0.00007436795,0.000051664458,0.00013922695,0.049006496,0.000027784348,0.9203687,0.00012923981],"study_design_scores_gemma":[0.0008848094,0.00014861352,0.00039741752,0.00039224568,0.00034370538,0.00005805523,0.0025104037,0.000007500059,0.004242985,0.0000074662817,0.99033684,0.0006699705],"about_ca_topic_score_codex":0.000500561,"about_ca_topic_score_gemma":0.002447359,"teacher_disagreement_score":0.069968164,"about_ca_system_score_codex":0.00016459261,"about_ca_system_score_gemma":0.00018564577,"threshold_uncertainty_score":0.99965477},"labels":[],"label_agreement":null},{"id":"W7070695158","doi":"","title":"Quels sont les facteurs organisationnels contributifs au maintien en emploi des personnes ayant des problèmes de santé mentale dans les milieux adaptés ?","year":2012,"lang":"fr","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Diafiltration; Liquation; Triacetin; Demotion; Emperipolesis","score_opus":0.004001730498408786,"score_gpt":0.16425687198983138,"score_spread":0.1602551414914226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070695158","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80445075,0.0039906837,0.0031011817,0.00077713793,0.00024931008,0.00058638956,0.0017175152,0.000018899042,0.18510811],"genre_scores_gemma":[0.92994606,0.0014028688,0.009561889,0.0002543367,0.000298352,0.00002195815,0.00020270361,0.000135091,0.05817676],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9970644,0.00028058433,0.0005121585,0.00037812142,0.0008670627,0.000897678],"domain_scores_gemma":[0.99857515,0.00017155564,0.00044006758,0.00032187643,0.0000030245233,0.00048832013],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000057266858,0.0005644175,0.00048104007,0.000036468336,0.0005484156,0.000052475087,0.00045934846,0.00022354377,0.0006910812],"category_scores_gemma":[0.000038690825,0.0005376736,0.00009311027,0.00005644202,0.00068467844,0.000055221593,0.0003371282,0.0002918738,4.5496275e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003165934,0.0001470592,0.7680525,0.001895048,0.00079054217,0.000034755623,0.0075994013,0.00028475435,0.16976513,0.012076313,0.001109872,0.037927993],"study_design_scores_gemma":[0.0012003967,0.0004852193,0.35031125,0.0009824482,0.0002901061,0.00012293413,0.05304871,0.0012515223,0.38659388,0.0004395549,0.20390195,0.0013720413],"about_ca_topic_score_codex":0.03998688,"about_ca_topic_score_gemma":0.27510226,"teacher_disagreement_score":0.4177413,"about_ca_system_score_codex":0.00010513381,"about_ca_system_score_gemma":0.0025223591,"threshold_uncertainty_score":0.99970746},"labels":[],"label_agreement":null},{"id":"W7070695660","doi":"","title":"Projet d'acquisition de connaissances sur les eaux souterraines en Estrie (PACES Estrie)- Portrait des ressources en eau souterraine en Estrie, Québec, Canada","year":2024,"lang":"fr","type":"other","venue":"EspaceINRS (National Institute for Scientific Research (Canada))","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Western europe; Ministry of Foreign Affairs; Prospection","score_opus":0.029146752813737856,"score_gpt":0.3045485062448532,"score_spread":0.27540175343111534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070695660","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36879146,0.04337304,0.011976206,0.38811016,0.018732168,0.011501389,0.032724317,0.0003534138,0.12443785],"genre_scores_gemma":[0.5692433,0.0004999117,0.0053725005,0.00037463143,0.0029692014,0.0005198212,0.0086407615,0.00033195835,0.41204792],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99178207,0.0007836433,0.0010714206,0.0014893002,0.0032183842,0.0016551898],"domain_scores_gemma":[0.9951637,0.0008318795,0.000559112,0.0007697045,0.0020287933,0.0006468449],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.004726232,0.000867901,0.00067537744,0.00062068587,0.0017089886,0.001039978,0.0017073572,0.00071822136,0.0006690266],"category_scores_gemma":[0.007298924,0.00083832536,0.00023171915,0.0009767817,0.0027141392,0.00010321336,0.000490359,0.0012313799,0.000017983408],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026049165,0.00015139628,0.0020934034,0.0032517589,0.0010176202,0.00016908626,0.0021368694,0.012008766,0.004416186,0.012055058,0.95632285,0.006116544],"study_design_scores_gemma":[0.0006416384,0.0002060028,0.00070850644,0.00078426034,0.000075894364,0.00007425034,0.001679049,0.0075130183,0.003142479,0.00039885473,0.9839204,0.0008556698],"about_ca_topic_score_codex":0.98531103,"about_ca_topic_score_gemma":0.99992514,"teacher_disagreement_score":0.38773552,"about_ca_system_score_codex":0.0029755544,"about_ca_system_score_gemma":0.06534072,"threshold_uncertainty_score":0.9999999},"labels":[],"label_agreement":null},{"id":"W7070696960","doi":"","title":"Quand le Canada partait en croisade : de la réalité au mythe des zouaves pontificaux canadiens, 1868-1941","year":2020,"lang":"fr","type":"other","venue":"Corpus Université Laval (Université Laval)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mythology; Coronation; ESPACE","score_opus":0.005222241246714286,"score_gpt":0.18092775317489443,"score_spread":0.17570551192818015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070696960","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":[0.39161488,0.007614504,0.0023676418,0.012837454,0.0013597267,0.0010465825,0.0015872905,0.00020702698,0.58136487],"genre_scores_gemma":[0.39268324,0.0048262384,0.0024424228,0.00070053013,0.0005946318,0.0000031106883,0.0009876878,0.0003797556,0.5973824],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99592984,0.0009427231,0.00042495414,0.0009719432,0.0004769852,0.0012535667],"domain_scores_gemma":[0.99706036,0.00023912737,0.00056295056,0.0009056582,0.0001842975,0.0010476055],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042052608,0.0009490642,0.00081651454,0.00025332565,0.0009825197,0.00012140129,0.001519094,0.0011560265,0.00041089012],"category_scores_gemma":[0.00026202833,0.0011636676,0.00041205372,0.0004807247,0.000762619,0.000036867274,0.0008029705,0.0010329804,0.000037484217],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019492077,0.0007455548,0.17125016,0.003790425,0.0073423665,0.0096673565,0.10591734,0.0048859534,0.14113893,0.06228783,0.38654134,0.10448353],"study_design_scores_gemma":[0.001679476,0.00032382103,0.010782282,0.00022769845,0.00054369314,0.00028834117,0.006640547,0.000680142,0.008847878,0.0000649057,0.9686669,0.0012543292],"about_ca_topic_score_codex":0.91704965,"about_ca_topic_score_gemma":0.97591805,"teacher_disagreement_score":0.58212554,"about_ca_system_score_codex":0.002925859,"about_ca_system_score_gemma":0.008864511,"threshold_uncertainty_score":0.9990813},"labels":[],"label_agreement":null},{"id":"W7070737440","doi":"","title":"Rapport de la journée régionale du Saguenay/Lac St-Jean et résumés des journées régionales","year":2015,"lang":"fr","type":"other","venue":"Bibliothèque et Archives nationales du Québec (Québec government)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Set (abstract data type); Context (archaeology); Identification (biology); Perspective (graphical)","score_opus":0.011648449641592179,"score_gpt":0.24903316908977746,"score_spread":0.2373847194481853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070737440","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":[0.12402178,0.024371719,0.008143472,0.033736475,0.00037479022,0.00086712977,0.0011262057,0.00016830837,0.8071901],"genre_scores_gemma":[0.234784,0.020416074,0.018167011,0.0058003333,0.0024371117,0.00021869609,0.0011191887,0.0007846326,0.71627295],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99394524,0.0014124915,0.0012246534,0.00089611195,0.0015805546,0.00094092457],"domain_scores_gemma":[0.99172986,0.005247254,0.0012669476,0.0007529027,0.00025600422,0.0007470573],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002228707,0.0011359152,0.000809824,0.00095450727,0.00046706185,0.00064443983,0.0014924537,0.00059071457,0.009162195],"category_scores_gemma":[0.010289244,0.0011210314,0.00064781454,0.0005565794,0.0016870298,0.00011217929,0.0010097427,0.0012153431,0.00056875875],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029387817,0.00074154546,0.14816459,0.0004889922,0.0010551162,0.00005753656,0.0028659361,0.003908128,0.0021462531,0.007647814,0.83205163,0.0005785959],"study_design_scores_gemma":[0.0016738148,0.00038755694,0.04586887,0.00051134813,0.0002013718,0.00066544674,0.00028753135,0.0023951402,0.00052676373,0.0010854292,0.9452312,0.0011655143],"about_ca_topic_score_codex":0.02766746,"about_ca_topic_score_gemma":0.7102328,"teacher_disagreement_score":0.68256533,"about_ca_system_score_codex":0.0028384773,"about_ca_system_score_gemma":0.06782134,"threshold_uncertainty_score":0.999124},"labels":[],"label_agreement":null},{"id":"W7070738823","doi":"","title":"Radio frequency microstrip line model of circulatory system vessels for cardiovascular application.","year":2019,"lang":"fr","type":"dissertation","venue":"EspaceINRS Institutional Digital Repository (Institut National de la Recherche Scientifique)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Ven; Coronary heart disease; Bellows; Fontan procedure","score_opus":0.040260060812151506,"score_gpt":0.2997784440104632,"score_spread":0.2595183831983117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070738823","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.087754644,0.010772041,0.7784133,0.000110521236,0.003289827,0.0038006774,0.0029854714,0.00012680497,0.112746716],"genre_scores_gemma":[0.9112253,0.00018311437,0.06150674,0.000055411285,0.00060127303,0.0004929738,0.007833113,0.00009636108,0.018005697],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946992,0.000598266,0.0013868578,0.0012203765,0.0015064335,0.00058888586],"domain_scores_gemma":[0.994147,0.0006991506,0.0009947403,0.0009171525,0.0029498779,0.0002921048],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0042264136,0.0007357165,0.0008041765,0.00042579597,0.0006591882,0.00042444564,0.0009711718,0.0024358707,0.000002696076],"category_scores_gemma":[0.005276215,0.0008366469,0.0015421591,0.00055908825,0.0011496954,0.0001852346,0.0001488621,0.0010969379,0.000033375352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001761273,0.0002949984,0.00081751746,0.004431186,0.0011999137,0.000004366026,0.0004190155,0.5295981,0.31399253,0.1474375,0.00043769283,0.0011910251],"study_design_scores_gemma":[0.0034512526,0.00027561816,0.0010342592,0.002946182,0.0010094295,0.0006957328,0.0005801357,0.66067165,0.24356878,0.0046497905,0.0786942,0.002422954],"about_ca_topic_score_codex":0.000058875903,"about_ca_topic_score_gemma":0.000009277251,"teacher_disagreement_score":0.82347065,"about_ca_system_score_codex":0.0026112976,"about_ca_system_score_gemma":0.012430945,"threshold_uncertainty_score":0.9994084},"labels":[],"label_agreement":null},{"id":"W7070742003","doi":"","title":"Pratiques d’enseignement\\n au Canada et au Brésil intégrant les arts dans les sciences et technologies","year":2017,"lang":"fr","type":"article","venue":"Érudit (Université de Montréal)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"The arts; Human science; Limiting; Context (archaeology)","score_opus":0.007964435683887064,"score_gpt":0.21032920746502717,"score_spread":0.2023647717811401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070742003","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81039774,0.0138666965,0.0045358404,0.097194925,0.0005273576,0.00031287782,0.00017916084,0.000091652146,0.07289374],"genre_scores_gemma":[0.9735011,0.0063975495,0.0055334256,0.00033701633,0.00009089715,0.000006037147,0.00007605929,0.000025090172,0.014032812],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982991,0.00012667738,0.00024205244,0.00040816198,0.0003097573,0.0006142411],"domain_scores_gemma":[0.9984775,0.000052065192,0.00048429702,0.0007692245,0.00010274021,0.00011412805],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0004917124,0.00033651735,0.00026249432,0.00008428777,0.0030145408,0.0001368047,0.001050353,0.00039374796,0.00001884764],"category_scores_gemma":[0.00043924237,0.00034830256,0.00010895955,0.00008231983,0.0010800584,0.0000610707,0.0011553974,0.00037621803,0.0000052432856],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002648784,0.00033243693,0.19923641,0.00083184126,0.00093394244,0.0016446311,0.008815401,0.005858297,0.034916624,0.2987979,0.21519889,0.23316872],"study_design_scores_gemma":[0.00055395055,0.00041836812,0.021050967,0.0001738414,0.00009583229,0.00025674087,0.008912432,0.0017101787,0.013367516,0.00023777668,0.95268804,0.000534333],"about_ca_topic_score_codex":0.85750306,"about_ca_topic_score_gemma":0.9969019,"teacher_disagreement_score":0.73748916,"about_ca_system_score_codex":0.0033038594,"about_ca_system_score_gemma":0.0016345615,"threshold_uncertainty_score":0.9998969},"labels":[],"label_agreement":null},{"id":"W7070744574","doi":"","title":"Reports of the Canada Presbyterian Church, Lagauchetiere Street, Montreal for 1861.","year":2014,"lang":"en","type":"article","venue":"QSpace (Queen's University Library)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Liquation; Diafiltration; Emperipolesis; Triacetin; Durvalumab","score_opus":0.0023589702650247822,"score_gpt":0.16144354139000397,"score_spread":0.15908457112497917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070744574","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95433086,0.000014890644,0.0010597083,0.013130785,0.0003308971,0.00049391564,0.00013997372,0.000041868403,0.030457113],"genre_scores_gemma":[0.94734323,0.000017024822,0.0020446416,0.0002217565,0.00008211997,8.387657e-7,0.00014164449,0.000019772844,0.050128955],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992325,0.00007617043,0.00014412099,0.00020247641,0.00014033577,0.00020439646],"domain_scores_gemma":[0.99905527,0.000026022366,0.0002325812,0.00055652414,0.00004167865,0.0000879033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005056881,0.00013831462,0.00014530854,0.000028818065,0.00011812286,0.000013267303,0.00035221665,0.000118097334,0.000029086299],"category_scores_gemma":[0.000089356225,0.00012135037,0.00010123146,0.00008703833,0.00007820093,0.000019320363,0.0002955291,0.00010138079,2.9526853e-7],"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":[0.00016819354,0.00004696729,0.097831115,0.0001772873,0.00011949885,0.000010726293,0.00014712446,0.00075018784,0.00072982605,0.00079641794,0.8982751,0.0009475742],"study_design_scores_gemma":[0.00038383546,0.00014925656,0.049273703,0.000023301827,0.000033912398,0.0000013012257,0.00019785526,0.00011001234,0.027295958,0.0000514426,0.92227465,0.00020477155],"about_ca_topic_score_codex":0.17555025,"about_ca_topic_score_gemma":0.05664207,"teacher_disagreement_score":0.11890819,"about_ca_system_score_codex":0.000020013003,"about_ca_system_score_gemma":0.00029362887,"threshold_uncertainty_score":0.96057177},"labels":[],"label_agreement":null},{"id":"W7070759534","doi":"","title":"Regional environmental assessment of forest management : experience in Ontario and Minnesota","year":2017,"lang":"en","type":"dissertation","venue":"Knowledge Commons (Lakehead University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Environmental impact statement; Strengths and weaknesses; Environmental impact assessment; Forest management; Process (computing); Landscape assessment; Environmental quality; Quality (philosophy); Work (physics); Impact assessment","score_opus":0.017861834090033998,"score_gpt":0.2668787412418348,"score_spread":0.2490169071518008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070759534","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78946877,0.00016589202,0.00002749163,0.000011292904,0.00010538254,0.00018100212,0.000010878152,0.000003555434,0.21002573],"genre_scores_gemma":[0.937472,0.000067681685,0.00020973648,0.0000011578284,0.0000145048825,0.0000033784518,0.0012949785,0.000014067832,0.060922485],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992114,0.00004338017,0.00019094055,0.000274671,0.00011422388,0.00016538384],"domain_scores_gemma":[0.9992089,0.000011329072,0.00022941342,0.00046339384,0.00002602436,0.00006093894],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00007104091,0.00020635086,0.00022232062,0.00021546576,0.0001322976,0.000016920883,0.0004248607,0.00021924169,0.000044216096],"category_scores_gemma":[0.0000073507103,0.00024535673,0.00006526702,0.00005106631,0.0001334289,0.000012174552,0.00019630838,0.00025175267,0.000002276172],"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":[0.00014459385,0.00029074642,0.98695815,0.00023625749,0.00011524891,0.00003397246,0.0025186923,0.000032768454,0.0012239781,0.0021924602,0.00062296796,0.0056301393],"study_design_scores_gemma":[0.0005224293,0.00008624762,0.6460789,0.00010338642,0.00003273709,0.0000034553868,0.0006225215,0.00003719245,0.000105570885,0.000008189255,0.35221517,0.00018423064],"about_ca_topic_score_codex":0.00059166463,"about_ca_topic_score_gemma":0.80588096,"teacher_disagreement_score":0.8052893,"about_ca_system_score_codex":0.00014142843,"about_ca_system_score_gemma":0.0001491853,"threshold_uncertainty_score":0.9999999},"labels":[],"label_agreement":null},{"id":"W7070760823","doi":"","title":"Psychometric Properties of the Alexithymia Questionnaire for Children in a Peruvian Sample of Adolescents","year":2016,"lang":"en","type":"article","venue":"Communities in DSpace (Pontifical Catholic University of Peru)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Alexithymia; Toronto Alexithymia Scale; Convergent validity; Psychometrics; Internal consistency; Depression (economics); Reliability (semiconductor)","score_opus":0.016196943477173428,"score_gpt":0.22925061765752672,"score_spread":0.2130536741803533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070760823","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99811476,0.00022901747,0.0008551401,0.0002932311,0.000044646644,0.00027605353,0.00008358681,0.0000039187694,0.00009965112],"genre_scores_gemma":[0.99867404,0.00015211012,0.00086862454,0.000016655906,0.000009436326,0.0000010817865,0.000015705966,0.000008001305,0.0002543578],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992667,0.00016888884,0.00020586731,0.00009155026,0.000121206926,0.00014581934],"domain_scores_gemma":[0.99913293,0.000034640674,0.00017262259,0.0005246692,0.00010950332,0.000025655709],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031338408,0.000100080695,0.00019804326,0.00017549575,0.000063857406,0.0000034339512,0.00062641816,0.00011889919,0.0000073488363],"category_scores_gemma":[0.00042400847,0.00007467148,0.00010203477,0.00021166244,0.0006337406,0.000009849364,0.00026932513,0.00012513541,3.71848e-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":[0.00033496073,0.00025557712,0.9526909,0.0004062449,0.000024444595,8.822715e-8,0.01173374,0.00008010728,0.030519389,0.0001371637,0.00010758636,0.0037098029],"study_design_scores_gemma":[0.0016705833,0.000205041,0.9773554,0.0013383643,0.000017668692,0.0000033864872,0.0040455186,0.00015968883,0.012705034,0.000030112782,0.0022961216,0.00017305787],"about_ca_topic_score_codex":0.001765852,"about_ca_topic_score_gemma":0.0030604044,"teacher_disagreement_score":0.024664527,"about_ca_system_score_codex":0.000033213666,"about_ca_system_score_gemma":0.00006109391,"threshold_uncertainty_score":0.30450147},"labels":[],"label_agreement":null},{"id":"W7070760947","doi":"","title":"Radical Reference Montreal. Part 1 of 2.","year":2010,"lang":"en","type":"other","venue":"eScholarship@McGill (McGill)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political radicalism; Work (physics); Economic Justice; Social justice; Group (periodic table)","score_opus":0.010367979803488827,"score_gpt":0.23545217093935458,"score_spread":0.22508419113586575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070760947","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":[0.023267364,0.00036638757,0.0000020380348,0.000012472384,0.0005988923,0.0003954385,0.0019050387,0.00013599535,0.9733164],"genre_scores_gemma":[0.14744551,0.001961633,0.012892751,0.0007289969,0.00057134446,0.000110744215,0.0028663806,0.0015463621,0.8318763],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99741584,0.00019436475,0.00068876287,0.00067893066,0.0004906254,0.0005314976],"domain_scores_gemma":[0.99742717,0.000040259,0.00074237224,0.0013817897,0.0001245271,0.00028391244],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00047866788,0.00059930916,0.00061654235,0.00019939504,0.00016645205,0.000022354192,0.00089273957,0.0017559611,0.0017712915],"category_scores_gemma":[0.00079034874,0.00058092223,0.0002470989,0.00015722757,0.00026527868,0.000009013503,0.00045654815,0.0014545191,0.00025520514],"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":[0.00046312506,0.0009834243,0.00042706367,0.0020139017,0.0016672722,0.000079020836,0.0000060677753,0.000041572966,0.38713124,0.049757436,0.055099305,0.50233054],"study_design_scores_gemma":[0.0005806314,0.00021146865,0.00008224082,0.00017204841,0.00007464447,0.00003487536,0.000004963999,0.00001417231,0.027681993,0.00037493833,0.9701703,0.0005976996],"about_ca_topic_score_codex":0.00046733304,"about_ca_topic_score_gemma":0.0013003362,"teacher_disagreement_score":0.915071,"about_ca_system_score_codex":0.000038668586,"about_ca_system_score_gemma":0.000056599718,"threshold_uncertainty_score":0.99966425},"labels":[],"label_agreement":null},{"id":"W7070768184","doi":"","title":"Portrait global de l'industrie du recyclage","year":2013,"lang":"fr","type":"article","venue":"NPARC","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"","score_opus":0.006053991401462771,"score_gpt":0.23370584640857486,"score_spread":0.2276518550071121,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070768184","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4183162,0.0011923024,0.005594497,0.017784793,0.0009415095,0.00038038005,0.0000907633,0.00004419602,0.55565536],"genre_scores_gemma":[0.942581,0.00043564246,0.025894774,0.0024700223,0.001190856,0.000029487774,0.00017920339,0.00003470469,0.027184326],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99850416,0.00011613329,0.0003464524,0.00025837644,0.00017195997,0.0006029261],"domain_scores_gemma":[0.9989985,0.000016925369,0.00015544573,0.0004428703,0.000110207824,0.0002760064],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002803834,0.0002480292,0.00018221626,0.000018510409,0.000103706625,0.000098639954,0.00033628708,0.00060834986,0.004565504],"category_scores_gemma":[0.00037621727,0.00026461706,0.00012621244,0.00012703415,0.00019057009,0.000012738966,0.00019783607,0.00033202447,0.0008384737],"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":[0.000026294625,0.00017742379,0.052725144,0.00015714506,0.00015723336,0.000028398594,0.00015374339,0.00018021595,0.044674575,0.013723615,0.70787036,0.18012585],"study_design_scores_gemma":[0.0006516364,0.0003414267,0.016581174,0.000059864655,0.000057220517,0.00034479387,0.00013125778,0.0052209087,0.00693907,0.004372563,0.96482545,0.00047464904],"about_ca_topic_score_codex":0.00018892708,"about_ca_topic_score_gemma":0.00002274265,"teacher_disagreement_score":0.52847105,"about_ca_system_score_codex":0.00009981647,"about_ca_system_score_gemma":0.00033612183,"threshold_uncertainty_score":0.9999806},"labels":[],"label_agreement":null},{"id":"W7070779822","doi":"","title":"Rimouski au temps d'Adèle Lamontagne, 1858-1875 : Partie 3: Commerce et société","year":2001,"lang":"fr","type":"article","venue":"Sémaphore (Université du Québec à Rimouski)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Government (linguistics); Power (physics); Focus (optics); Perspective (graphical); Subject (documents)","score_opus":0.00897630236534925,"score_gpt":0.22609578052691595,"score_spread":0.2171194781615667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070779822","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25619066,0.007851782,0.0021393092,0.012347606,0.00094037334,0.0005561778,0.00011101082,0.00016952604,0.71969354],"genre_scores_gemma":[0.9651931,0.0027092309,0.001184041,0.0026696196,0.0007728813,0.000012977704,0.0005064703,0.00014849483,0.026803216],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962141,0.00046110523,0.000642415,0.0008484275,0.000507199,0.0013267739],"domain_scores_gemma":[0.99717116,0.00018102942,0.00054936326,0.0012616729,0.00033029538,0.00050650246],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007473736,0.00079137896,0.00069324474,0.00022448781,0.00089645956,0.00015133037,0.0010799007,0.00090569735,0.0023025626],"category_scores_gemma":[0.00037650333,0.0009821687,0.0005857671,0.0005159915,0.00084758905,0.00009201699,0.00074637326,0.001003068,0.0010344436],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007300439,0.0013068207,0.083181046,0.0006198012,0.0011217996,0.0001553689,0.015212218,0.003298816,0.0030648366,0.65043503,0.20245521,0.038418997],"study_design_scores_gemma":[0.0021294982,0.00066995836,0.014876299,0.00010584469,0.00030825078,0.00044085624,0.005638189,0.0021284383,0.00056419586,0.000101197984,0.9719203,0.0011169399],"about_ca_topic_score_codex":0.04270439,"about_ca_topic_score_gemma":0.6644311,"teacher_disagreement_score":0.76946515,"about_ca_system_score_codex":0.00074250594,"about_ca_system_score_gemma":0.0023030965,"threshold_uncertainty_score":0.99974334},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W7070784485","doi":"","title":"âThe pipes play onâ: Canadian Pipers at War, 1914â1918: An Inspired Tradition","year":2012,"lang":"en","type":"article","venue":"Scholars Commons (Wilfrid Laurier University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Diafiltration; Liquation; Emperipolesis; Triacetin; Fusible alloy","score_opus":0.010486078571771248,"score_gpt":0.21154197206185799,"score_spread":0.20105589349008673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070784485","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94928694,0.00017146127,0.0001439324,0.0003299814,0.00029638587,0.00020519062,0.00018764002,0.000059314883,0.049319174],"genre_scores_gemma":[0.9937762,0.000048336376,0.0011992927,0.0005385639,0.00016326939,0.0000016617543,0.0009800169,0.0000369947,0.0032556546],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984539,0.0002449711,0.00018882364,0.0002867449,0.00020401318,0.00062156026],"domain_scores_gemma":[0.998338,0.000019264919,0.000116287425,0.000688008,0.0000778585,0.0007606002],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033549307,0.00026866427,0.00018578763,0.0003530551,0.0007356007,0.00004996799,0.0005812857,0.0003034999,0.00015191128],"category_scores_gemma":[0.00008573373,0.00030232372,0.00012674286,0.00032105634,0.00017113177,0.00011933258,0.00017604312,0.00042530728,0.00009719894],"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":[0.0007272469,0.00080006494,0.8481039,0.00012268663,0.00073484454,0.00014104026,0.0075318646,0.0011159446,0.0661633,0.014107466,0.05203676,0.0084149055],"study_design_scores_gemma":[0.00087815215,0.00022474615,0.03178594,0.00001817711,0.00007697975,0.00004827547,0.0008879493,0.00018880384,0.0071952855,0.000016951788,0.9581332,0.0005455253],"about_ca_topic_score_codex":0.0032652367,"about_ca_topic_score_gemma":0.03412409,"teacher_disagreement_score":0.90609646,"about_ca_system_score_codex":0.00027117968,"about_ca_system_score_gemma":0.00023635282,"threshold_uncertainty_score":0.9999429},"labels":[],"label_agreement":null},{"id":"W7070795235","doi":"","title":"Power-One Announces First Quarter 2012 Results | Stock Market Summary for Today | NSDQ, NYSE and AMEX Stock Market Summaries | Chron.com","year":2012,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Stock market; Stock (firearms); Stock exchange; Primary market","score_opus":0.00813373501084176,"score_gpt":0.24235964386436248,"score_spread":0.23422590885352074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070795235","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":[0.00012974003,0.00991751,0.002609159,0.0013631257,0.0008744927,0.0017356698,0.0037670252,0.00016556318,0.9794377],"genre_scores_gemma":[0.00073356944,0.0016971411,0.009923487,0.0005179736,0.0010885006,0.00014728538,0.0036457768,0.00039450586,0.98185176],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972531,0.0001479098,0.0007041725,0.0007152351,0.00034476258,0.00083477277],"domain_scores_gemma":[0.99773574,0.00017320181,0.0006241451,0.0010846455,0.000108719265,0.00027353675],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007723068,0.00078302604,0.00068797707,0.00019084795,0.00020367344,0.00014969325,0.000523341,0.0010876833,0.003505883],"category_scores_gemma":[0.0002803251,0.00068683835,0.00020372075,0.00009488351,0.0003288456,0.000025518253,0.00040607757,0.00036324735,0.00003570646],"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":[0.0007537997,0.00010540383,0.0012138401,0.0006989286,0.00038057816,0.000001127075,0.000090491456,0.0000011559432,0.00010592011,0.000036223413,0.9954132,0.0011993384],"study_design_scores_gemma":[0.0015996833,0.0007004441,0.0012313036,0.00019101496,0.000120570556,0.000016457941,0.00008382405,0.00027461167,0.00007476396,0.000014569808,0.99476373,0.00092903886],"about_ca_topic_score_codex":0.00015168799,"about_ca_topic_score_gemma":0.0010248851,"teacher_disagreement_score":0.008220368,"about_ca_system_score_codex":0.00003567837,"about_ca_system_score_gemma":0.00011870945,"threshold_uncertainty_score":0.99955827},"labels":[],"label_agreement":null},{"id":"W7070800774","doi":"","title":"Procedural Intervention for Benign Prostatic Hyperplasia in Men &ge; Age 70 Years &ndash; A Review of Published Literature","year":2023,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Modalities; Intervention (counseling); Health care; Medical literature; MEDLINE; Inclusion and exclusion criteria","score_opus":0.07372677178109903,"score_gpt":0.5067173673971553,"score_spread":0.4329905956160563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070800774","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9409122,0.050348688,0.000413547,0.0007338282,0.00041140747,0.0031687843,0.00022908115,0.00004149506,0.0037409542],"genre_scores_gemma":[0.9426704,0.0499662,0.0024064411,0.00078275363,0.00018203616,0.00038588935,0.0016197506,0.000100105026,0.0018864174],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9979302,0.00017292345,0.0009890174,0.00029152655,0.00033433313,0.00028197895],"domain_scores_gemma":[0.9983316,0.00006495385,0.0008324261,0.00037958796,0.00029846485,0.00009295575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018425698,0.00021228648,0.0005437937,0.0004405356,0.000049862974,0.0004216952,0.0012357533,0.00013858826,0.0003332279],"category_scores_gemma":[0.001838596,0.0001912134,0.00023247511,0.00094083144,0.000060229613,0.00016176325,0.00054146553,0.00027380942,0.0000034207803],"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":[0.0008797738,0.00056934595,0.12713796,0.037309676,0.00053977483,0.000058064856,0.001451294,0.00043160986,0.25681707,0.00020466765,0.5393067,0.03529407],"study_design_scores_gemma":[0.0068644607,0.00048149916,0.6819306,0.06170279,0.00036494245,0.00013808117,0.0005289475,0.0032281496,0.07719389,0.0056838426,0.15994895,0.001933838],"about_ca_topic_score_codex":0.00003676397,"about_ca_topic_score_gemma":0.000020961063,"teacher_disagreement_score":0.55479264,"about_ca_system_score_codex":0.000029571955,"about_ca_system_score_gemma":0.00010284774,"threshold_uncertainty_score":0.77974564},"labels":[],"label_agreement":null},{"id":"W7070806052","doi":"","title":"Preventing avoidable deaths in people who are homeless through evidence-based vaccination strategies","year":2021,"lang":"en","type":"article","venue":"Griffith Research Online (Griffith University, Queensland, Australia)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pandemic; Coronavirus disease 2019 (COVID-19); Vaccination; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Public health; Baseline (sea); Population; Epidemiology","score_opus":0.11079636719815657,"score_gpt":0.38701198370743595,"score_spread":0.2762156165092794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070806052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99400854,0.00042992705,0.001783561,0.0017505186,0.000113656664,0.000534672,0.00015143008,0.000049276405,0.0011784086],"genre_scores_gemma":[0.9803298,0.0011695654,0.0060166605,0.00008511977,0.00025285015,0.000006956719,0.00081701326,0.000042152315,0.011279874],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9959593,0.00096743664,0.00044602354,0.00075809483,0.0008796857,0.0009894947],"domain_scores_gemma":[0.9975262,0.00025313598,0.00025983757,0.0007447785,0.0010180305,0.00019798978],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011679969,0.00035214098,0.00053844857,0.00036674066,0.000397442,0.00023301908,0.0007329872,0.00044694068,0.00019709027],"category_scores_gemma":[0.00081990263,0.0003797613,0.00016509206,0.0013895589,0.0001337356,0.00014959401,0.0005647765,0.0011686971,0.000030400122],"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":[0.0011754056,0.0014232341,0.9298436,0.0023524673,0.00026002107,0.0007116314,0.0016335484,0.033472158,0.010873788,0.0026281765,0.01343975,0.0021862192],"study_design_scores_gemma":[0.0047149793,0.0007851269,0.9355641,0.0018732947,0.00007048868,0.00005291354,0.015672425,0.0052128886,0.010746171,0.00027593767,0.023951804,0.0010798774],"about_ca_topic_score_codex":0.0016518235,"about_ca_topic_score_gemma":0.024150182,"teacher_disagreement_score":0.028259272,"about_ca_system_score_codex":0.00023436542,"about_ca_system_score_gemma":0.0010525224,"threshold_uncertainty_score":0.9998654},"labels":[],"label_agreement":null},{"id":"W7070815035","doi":"","title":"Quality evaluation of essential oil from Nova Scotia grown mint","year":2000,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Essential oil; Nova scotia; Yield (engineering); Production (economics)","score_opus":0.00492412664375065,"score_gpt":0.19780494033007848,"score_spread":0.19288081368632784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070815035","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07733701,0.00074750744,0.000044756962,0.0002020232,0.00023047498,0.00010727233,0.0011451908,0.000004606401,0.92018116],"genre_scores_gemma":[0.8375943,0.0004420022,0.0031130877,0.00057325175,0.0003779283,0.0000047083813,0.0009351103,0.00015290988,0.15680675],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99759847,0.00013212464,0.00036531937,0.00022345976,0.001521225,0.00015943043],"domain_scores_gemma":[0.9991341,0.0000369481,0.00040256715,0.00032531936,8.8648136e-7,0.00010015415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000025690673,0.00020440647,0.00027093658,0.000020519614,0.00002606348,0.000008325632,0.00022046649,0.00009412283,0.0007413607],"category_scores_gemma":[0.000008391494,0.00020336421,0.000041402145,0.000029493473,0.00008820858,0.000007004485,0.00011588509,0.00010810674,8.737676e-9],"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":[0.0022261254,0.00027752135,0.07639784,0.0030545667,0.0022423086,0.000023532953,0.0002552275,0.0010813862,0.3476174,0.0050981767,0.36882883,0.19289708],"study_design_scores_gemma":[0.0020961978,0.00018914597,0.046885487,0.0006691532,0.00029070495,0.000005603025,0.00073446805,0.0028260846,0.33494362,0.0002445709,0.609973,0.0011419286],"about_ca_topic_score_codex":0.037264667,"about_ca_topic_score_gemma":0.21533923,"teacher_disagreement_score":0.7633744,"about_ca_system_score_codex":0.0000027425156,"about_ca_system_score_gemma":0.0015067246,"threshold_uncertainty_score":0.96914625},"labels":[],"label_agreement":null},{"id":"W7070818915","doi":"","title":"Proyecto de exportación: Ron blanco a Ontario Canadá","year":2013,"lang":"es","type":"other","venue":"DSpace (Universidad Veracruzana)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Term (time); Table (database)","score_opus":0.004118915006875816,"score_gpt":0.21279273261054787,"score_spread":0.20867381760367207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070818915","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":[0.21184044,0.0008577773,0.0030660345,0.0019640857,0.0009907358,0.001650928,0.00020185107,0.00013644181,0.7792917],"genre_scores_gemma":[0.08945538,0.00054018374,0.005287861,0.00065334525,0.00061835005,0.000031991927,0.0010262076,0.00036621085,0.90202045],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970417,0.00016533562,0.0003423093,0.0008605431,0.00047632185,0.0011137625],"domain_scores_gemma":[0.99720067,0.000029109398,0.00073250156,0.0013402833,0.00016036809,0.000537098],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00021667106,0.00087865564,0.00069553754,0.00035947087,0.00027862974,0.00019820877,0.0009442141,0.0013038695,0.008247607],"category_scores_gemma":[0.00012422772,0.0009941456,0.00034837273,0.00024670822,0.00022711472,0.000030579627,0.00045020005,0.0009747658,0.0011303956],"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":[0.00023604493,0.00025694066,0.04580099,0.0008004566,0.0016442513,0.00031321243,0.004041615,0.0009069568,0.0030408553,0.0016043677,0.93425655,0.0070977295],"study_design_scores_gemma":[0.0011680933,0.00050095463,0.0076438542,0.0002516846,0.00021963213,0.00005734931,0.0014683222,0.0020614255,0.00036728362,0.000011820623,0.9850539,0.0011956929],"about_ca_topic_score_codex":0.17317581,"about_ca_topic_score_gemma":0.35730645,"teacher_disagreement_score":0.18413062,"about_ca_system_score_codex":0.0008423302,"about_ca_system_score_gemma":0.0019668934,"threshold_uncertainty_score":0.99999267},"labels":[],"label_agreement":null},{"id":"W7070820871","doi":"","title":"Proposição de uma estrutura de indicadores para apoiar a gestão dos ativos intangíveis de capital intelectual em IFES","year":2018,"lang":"pt","type":"dissertation","venue":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Universidade Federal do Rio Grande do Sul; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Pró-Reitoria de Pesquisa, Universidade Federal do Rio Grande do Sul; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Canadian Imperial Bank of Commerce","keywords":"Context (archaeology); Capital (architecture); State of art","score_opus":0.012678300695861964,"score_gpt":0.2628333605546561,"score_spread":0.25015505985879416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070820871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9719876,0.0009857233,0.009665226,0.0021763765,0.001249156,0.0014618003,0.0002751584,0.0003061977,0.011892783],"genre_scores_gemma":[0.97380024,0.00053680525,0.015926357,0.0004392659,0.001939414,0.0005424733,0.005437264,0.00023547918,0.0011427077],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99238557,0.0010598018,0.0017471674,0.0015172523,0.0012130634,0.002077136],"domain_scores_gemma":[0.9947029,0.00025743968,0.0016506889,0.0012331969,0.00104505,0.0011107347],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.0013822754,0.001501004,0.0010957271,0.0007454525,0.0013375886,0.00075105426,0.0018009846,0.003156308,0.00011287706],"category_scores_gemma":[0.0033079982,0.0015251499,0.0006631462,0.00075684744,0.000136929,0.0001214273,0.0005642626,0.00245604,0.000056607467],"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":[0.010984542,0.006588453,0.025988517,0.00798044,0.008398287,0.0017696641,0.20637482,0.00092786446,0.2938042,0.3609264,0.016158385,0.06009842],"study_design_scores_gemma":[0.0052629374,0.0027354374,0.02548273,0.0019377001,0.0013270507,0.012371808,0.01663119,0.01542609,0.1444682,0.00059558527,0.7684158,0.0053454777],"about_ca_topic_score_codex":0.000019000232,"about_ca_topic_score_gemma":0.0006464985,"teacher_disagreement_score":0.7522574,"about_ca_system_score_codex":0.001685645,"about_ca_system_score_gemma":0.0042906743,"threshold_uncertainty_score":0.9999625},"labels":[],"label_agreement":null},{"id":"W7070826512","doi":"","title":"RBC bullfrogpowers(R) the 2013 RBC Canadian Open","year":2013,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.006007647367295461,"score_gpt":0.24428528309883013,"score_spread":0.23827763573153468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070826512","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":[0.000026989499,0.00063805515,0.00021169512,0.0024219756,0.00038721846,0.0007789303,0.000062011386,0.000031577314,0.99544156],"genre_scores_gemma":[0.00032613412,0.00045416184,0.0026423235,0.0038256033,0.00045530635,0.00005701428,0.0005634834,0.0002887888,0.9913872],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99893993,0.000055309316,0.00020056638,0.00028203585,0.0001298719,0.0003922617],"domain_scores_gemma":[0.9985663,0.000007710828,0.00016146582,0.001013687,0.00003777999,0.00021300773],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00016863024,0.00029785145,0.00020312685,0.00008160188,0.00010200983,0.00020643923,0.0015267198,0.0005047189,0.021004789],"category_scores_gemma":[0.00004793671,0.00019428098,0.000080058184,0.000059508835,0.00009911281,0.0000022492984,0.00048074283,0.00026527353,0.0032136429],"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":[0.0000016355204,0.0000054170514,0.000113441725,0.000015774542,0.00008505704,9.208148e-7,0.000017090892,0.0000051928387,0.000045382236,0.0005491625,0.99828523,0.0008756776],"study_design_scores_gemma":[0.00015427028,0.000053863994,0.000043365035,0.00002310352,0.000016565873,0.000011046928,0.000050052273,0.00013861062,0.00007234502,0.000011370735,0.9991235,0.00030188507],"about_ca_topic_score_codex":0.38701737,"about_ca_topic_score_gemma":0.36648867,"teacher_disagreement_score":0.020528687,"about_ca_system_score_codex":0.00002285029,"about_ca_system_score_gemma":0.0003017319,"threshold_uncertainty_score":0.99756247},"labels":[],"label_agreement":null},{"id":"W7070849165","doi":"","title":"The 2013 road atlas : United States, Canada, and Mexico","year":2013,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Atlas (anatomy); Feature (linguistics); Geographic information system","score_opus":0.0025032587972816443,"score_gpt":0.17052628543801554,"score_spread":0.1680230266407339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070849165","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":[0.00042632304,0.0008445142,9.4891874e-7,0.00050626363,0.00018121499,0.0003347953,0.00014014477,0.000030229323,0.9975356],"genre_scores_gemma":[0.00021639044,0.0029032235,0.00040955737,0.0006078829,0.00008544451,0.000014376452,0.001281905,0.00008346924,0.99439776],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99876195,0.000069643276,0.00046676092,0.0001397683,0.00028149472,0.0002803782],"domain_scores_gemma":[0.99877834,0.000045705132,0.0005067202,0.00042030905,0.00013358115,0.00011531803],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00016096466,0.0002894588,0.00021798915,0.000034010696,0.00011020077,0.00006787342,0.00032089968,0.00030913568,0.025775341],"category_scores_gemma":[0.000114442046,0.00022313037,0.000055163924,0.000006567337,0.00015835009,2.1710706e-8,0.00016588658,0.00023091359,0.00081203063],"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":[0.000023168532,0.0000057902594,0.000009225905,0.00014469682,0.00007693473,0.0000013069887,0.000028685843,0.000485275,5.7210053e-7,0.000010609116,0.99772555,0.0014882032],"study_design_scores_gemma":[0.00026057754,0.00009921672,0.000023209159,0.000053489006,0.000022719822,0.00003697083,0.00008302669,0.00050203985,0.0000147696055,0.0000015466064,0.99864215,0.000260276],"about_ca_topic_score_codex":0.7244447,"about_ca_topic_score_gemma":0.5811826,"teacher_disagreement_score":0.1432621,"about_ca_system_score_codex":0.000022540687,"about_ca_system_score_gemma":0.00008207783,"threshold_uncertainty_score":0.99996597},"labels":[],"label_agreement":null},{"id":"W7070878235","doi":"","title":"Polarized neutron reflectometry as a unique tool in magnetization reversal studies of thin films and multilayers","year":2006,"lang":"en","type":"article","venue":"NPARC","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Neutron reflectometry; Thin film; Magnetization reversal; Reflectometry; Magnetization; Magnetometer; Neutron","score_opus":0.008077586304784265,"score_gpt":0.2846553578797473,"score_spread":0.276577771574963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070878235","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9957905,0.00026367602,0.00022358319,0.00013925285,0.000034400866,0.00014339766,0.0000052301302,0.000009468605,0.0033905362],"genre_scores_gemma":[0.9750144,0.00015414906,0.023997387,0.0001223385,0.000020025858,0.0000058654477,0.000050279716,0.000009721923,0.00062582793],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99937254,0.00006131135,0.00022946123,0.00012849276,0.00008841368,0.00011976024],"domain_scores_gemma":[0.9996641,0.000024213115,0.000099231,0.0001468055,0.000052406467,0.000013238415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021919781,0.000093348615,0.00013345678,0.000078894496,0.00002542954,0.00000838428,0.00006900365,0.000106121566,0.000019147383],"category_scores_gemma":[0.00026541427,0.00008796121,0.000024408671,0.00011970595,0.0000671095,0.000005166632,0.000076143544,0.00009722383,0.0000014087856],"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":[0.000091723916,0.000027216307,0.016856043,0.00007873846,0.000015272293,0.0000011775289,0.00019520783,0.0003554165,0.9808497,0.00042376356,0.0008068374,0.00029890332],"study_design_scores_gemma":[0.008970313,0.002769384,0.18194999,0.00029495003,0.000108187334,0.00007216215,0.0018375914,0.043471668,0.74231076,0.004252428,0.01266613,0.001296413],"about_ca_topic_score_codex":0.000081707825,"about_ca_topic_score_gemma":0.000059567123,"teacher_disagreement_score":0.23853892,"about_ca_system_score_codex":0.000010758722,"about_ca_system_score_gemma":0.000028829423,"threshold_uncertainty_score":0.35869542},"labels":[],"label_agreement":null},{"id":"W7070888265","doi":"","title":"A promoção da saúde na Constituição Federal de 1988","year":2021,"lang":"pt","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Context (archaeology); Perspective (graphical); Order (exchange); Liability; Qualitative research; State (computer science); Exploratory research","score_opus":0.14374694389164408,"score_gpt":0.5252246957517063,"score_spread":0.38147775186006216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070888265","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9038426,0.04759812,0.006476144,0.00080561097,0.0018806254,0.001004773,0.0003195381,0.00004976241,0.038022794],"genre_scores_gemma":[0.9800126,0.010302462,0.0025084591,0.0016055928,0.0005129786,0.00004076055,0.00027666823,0.000115264185,0.0046251975],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9951415,0.0007630415,0.0015590423,0.0007786669,0.0007974976,0.0009602357],"domain_scores_gemma":[0.9957927,0.00016821644,0.0015009391,0.0011551105,0.0007593785,0.0006236621],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016449373,0.0007064952,0.001128517,0.00036096666,0.0005892182,0.0027742714,0.0031083738,0.00057117717,0.008778558],"category_scores_gemma":[0.0017752964,0.0007287653,0.0004934461,0.00077741285,0.00039754104,0.00019769448,0.003041808,0.0011302667,0.000050414823],"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":[0.00041719482,0.00073702127,0.41335422,0.00090012746,0.0010666256,0.00035300135,0.0006407343,0.00081208034,0.4862866,0.00018667986,0.07752059,0.017725142],"study_design_scores_gemma":[0.0036649215,0.00016121853,0.17064758,0.0019369329,0.00059937825,0.001334532,0.00064757327,0.0036805037,0.49844858,0.0012452143,0.31489718,0.0027363761],"about_ca_topic_score_codex":0.00041865662,"about_ca_topic_score_gemma":0.000120315824,"teacher_disagreement_score":0.24270663,"about_ca_system_score_codex":0.00014989897,"about_ca_system_score_gemma":0.0018098338,"threshold_uncertainty_score":0.99951637},"labels":[],"label_agreement":null},{"id":"W7070898764","doi":"","title":"Relatório de Consultadoria Técnico-Científico INNEA-Alternativas Biotecnológicas Valladolid, Espanha","year":2018,"lang":"pt","type":"report","venue":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Practicum; Olive trees; Christian ministry","score_opus":0.0576450999795977,"score_gpt":0.3980073735416292,"score_spread":0.34036227356203147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070898764","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.736872,0.042632565,0.010175287,0.006591955,0.0071801185,0.016481822,0.0059820656,0.0010753549,0.17300878],"genre_scores_gemma":[0.86358726,0.02654889,0.012157581,0.00016554364,0.0019017416,0.0013497322,0.0030648683,0.0002746359,0.09094975],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98786956,0.0002818559,0.0017292378,0.0026562803,0.004281414,0.003181655],"domain_scores_gemma":[0.9876844,0.00055874663,0.0012549823,0.0013127371,0.008552006,0.0006370727],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["sts","research_integrity"],"category_scores_codex":[0.019093595,0.0009842124,0.00093783595,0.0056912377,0.003008752,0.0005791776,0.003229979,0.0025609212,0.00008664701],"category_scores_gemma":[0.030663092,0.0009334292,0.00028846937,0.0061802836,0.0083133895,0.0001178892,0.0025712834,0.0028230331,0.00007487688],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019196956,0.0031239057,0.04562017,0.0042477283,0.0027570336,0.00022679345,0.0024887677,0.000033807304,0.3018132,0.05010949,0.42077896,0.16688046],"study_design_scores_gemma":[0.0033231694,0.007977028,0.0013235726,0.0009500724,0.00016907702,0.0018352764,0.0009711204,0.010042434,0.059363622,0.010048802,0.9013897,0.0026061186],"about_ca_topic_score_codex":0.00015813623,"about_ca_topic_score_gemma":0.00004140334,"teacher_disagreement_score":0.48061076,"about_ca_system_score_codex":0.0013651553,"about_ca_system_score_gemma":0.015188832,"threshold_uncertainty_score":0.9994775},"labels":[],"label_agreement":null},{"id":"W7070914475","doi":"","title":"Quantifying the economic impact of CETA on Portugal","year":2017,"lang":"en","type":"dissertation","venue":"Repositório do ISCTE-IUL","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Economic impact analysis; Wine; Revenue; European union; Production (economics); Productivity; Portuguese; Value (mathematics); Agriculture","score_opus":0.01593299632048955,"score_gpt":0.3398157778595066,"score_spread":0.32388278153901706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070914475","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8975826,0.0005401674,0.000012122031,0.000041415697,0.00070640515,0.00031838837,0.000057341218,0.000015717835,0.10072584],"genre_scores_gemma":[0.9846933,0.00027011576,0.00013197544,0.000053559175,0.00036177094,0.000015747375,0.0018910061,0.00007063857,0.0125118755],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99837255,0.000072488016,0.00060997315,0.00039150784,0.00019510722,0.00035839612],"domain_scores_gemma":[0.99685264,0.000033475924,0.0013402738,0.001530802,0.00010073542,0.00014209455],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044003248,0.00039503726,0.00042853944,0.00008441065,0.00027284914,0.00015453636,0.0007225317,0.00049907726,0.00008658974],"category_scores_gemma":[0.0005351674,0.00027979453,0.0005384326,0.000026951857,0.00007006316,0.0000076881815,0.000074898824,0.00044523575,0.000056183184],"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":[0.005489491,0.0005179002,0.127448,0.0034301088,0.009311852,0.00014233531,0.007000479,0.03371045,0.58500504,0.0048070927,0.15575738,0.0673799],"study_design_scores_gemma":[0.0037705142,0.0064721014,0.33901808,0.002278826,0.0015498154,0.0007531935,0.0014762583,0.009956362,0.4814706,0.00024905478,0.14806071,0.0049444865],"about_ca_topic_score_codex":0.000484678,"about_ca_topic_score_gemma":0.00028371092,"teacher_disagreement_score":0.21157007,"about_ca_system_score_codex":0.00014207151,"about_ca_system_score_gemma":0.0011896852,"threshold_uncertainty_score":0.9999654},"labels":[],"label_agreement":null},{"id":"W7070920601","doi":"","title":"The relationship between home visiting and parental behaviour in a community based prevention research project","year":2001,"lang":"en","type":"dissertation","venue":"The Atrium (University of Guelph)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scale (ratio); Multivariate analysis of variance; Sample (material); Child rearing; Descriptive research; Research design; Descriptive statistics","score_opus":0.05129594166877181,"score_gpt":0.34129206495144404,"score_spread":0.2899961232826722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070920601","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9980428,0.00016761558,0.000050569637,0.000167985,0.000033385524,0.0003676121,0.00002199428,0.000006884983,0.001141134],"genre_scores_gemma":[0.9941648,0.00006576993,0.00018731866,0.0000035015662,0.00004001473,0.000001127505,0.0018851664,0.000011514013,0.0036407565],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983519,0.0009635752,0.00016177156,0.00011887961,0.0002247073,0.00017919278],"domain_scores_gemma":[0.9989567,0.0003002601,0.00023086325,0.00037256547,0.00011492306,0.000024684097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020484452,0.00010827004,0.0001319312,0.0001331195,0.00090730225,0.000027252088,0.00046696758,0.00022713337,0.0000018883134],"category_scores_gemma":[0.00026481747,0.0000953255,0.00007431828,0.00024778448,0.00010917933,0.00000874332,0.00016250281,0.000899239,0.0000021029475],"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":[0.00046155744,0.000074657386,0.9878825,0.00035894028,0.000056647983,0.0000025006227,0.0043766717,0.000024791769,0.0034574734,0.00012708588,0.00089307973,0.0022841266],"study_design_scores_gemma":[0.00042030736,0.00020408639,0.9615571,0.000108458684,0.00004819973,0.0000018966833,0.03671285,0.00013290592,0.000065744985,0.0002104303,0.00043314457,0.00010488096],"about_ca_topic_score_codex":0.0014449016,"about_ca_topic_score_gemma":0.0036759477,"teacher_disagreement_score":0.03233618,"about_ca_system_score_codex":0.000035336776,"about_ca_system_score_gemma":0.00017271755,"threshold_uncertainty_score":0.6978327},"labels":[],"label_agreement":null},{"id":"W7070921832","doi":"","title":"Race, Class, Gender and the Making of Difference: The Social Organization of\\n \"Migrant Workers\" in Canada","year":2000,"lang":"en","type":"article","venue":"Journals @ The Mount (Mount Saint Vincent University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Diafiltration; Liquation; Triacetin; Emperipolesis; Demotion","score_opus":0.006531888209434547,"score_gpt":0.20890808314728376,"score_spread":0.20237619493784922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070921832","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99689335,0.00032486118,0.00037458094,0.0017668479,0.000051191982,0.00018232319,0.000011273223,0.0000022224674,0.00039334828],"genre_scores_gemma":[0.99895304,0.00045904607,0.00003641644,0.00033514813,0.000049799408,2.7199118e-7,0.000007105341,0.000008074336,0.00015109094],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989041,0.0002753356,0.00028580628,0.00010375861,0.00025614805,0.00017484147],"domain_scores_gemma":[0.99928164,0.000061351835,0.0003266675,0.00020672767,0.00010459448,0.00001902533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000474482,0.00012026644,0.00018335218,0.00004945112,0.0002804827,0.000024509953,0.00041879533,0.00006824135,0.000072856004],"category_scores_gemma":[0.0000690964,0.00006721432,0.000056023622,0.00030712297,0.00021109024,0.000007799865,0.00013764945,0.0002603595,5.5158995e-7],"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":[0.0023241935,0.00023543596,0.8213541,0.00026665753,0.0010343727,0.0000433452,0.019037532,0.04035894,0.019022234,0.07313801,0.0029377863,0.020247413],"study_design_scores_gemma":[0.0031627847,0.000066208864,0.7049151,0.00016209859,0.00019135597,0.00006812424,0.017050197,0.008779656,0.0009814802,0.00012997011,0.26411444,0.0003786019],"about_ca_topic_score_codex":0.0876142,"about_ca_topic_score_gemma":0.060949765,"teacher_disagreement_score":0.26117665,"about_ca_system_score_codex":0.0010186206,"about_ca_system_score_gemma":0.00036506917,"threshold_uncertainty_score":0.95618546},"labels":[],"label_agreement":null},{"id":"W7070942963","doi":"","title":"Saloom, recuperación de espacio público para la integración interdistrital","year":2022,"lang":"es","type":"dissertation","venue":"Communities in DSpace (Pontifical Catholic University of Peru)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mexico city; Quarter (Canadian coin); Urban landscape; Urban space","score_opus":0.011933101609909626,"score_gpt":0.27509927271126267,"score_spread":0.26316617110135304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070942963","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97911495,0.0009179825,0.00040995446,0.00042888595,0.00032488338,0.0003448323,0.0005533412,0.00003945798,0.017865693],"genre_scores_gemma":[0.9772883,0.002527019,0.0022045046,0.00006182113,0.000060252383,0.0000051150746,0.008530285,0.00006671781,0.009255965],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963404,0.0017008098,0.0005510584,0.00040600737,0.0004134128,0.00058832613],"domain_scores_gemma":[0.9972801,0.00036936277,0.00054331165,0.0013791007,0.00024181136,0.00018631852],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0011909511,0.0005869742,0.00078305276,0.0005202879,0.00058225234,0.00010778107,0.001970936,0.0009394893,0.0007298217],"category_scores_gemma":[0.00050250534,0.000762347,0.00046611202,0.00037504418,0.0010656958,0.000035973837,0.0012827993,0.0026113074,0.00001855465],"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":[0.005879479,0.0031742987,0.051110584,0.005105545,0.0011187359,0.00043850968,0.8565122,0.002132911,0.023801135,0.00457956,0.008219681,0.03792739],"study_design_scores_gemma":[0.0015721011,0.0006719567,0.013975255,0.00059526315,0.00021372872,0.00011635235,0.39180005,0.0022789997,0.0009878123,0.000033654374,0.58664906,0.0011057842],"about_ca_topic_score_codex":0.005983992,"about_ca_topic_score_gemma":0.0070259664,"teacher_disagreement_score":0.57842934,"about_ca_system_score_codex":0.0003444572,"about_ca_system_score_gemma":0.0004987449,"threshold_uncertainty_score":0.9996897},"labels":[],"label_agreement":null},{"id":"W7070945325","doi":"","title":"/R E P E A T -- Advisory - Second Quarter 2020 Results Conference Call and Webcast/ - TSX (TSXTSX01) News","year":2020,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Advisory committee; Subject (documents)","score_opus":0.007532447554372386,"score_gpt":0.23404774798689404,"score_spread":0.22651530043252166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070945325","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":[0.00029691844,0.00058459275,0.0011787633,0.0013326143,0.00019579381,0.00035200876,0.00034638555,0.000095372896,0.99561757],"genre_scores_gemma":[0.0047939545,0.00067134673,0.007596346,0.0037346925,0.00081675913,0.000017997983,0.0012662641,0.00028432132,0.98081833],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99854773,0.00007087513,0.00039086706,0.0005464469,0.00015772387,0.00028635768],"domain_scores_gemma":[0.9989308,0.000019464227,0.00027909124,0.00053504953,0.000029732657,0.00020583834],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000088982924,0.00040763238,0.00035999808,0.000056172692,0.000036094785,0.000071432616,0.00029207655,0.00058994826,0.0029729013],"category_scores_gemma":[0.00014172941,0.00036030318,0.000087252236,0.000055228764,0.00011846973,0.0000028142153,0.00026017116,0.00036389747,0.00024207712],"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":[0.00006816254,0.000014538662,0.00014032176,0.00018826962,0.00008935409,0.000008090889,0.00011231886,7.590745e-7,0.0011320548,0.000054257383,0.9969607,0.0012311626],"study_design_scores_gemma":[0.00085325853,0.0003441663,0.000106258725,0.000054710235,0.000025448804,0.000025044525,0.00007703515,0.0003703191,0.00028541996,0.000010078229,0.9973914,0.00045685284],"about_ca_topic_score_codex":0.000120443954,"about_ca_topic_score_gemma":0.0010535629,"teacher_disagreement_score":0.014799233,"about_ca_system_score_codex":0.0000061136393,"about_ca_system_score_gemma":0.00010430805,"threshold_uncertainty_score":0.9998849},"labels":[],"label_agreement":null},{"id":"W7070945656","doi":"","title":"Quand tombe la neige à Bamako","year":2021,"lang":"fr","type":"book-chapter","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Identity (music); Period (music); Middle Ages; Photography","score_opus":0.007306229682642095,"score_gpt":0.176736318919746,"score_spread":0.1694300892371039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070945656","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":[0.043874294,0.034042746,0.0018973325,0.0007407562,0.0011066251,0.00032349577,0.00019340226,0.00006274617,0.9177586],"genre_scores_gemma":[0.27636725,0.0039224233,0.004327599,0.0004434074,0.0005311041,0.000008489571,0.0010220993,0.00008233193,0.7132953],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975548,0.000161554,0.0005297919,0.0007025575,0.00054618926,0.0005051401],"domain_scores_gemma":[0.99792767,0.000096690055,0.0004748653,0.00078302727,0.0003050838,0.00041266464],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0002601377,0.00064979476,0.0004992262,0.0001492115,0.003251392,0.000098293734,0.0005096029,0.0012074834,0.00035092738],"category_scores_gemma":[0.00012326353,0.00078479946,0.00054866046,0.000080601465,0.0007691348,0.00003059699,0.0008145557,0.0007707824,0.00014993898],"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":[0.00080198183,0.000313173,0.010527004,0.00068311807,0.0020526466,0.006488764,0.004552012,0.005066578,0.044792794,0.90386903,0.0043803,0.01647261],"study_design_scores_gemma":[0.0009939836,0.00020588802,0.0023866983,0.00030134467,0.00032134049,0.0037148881,0.001153135,0.0012986185,0.006241409,0.00018738666,0.98234487,0.00085043896],"about_ca_topic_score_codex":0.0029683078,"about_ca_topic_score_gemma":0.0012658548,"teacher_disagreement_score":0.9779646,"about_ca_system_score_codex":0.0016467675,"about_ca_system_score_gemma":0.0016829363,"threshold_uncertainty_score":0.9994603},"labels":[],"label_agreement":null},{"id":"W7070955053","doi":"","title":"Piecing the puzzle : real exchange rates and long-run fundamentals","year":2024,"lang":"en","type":"article","venue":"The central bank of Norways Open Archive","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Purchasing power parity; Exchange rate; Depreciation (economics); Interest rate parity; Bayesian probability; Monetary policy; Productivity; Purchasing power; Real interest rate","score_opus":0.013571343609695165,"score_gpt":0.2890028394107997,"score_spread":0.27543149580110454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070955053","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9676488,0.0018235905,0.0011407139,0.0019934864,0.0002512495,0.0008042315,0.00014062278,0.000016411605,0.026180916],"genre_scores_gemma":[0.99607205,0.0014475645,0.0006069654,0.00024818204,0.00016772278,0.000018560375,0.0001221257,0.00001979654,0.0012970582],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991076,0.00011830023,0.00020585704,0.00018267616,0.000113827744,0.00027171045],"domain_scores_gemma":[0.9994154,0.00010715891,0.00007477136,0.00033186682,0.000015142602,0.0000556701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039021723,0.00013794836,0.00012964608,0.000020380217,0.00019842983,0.00016821611,0.0006018624,0.00003754569,0.000092726026],"category_scores_gemma":[0.00004779184,0.00007753672,0.000060539613,0.000065110384,0.000248362,0.000012187985,0.0008072786,0.00016305802,0.000016044365],"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":[0.0014990824,0.0003389263,0.08933231,0.002025393,0.0019653004,0.00005854854,0.056370243,0.0012136993,0.5321577,0.027136978,0.095034495,0.19286731],"study_design_scores_gemma":[0.0028111,0.001998974,0.35644498,0.0009535805,0.00045571302,0.0003833609,0.0050819283,0.021565888,0.18825307,0.00562103,0.4148779,0.0015524749],"about_ca_topic_score_codex":0.00021858091,"about_ca_topic_score_gemma":0.00019514811,"teacher_disagreement_score":0.34390464,"about_ca_system_score_codex":0.000009426023,"about_ca_system_score_gemma":0.000043479784,"threshold_uncertainty_score":0.3161856},"labels":[],"label_agreement":null},{"id":"W7070959602","doi":"","title":"Review of <i>Saskatchewan: Uncommon Views</i> Photographsby John Conway","year":2007,"lang":"en","type":"article","venue":"Lincoln (University of Nebraska)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Solitude; Lament; Proposition; Tranquillity; Wishful thinking; The Thing; Statement (logic); Space (punctuation)","score_opus":0.007688419986342857,"score_gpt":0.23447776925340794,"score_spread":0.22678934926706507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070959602","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7980937,0.04588905,0.04230776,0.0013374081,0.0005466807,0.00189823,0.00022590357,0.00010290265,0.1095984],"genre_scores_gemma":[0.94426286,0.017079087,0.03196312,0.0026342794,0.0001309621,7.855421e-7,0.00041814704,0.000038906186,0.0034718437],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990616,0.00005523314,0.00029271515,0.00018934425,0.00019811228,0.0002030182],"domain_scores_gemma":[0.9988349,0.00003569638,0.00040555547,0.0004480824,0.00017721186,0.000098529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006393688,0.00014482762,0.00032284492,0.00009432655,0.00007105128,0.0000030097208,0.00040790264,0.0001622836,0.00013645197],"category_scores_gemma":[0.000058885744,0.00016723775,0.00023020043,0.00030029812,0.00019384375,0.000008510885,0.0002032049,0.00014689095,0.000012070134],"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":[0.0014699526,0.0014072128,0.06359668,0.036130488,0.001206049,0.00007223198,0.005707176,0.00022391039,0.54000926,0.00071280944,0.19846016,0.15100409],"study_design_scores_gemma":[0.0012992782,0.00061616936,0.004458926,0.0018634107,0.00012647995,0.0000228112,0.00236092,0.000112155925,0.036445625,0.0000372319,0.95224947,0.00040752304],"about_ca_topic_score_codex":0.0002013794,"about_ca_topic_score_gemma":0.0006059997,"teacher_disagreement_score":0.7537893,"about_ca_system_score_codex":0.000012375964,"about_ca_system_score_gemma":0.00009119179,"threshold_uncertainty_score":0.6819757},"labels":[],"label_agreement":null},{"id":"W7070964189","doi":"","title":"REACTIVE TRANSPORT OF IRON AND HYDROCHAR COLLOIDS IN A HYDROCARBON-CONTAMINATED SUBSURFACE ENVIRONMENT","year":2024,"lang":"en","type":"dissertation","venue":"University Library (University of Saskatchewan)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bioavailability; Biogeochemical cycle; Anoxic waters; Biostimulation; Hydrothermal carbonization; Bioremediation; Biodegradation","score_opus":0.0021327740275253154,"score_gpt":0.15670477358720858,"score_spread":0.15457199955968326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070964189","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99192077,0.00030890267,0.00004389477,0.000057088822,0.00005508487,0.00025851998,0.00018583462,0.000021129083,0.0071487776],"genre_scores_gemma":[0.9628386,0.00046821777,0.0009590835,0.000007397087,0.000009263416,6.088279e-8,0.0020416551,0.000026578096,0.033649184],"study_design_codex":"bench_or_experimental","study_design_gemma":"qualitative","domain_scores_codex":[0.9990501,0.000057006564,0.00017270046,0.00037327674,0.00017354454,0.00017338703],"domain_scores_gemma":[0.99936396,0.000016776508,0.00026414572,0.00025452045,0.000018112978,0.00008247948],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00007210992,0.00024802613,0.00038008846,0.00028471954,0.00005417743,0.000004437004,0.00032466248,0.00047541136,0.000079448066],"category_scores_gemma":[0.0000030329281,0.0003469524,0.00013899615,0.00019726141,0.00016760007,0.00005118637,0.00013239849,0.00032470428,0.00000496154],"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":[0.012133492,0.0012207389,0.14501405,0.010744076,0.0019751787,0.0010441804,0.405108,0.0021954263,0.41485983,0.0003311467,0.0013102109,0.00406366],"study_design_scores_gemma":[0.005754969,0.0018094842,0.10397043,0.0013006008,0.001211604,0.000020901052,0.76511407,0.0025250716,0.089241564,0.0001691089,0.026782015,0.0021002071],"about_ca_topic_score_codex":0.001033369,"about_ca_topic_score_gemma":0.0016863672,"teacher_disagreement_score":0.36000603,"about_ca_system_score_codex":0.000041398445,"about_ca_system_score_gemma":0.0002319933,"threshold_uncertainty_score":0.99989825},"labels":[],"label_agreement":null},{"id":"W7070976428","doi":"","title":"Reinforcement Learning-based User-centric Handover Decision-making in 5G Vehicular Networks","year":2023,"lang":"en","type":"other","venue":"Brock University Digital Repository (Brock University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"Brock University","keywords":"Transmission (telecommunications); Stability (learning theory); Filter (signal processing); Handover; Frame (networking); Gestational period","score_opus":0.0041453641211837275,"score_gpt":0.191818175034962,"score_spread":0.1876728109137783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070976428","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":[0.014924637,0.0005637161,0.16446267,0.0000058923656,0.0017631497,0.0018278388,0.00009849702,0.0016865124,0.8146671],"genre_scores_gemma":[0.054827776,0.0002030019,0.00019970705,0.00003652437,0.00017976294,3.6169726e-7,0.00021222603,0.00033337245,0.9440073],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978793,0.00010875967,0.00030658863,0.00070082454,0.0004305919,0.00057393813],"domain_scores_gemma":[0.99848306,0.000107148175,0.0004933525,0.0006047335,0.00010701657,0.00020466976],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000007878868,0.00052658323,0.0004329856,0.0010062647,0.00024137531,0.00012682342,0.0008157055,0.0008225761,0.000024310402],"category_scores_gemma":[0.00017151501,0.0006662882,0.00034390876,0.0007876563,0.00011094433,0.00005447619,0.0006264095,0.000615696,0.000071888986],"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":[0.0006621427,0.00013070992,0.043963797,0.00013686865,0.00029640662,0.00050826004,0.000008375612,0.49890324,0.0002569277,0.000015787085,0.45389527,0.0012222056],"study_design_scores_gemma":[0.0018204268,0.0002585081,0.0011587722,0.0006438885,0.000098012424,0.000020065028,0.00052716874,0.0023986478,0.00003916386,0.00000124738,0.99223566,0.0007984578],"about_ca_topic_score_codex":0.0001237669,"about_ca_topic_score_gemma":0.0009832922,"teacher_disagreement_score":0.5383404,"about_ca_system_score_codex":0.0004111321,"about_ca_system_score_gemma":0.00022132102,"threshold_uncertainty_score":0.99957883},"labels":[],"label_agreement":null},{"id":"W7070990072","doi":"","title":"Putin's Ukraine Invasion Is About Energy and Natural Resources","year":2022,"lang":"en","type":"other","venue":"Internet Archive (Internet Archive)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Natural resource; Energy resources; Knight; Natural (archaeology); Energy (signal processing); Work (physics); Government (linguistics); Energy policy","score_opus":0.004877813914221,"score_gpt":0.22198603449785748,"score_spread":0.21710822058363646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070990072","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":[0.01024423,0.0040748115,0.0025568116,0.00019719712,0.00078391976,0.000446347,0.00082079927,0.00018002928,0.98069584],"genre_scores_gemma":[0.02535704,0.0011520684,0.0025852781,0.0017529343,0.0008028873,0.000059210077,0.0038033675,0.00050367345,0.96398354],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99718463,0.00026261812,0.0005654318,0.0009895789,0.00040953408,0.00058821787],"domain_scores_gemma":[0.998293,0.00008513911,0.00054669485,0.0008239374,0.000025054365,0.00022617447],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017274712,0.00073922216,0.0005518278,0.00044780184,0.00006476106,0.00012715564,0.0011203509,0.00024107214,0.007930214],"category_scores_gemma":[0.00011581899,0.00068974786,0.00027613292,0.000077738754,0.0004953859,0.000006240937,0.0028931368,0.0007641166,0.000095895106],"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":[0.00025508358,0.000066276065,0.00132625,0.00015572389,0.0003994377,0.000034310244,0.0015088689,0.0000034000204,0.0015223029,0.0006380118,0.9927352,0.0013551123],"study_design_scores_gemma":[0.0007055185,0.0007616272,0.00037874404,0.00027056196,0.00004772918,0.0001727021,0.00006804552,0.0018070647,0.00089023216,0.00020071595,0.9939798,0.0007172319],"about_ca_topic_score_codex":0.004541848,"about_ca_topic_score_gemma":0.0050497996,"teacher_disagreement_score":0.016712314,"about_ca_system_score_codex":0.000024851623,"about_ca_system_score_gemma":0.000050861527,"threshold_uncertainty_score":0.99955535},"labels":[],"label_agreement":null},{"id":"W7070992157","doi":"","title":"Season Two - Episode Three - Bayani Trinidad and Forrest Eaglespeaker","year":2019,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Work (physics)","score_opus":0.004359523016685494,"score_gpt":0.19916233539031328,"score_spread":0.1948028123736278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070992157","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":[0.00034617807,0.00064366095,0.00000582993,0.00009741459,0.0002597543,0.0005367249,0.0002751058,0.00006692519,0.9977684],"genre_scores_gemma":[0.0011741814,0.00027226115,0.0022577953,0.00031072876,0.00019403938,0.000012444291,0.0010680073,0.00012424009,0.9945863],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985668,0.000053770127,0.00053567166,0.00024282934,0.00029234547,0.0003085643],"domain_scores_gemma":[0.99859846,0.00004057434,0.00059647876,0.00056264125,0.00008307788,0.00011874407],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00021990319,0.00039346056,0.0003957683,0.000059100184,0.00005020094,0.000055358665,0.00031409718,0.0005036939,0.037797634],"category_scores_gemma":[0.00014974423,0.00038108858,0.00012863301,0.0000059774834,0.00013587106,4.5732758e-8,0.00022886689,0.00028193308,0.005109404],"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":[0.000087189626,0.000021573343,0.0001448887,0.00058963324,0.00009057548,0.0000026388684,0.00003011302,0.00014799669,0.0000034387292,0.000032193697,0.9970755,0.0017742319],"study_design_scores_gemma":[0.0009997613,0.0001942932,0.00005361337,0.00014564276,0.000053689928,0.000057982495,0.000021295455,0.000097120246,0.000028457645,0.0000038113856,0.99793124,0.0004131128],"about_ca_topic_score_codex":0.0015956443,"about_ca_topic_score_gemma":0.0038128565,"teacher_disagreement_score":0.032688227,"about_ca_system_score_codex":0.000014788992,"about_ca_system_score_gemma":0.000033546374,"threshold_uncertainty_score":0.9998641},"labels":[],"label_agreement":null},{"id":"W7071000848","doi":"","title":"School violence : the role of families, communities, educators and school counsellors","year":2002,"lang":"en","type":"dissertation","venue":"Memorial University Research Repository (Memorial University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Pretext; Articular cartilage damage; Diafiltration","score_opus":0.00964882694740072,"score_gpt":0.24272671025129997,"score_spread":0.23307788330389925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071000848","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87555087,0.00067101215,0.000008571244,0.000022607923,0.002836757,0.0007186557,0.00007264794,0.00003734717,0.12008153],"genre_scores_gemma":[0.87393534,0.009396039,0.00019191536,0.000016860333,0.0036768366,0.0000016944141,0.0009885757,0.000084348896,0.11170842],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965714,0.0011819007,0.00033280728,0.00048146126,0.00088180235,0.0005506289],"domain_scores_gemma":[0.9970637,0.00021515704,0.00039583992,0.0010586658,0.00087888975,0.00038774987],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0007406344,0.00039790297,0.0004453481,0.00070526014,0.0014370207,0.00011843855,0.0018544678,0.00074433733,0.00010367891],"category_scores_gemma":[0.00034205665,0.00041556408,0.00021644127,0.00075748214,0.0008241839,0.000054607965,0.0005770549,0.0016156145,0.000027647777],"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":[0.07348842,0.004148625,0.08539828,0.006941485,0.009935531,0.001552732,0.043619867,0.0020075927,0.46921378,0.028390622,0.2328871,0.042415958],"study_design_scores_gemma":[0.0023431994,0.000959212,0.0014751537,0.0004460086,0.00031025842,0.000034158904,0.12528406,0.0002697258,0.02039301,0.00010136387,0.84753746,0.0008463769],"about_ca_topic_score_codex":0.0051837307,"about_ca_topic_score_gemma":0.001114345,"teacher_disagreement_score":0.61465037,"about_ca_system_score_codex":0.00033299314,"about_ca_system_score_gemma":0.0014866958,"threshold_uncertainty_score":0.99986297},"labels":[],"label_agreement":null},{"id":"W7071009620","doi":"","title":"Rogues Among Rebels: Entanglements between Irish Catholics and the Fishermen’s Protective Union of Newfoundland","year":2017,"lang":"en","type":"dissertation","venue":"Summit (Simon Fraser University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Social Sciences and Humanities Research Council of Canada","keywords":"Irish; Opposition (politics); Chose; Ambivalence; Newspaper; Politics; Ethnic group","score_opus":0.008777892947754646,"score_gpt":0.2380838456386994,"score_spread":0.22930595269094475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071009620","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96889913,0.00011995488,0.00008881592,0.0000474898,0.00014903674,0.0006662898,0.00012907684,0.000014066411,0.029886156],"genre_scores_gemma":[0.9764865,0.00038987177,0.00010440797,0.000016834469,0.00013394216,0.0000045188704,0.0027114225,0.000031757543,0.020120718],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988899,0.00019139412,0.00022433235,0.00029427814,0.00020436227,0.00019572876],"domain_scores_gemma":[0.99856186,0.000032433272,0.0006457525,0.00052719325,0.00016499405,0.000067744324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029714114,0.00025980276,0.0003221873,0.00013585092,0.00030271942,0.00005857607,0.0005308342,0.00040549107,0.0000120130435],"category_scores_gemma":[0.00014662703,0.00022986636,0.00012002844,0.00008984668,0.00028602433,0.000022898996,0.00014682696,0.00034352558,0.0000019879656],"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":[0.0004429175,0.000031710268,0.9896138,0.00027191747,0.0004250353,0.000007377435,0.0003719119,0.000015592463,0.000054973203,0.000053735937,0.003776587,0.0049344576],"study_design_scores_gemma":[0.01062007,0.0009853047,0.40359494,0.0007679708,0.0015550108,7.232037e-8,0.03972111,0.00018571937,0.014510707,0.0003199759,0.52610666,0.0016324312],"about_ca_topic_score_codex":0.0014087494,"about_ca_topic_score_gemma":0.064974084,"teacher_disagreement_score":0.58601886,"about_ca_system_score_codex":0.000052638195,"about_ca_system_score_gemma":0.00009322354,"threshold_uncertainty_score":0.9520877},"labels":[],"label_agreement":null},{"id":"W7071009751","doi":"","title":"The role of political culture in shaping Canadian, EU and US disarmament initiaves","year":2017,"lang":"en","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Japan Atomic Energy Agency; International Atomic Energy Agency; McGill University","keywords":"Disarmament; Politics; Political culture; Government (linguistics)","score_opus":0.003993360819315483,"score_gpt":0.19767941988138266,"score_spread":0.19368605906206718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071009751","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83371484,0.015623514,0.000002789351,0.00014069675,0.00021731564,0.00018887309,0.000054041433,0.0000062190743,0.15005173],"genre_scores_gemma":[0.9901704,0.00065896724,0.00009998093,0.000059727787,0.00006625406,0.000006703835,0.0004188907,0.000010474053,0.008508567],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99914885,0.00004115247,0.00019383777,0.00018391269,0.00017166963,0.00026058595],"domain_scores_gemma":[0.99929553,0.000015440419,0.00018773883,0.00024785532,0.000086916654,0.00016650923],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.000099826095,0.00016410278,0.00014618355,0.00007612931,0.0019935737,0.000040265517,0.00026262866,0.00027969957,0.0000026993787],"category_scores_gemma":[0.00010649564,0.00014779733,0.00007167121,0.00003075747,0.00017440297,0.000010708459,0.00007177523,0.00022922238,0.0000014920759],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002283583,0.0002644208,0.427947,0.0009785717,0.0013772781,0.00085071207,0.054699395,0.001220758,0.16827404,0.30292892,0.0021739055,0.037001394],"study_design_scores_gemma":[0.0010893368,0.00021900878,0.29410115,0.00042382206,0.00016664005,0.00040767936,0.045242585,0.0015030698,0.044598833,0.0006682583,0.61084044,0.0007391697],"about_ca_topic_score_codex":0.1429169,"about_ca_topic_score_gemma":0.27534533,"teacher_disagreement_score":0.60866654,"about_ca_system_score_codex":0.00052394427,"about_ca_system_score_gemma":0.0009141608,"threshold_uncertainty_score":0.99930567},"labels":[],"label_agreement":null},{"id":"W7071011029","doi":"","title":"Safety and effectiveness of low-dose amikacin in nontuberculous mycobacterial pulmonary disease treated in Toronto","year":2021,"lang":"en","type":"article","venue":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Amikacin; Pulmonary disease; Antibiotics; Pulmonary tuberculosis; Disease; Respiratory disease","score_opus":0.0032537937574785005,"score_gpt":0.21986630368553559,"score_spread":0.21661250992805708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071011029","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9954916,0.0011414695,0.00008707458,0.000050211354,0.0000588484,0.00024503632,0.0001235413,0.000013336117,0.002788848],"genre_scores_gemma":[0.9975236,0.001001703,0.00030903931,0.0000384886,0.000026386646,0.0000045359,0.00091572636,0.00002291303,0.00015758617],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984625,0.00045815815,0.0002870684,0.0003568595,0.00010295002,0.0003324446],"domain_scores_gemma":[0.99915594,0.00008410054,0.0000937543,0.00039905074,0.00008792866,0.00017922337],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004421924,0.0002153684,0.00031212484,0.000102472455,0.000047461883,0.000017514163,0.00019159014,0.0002413567,0.00005878515],"category_scores_gemma":[0.00019940852,0.0002544277,0.000086854285,0.00024128184,0.000092189046,0.00003400243,0.00024343382,0.00017356106,0.0000021497917],"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":[0.0047098626,0.0003840035,0.8569513,0.0010604162,0.00011000342,0.00047515397,0.00046366206,0.0022295662,0.13070698,0.00038819562,0.000024561157,0.0024963089],"study_design_scores_gemma":[0.0023554573,0.00012511185,0.96582824,0.00022863514,0.000057396843,0.00007361868,0.0007141677,0.002409153,0.027035683,0.00003634038,0.0007877524,0.0003484573],"about_ca_topic_score_codex":0.0031746768,"about_ca_topic_score_gemma":0.0035349145,"teacher_disagreement_score":0.10887694,"about_ca_system_score_codex":0.00057045155,"about_ca_system_score_gemma":0.0002873605,"threshold_uncertainty_score":0.9999908},"labels":[],"label_agreement":null},{"id":"W7071017134","doi":"","title":"Queer occult: How Queer People in Montréal “Reclaim” Practices of Astrology, Tarot, and Magic to Divest from Legacies of Settler Colonialism, Whiteness, and Imperial Modernity","year":2024,"lang":"en","type":"dissertation","venue":"Spectrum Research Repository (Concordia University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Social Sciences and Humanities Research Council of Canada","keywords":"Queer; Modernity; MAGIC (telescope); Appropriation; Occult; Kinship; Ethnography; Queer theory; Liminality; Temporality","score_opus":0.012586910217606927,"score_gpt":0.27927892747507854,"score_spread":0.2666920172574716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071017134","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99552286,0.0009970565,0.00002596829,0.00067365245,0.00029681544,0.00045258895,0.00014840094,0.0000106509815,0.0018720062],"genre_scores_gemma":[0.99450886,0.0005778005,0.00017855842,0.0000068146105,0.0001544932,0.0000046504883,0.00036355975,0.000027798465,0.004177448],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99810874,0.00041964438,0.00027211546,0.000513784,0.00035020645,0.0003355051],"domain_scores_gemma":[0.9987625,0.00012822385,0.00036882242,0.00036082152,0.00023505566,0.00014456724],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039410382,0.00025278292,0.00044805792,0.0004995448,0.00013428912,0.00012556672,0.00033105424,0.00046655358,0.000008244614],"category_scores_gemma":[0.00034479835,0.00026376735,0.000082252765,0.00031931757,0.0002731822,0.000049560025,0.00040211066,0.00069306255,0.0000015832295],"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":[0.007225163,0.00018712551,0.5045127,0.0016672057,0.0007827872,0.00021263138,0.012547287,0.00029637746,0.46916428,0.00054102263,0.0024896339,0.00037373952],"study_design_scores_gemma":[0.0027229048,0.0029881103,0.8182439,0.00059930095,0.00037777956,0.00005117868,0.021944016,0.0015696925,0.124610156,0.0003875684,0.0254565,0.0010488903],"about_ca_topic_score_codex":0.057980966,"about_ca_topic_score_gemma":0.13715027,"teacher_disagreement_score":0.34455413,"about_ca_system_score_codex":0.00007765038,"about_ca_system_score_gemma":0.00045734533,"threshold_uncertainty_score":0.99998146},"labels":[],"label_agreement":null},{"id":"W7071021877","doi":"","title":"1 Second From Every Episode Of Hilda","year":2020,"lang":"en","type":"other","venue":"Internet Archive (Internet Archive)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Term (time); Table (database)","score_opus":0.006701821758102097,"score_gpt":0.22664856175560638,"score_spread":0.21994673999750428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071021877","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":[0.00407242,0.00074258447,0.023803726,0.000080216254,0.0007012543,0.00054710003,0.004073544,0.00011958954,0.9658596],"genre_scores_gemma":[0.026397986,0.0002018376,0.015614583,0.00080635125,0.0011944143,0.000037046026,0.0074508,0.0006402117,0.94765675],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972698,0.0002503849,0.0008027739,0.0008584478,0.00034157195,0.00047700567],"domain_scores_gemma":[0.99786484,0.000112743415,0.0008193385,0.00091475283,0.000026555956,0.00026179256],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00010016012,0.00072239176,0.0007987037,0.0002603811,0.0000144987425,0.00004811329,0.0014020274,0.00034866564,0.014263465],"category_scores_gemma":[0.00018009359,0.00070579397,0.00050049054,0.000063347434,0.00041212345,0.0000055431838,0.0013981918,0.0007703328,0.0008556369],"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":[0.0002672899,0.00007251026,0.0014683943,0.0002712716,0.0008747364,0.000022668917,0.0007569503,0.000010465569,0.010004431,0.00029040032,0.9855223,0.00043860506],"study_design_scores_gemma":[0.000713639,0.0005517718,0.0005892455,0.00053741905,0.00008571458,0.00002216096,0.000025370055,0.0018137508,0.010842933,0.00034035154,0.9838048,0.00067283685],"about_ca_topic_score_codex":0.0058960724,"about_ca_topic_score_gemma":0.010666664,"teacher_disagreement_score":0.022325568,"about_ca_system_score_codex":0.000014315792,"about_ca_system_score_gemma":0.00008805569,"threshold_uncertainty_score":0.99992234},"labels":[],"label_agreement":null},{"id":"W7071028644","doi":"","title":"Review of \"A Samaritan State Revisited: Historical Perspectives on Canadian Foreign Aid\" edited by Greg Donaghy and David Webster","year":2024,"lang":"en","type":"article","venue":"Scholars Commons (Wilfrid Laurier University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Liquation; Diafiltration; Emperipolesis; Triacetin; Durvalumab","score_opus":0.006133588833373671,"score_gpt":0.21498404893934675,"score_spread":0.20885046010597308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071028644","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26279977,0.36773947,0.0016535734,0.012257317,0.00094199745,0.002211731,0.0029558842,0.00029615627,0.3491441],"genre_scores_gemma":[0.8226458,0.11507166,0.0053391354,0.006176486,0.00047019898,0.000008908923,0.0024817898,0.00023297433,0.04757308],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998797,0.0001664837,0.00022289806,0.00036337425,0.00017401642,0.00027623452],"domain_scores_gemma":[0.99900866,0.000042300297,0.00008620795,0.00046492813,0.00013170144,0.00026621678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000320108,0.0002176185,0.00025585215,0.0003292147,0.00016163196,0.000057201,0.00032978234,0.00014504022,0.000065064196],"category_scores_gemma":[0.00017897773,0.00022302128,0.000119443444,0.00044236914,0.000121556935,0.000039726456,0.00015631443,0.00048177445,0.000010037399],"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":[0.00030892694,0.00018669799,0.017033093,0.005525648,0.00077188277,0.00022770789,0.0011564814,0.00001873629,0.0038401016,0.023350602,0.937937,0.009643104],"study_design_scores_gemma":[0.00027350185,0.00024423434,0.0002079021,0.0011229566,0.0000757861,0.000017477847,0.00020437458,0.000054307682,0.00026841857,0.000057886573,0.9972231,0.00025006777],"about_ca_topic_score_codex":0.0009497888,"about_ca_topic_score_gemma":0.0010372389,"teacher_disagreement_score":0.559846,"about_ca_system_score_codex":0.0003106884,"about_ca_system_score_gemma":0.00018713975,"threshold_uncertainty_score":0.9094544},"labels":[],"label_agreement":null},{"id":"W7071038005","doi":"","title":"Shipping, \"Cape Breton Miner\"","year":2008,"lang":"en","type":"other","venue":"York University Digital Library (York University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"DOCK; Cape; Port (circuit theory); Foot (prosody); Identity (music)","score_opus":0.005675699934751429,"score_gpt":0.15666714954088087,"score_spread":0.15099144960612945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071038005","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":[0.0014265388,0.00039534195,0.00046824763,0.00009076098,0.00022731583,0.00026335122,0.00087837473,0.00047683308,0.99577326],"genre_scores_gemma":[0.0049765375,0.0007478928,0.0014080699,0.00016853263,0.0003532595,6.840613e-8,0.0035641834,0.00029190286,0.98848957],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99838346,0.00007609563,0.00016615044,0.0006370962,0.00025488206,0.00048231467],"domain_scores_gemma":[0.9985649,0.000022381177,0.00033439897,0.00075083313,0.000022937174,0.00030454426],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000017916222,0.0005382672,0.00039512382,0.0006986844,0.00020329915,0.00012374006,0.0012914798,0.0008065737,0.00082521106],"category_scores_gemma":[0.000020641497,0.0006799821,0.00034618887,0.0006372188,0.0003612985,0.00008574545,0.00094278436,0.00041562325,0.00039854812],"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":[0.00015559178,0.00008518454,0.0035517542,0.00011140628,0.0002522108,0.0002639384,0.000054740274,0.000032161995,0.000033274366,0.00088382664,0.99383223,0.00074367586],"study_design_scores_gemma":[0.0007383733,0.00017757424,0.00008183318,0.00014064558,0.00006000629,0.000041470135,0.0004688123,0.000024881505,0.00006781662,0.000004597487,0.99743736,0.0007566072],"about_ca_topic_score_codex":0.00004465216,"about_ca_topic_score_gemma":0.0000247535,"teacher_disagreement_score":0.0072836825,"about_ca_system_score_codex":0.00005316525,"about_ca_system_score_gemma":0.00030441885,"threshold_uncertainty_score":0.9995651},"labels":[],"label_agreement":null},{"id":"W7071042255","doi":"","title":"Sokoman Minerals Corp. Invites Shareholders and Investment Community to visit us at Booth 336 at the VRIC in Vancouver, January 19-20, 2020 - Commodities (COMMODIT) News","year":2020,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Shareholder; Investment (military); Feature (linguistics); Capital (architecture)","score_opus":0.01496162668426816,"score_gpt":0.24572316638503147,"score_spread":0.23076153970076332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071042255","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":[0.11338045,0.004980372,0.0001063548,0.0045277714,0.00067938655,0.0025834555,0.0013807766,0.00018946151,0.872172],"genre_scores_gemma":[0.009985461,0.0015064448,0.003364898,0.08058684,0.0006488241,0.00020516105,0.006161601,0.000554084,0.89698666],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979107,0.0004683995,0.0005040338,0.00041346278,0.00028263323,0.00042080745],"domain_scores_gemma":[0.9981306,0.00011889647,0.00033228454,0.0011062956,0.000021388292,0.00029048987],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025961842,0.0006073812,0.0005653359,0.00012980014,0.00028012914,0.000081293045,0.00077935203,0.00038115922,0.0008589653],"category_scores_gemma":[0.00016426317,0.00046494562,0.00012789246,0.00016921067,0.00028209388,0.000006913311,0.0023095377,0.00066286407,0.00007798105],"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":[0.000061428276,0.000051741245,0.008853089,0.000247261,0.000115321294,0.0000076200063,0.0004978021,0.00015823537,0.0015091716,0.000024045969,0.98836046,0.00011380382],"study_design_scores_gemma":[0.0007439117,0.00036228384,0.0009391106,0.00011152337,0.00004039655,0.000018032086,0.00048337778,0.00031350402,0.00061376,0.000036733338,0.99574435,0.0005930226],"about_ca_topic_score_codex":0.0059024356,"about_ca_topic_score_gemma":0.15125489,"teacher_disagreement_score":0.14535247,"about_ca_system_score_codex":0.00013027189,"about_ca_system_score_gemma":0.00006776512,"threshold_uncertainty_score":0.99978024},"labels":[],"label_agreement":null},{"id":"W7071047345","doi":"","title":"RE Royalties Announces Second Quarter 2024 Financial Results and Highlights","year":2024,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Work (physics); Payment; Financial services; Financial Audit","score_opus":0.004628071482261741,"score_gpt":0.23196398208598995,"score_spread":0.2273359106037282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071047345","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":[0.00023330991,0.0038379438,0.000046346195,0.0005076571,0.0009270075,0.00015244486,0.00035456257,0.00007438782,0.9938663],"genre_scores_gemma":[0.000827472,0.00037192937,0.0013009638,0.00035022653,0.0010517804,0.000009746806,0.00037934387,0.00013626894,0.99557227],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99901444,0.00002601227,0.0002548099,0.00038024582,0.00012597028,0.00019850001],"domain_scores_gemma":[0.99944305,0.000007358668,0.000117231204,0.0003531018,0.00002108677,0.00005819243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001196949,0.00028174013,0.00021512523,0.0000989825,0.000029891544,0.000083466,0.00014884102,0.00051663624,0.00085594173],"category_scores_gemma":[0.000053933738,0.00021472713,0.00006462864,0.000046176447,0.00009278979,0.0000016817108,0.00013870907,0.0002157561,0.00033577098],"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":[0.000024383386,0.0000062364384,0.000013892324,0.0003188579,0.000055165838,0.000004849456,0.00011625001,5.063413e-7,0.000093319584,0.00025809565,0.9989554,0.00015300355],"study_design_scores_gemma":[0.0002194902,0.00018804976,0.000025491714,0.00012018387,0.000024494784,0.0000072317084,0.000077348275,0.000038932892,0.00031855545,0.00007602287,0.99860466,0.0002995439],"about_ca_topic_score_codex":0.000045777055,"about_ca_topic_score_gemma":0.0017101152,"teacher_disagreement_score":0.0034660145,"about_ca_system_score_codex":0.000005298842,"about_ca_system_score_gemma":0.00005650871,"threshold_uncertainty_score":0.9371962},"labels":[],"label_agreement":null},{"id":"W7071048835","doi":"","title":"The Red + Green: creating a regenerative narrative through the industrial wastelands of Sudbury, Ontario","year":2023,"lang":"en","type":"dissertation","venue":"Lu Zone Ul (Laurentian University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Thriving; Stewardship (theology); Environmental stewardship; Tailings; Narrative; Storytelling; Subject (documents); Industrial heritage; Sustainable development; Situated; Land use","score_opus":0.013234632381388318,"score_gpt":0.23134456552223592,"score_spread":0.21810993314084762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071048835","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91089094,0.00037219128,0.00049055653,0.00051305426,0.0020588175,0.001078694,0.0000878622,0.00006363296,0.084444255],"genre_scores_gemma":[0.3043988,0.00020940193,0.00040527823,0.000039974962,0.0006406261,0.0000076105366,0.0067391754,0.000082231636,0.6874769],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99847084,0.00023033757,0.00036028202,0.00033246248,0.00031107105,0.0002949951],"domain_scores_gemma":[0.99838537,0.00008349622,0.00069024833,0.00055390544,0.00023586737,0.000051118746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021129889,0.00032129497,0.00030003808,0.00009905392,0.0007207365,0.000056307104,0.00069562497,0.0005237874,0.0000647811],"category_scores_gemma":[0.00013976658,0.00023454658,0.00023910214,0.0003910959,0.0001698045,0.0000128850625,0.0001766566,0.00072739273,0.000005297789],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008714693,0.00039446878,0.007867887,0.00068984134,0.010596856,0.00016892621,0.74235034,0.0035459376,0.02126734,0.013238122,0.17450213,0.01666347],"study_design_scores_gemma":[0.0034710479,0.0012369043,0.0012902858,0.0005264669,0.00092071027,0.000017257076,0.423206,0.00039275948,0.023716766,0.00013835257,0.5439204,0.0011630666],"about_ca_topic_score_codex":0.008899568,"about_ca_topic_score_gemma":0.43807364,"teacher_disagreement_score":0.6064921,"about_ca_system_score_codex":0.00008735599,"about_ca_system_score_gemma":0.0004929217,"threshold_uncertainty_score":0.9977003},"labels":[],"label_agreement":null},{"id":"W7071054960","doi":"","title":"Risk factors related to chronic pain after breast cancer surgery: a prospective cohort study","year":2016,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Breast cancer; Prospective cohort study; Logistic regression; Chronic pain; Depression (economics); Risk factor; Cohort study; Chemotherapy","score_opus":0.0042025761581164,"score_gpt":0.24007193491602277,"score_spread":0.23586935875790638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071054960","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9862036,0.00022734322,7.109893e-7,0.000014651962,0.0010832595,0.0025572975,0.0036948882,0.00014045209,0.0060777655],"genre_scores_gemma":[0.9869352,0.00031963736,0.000056104444,0.00011357812,0.00011262314,0.0011916423,0.0016915365,0.00028552875,0.009294146],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9948231,0.00095884997,0.0011058407,0.0013970827,0.0008227867,0.00089232787],"domain_scores_gemma":[0.9967439,0.0001720958,0.00090912613,0.0011956822,0.00056452205,0.00041468124],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002252442,0.0010416935,0.0009319379,0.00035398072,0.00069945486,0.000092727736,0.0006485034,0.0010568415,0.0005770606],"category_scores_gemma":[0.0015131567,0.0008883273,0.000479854,0.0004575463,0.000058384278,0.00004183619,0.0002572077,0.0013042105,0.00021325034],"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":[0.0010078354,0.00042696125,0.9396192,0.00029206555,0.0021552546,0.000032750704,0.000061747494,0.00008095917,0.011029196,0.000122015226,0.00007936947,0.045092653],"study_design_scores_gemma":[0.0009138565,0.000637044,0.96718496,0.00048775264,0.00049757055,0.000016607262,0.00025593062,0.0000156837,0.013305457,0.00023533808,0.014661474,0.0017883425],"about_ca_topic_score_codex":0.0008750041,"about_ca_topic_score_gemma":0.003824431,"teacher_disagreement_score":0.043304313,"about_ca_system_score_codex":0.00092896895,"about_ca_system_score_gemma":0.00021517788,"threshold_uncertainty_score":0.99935675},"labels":[],"label_agreement":null},{"id":"W7071058515","doi":"","title":"RES and Cowessess First Nation to Accelerate Renewable Energy Goals in Saskatchewan","year":2021,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Renewable energy; First nation; Energy (signal processing); Feed-in tariff; Sustainability; Energy consumption","score_opus":0.012762587167356322,"score_gpt":0.2512869767297847,"score_spread":0.23852438956242836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071058515","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":[0.0022914764,0.0017718341,0.0049857073,0.00048195114,0.00023989192,0.00023234951,0.00002807126,0.000045413057,0.9899233],"genre_scores_gemma":[0.010933817,0.00076437613,0.0065009836,0.0010694548,0.00025689157,0.000033999448,0.0007945053,0.00016365385,0.9794823],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99917537,0.000039301605,0.0002048077,0.0002938177,0.00010581413,0.00018090763],"domain_scores_gemma":[0.9994762,0.000010590095,0.00010414533,0.0003062926,0.00003600894,0.00006673931],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010659483,0.0001968993,0.0002071758,0.00012937232,0.00002799143,0.00005937462,0.00014504188,0.00035145247,0.0006832946],"category_scores_gemma":[0.00008115781,0.00019024403,0.00002771996,0.00012096942,0.000022337912,0.0000015502633,0.0002031752,0.000079518024,0.0000043130017],"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":[0.000023222614,0.000038843733,0.0024416172,0.0002988655,0.00006537115,0.000006810893,0.00014660081,0.00091834617,0.008026298,0.00006181653,0.9864005,0.0015717025],"study_design_scores_gemma":[0.00023547308,0.000059885344,0.00015307212,0.0001509065,0.0000055917167,0.0000051425086,0.00017904176,0.00014714616,0.009419191,0.00001228726,0.9893627,0.00026952356],"about_ca_topic_score_codex":0.008808222,"about_ca_topic_score_gemma":0.23636745,"teacher_disagreement_score":0.22755922,"about_ca_system_score_codex":0.000013669675,"about_ca_system_score_gemma":0.00009219539,"threshold_uncertainty_score":0.9977922},"labels":[],"label_agreement":null},{"id":"W7071058517","doi":"","title":"Public Assistance Programs Help Mitigate the Adverse Economic Effects of Covid-19 on Argentine Households","year":2023,"lang":"en","type":"other","venue":"OpenDocs (Institute of Development Studies)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Fell; Unemployment; Quarter (Canadian coin); Falling (accident); Public assistance; Pandemic; Coronavirus disease 2019 (COVID-19); Job loss; Tourism","score_opus":0.039423708758642886,"score_gpt":0.2956080795003753,"score_spread":0.25618437074173245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071058517","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":[0.089908406,0.021064326,0.0034401447,0.005468648,0.020754881,0.020999752,0.0008147743,0.001589223,0.83595985],"genre_scores_gemma":[0.07620023,0.018342948,0.016680712,0.0012137617,0.0009296174,0.0014887019,0.0019904878,0.0017078451,0.8814457],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980779,0.00006505207,0.0006858529,0.00045924957,0.0003204165,0.0003915243],"domain_scores_gemma":[0.99807733,0.000043918488,0.0009859786,0.00070011977,0.000063374915,0.00012926235],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004759897,0.00045237975,0.0006327359,0.00012719064,0.00016548991,0.000019006411,0.0006799872,0.00020960368,0.00006181496],"category_scores_gemma":[0.0005426364,0.00034369738,0.00015911857,0.00015898178,0.00042118604,0.000008388466,0.0005772923,0.00019305677,0.00013076524],"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":[0.00029918633,0.00059585756,0.009765698,0.010467183,0.010095493,0.00010040007,0.001052933,0.0010016063,0.00059116096,0.0043821842,0.93907446,0.022573821],"study_design_scores_gemma":[0.0010089258,0.00017096997,0.0003850851,0.00048025465,0.000061221835,0.000004625149,0.000065932894,0.0000074075106,0.0023966553,0.0000067675505,0.9950503,0.00036183506],"about_ca_topic_score_codex":0.000051252355,"about_ca_topic_score_gemma":0.0010962845,"teacher_disagreement_score":0.055975843,"about_ca_system_score_codex":0.0001393511,"about_ca_system_score_gemma":0.00077230606,"threshold_uncertainty_score":0.99990153},"labels":[],"label_agreement":null},{"id":"W7071061174","doi":"","title":"Release: Media Invitation: U of R Varsity Sport breakfast to celebrate Academic All-Canadian student-athletes","year":2021,"lang":"en","type":"other","venue":"oURspace (University of Regina)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Subject (documents)","score_opus":0.008642054127122682,"score_gpt":0.23302333593504476,"score_spread":0.22438128180792208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071061174","genre_codex":"commentary","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":[0.24021803,0.00666895,0.0033746287,0.51955795,0.0012228922,0.0018163543,0.0011448213,0.0001499502,0.22584642],"genre_scores_gemma":[0.007772708,0.002345415,0.0132238455,0.00047963086,0.00022386332,6.5950485e-7,0.0015153305,0.00016908233,0.97426945],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99905795,0.00004616452,0.000034497654,0.00031305914,0.0002810999,0.0002672136],"domain_scores_gemma":[0.9986677,0.000011183029,0.0003961988,0.0005072879,0.00013411448,0.00028349968],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016169762,0.00022139614,0.00036734363,0.0003070992,0.00005226665,0.000006721597,0.0005682469,0.0005382222,0.000090841284],"category_scores_gemma":[0.00006203612,0.00029734123,0.0001273627,0.00022102504,0.00013797362,0.000005502528,0.00023870906,0.00028986187,0.000025150088],"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":[0.00001762934,0.0000115565,0.0050389497,0.0001471324,0.00018675688,0.00002735835,0.0003018726,0.000048588747,0.0013972507,0.00020482927,0.9921155,0.00050256413],"study_design_scores_gemma":[0.0003013803,0.00009193124,0.0021626092,0.00021967168,0.00009292776,0.000008399761,0.0013622333,0.00001562633,0.00020771821,0.0000010596021,0.99527276,0.00026369822],"about_ca_topic_score_codex":0.0010024583,"about_ca_topic_score_gemma":0.030520286,"teacher_disagreement_score":0.74842304,"about_ca_system_score_codex":0.000048811726,"about_ca_system_score_gemma":0.00032700095,"threshold_uncertainty_score":0.99994785},"labels":[],"label_agreement":null},{"id":"W7071074756","doi":"","title":"Robust, Multi-Constellation, Multi-Frequency Precise Point Positioning for Instantaneous cm-level Positioning","year":2025,"lang":"en","type":"other","venue":"York University Digital Library (York University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Pseudorange; Precise Point Positioning; GNSS applications; Multipath propagation; BeiDou Navigation Satellite System; Global Positioning System; Satellite navigation; Outlier; Satellite; Geodetic datum","score_opus":0.016473001233155798,"score_gpt":0.19194346603746484,"score_spread":0.17547046480430906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071074756","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":[0.00032506906,0.00029483045,0.13667378,0.000113327544,0.000281852,0.0009937182,0.00659786,0.00048064458,0.8542389],"genre_scores_gemma":[0.0059267147,0.0001936899,0.102132566,0.00014680348,0.00016495702,3.7114106e-7,0.009429236,0.00022187526,0.8817838],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99830186,0.000086261316,0.00026850135,0.0007052409,0.00018050705,0.0004576517],"domain_scores_gemma":[0.9986244,0.00006994254,0.00043729888,0.00056669215,0.00008680689,0.00021490282],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000040007024,0.0005287045,0.00040533004,0.0008028745,0.00044206143,0.00024487588,0.00086375955,0.0007263771,0.0002646681],"category_scores_gemma":[0.00004916541,0.0006987382,0.00035408526,0.0005643826,0.00023154008,0.0001451099,0.0005873085,0.00034324636,0.00004193837],"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":[0.0021102452,0.0013450896,0.013948624,0.0017413638,0.003103011,0.0007998164,0.00058753224,0.011776054,0.0009115215,0.022820158,0.9320479,0.008808689],"study_design_scores_gemma":[0.0031381368,0.00028246574,0.000091172216,0.00073898747,0.00024361502,0.0000535794,0.0011931597,0.0017275035,0.0002848026,0.000037429243,0.99101114,0.0011980179],"about_ca_topic_score_codex":0.00005643746,"about_ca_topic_score_gemma":0.000049694656,"teacher_disagreement_score":0.058963235,"about_ca_system_score_codex":0.00013491073,"about_ca_system_score_gemma":0.00051957404,"threshold_uncertainty_score":0.99954635},"labels":[],"label_agreement":null},{"id":"W7071079685","doi":"","title":"Prospects for multilateral cooperation in taxation","year":2006,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Université de Montréal; McGill University","keywords":"Globalization; International taxation; Double taxation; Tax policy; Tax revenue; Work (physics)","score_opus":0.007318504832107203,"score_gpt":0.2487722353136156,"score_spread":0.2414537304815084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071079685","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9775209,0.00009845915,0.0000074728164,0.0000084791,0.00068255904,0.0014712046,0.0005448002,0.00006161016,0.019604526],"genre_scores_gemma":[0.9574277,0.00004724203,0.0041511673,0.00014547029,0.00012696703,0.00040108414,0.023278393,0.0001455192,0.014276447],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976198,0.00011573571,0.0008145231,0.000675444,0.0002954749,0.00047902606],"domain_scores_gemma":[0.99825454,0.00003313438,0.00079792034,0.0004628477,0.0003592019,0.00009233581],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00050466525,0.0005179002,0.00039374278,0.0002321,0.0003840056,0.000080938225,0.00032547757,0.0009443692,0.000023775663],"category_scores_gemma":[0.000984766,0.0005636506,0.00019346645,0.00020524314,0.000025562835,0.000039499042,0.000058101767,0.00060027424,0.000036961555],"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":[0.0012126977,0.0004668334,0.001308269,0.0015135386,0.00017534826,0.000012093746,0.0000278938,0.0048577576,0.910327,0.018371241,0.00016821822,0.061559062],"study_design_scores_gemma":[0.0044368585,0.0009586647,0.015649557,0.00046280058,0.00014422629,0.000023622191,0.00008624926,0.0042155334,0.8155175,0.0025428277,0.15379526,0.0021669364],"about_ca_topic_score_codex":0.00018186818,"about_ca_topic_score_gemma":0.003973342,"teacher_disagreement_score":0.15362704,"about_ca_system_score_codex":0.0002103893,"about_ca_system_score_gemma":0.000060066504,"threshold_uncertainty_score":0.9996815},"labels":[],"label_agreement":null},{"id":"W7071084054","doi":"","title":"/R E P E A T -- Advisory - Third Quarter 2018 Results Conference Call/ - TSX (TSXTSX01) News","year":2018,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Term (time); Advisory committee","score_opus":0.010631283397763687,"score_gpt":0.25785880548482054,"score_spread":0.24722752208705687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071084054","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":[0.000091315094,0.00016678494,0.0040239943,0.0004104016,0.00056735147,0.00034498313,0.00013027893,0.0001521994,0.9941127],"genre_scores_gemma":[0.0006110065,0.00031356848,0.009523361,0.0015220528,0.0013856449,0.000020608652,0.0010946314,0.0002608129,0.9852683],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99814296,0.00009331389,0.00049620727,0.0005746512,0.00026063639,0.000432249],"domain_scores_gemma":[0.9981003,0.000018361081,0.00041635154,0.0012225476,0.00008581434,0.00015666762],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001978777,0.00048502852,0.00036835668,0.00012167418,0.000057848305,0.000070066315,0.00059620437,0.00096141605,0.0026601253],"category_scores_gemma":[0.00021059917,0.00040189334,0.00015313264,0.00006748282,0.00023763123,0.000002989959,0.00025848675,0.00027606165,0.0029817694],"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":[0.000073310606,0.000032370517,0.0001150626,0.00007673277,0.0000973408,0.00000232274,0.000060157494,9.2053466e-7,0.00044370757,0.000087822635,0.9985072,0.0005030645],"study_design_scores_gemma":[0.00073770754,0.00046599208,0.0000475021,0.000100115365,0.000029172985,0.000012842066,0.0000464207,0.00017254282,0.00047137172,0.000021034191,0.9973453,0.0005499492],"about_ca_topic_score_codex":0.000420632,"about_ca_topic_score_gemma":0.0012340298,"teacher_disagreement_score":0.0088443775,"about_ca_system_score_codex":0.000014835985,"about_ca_system_score_gemma":0.00016466717,"threshold_uncertainty_score":0.9998433},"labels":[],"label_agreement":null},{"id":"W7071096693","doi":"","title":"A Quarterly Report on Full-Time Equivalent State Employees For the Report Quarter Ending August 31, 2001","year":2002,"lang":"en","type":"report","venue":"The Portal to Texas History (University of North Texas)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); State (computer science); State government; Annual report","score_opus":0.024422295605983028,"score_gpt":0.24509278188190664,"score_spread":0.22067048627592362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071096693","genre_codex":"empirical","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":[0.7275003,0.0015076114,0.0090143215,0.0015482225,0.005370424,0.005971382,0.0011489016,0.0003237705,0.24761504],"genre_scores_gemma":[0.17216195,0.0005939682,0.0018231223,0.00039769796,0.0012035475,0.00001914688,0.003950424,0.0002595044,0.8195906],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964353,0.00010614609,0.0008829964,0.0008100953,0.0010448662,0.0007205916],"domain_scores_gemma":[0.99537647,0.00010774746,0.0015941182,0.0021230595,0.0005575473,0.00024106281],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015969564,0.0006089723,0.00072548346,0.0002487145,0.00043617218,0.000026835176,0.0012917197,0.00033413875,0.00089833967],"category_scores_gemma":[0.00025279337,0.00047293454,0.00071832456,0.00013271777,0.0004037672,0.00002092948,0.00030279453,0.0006030963,0.00018758491],"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":[0.0003346144,0.0001914314,0.0075618876,0.0002518759,0.00075079367,0.00086499425,0.0006232122,0.00054353545,0.00014591252,0.0000058656124,0.98660076,0.002125102],"study_design_scores_gemma":[0.0003777548,0.0016970141,0.020983135,0.00008897588,0.00042511756,0.0012993197,0.00008684803,0.00014011675,0.000026481213,0.000003950037,0.97422814,0.00064316933],"about_ca_topic_score_codex":0.000732542,"about_ca_topic_score_gemma":0.0018121755,"teacher_disagreement_score":0.5719756,"about_ca_system_score_codex":0.0005223231,"about_ca_system_score_gemma":0.00081274257,"threshold_uncertainty_score":0.99977225},"labels":[],"label_agreement":null},{"id":"W7071109841","doi":"","title":"Rehearsal Vienna VCI talk Peter Schade","year":2010,"lang":"en","type":"other","venue":"International Linear Collider","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Czech; Phone; Bridge (graph theory); Special section; Kingdom","score_opus":0.005703164787302617,"score_gpt":0.2704836381333639,"score_spread":0.2647804733460613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071109841","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":[0.001095861,0.00023958473,0.0026349213,0.0006354062,0.0030080404,0.0003141705,0.00029399712,0.000105340034,0.9916727],"genre_scores_gemma":[0.0024130677,0.000121014586,0.027675796,0.0013093246,0.0033055472,0.000027138823,0.0014724571,0.00037828644,0.96329737],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99882317,0.000027977216,0.0002781257,0.00032233054,0.0003362127,0.00021219204],"domain_scores_gemma":[0.9991354,0.000012030939,0.00023792525,0.00043781332,0.00009312158,0.00008373295],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012082328,0.00026844742,0.00018156852,0.00014792745,0.000033418582,0.00005522501,0.00050368905,0.00059985404,0.003975943],"category_scores_gemma":[0.00022833562,0.00025660294,0.00014366671,0.00004869497,0.00008706867,0.0000041290127,0.00024871124,0.0004682982,0.0005670689],"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":[0.00005282233,0.000073533185,0.00076057354,0.000050648923,0.00034037913,0.000019461624,0.000025907464,0.000059835795,0.010132618,0.00047944864,0.986733,0.0012717596],"study_design_scores_gemma":[0.00034604993,0.000058854035,0.0001565361,0.000049874812,0.00001448819,0.000056457306,0.0000031979675,0.0007620686,0.0015564254,0.000012961187,0.99669725,0.00028585515],"about_ca_topic_score_codex":0.000058712405,"about_ca_topic_score_gemma":0.00014918039,"teacher_disagreement_score":0.02837531,"about_ca_system_score_codex":0.000017318467,"about_ca_system_score_gemma":0.00008492696,"threshold_uncertainty_score":0.9999886},"labels":[],"label_agreement":null},{"id":"W7071116768","doi":"","title":"Seeking employment in the Québec public service : activity sheets for secondary school students /","year":2015,"lang":"fr","type":"other","venue":"Bibliothèque et Archives nationales du Québec (Québec government)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Public service; Service (business); Public sector; Work (physics); Public policy","score_opus":0.012810174456023577,"score_gpt":0.25921812111807113,"score_spread":0.24640794666204754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071116768","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40275896,0.01470828,0.0031191758,0.076965034,0.00058807904,0.004184913,0.0013610561,0.0001185703,0.49619594],"genre_scores_gemma":[0.7113074,0.0007915169,0.0018815249,0.012449263,0.0013346152,0.001125875,0.0005352772,0.0004662529,0.27010825],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99501765,0.0007328582,0.00091568305,0.00090451824,0.0016568836,0.0007724136],"domain_scores_gemma":[0.9946322,0.0028809893,0.0009884761,0.0009624673,0.00018909964,0.00034679583],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015058251,0.00088761357,0.00064372196,0.0007137984,0.00033424702,0.0007579795,0.0024684814,0.00036941134,0.0043949015],"category_scores_gemma":[0.0050670854,0.0007774934,0.00035005374,0.0007277481,0.000292628,0.00010799703,0.001225113,0.0010235104,0.00030710138],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0009156058,0.002626495,0.30619785,0.0017899699,0.0017402072,0.000023623641,0.011400744,0.0008812657,0.0037221822,0.0020216743,0.6610878,0.0075925724],"study_design_scores_gemma":[0.0023806216,0.00038533087,0.108504936,0.00024545184,0.000102809594,0.000050080675,0.00036410175,0.0017188033,0.00012702761,0.000044631615,0.8852999,0.0007762955],"about_ca_topic_score_codex":0.17484818,"about_ca_topic_score_gemma":0.9890703,"teacher_disagreement_score":0.8142221,"about_ca_system_score_codex":0.0046956628,"about_ca_system_score_gemma":0.07917587,"threshold_uncertainty_score":0.9994676},"labels":[],"label_agreement":null},{"id":"W7071122148","doi":"","title":"Représentations sociales du développement durable et de l'éducation au développement durable chez des étudiantes et des étudiants en génie au premier cycle au Québec","year":2022,"lang":"fr","type":"other","venue":"Le dépôt institutionnel (Université du Québec à Trois-Rivières)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Diafiltration; Dysgeusia; Liquation; Emperipolesis; Triacetin; Fusible alloy","score_opus":0.019338585929213,"score_gpt":0.2682870501601573,"score_spread":0.2489484642309443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071122148","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85831845,0.00075638667,0.044762418,0.04687171,0.0010288907,0.0012418708,0.00029251978,0.0001735283,0.04655425],"genre_scores_gemma":[0.9508578,0.0025565766,0.008172721,0.0007634514,0.000754416,0.00019832015,0.0014602125,0.0002296665,0.03500683],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9955742,0.0008506363,0.00082753104,0.0010041501,0.0005519531,0.0011915553],"domain_scores_gemma":[0.9972807,0.00021607976,0.00086490606,0.0008614157,0.00036180072,0.00041508555],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011397004,0.0008983533,0.0006892321,0.00043671936,0.0035391257,0.00016101207,0.0010172693,0.0005617332,0.004118009],"category_scores_gemma":[0.0010235121,0.0010393062,0.00044980232,0.0006506703,0.0014175285,0.00022033318,0.00091377686,0.00075566187,0.00027730584],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00022557082,0.0014716506,0.70834357,0.0009912964,0.0015853108,0.00007445409,0.1992896,0.053384814,0.004117466,0.0122572165,0.016349746,0.0019093009],"study_design_scores_gemma":[0.0065821805,0.00071790913,0.7179011,0.00082042196,0.0010312673,0.00038145136,0.08611514,0.007182262,0.002354352,0.0006586787,0.17338134,0.002873899],"about_ca_topic_score_codex":0.7020337,"about_ca_topic_score_gemma":0.9734601,"teacher_disagreement_score":0.2714264,"about_ca_system_score_codex":0.019071119,"about_ca_system_score_gemma":0.030119857,"threshold_uncertainty_score":0.9992057},"labels":[],"label_agreement":null},{"id":"W7071143256","doi":"","title":"Second Quarter Surge Propels Minnesota Duluth Past Minnesota Crookston 74-64","year":2017,"lang":"en","type":"other","venue":"University of Minnesota Digital Conservancy (University of Minnesota)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Surge; Work (physics); Government (linguistics)","score_opus":0.007414261259070002,"score_gpt":0.18731852192507809,"score_spread":0.1799042606660081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071143256","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":[0.16308081,0.0019752586,0.0013586709,0.001339284,0.00091253413,0.0018206711,0.0068411306,0.00025403357,0.8224176],"genre_scores_gemma":[0.08376984,0.0018660534,0.003673628,0.00009208571,0.00037834854,6.858891e-7,0.0029200704,0.00047120356,0.9068281],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962546,0.00019290592,0.0005554152,0.0013079476,0.0007394193,0.0009496935],"domain_scores_gemma":[0.994097,0.0001025574,0.0023412835,0.0024669697,0.00053658686,0.00045563077],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00036756674,0.0010997641,0.0015994259,0.00071723765,0.00052365987,0.00009636932,0.002719575,0.0013908568,0.002289835],"category_scores_gemma":[0.00015295073,0.0014359916,0.0009283526,0.00028706554,0.0019393445,0.00023971025,0.0014068556,0.00060136244,0.00025682116],"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":[0.0008272303,0.00051761285,0.011870826,0.0017172561,0.001065944,0.0003316056,0.0010070961,0.0000073210463,0.0021102896,0.0002255725,0.97695065,0.0033686087],"study_design_scores_gemma":[0.0030488898,0.00061976357,0.002261889,0.00082744093,0.0003453701,0.000093240815,0.002333191,0.00008811883,0.00032609908,0.000015397813,0.9886215,0.0014191347],"about_ca_topic_score_codex":0.00074838405,"about_ca_topic_score_gemma":0.004010922,"teacher_disagreement_score":0.08441047,"about_ca_system_score_codex":0.000095929645,"about_ca_system_score_gemma":0.00051244284,"threshold_uncertainty_score":0.9999055},"labels":[],"label_agreement":null},{"id":"W7071155262","doi":"","title":"South Jersey Industries : SJI TO HOST FOURTH QUARTER 2015 CONFERENCE CALL AND LIVE WEBCAST - NYSE (NYSE0001) News","year":2016,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Webcast; Quarter (Canadian coin); Host (biology)","score_opus":0.010997051941348462,"score_gpt":0.2600764072726886,"score_spread":0.24907935533134015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071155262","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":[0.0023639419,0.00034606975,0.012012906,0.0023153024,0.000452097,0.0008954603,0.00047771246,0.00013667597,0.9809998],"genre_scores_gemma":[0.013670323,0.00022272795,0.004401836,0.0013085415,0.0007210636,0.000030180416,0.00022480456,0.00024492329,0.9791756],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986392,0.000060696748,0.00028914688,0.00044555796,0.00018360557,0.00038174452],"domain_scores_gemma":[0.9988159,0.00001502148,0.00023254492,0.00058644457,0.00008467601,0.00026542746],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000103143844,0.00043799198,0.00035095942,0.00012567354,0.000048736067,0.00009225496,0.0003072578,0.0007366983,0.0030339898],"category_scores_gemma":[0.00012332301,0.00032192917,0.000060270686,0.000047691723,0.00015443604,0.0000039794363,0.00028930514,0.00027126377,0.0010732064],"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":[0.000036385834,0.000014492308,0.0016781418,0.00005157273,0.00009833572,0.000003103497,0.00041494126,7.624811e-7,0.00078831776,0.000086102926,0.995224,0.0016038724],"study_design_scores_gemma":[0.00055802765,0.00035696902,0.00015458731,0.00014079578,0.000035138815,0.000015070795,0.0005907518,0.00003064703,0.00044182382,0.000004474175,0.9971022,0.0005695103],"about_ca_topic_score_codex":0.00032505463,"about_ca_topic_score_gemma":0.00096370187,"teacher_disagreement_score":0.011306381,"about_ca_system_score_codex":0.000013247938,"about_ca_system_score_gemma":0.00017355153,"threshold_uncertainty_score":0.9999233},"labels":[],"label_agreement":null},{"id":"W7071166116","doi":"","title":"Så den fremmede ikke blir mer fremmed","year":2015,"lang":"no","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Feminism; Quarter (Canadian coin); Sine","score_opus":0.024006866525663747,"score_gpt":0.2810396457615874,"score_spread":0.25703277923592366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071166116","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24030863,0.0066992403,0.01802654,0.0069983033,0.0033450436,0.0010979141,0.0001485566,0.00021480916,0.723161],"genre_scores_gemma":[0.91601557,0.00025440214,0.019816777,0.0042870836,0.0013282028,0.000021357731,0.0007281388,0.00010509117,0.0574434],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99738276,0.000179442,0.0006568701,0.00049892406,0.0005456449,0.00073637295],"domain_scores_gemma":[0.99769276,0.000035445017,0.00027192212,0.0010640372,0.00032545396,0.0006103517],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00080568023,0.00047624548,0.00038083395,0.000098896046,0.00013307508,0.00016380868,0.0007747509,0.0006375042,0.00065078726],"category_scores_gemma":[0.00091408216,0.00042476473,0.00020855591,0.00020068324,0.00021371312,0.000013003521,0.00063178124,0.0004321027,0.0013371404],"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":[0.00032970062,0.00042713268,0.019264633,0.00027170562,0.0010758156,0.000035277946,0.0020952877,0.0009442644,0.028019324,0.0016962897,0.9313923,0.014448237],"study_design_scores_gemma":[0.0026422793,0.0009054596,0.0015097039,0.00004968158,0.00023276701,0.00011984532,0.0011300342,0.009715173,0.04121765,0.0002033645,0.9411608,0.001113215],"about_ca_topic_score_codex":0.00022426229,"about_ca_topic_score_gemma":0.00016668875,"teacher_disagreement_score":0.6757069,"about_ca_system_score_codex":0.000055265366,"about_ca_system_score_gemma":0.00042321402,"threshold_uncertainty_score":0.9998204},"labels":[],"label_agreement":null},{"id":"W7071168590","doi":"","title":"Probabilistic Modeling in Community-based Question Answering Services","year":2012,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Question answering; Topic model; Task (project management); Dependency (UML); Cluster analysis; Probabilistic logic; Statistical model; Ask price","score_opus":0.004050178991610728,"score_gpt":0.16860453006075563,"score_spread":0.1645543510691449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071168590","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038759705,0.000967726,0.0008715683,0.00037893993,0.0002079709,0.0003503497,0.00024512832,0.000019691588,0.9581989],"genre_scores_gemma":[0.95421845,0.00014489559,0.0044357083,0.0010230198,0.00012626749,0.000013507694,0.00032610534,0.00015669319,0.039555356],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99894404,0.000112830574,0.00020516703,0.00011375403,0.0004292087,0.00019498699],"domain_scores_gemma":[0.99947834,0.000028315999,0.0001512659,0.0002470905,3.0413565e-7,0.000094698924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000021262274,0.00017987723,0.000177056,0.000028270882,0.000056304634,0.000010196746,0.0002049951,0.00007405332,0.000019268518],"category_scores_gemma":[0.0000028390168,0.00018364236,0.000016264952,0.000029714718,0.0000322612,0.0000087308135,0.00013051696,0.0002242572,1.976785e-9],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003917551,0.0011657504,0.33501783,0.08922164,0.0014463617,0.00012746513,0.0018428925,0.2922445,0.12914687,0.055639416,0.025944825,0.0642849],"study_design_scores_gemma":[0.0014312415,0.00029981023,0.0044021164,0.0033338638,0.000084519656,0.000011118968,0.0024015126,0.3968577,0.018883033,0.00036226196,0.570345,0.0015878471],"about_ca_topic_score_codex":0.013671294,"about_ca_topic_score_gemma":0.15821777,"teacher_disagreement_score":0.9186436,"about_ca_system_score_codex":0.0000036346812,"about_ca_system_score_gemma":0.00046700795,"threshold_uncertainty_score":0.99289674},"labels":[],"label_agreement":null},{"id":"W7071170448","doi":"","title":"A qualitative study of presently and formerly homeless female adolescents","year":2001,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Diafiltration; Liquation; Emperipolesis; Triacetin; Durvalumab","score_opus":0.004197728118562744,"score_gpt":0.20527160264643177,"score_spread":0.201073874527869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071170448","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38665923,0.0011390817,0.000110218956,0.00013653308,0.00013376714,0.0006665574,0.0005191548,0.000007911774,0.61062753],"genre_scores_gemma":[0.8673903,0.00033474664,0.00042411024,0.00012615172,0.00005372134,0.0000075498924,0.00003458539,0.00008186839,0.13154699],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99850386,0.0000941774,0.00026571142,0.00021018741,0.000743137,0.00018293814],"domain_scores_gemma":[0.9992824,0.000028394206,0.00033696744,0.00022831597,6.655159e-7,0.00012325843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000012335089,0.00021118417,0.00031648125,0.000028544315,0.00004113647,0.000008696199,0.0001831617,0.00005863301,0.000028310846],"category_scores_gemma":[0.0000046646555,0.00019870879,0.000019808722,0.000037513746,0.00008042202,0.0000081351545,0.00020183632,0.000110135996,1.1643406e-9],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005245465,0.0021940733,0.66279036,0.019368008,0.0051769293,0.0002623874,0.02878445,0.00018578644,0.04270129,0.010027578,0.15314147,0.070122205],"study_design_scores_gemma":[0.006477166,0.0037003953,0.058370408,0.0021550157,0.0002418875,0.00003088761,0.36007065,0.000727995,0.03165916,0.00015856263,0.53424263,0.002165251],"about_ca_topic_score_codex":0.0073452555,"about_ca_topic_score_gemma":0.0693711,"teacher_disagreement_score":0.60441995,"about_ca_system_score_codex":0.000001534505,"about_ca_system_score_gemma":0.00036024838,"threshold_uncertainty_score":0.9992649},"labels":[],"label_agreement":null},{"id":"W7071205494","doi":"","title":"Rogers-Shaw deal approved by Ottawa in blockbuster telecom merger","year":2023,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corporate governance; Government (linguistics); Launched; Merger control","score_opus":0.003422034832781606,"score_gpt":0.18812419499511737,"score_spread":0.18470216016233576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071205494","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":[0.0003834022,0.00026595322,0.00000203691,0.00013939824,0.0002168773,0.00042379607,0.0001844078,0.00014631166,0.9982378],"genre_scores_gemma":[0.00070032885,0.00028835423,0.0016771535,0.00038596732,0.0001319906,0.000030119367,0.0008624849,0.00029950924,0.99562407],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981227,0.00007928006,0.00080399675,0.00025812356,0.00033077094,0.00040515186],"domain_scores_gemma":[0.9987179,0.00004400423,0.00058875035,0.0004662154,0.00007840117,0.00010469755],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00030506216,0.00040463972,0.0004083854,0.00009922112,0.00003911532,0.00003881638,0.00041049763,0.0007378883,0.04563391],"category_scores_gemma":[0.00019196839,0.00040805188,0.00016318854,0.000015481135,0.00010467925,4.3409162e-8,0.00016550101,0.0003622743,0.004143599],"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":[0.000048518992,0.000036773727,0.00006913205,0.00029231198,0.00007874587,0.000004749305,0.00005430807,0.00033189714,0.000019829782,0.0000032891576,0.99800634,0.0010541197],"study_design_scores_gemma":[0.000663662,0.00013650877,0.000015590535,0.00012752425,0.00002488878,0.000024014444,0.000050770486,0.00014708893,0.00012258743,8.7849565e-7,0.9982629,0.0004235907],"about_ca_topic_score_codex":0.003078763,"about_ca_topic_score_gemma":0.005193718,"teacher_disagreement_score":0.04149031,"about_ca_system_score_codex":0.000031966505,"about_ca_system_score_gemma":0.000038184386,"threshold_uncertainty_score":0.99983716},"labels":[],"label_agreement":null},{"id":"W7071237663","doi":"","title":"Règlement relatif à la mission et à certains aspects du fonctionnement de l'Institut maritime du Québec","year":2006,"lang":"fr","type":"other","venue":"Bibliothèque et Archives nationales du Québec (Québec government)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Work (physics); Shore; Fishing","score_opus":0.004757660498262108,"score_gpt":0.21718856203493073,"score_spread":0.21243090153666863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071237663","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":[0.030352736,0.006413032,0.01768677,0.038559906,0.00037226992,0.0011395381,0.00039486686,0.00015070401,0.9049302],"genre_scores_gemma":[0.4732116,0.00594279,0.01155808,0.0056271604,0.0019824493,0.00028616373,0.0010035113,0.00056614977,0.4998221],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949189,0.0007602376,0.0012435322,0.0010170349,0.0012728896,0.0007874188],"domain_scores_gemma":[0.9950637,0.0024309126,0.0011734964,0.0008048018,0.0001176275,0.00040946083],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008195089,0.0010818486,0.0006670887,0.0010562931,0.0005334175,0.0004683602,0.0010215334,0.00051261456,0.008363384],"category_scores_gemma":[0.0035828003,0.0011026158,0.0005800587,0.0005583072,0.00064317865,0.00007974708,0.0009798068,0.00090972515,0.000487744],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00033092566,0.0015876415,0.16273305,0.0007345834,0.0010025684,0.00008003303,0.0020070868,0.009121085,0.0034623276,0.04223243,0.7750013,0.001707002],"study_design_scores_gemma":[0.0021802073,0.0004050308,0.07349886,0.00048218216,0.000210878,0.00019886706,0.00009842175,0.0056196824,0.0006084868,0.00014207866,0.91551566,0.0010396224],"about_ca_topic_score_codex":0.3963603,"about_ca_topic_score_gemma":0.97393376,"teacher_disagreement_score":0.5775735,"about_ca_system_score_codex":0.0055357106,"about_ca_system_score_gemma":0.054244842,"threshold_uncertainty_score":0.9991424},"labels":[],"label_agreement":null},{"id":"W7071237772","doi":"","title":"A Restrição ao capital externo preocupa mineradoras do canada","year":2008,"lang":"pt","type":"other","venue":"Institutional Digital Library (Federal Senate)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Capital (architecture); Government (linguistics); Work (physics); Investment (military); Population","score_opus":0.0048492991055363215,"score_gpt":0.19216449181911902,"score_spread":0.18731519271358268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071237772","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19062103,0.0060718283,0.00022329588,0.0010564094,0.0020997503,0.00097638846,0.008225317,0.00018073514,0.7905452],"genre_scores_gemma":[0.62529725,0.00054970535,0.000468971,0.0012845715,0.0017088227,0.000029001872,0.013497833,0.00028724203,0.35687658],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958682,0.00009140283,0.0010264148,0.0010651646,0.0009786248,0.00097021187],"domain_scores_gemma":[0.9979194,0.000042126285,0.0005551678,0.0008067342,0.00008990466,0.00058668025],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000048163132,0.0011775742,0.00071349996,0.00020088055,0.0005214413,0.00093897077,0.0009777368,0.0009496482,0.0014319057],"category_scores_gemma":[0.00018454903,0.0011365835,0.00039813868,0.00025316206,0.0006124826,0.00022010376,0.00063371647,0.0008392127,0.00058015995],"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":[0.00046867545,0.00048085346,0.01543746,0.0005957782,0.0008975062,0.0014645811,0.00010292669,0.0015836715,0.00070361735,0.0034488172,0.97033954,0.0044765635],"study_design_scores_gemma":[0.0011212125,0.00023449014,0.0013691364,0.00046282215,0.000028482667,0.0011633307,0.000041503317,0.00028575282,0.001223998,0.00007725313,0.9925245,0.0014674868],"about_ca_topic_score_codex":0.015304828,"about_ca_topic_score_gemma":0.00962626,"teacher_disagreement_score":0.43467623,"about_ca_system_score_codex":0.0001871545,"about_ca_system_score_gemma":0.005053684,"threshold_uncertainty_score":0.9994809},"labels":[],"label_agreement":null},{"id":"W7071243769","doi":"","title":"The role of neuronal activity on radial glia behaviour in «Xenopus laevis» tectum","year":2009,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Xenopus; Filopodia; Population; Premovement neuronal activity; Calcium imaging; Tectum; Motility; Zebrafish","score_opus":0.0012412292942819573,"score_gpt":0.14798462908475732,"score_spread":0.14674339979047535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071243769","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07128711,0.00062127016,0.0000069870216,0.0006655641,0.0001760904,0.00024491313,0.0003317011,0.000005539894,0.92666084],"genre_scores_gemma":[0.9032539,0.00037733,0.00022723088,0.00039969618,0.00013312027,0.0000052590904,0.000031047228,0.00008157684,0.09549081],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987106,0.00006624345,0.00018999777,0.00016766645,0.0006646032,0.00020092091],"domain_scores_gemma":[0.9993741,0.00004847278,0.00024314334,0.00025071122,2.904219e-7,0.00008329999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000121410385,0.00018754277,0.00019813662,0.000021715083,0.000050267074,0.000009175198,0.0002522826,0.00007004745,0.00001783983],"category_scores_gemma":[0.000007040229,0.00015410778,0.0000311454,0.00003133298,0.000073665855,0.00000448041,0.000099278775,0.00020329576,2.2307494e-9],"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":[0.0059306603,0.00049460627,0.14705549,0.00092944567,0.00063788577,0.00011617708,0.00015197966,0.0008152914,0.30379948,0.03415403,0.1549187,0.35099626],"study_design_scores_gemma":[0.0005273291,0.0004708967,0.061229255,0.00016631208,0.000023138295,0.0000053010567,0.00018485168,0.00059059134,0.16816078,0.00014500525,0.76811343,0.00038313612],"about_ca_topic_score_codex":0.0029904176,"about_ca_topic_score_gemma":0.04751723,"teacher_disagreement_score":0.8319668,"about_ca_system_score_codex":0.000003172527,"about_ca_system_score_gemma":0.0006786761,"threshold_uncertainty_score":0.9698631},"labels":[],"label_agreement":null},{"id":"W7071271829","doi":"","title":"Researchers in Ontario Push the Envelope: Can They Generate a Breakthrough?","year":2019,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Work (physics); Key (lock); Agency (philosophy); Perspective (graphical)","score_opus":0.02681887810062199,"score_gpt":0.28042860932116315,"score_spread":0.25360973122054115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071271829","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":[0.0023376301,0.00024887145,0.00010469976,0.00062908,0.00021564889,0.00054485764,0.000018907249,0.000026071388,0.9958742],"genre_scores_gemma":[0.0034389673,0.00022168475,0.0019390532,0.0009305592,0.0001818837,0.000024713354,0.00029781758,0.00022206632,0.99274325],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987152,0.00012862572,0.00023128334,0.00031390408,0.00023160783,0.00037933927],"domain_scores_gemma":[0.9989239,0.00001436537,0.00013380499,0.00084182364,0.000028417759,0.000057692818],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00039407267,0.00027137526,0.00021742939,0.00008924177,0.000036648817,0.00005788335,0.0006048803,0.0004525375,0.0012045772],"category_scores_gemma":[0.00006992359,0.00017689199,0.00007833174,0.00006668908,0.0000840878,0.0000011837694,0.00032015264,0.00062727754,0.00024663337],"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":[0.000030312132,0.000025006446,0.009213682,0.000065060805,0.00015552831,0.000005226004,0.00070763053,0.00020185116,0.00068112323,0.00044920138,0.9870584,0.001406995],"study_design_scores_gemma":[0.0003391602,0.00006791532,0.001275001,0.000037986036,0.000007594281,0.000009035747,0.000082723134,0.000062883235,0.00023826737,0.000016912763,0.9976011,0.00026144102],"about_ca_topic_score_codex":0.2519727,"about_ca_topic_score_gemma":0.89874315,"teacher_disagreement_score":0.6467705,"about_ca_system_score_codex":0.00008412488,"about_ca_system_score_gemma":0.0008005735,"threshold_uncertainty_score":0.9997085},"labels":[],"label_agreement":null},{"id":"W7071293025","doi":"","title":"Sedimentology and ichnology of a shallow-marine clastic system from the Silurian-Devonian Furada Formation of Asturias, Spain: Benthic response to event deposition and environmental disturbance","year":2024,"lang":"en","type":"dissertation","venue":"University Library (University of Saskatchewan)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; International Association of Sedimentologists","keywords":"Sedimentary depositional environment; Bioturbation; Ichnology; Benthic zone; Sedimentology; Clastic rock; Paleozoic; Fluvial","score_opus":0.002024414376962718,"score_gpt":0.15763432878890235,"score_spread":0.15560991441193964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071293025","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.997222,0.0004455713,0.00079376285,0.00047965324,0.00009885337,0.00028768778,0.0004948026,0.000017255988,0.00016040895],"genre_scores_gemma":[0.99428356,0.0001638735,0.0015375988,0.000021313223,0.000018846538,1.4667091e-7,0.0024037801,0.000013506783,0.0015573486],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99909997,0.00017465172,0.00019296008,0.00026192467,0.00014506903,0.00012542229],"domain_scores_gemma":[0.99922687,0.00007906391,0.00035500494,0.00025099594,0.00002168568,0.00006636765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009707826,0.00018497562,0.00029144113,0.00015685926,0.000107539265,0.000008177221,0.0002896134,0.00032622283,0.000027714603],"category_scores_gemma":[0.000011232013,0.00020326264,0.00008623249,0.00011352779,0.00018154507,0.000049422157,0.00040351614,0.00019949341,0.0000020711318],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.057025902,0.0008232592,0.13172054,0.0140741365,0.004108566,0.00037541898,0.40477285,0.0012129891,0.36022496,0.0011287269,0.0027688562,0.021763813],"study_design_scores_gemma":[0.0029070592,0.002087379,0.21864267,0.001247794,0.0013074514,0.000054455355,0.7401049,0.0046211137,0.018747097,0.00008803048,0.0093601355,0.00083188235],"about_ca_topic_score_codex":0.0004984878,"about_ca_topic_score_gemma":0.0017113837,"teacher_disagreement_score":0.34147787,"about_ca_system_score_codex":0.00004166215,"about_ca_system_score_gemma":0.00009696445,"threshold_uncertainty_score":0.828881},"labels":[],"label_agreement":null},{"id":"W7071302705","doi":"","title":"Start Something to Live For","year":2013,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Capital (architecture); Shut down; Optimism; Fish <Actinopterygii>","score_opus":0.005706048355217066,"score_gpt":0.20747144528849296,"score_spread":0.2017653969332759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071302705","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":[0.00008289608,0.00015907234,0.000038776194,0.00012545958,0.00024978796,0.00092717895,0.00026227534,0.00006452607,0.99809],"genre_scores_gemma":[0.00010627476,0.000084953004,0.024914743,0.0008970634,0.0002640512,0.000066307155,0.0007411562,0.00014503254,0.9727804],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987295,0.000037415513,0.00051244505,0.00018895835,0.00023207928,0.00029958063],"domain_scores_gemma":[0.9987645,0.000044556804,0.00045542346,0.0004272425,0.00017572574,0.00013250728],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00022477453,0.0003042332,0.00031176064,0.000071640905,0.000052739328,0.000050894127,0.00035369722,0.00047608986,0.092158794],"category_scores_gemma":[0.00039667005,0.0003022081,0.00015978947,0.0000048492466,0.00005718067,2.1891811e-8,0.00015733059,0.0001729363,0.008615532],"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":[0.000051483497,0.00001669202,0.0000023024272,0.000516426,0.000076476535,4.563906e-7,0.00013352164,0.0003925703,0.00001073441,0.000027092845,0.9972955,0.001476743],"study_design_scores_gemma":[0.00035730834,0.00039059293,0.0000026423363,0.00012536107,0.000030924428,0.000013468177,0.00011012016,0.000073524054,0.00010040247,0.0000047369163,0.99845034,0.00034055242],"about_ca_topic_score_codex":0.00119889,"about_ca_topic_score_gemma":0.00042084075,"teacher_disagreement_score":0.08354326,"about_ca_system_score_codex":0.000018264755,"about_ca_system_score_gemma":0.0000337643,"threshold_uncertainty_score":0.999943},"labels":[],"label_agreement":null},{"id":"W7071337836","doi":"","title":"Secret 7: The Best Tax Sheltering in Canada","year":2009,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Legislation; Work (physics)","score_opus":0.0033978864412206626,"score_gpt":0.17837294612747442,"score_spread":0.17497505968625376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071337836","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":[0.00050275,0.0003190183,8.6050477e-7,0.00016363223,0.0001593046,0.00028054882,0.00009575683,0.00001628923,0.99846184],"genre_scores_gemma":[0.004770603,0.00028625046,0.0005834872,0.0006574662,0.00013123237,0.000008516223,0.00030613414,0.000068645415,0.99318767],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987662,0.00005698435,0.00050187483,0.00013591317,0.0002742618,0.00026478487],"domain_scores_gemma":[0.9990227,0.000023834218,0.0004188861,0.00042379732,0.00004934525,0.00006142866],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000166472,0.0002647366,0.00024675057,0.000035455305,0.000039273073,0.000027430557,0.00041683886,0.00025016247,0.026122894],"category_scores_gemma":[0.00011535795,0.00022215082,0.00007179159,0.000006874241,0.000057303867,1.5906394e-8,0.000114643735,0.0002837644,0.00049328164],"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":[0.00002433271,0.000009101259,0.00003932391,0.00016225276,0.000025135585,0.0000059549216,0.000032061078,0.0012261176,0.0000020582265,0.0000035228718,0.99662113,0.0018490178],"study_design_scores_gemma":[0.00025815872,0.0000916708,0.000043242584,0.00013539544,0.000014318611,0.00004761115,0.00012114243,0.0000989627,0.000028227532,0.0000010037196,0.9989168,0.00024343202],"about_ca_topic_score_codex":0.7614442,"about_ca_topic_score_gemma":0.90590876,"teacher_disagreement_score":0.14446454,"about_ca_system_score_codex":0.000067826295,"about_ca_system_score_gemma":0.0001954494,"threshold_uncertainty_score":0.9747674},"labels":[],"label_agreement":null},{"id":"W7071361142","doi":"","title":"St. John Fisher defeats AU womens basketball team, January 25, 2005","year":2005,"lang":"en","type":"other","venue":"Alfred University Research and Archives (AURA) (Alfred University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Basketball; Population; Government (linguistics); Data collection","score_opus":0.011629310308861092,"score_gpt":0.23550907518768918,"score_spread":0.2238797648788281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071361142","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":[0.011223939,0.0003913223,0.0005774505,0.0004442651,0.00013317923,0.00072518527,0.0017216895,0.00014540504,0.98463756],"genre_scores_gemma":[0.0049633854,0.004830452,0.003401739,0.00007968147,0.0005244446,7.531222e-7,0.0021065073,0.00020171456,0.9838913],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962924,0.00048727368,0.00023025378,0.0010138805,0.0005612699,0.0014148932],"domain_scores_gemma":[0.9977014,0.00016211944,0.00024033547,0.0010242973,0.000077278615,0.0007945796],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027067788,0.00061863754,0.00053623307,0.0017713353,0.0008248539,0.00007956463,0.0014675538,0.00066836487,0.0007591033],"category_scores_gemma":[0.000082761275,0.00072373415,0.00025606403,0.0005578468,0.0013758903,0.000045005945,0.0016865565,0.0012466989,0.00009629338],"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":[0.0010087747,0.0003394268,0.004034754,0.0003118129,0.0009431765,0.00033940488,0.0008363096,0.00004430862,0.0035953538,0.0028349548,0.9804349,0.0052768136],"study_design_scores_gemma":[0.0020045713,0.0005350367,0.0012513018,0.00017221677,0.00007844231,0.00002765684,0.002020724,0.00020841986,0.00016292908,0.000048897396,0.9927388,0.00075103744],"about_ca_topic_score_codex":0.00091979036,"about_ca_topic_score_gemma":0.003920951,"teacher_disagreement_score":0.012303857,"about_ca_system_score_codex":0.00016522486,"about_ca_system_score_gemma":0.0005794979,"threshold_uncertainty_score":0.9995214},"labels":[],"label_agreement":null},{"id":"W7071363533","doi":"","title":"Solar capacity has increased 99% since last quarter - NationofChange","year":2016,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Government (linguistics); Gloom; Solar energy; Climate change","score_opus":0.01143070436931767,"score_gpt":0.2368356162804327,"score_spread":0.22540491191111503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071363533","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":[0.00026948503,0.00014679477,0.0236275,0.00041506963,0.00029300657,0.00029738812,0.0001869233,0.00012631483,0.9746375],"genre_scores_gemma":[0.009986496,0.00016216646,0.008566533,0.0013226696,0.0015255528,0.00003936011,0.0009131667,0.00038383622,0.9771002],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990126,0.00006595122,0.00020687653,0.00028296578,0.00017995597,0.00025165454],"domain_scores_gemma":[0.99910927,0.00001250107,0.00021265606,0.0005239476,0.000050355546,0.00009125511],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00014362871,0.00028567173,0.00020290974,0.00010401847,0.00006285253,0.000049545666,0.0002766317,0.0005138193,0.002709551],"category_scores_gemma":[0.00008764126,0.00021775704,0.00009565449,0.000036784102,0.00012944003,0.0000026272503,0.00010482552,0.00014748226,0.0010057795],"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":[0.0000091720385,0.000027039536,0.00035307754,0.00006730226,0.00008433632,8.145104e-7,0.00002718345,3.3177656e-7,0.0043042535,0.0002670035,0.99395216,0.00090730086],"study_design_scores_gemma":[0.00037370023,0.0000790547,0.00007150515,0.000052278567,0.000016382364,0.000011068525,0.000009161184,0.000045850393,0.0026275078,0.000014174305,0.99636775,0.00033154883],"about_ca_topic_score_codex":0.0002227827,"about_ca_topic_score_gemma":0.00089862646,"teacher_disagreement_score":0.015060965,"about_ca_system_score_codex":0.000019177294,"about_ca_system_score_gemma":0.000073290415,"threshold_uncertainty_score":0.9997721},"labels":[],"label_agreement":null},{"id":"W7071370442","doi":"","title":"Sol-gel derived silicate-based titanium-containing bioactive glass for enamel remineralization","year":2020,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Enamel paint; Bioactive glass; Tooth enamel; Remineralisation","score_opus":0.01327713530237525,"score_gpt":0.25571961636531176,"score_spread":0.2424424810629365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071370442","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9369594,0.00037277897,0.0007699952,0.00016984806,0.0016769428,0.003074893,0.0027094556,0.00041954088,0.053847164],"genre_scores_gemma":[0.9507106,0.00010854279,0.014347302,0.0013135357,0.00020017609,0.000407605,0.029541887,0.00034335363,0.003026987],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99665284,0.00021552145,0.00092981325,0.0010719323,0.00046474143,0.00066515873],"domain_scores_gemma":[0.99718153,0.00013107403,0.0009963316,0.00073360826,0.0006561674,0.00030128952],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004946477,0.00083153247,0.0006795574,0.0002021798,0.00071523245,0.00010647656,0.0006689736,0.0012162542,0.000049934446],"category_scores_gemma":[0.0022422094,0.0009153912,0.00047038868,0.00025433904,0.00006448151,0.0000424493,0.0001260184,0.00086571777,0.00006297959],"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":[0.0016482343,0.00011865202,0.000079725105,0.0008163168,0.00039501424,0.0000072561566,0.000025118106,0.00065895787,0.9759004,0.004310693,0.00009402147,0.0159456],"study_design_scores_gemma":[0.0022886738,0.0010713573,0.00030881463,0.00025565928,0.0003195925,0.000009685205,0.00027654937,0.004906873,0.8560338,0.0008845375,0.13220055,0.0014438966],"about_ca_topic_score_codex":0.0000545929,"about_ca_topic_score_gemma":0.0003307023,"teacher_disagreement_score":0.13210654,"about_ca_system_score_codex":0.00027371122,"about_ca_system_score_gemma":0.00017097831,"threshold_uncertainty_score":0.9993297},"labels":[],"label_agreement":null},{"id":"W7071376556","doi":"","title":"SentemQC - software","year":2024,"lang":"en","type":"other","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Communitech","funders":"","keywords":"","score_opus":0.00447576596127469,"score_gpt":0.2527968859757016,"score_spread":0.2483211200144269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071376556","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":[0.0000046611044,0.0019027338,0.0047802343,0.000054595494,0.00045984003,0.00010297525,0.00004018898,0.00020492454,0.9924498],"genre_scores_gemma":[0.00003309299,0.00013756123,0.012490619,0.00035697088,0.00062670204,0.000006871699,0.00035548117,0.00046187354,0.98553085],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994599,0.00001090948,0.00010849156,0.00019884059,0.00009066544,0.00013118035],"domain_scores_gemma":[0.99953496,0.0000015645317,0.000052237214,0.0003620207,0.000008785693,0.000040427443],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000044307588,0.00017323597,0.00011025607,0.00006369661,0.0000078661615,0.000026009187,0.0001502566,0.00032610496,0.002649561],"category_scores_gemma":[0.000043497665,0.00014230149,0.000080745915,0.000034328063,0.000028572542,2.2212618e-7,0.00015406279,0.00013904482,0.0034571465],"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":[0.0000012148436,0.000004555315,0.000045055553,0.0001893724,0.00006954447,0.0000022411878,0.0000048290694,0.0000010768391,0.00010634672,0.00009617558,0.9985882,0.00089139544],"study_design_scores_gemma":[0.00005419999,0.00003402268,0.000002080833,0.00006420006,0.000017180857,0.000013191922,0.0000065531694,0.000019280295,0.00021374408,0.0000244115,0.9993706,0.00018053735],"about_ca_topic_score_codex":0.00002846857,"about_ca_topic_score_gemma":0.000046712703,"teacher_disagreement_score":0.0077103847,"about_ca_system_score_codex":0.000003904217,"about_ca_system_score_gemma":0.000026885913,"threshold_uncertainty_score":0.99826217},"labels":[],"label_agreement":null},{"id":"W7071388201","doi":"","title":"STRUCTURE DETERMINATION FROM POWDER DIFFRACTION DATA OF SOME MOISTURE-SENSITIVE NETWORK COORDINATION COMPOUNDS","year":2013,"lang":"en","type":"article","venue":"NPARC","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Monoclinic crystal system; Orthorhombic crystal system; Powder diffraction; Ionic conductivity; Lithium (medication); Crystal structure; Adduct; Coordination complex; Electrolyte","score_opus":0.009501399360283744,"score_gpt":0.25213091999566173,"score_spread":0.242629520635378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071388201","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98969656,0.000036560796,0.0067235515,0.00034381225,0.0002709246,0.0002223032,0.00012658894,0.000015866359,0.002563842],"genre_scores_gemma":[0.982824,0.000011158926,0.012590037,0.00021978134,0.00039500534,0.0000033777724,0.0037792136,0.000012926541,0.00016450108],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9992756,0.00006051877,0.00020484463,0.00018912504,0.0001439196,0.00012594329],"domain_scores_gemma":[0.9991288,0.0000322225,0.000210618,0.00046498308,0.00013025104,0.0000330819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008679188,0.00010835235,0.000116943425,0.000024019891,0.00005766038,0.000028826733,0.00020436903,0.00014790261,0.00008632856],"category_scores_gemma":[0.000121875666,0.00010075286,0.000025491785,0.000051406678,0.000047980357,0.00002998909,0.00016855569,0.000121772995,0.000009682529],"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":[0.000028924653,0.000025720998,0.0048046648,0.000020166353,0.000051009123,3.3259306e-7,0.000094580995,0.00032670939,0.95993656,0.00020340366,0.02104897,0.01345895],"study_design_scores_gemma":[0.0017795586,0.00041750405,0.47364435,0.000080358666,0.00013827618,0.000026269829,0.0002953358,0.26370734,0.22255088,0.015127031,0.021442203,0.0007908887],"about_ca_topic_score_codex":0.00008890213,"about_ca_topic_score_gemma":0.000036982176,"teacher_disagreement_score":0.7373857,"about_ca_system_score_codex":0.000013755884,"about_ca_system_score_gemma":0.000019772238,"threshold_uncertainty_score":0.41085827},"labels":[],"label_agreement":null},{"id":"W7071391185","doi":"","title":"Soil processes at well drained sites, Devon Island, Nunavut, Canada","year":2002,"lang":"en","type":"article","venue":"Florence Research (University of Florence)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Hydrology (agriculture); Soil water; Erosion; Surface runoff; Vegetation (pathology)","score_opus":0.022625042060418907,"score_gpt":0.24710975890977036,"score_spread":0.22448471684935145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071391185","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9668474,0.000615016,0.0009419511,0.0009782307,0.00010462143,0.0002802045,0.00016937238,0.000021013424,0.030042145],"genre_scores_gemma":[0.9844818,0.0008678522,0.0012134,0.0000486411,0.00009733145,0.0000010512279,0.0003670027,0.000013545555,0.012909389],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99802345,0.0001293796,0.0001672834,0.00036268614,0.0007476559,0.0005695387],"domain_scores_gemma":[0.998561,0.00008505127,0.00011573467,0.00047504986,0.00054562115,0.00021749242],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000414327,0.00016999176,0.00019655204,0.0001340659,0.00046378467,0.000023973205,0.00083485775,0.00015147038,0.0030792113],"category_scores_gemma":[0.0004977142,0.00018539834,0.000057869285,0.0005368344,0.00047276603,0.000022775683,0.00056043634,0.0003180822,0.00012504563],"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":[0.0004462589,0.00028135206,0.08450596,0.001347418,0.00022654142,0.00020758405,0.0055290908,0.002027408,0.052329578,0.00020270783,0.8446763,0.008219756],"study_design_scores_gemma":[0.0036020426,0.002185969,0.016305767,0.0003687569,0.0000703159,0.00012865619,0.008864049,0.06900496,0.047430888,0.00019515464,0.8500686,0.0017747876],"about_ca_topic_score_codex":0.045516934,"about_ca_topic_score_gemma":0.70763373,"teacher_disagreement_score":0.6621168,"about_ca_system_score_codex":0.00013342654,"about_ca_system_score_gemma":0.0006086827,"threshold_uncertainty_score":0.9978321},"labels":[],"label_agreement":null},{"id":"W7071411188","doi":"","title":"Selfie feedback on Instagram: The impact on self-esteem and appearance satisfaction","year":2019,"lang":"en","type":"article","venue":"Scholarship at UWindsor (University of Windsor)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Windsor","funders":"University of Windsor","keywords":"Nucleofection; Gestational period; Liquation; TSG101; Dysgeusia; Diafiltration; Emperipolesis; Triacetin; Demotion","score_opus":0.005688799670189853,"score_gpt":0.22054633620220238,"score_spread":0.21485753653201253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071411188","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9936898,0.000068181704,0.000021454189,0.0003182314,0.00009382197,0.0003021276,0.00002061876,0.00003043971,0.0054553314],"genre_scores_gemma":[0.99814355,0.00007496673,0.0003255668,0.00021257425,0.00004461578,2.981545e-7,0.000025957197,0.000018512774,0.0011539528],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99888074,0.00014514607,0.00012970231,0.00031163424,0.00027667673,0.0002560731],"domain_scores_gemma":[0.999033,0.00004132221,0.0001986833,0.0005559659,0.00006934965,0.000101690624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039066983,0.00021581474,0.00019406443,0.00008562972,0.00027929642,0.000032835556,0.00031586539,0.00023825928,0.00008108039],"category_scores_gemma":[0.00005103046,0.000181302,0.0001357345,0.00015117641,0.00010393405,0.00003288611,0.00018573704,0.00043072924,0.00019514572],"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":[0.001443173,0.0001688107,0.94892037,0.00013851549,0.00029157885,0.000004821059,0.0013822747,0.0022967781,0.039354738,0.0003913692,0.00088755786,0.0047200136],"study_design_scores_gemma":[0.0012834062,0.0011553034,0.9887061,0.00006632025,0.000029000703,0.000020221843,0.0004224093,0.0004281702,0.002949376,0.00004272416,0.004644999,0.00025195317],"about_ca_topic_score_codex":0.00007525162,"about_ca_topic_score_gemma":0.00005795366,"teacher_disagreement_score":0.039785746,"about_ca_system_score_codex":0.000060351744,"about_ca_system_score_gemma":0.00005085139,"threshold_uncertainty_score":0.7393281},"labels":[],"label_agreement":null},{"id":"W7071411905","doi":"","title":"School-Level Perspectives of the Ontario School Nutrition Program","year":2022,"lang":"en","type":"article","venue":"Scholarship@Western (Western University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Fieldnotes; Program evaluation; Research program; Public health; Work (physics); School district","score_opus":0.04753577355398585,"score_gpt":0.300144336296473,"score_spread":0.25260856274248716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071411905","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9979333,0.000120971585,0.00012818782,0.00017933981,0.00017668065,0.0006185226,0.000056529596,0.00004516934,0.0007412579],"genre_scores_gemma":[0.98306483,0.000023094392,0.00034916095,0.00016728802,0.00007698294,0.000011810912,0.00007706207,0.000027555265,0.016202204],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983741,0.00030900232,0.00024013768,0.00036434017,0.00041009093,0.00030231156],"domain_scores_gemma":[0.99870884,0.000014338023,0.00028169082,0.0006855242,0.00015696703,0.00015261049],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000294312,0.00022052857,0.00019036068,0.00016594667,0.00043988947,0.0000758135,0.0010113196,0.00012896903,0.00016201896],"category_scores_gemma":[0.000105928724,0.00021933243,0.00020981175,0.00034190633,0.00014416841,0.00005440645,0.0011111861,0.0008249263,0.00002124366],"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":[0.00016802746,0.00033665737,0.9914172,0.000049413273,0.00008605481,0.000007983009,0.00076112995,0.00016784384,0.006753846,0.00003350442,0.000015815336,0.00020250841],"study_design_scores_gemma":[0.001299373,0.00058295246,0.94442964,0.00004994019,0.0000610396,0.000054476604,0.0026748618,0.0000010066692,0.0064204065,0.000030477373,0.04408921,0.0003066416],"about_ca_topic_score_codex":0.000068990346,"about_ca_topic_score_gemma":0.0074235266,"teacher_disagreement_score":0.0469876,"about_ca_system_score_codex":0.0003461181,"about_ca_system_score_gemma":0.00036028557,"threshold_uncertainty_score":0.89441174},"labels":[],"label_agreement":null},{"id":"W7071435624","doi":"","title":"Talking to the President of the Early Onset Dementia Alberta Foundation","year":2019,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Foundation (evidence); Dementia; Primary care; MEDLINE","score_opus":0.0032875529764307783,"score_gpt":0.18907406947036184,"score_spread":0.18578651649393108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071435624","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":[0.0016163175,0.00010437955,0.0000062326712,0.00025341223,0.00033485764,0.00071573665,0.000047449772,0.00001250081,0.99690914],"genre_scores_gemma":[0.021983167,0.000045527948,0.00053303875,0.00038053247,0.000096547665,0.000013834682,0.00015682884,0.00006442668,0.9767261],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987434,0.000089299545,0.00051174656,0.00013265994,0.0003402553,0.00018262064],"domain_scores_gemma":[0.9983881,0.00004442347,0.0007323969,0.0006896546,0.00010530916,0.00004012084],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00023361985,0.00021655785,0.0001999298,0.000032747284,0.00006240093,0.000040464787,0.000597819,0.00024239744,0.02100202],"category_scores_gemma":[0.00026434465,0.00014945089,0.00014542181,0.000009489085,0.00007852354,3.785597e-8,0.00030051288,0.00016868992,0.0025916898],"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":[0.000036827307,0.000012027107,0.0001588246,0.00022152551,0.00011166449,1.1639225e-7,0.00017582133,0.0010752201,0.0000070998026,0.000013138766,0.9976167,0.0005710529],"study_design_scores_gemma":[0.00021178905,0.00013681072,0.00042939372,0.0001520634,0.000065896704,0.0000138933765,0.000040292147,0.00003812159,0.000162488,0.0000013468269,0.9985815,0.00016635055],"about_ca_topic_score_codex":0.0068581128,"about_ca_topic_score_gemma":0.0044217026,"teacher_disagreement_score":0.02036685,"about_ca_system_score_codex":0.000013005779,"about_ca_system_score_gemma":0.00004298408,"threshold_uncertainty_score":0.9997553},"labels":[],"label_agreement":null},{"id":"W7071447567","doi":"","title":"Three Essays on The Interface of Sales and Operations Management","year":2021,"lang":"en","type":"article","venue":"Scholars Commons (Wilfrid Laurier University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Supply chain; Exploit; Profit (economics); Supply chain management; Channel (broadcasting); Flow network; Maximization; Profit maximization; Attractiveness; Service quality; Process (computing)","score_opus":0.009617067950331997,"score_gpt":0.2367739197408827,"score_spread":0.2271568517905507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071447567","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94212675,0.00022054055,0.0063168197,0.0014756256,0.00006658005,0.00014640369,0.000036729172,0.000013436127,0.04959711],"genre_scores_gemma":[0.9933934,0.00014820018,0.0034610336,0.00018164117,0.000013607107,7.595389e-7,0.000052747764,0.000009467865,0.002739127],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99946374,0.00008398849,0.00009847984,0.00014955903,0.00009632231,0.00010791855],"domain_scores_gemma":[0.9993841,0.00002528464,0.000038360176,0.0004381623,0.0000724766,0.00004160849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014055075,0.000094800176,0.00008509355,0.000062462044,0.00020499842,0.00003946439,0.00025256645,0.00005857768,0.00003280164],"category_scores_gemma":[0.00005980963,0.00008317462,0.000045288365,0.00017002583,0.00011848614,0.000011125772,0.00041189467,0.0001843092,0.0000079189285],"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":[0.00038346223,0.00060737075,0.07070319,0.0002693056,0.001474829,0.00014676027,0.0010560468,0.0084221875,0.07486136,0.8102246,0.022405267,0.009445599],"study_design_scores_gemma":[0.0020795164,0.00050004915,0.022565674,0.00020817736,0.00024308535,0.000049603237,0.004385275,0.0024704307,0.102432534,0.00085238356,0.86351454,0.00069873786],"about_ca_topic_score_codex":0.000006980675,"about_ca_topic_score_gemma":0.00034445382,"teacher_disagreement_score":0.8411093,"about_ca_system_score_codex":0.000011442309,"about_ca_system_score_gemma":0.000032935055,"threshold_uncertainty_score":0.33917627},"labels":[],"label_agreement":null},{"id":"W7071462704","doi":"","title":"1st Record of the Great Auk (Pinguinus-Impennis) from Labrador","year":2008,"lang":"en","type":"article","venue":"Smithsonian Digital Repository (Smithsonian Institution)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Period (music); Feature (linguistics); Population; Field (mathematics)","score_opus":0.0064212233559301545,"score_gpt":0.20048887876684338,"score_spread":0.19406765541091323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071462704","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95030683,0.0002526543,0.0010958207,0.00015186757,0.0012556517,0.00038571964,0.00015469818,0.00008624651,0.046310537],"genre_scores_gemma":[0.99081415,0.000043839435,0.0018430586,0.00026771295,0.0005842027,0.000023490817,0.000004488531,0.000051396644,0.0063676867],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99759394,0.000089165136,0.0007897393,0.00054421695,0.00052509736,0.00045785878],"domain_scores_gemma":[0.99774176,0.000039100414,0.00051727204,0.0012780309,0.00021589638,0.00020796603],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0000997896,0.0004189319,0.00037014426,0.000087072636,0.0006340793,0.00014367203,0.00086495985,0.0003077602,0.000032263113],"category_scores_gemma":[0.0004877753,0.00033776078,0.00036889678,0.00030430825,0.00093400764,0.00008243862,0.00038962965,0.00037673634,0.00007868129],"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":[0.00010490259,0.00010098092,0.98862594,0.000041160176,0.00013755607,0.000036282214,0.00030016978,0.00016746494,0.00049469236,0.00032587993,0.0030085708,0.0066564195],"study_design_scores_gemma":[0.0008662246,0.00028766828,0.9421202,0.00016848938,0.00004909127,0.00046415065,0.00010116136,0.0002462939,0.026380826,0.00008325984,0.028683292,0.00054936646],"about_ca_topic_score_codex":0.00031977697,"about_ca_topic_score_gemma":0.0001269463,"teacher_disagreement_score":0.046505746,"about_ca_system_score_codex":0.00011405396,"about_ca_system_score_gemma":0.00058003806,"threshold_uncertainty_score":0.99990743},"labels":[],"label_agreement":null},{"id":"W7071488870","doi":"","title":"Subcontract \"FIDOR-Action\" : feasibility study of the FIDOR concept in the receiving environment around different industrial sites and of its potential to act on the odour reduction.","year":2011,"lang":"en","type":"report","venue":"Open Repository and Bibliography (University of Liège)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"GDG Environnement","funders":"","keywords":"Annoyance; Control (management); Property (philosophy); Continuation; Air pollution","score_opus":0.08233732989730388,"score_gpt":0.2764026096630077,"score_spread":0.19406527976570384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071488870","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9965514,0.00021542942,0.000009507743,0.0001359011,0.00021365803,0.0015876931,0.00004094951,0.0000017855954,0.001243703],"genre_scores_gemma":[0.99823105,0.0013063601,0.000022388325,0.000009732804,0.00008580861,0.0000033923436,0.000013631812,0.0000070192414,0.00032060192],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99831647,0.0005392461,0.00032099383,0.0003096257,0.00039361877,0.0001200637],"domain_scores_gemma":[0.9984944,0.00006721678,0.00072326045,0.00057408056,0.00009717267,0.00004389822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008906567,0.00019167492,0.00032875,0.00064016075,0.00029710197,0.00005234964,0.0006479747,0.00022939358,0.000018580147],"category_scores_gemma":[0.0000091561815,0.00012043024,0.00016226336,0.0008183027,0.0002551819,0.000023850676,0.0005139653,0.00037809985,1.0327262e-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":[0.00094854966,0.0010210223,0.9683418,0.00013486983,0.0005398041,0.0000050896247,0.0025851978,0.00009218057,0.021139644,0.0000063605394,0.004719556,0.00046590628],"study_design_scores_gemma":[0.00078606367,0.0014448637,0.98424715,0.0001448997,0.00022520192,0.000032810134,0.008356877,0.000008599429,0.0038622546,0.0000054082166,0.00071757473,0.0001682998],"about_ca_topic_score_codex":0.0018109453,"about_ca_topic_score_gemma":0.00007233414,"teacher_disagreement_score":0.01727739,"about_ca_system_score_codex":0.0000148563895,"about_ca_system_score_gemma":0.00007030973,"threshold_uncertainty_score":0.49110025},"labels":[],"label_agreement":null},{"id":"W7071493105","doi":"","title":"Terijoki Suomen Riviera","year":2012,"lang":"fi","type":"other","venue":"Doria (University of Helsinki)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Riviera; Quarter (Canadian coin); Line (geometry); Work (physics)","score_opus":0.005587193254959319,"score_gpt":0.19804577182688168,"score_spread":0.19245857857192236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071493105","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":[0.023900347,0.0027123652,0.004817382,0.00048341847,0.0025008006,0.0006019253,0.00041156533,0.000060234735,0.964512],"genre_scores_gemma":[0.08734778,0.0016732354,0.008818327,0.00012749317,0.0010472134,4.233056e-7,0.0011314348,0.00019103085,0.89966303],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99838555,0.0001356607,0.00025343683,0.00039693067,0.00029562687,0.0005328038],"domain_scores_gemma":[0.9981625,0.000019484756,0.00063940784,0.0008474209,0.00010915481,0.00022204538],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00027304326,0.00043726552,0.0005583692,0.00020246228,0.00018010943,0.000022893915,0.0007961796,0.00097242725,0.010125478],"category_scores_gemma":[0.00003823078,0.000545055,0.00030910777,0.00015905962,0.00036989004,0.000015475724,0.00059970265,0.00039942947,0.0010521689],"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":[0.0014425442,0.0018446815,0.029696345,0.0065728,0.006202327,0.00012926845,0.011370161,0.00020969781,0.07016991,0.0067501487,0.64127547,0.22433667],"study_design_scores_gemma":[0.0009205009,0.00025975113,0.0014169732,0.00014260181,0.00020615228,0.000017341321,0.00049113366,0.00017599402,0.00042818746,0.000017947174,0.99536407,0.0005593667],"about_ca_topic_score_codex":0.0002598142,"about_ca_topic_score_gemma":0.00013326888,"teacher_disagreement_score":0.3540886,"about_ca_system_score_codex":0.00005633943,"about_ca_system_score_gemma":0.00014638292,"threshold_uncertainty_score":0.99972564},"labels":[],"label_agreement":null},{"id":"W7071497900","doi":"","title":"SHORT CUTS #100 - The Best Of The Imposter (So Far) pt.2","year":2016,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Shot (pellet); Character (mathematics); Cult; Paradise; Documentary film; Front (military)","score_opus":0.004480521380375534,"score_gpt":0.20574744576503953,"score_spread":0.201266924384664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071497900","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":[0.00033342477,0.0003969295,0.0000026088085,0.00031120388,0.00030997832,0.0004516987,0.00017860383,0.000023586294,0.997992],"genre_scores_gemma":[0.0046957233,0.0004800536,0.00023777483,0.00050067564,0.00019157444,0.000012197238,0.00010947796,0.000093258364,0.9936793],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985196,0.00009489228,0.0006277421,0.00014746512,0.00036236164,0.00024796725],"domain_scores_gemma":[0.9983253,0.000044805467,0.000619778,0.0008184234,0.0001378605,0.000053857715],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00024351706,0.00030780013,0.0002799005,0.000031839772,0.0000880463,0.000032763444,0.00075706095,0.00043079752,0.039522894],"category_scores_gemma":[0.00015457385,0.00017326714,0.00024448946,0.000006783254,0.00036553488,3.2368543e-8,0.00032202454,0.0002440237,0.0020351526],"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":[0.00004128451,0.000020375443,0.00005617676,0.0002288059,0.000094124436,5.852777e-7,0.000071617746,0.00004079892,0.000024385843,0.000014871578,0.9954651,0.0039418885],"study_design_scores_gemma":[0.00023406331,0.00013082851,0.0000434328,0.00018053984,0.000056104655,0.000058683727,0.00005993977,0.0000083939085,0.00031333417,0.0000019152062,0.99869424,0.00021853624],"about_ca_topic_score_codex":0.0006270049,"about_ca_topic_score_gemma":0.00046368802,"teacher_disagreement_score":0.03748774,"about_ca_system_score_codex":0.00001446623,"about_ca_system_score_gemma":0.000050948376,"threshold_uncertainty_score":0.99874187},"labels":[],"label_agreement":null},{"id":"W7071536225","doi":"","title":"Spatial heterogeneity and temporal variations in Echinococcus multilocularis infections in wild&#13;\\nhosts in a North American urban setting","year":2014,"lang":"en","type":"article","venue":"CINECA IRIS Institutial research information system (University of Pisa)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Echinococcus multilocularis; Feces; Vulpes; Rodent; Cestoda; Intermediate host; Host (biology); Abundance (ecology); Parasite hosting; Mammal","score_opus":0.013338709565552241,"score_gpt":0.2721363577825091,"score_spread":0.2587976482169569,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071536225","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9557512,0.000006765258,0.04197551,0.000100225996,0.00005300498,0.00047568747,0.00003517894,0.000016630836,0.0015858255],"genre_scores_gemma":[0.99797785,0.000014955851,0.0017760306,0.000017637522,0.000035010253,0.000004224171,0.000162694,0.0000054895163,0.0000061131373],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99835354,0.00038499737,0.00043021335,0.00018707756,0.00033014844,0.00031402064],"domain_scores_gemma":[0.9990849,0.00006458478,0.00025225288,0.00029833734,0.00019213384,0.00010777564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014705413,0.00013427524,0.00024951698,0.000848829,0.00021145168,0.00004207171,0.00024546692,0.00012706884,0.0000022092875],"category_scores_gemma":[0.00066570396,0.0001622811,0.000045477478,0.0008464179,0.000273294,0.00012964185,0.00028353272,0.00039866572,0.000010720351],"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":[0.00009113171,0.000043666758,0.9885342,0.00019021331,0.000012124239,0.0000024874005,0.0022020522,0.0028143488,0.00014392697,0.00020290907,0.0000622748,0.0057006627],"study_design_scores_gemma":[0.0018709966,0.00025605122,0.87998265,0.000096507356,0.0000044008643,0.000012695301,0.001854627,0.11215436,0.00007828848,0.0000022666165,0.0035138424,0.0001732925],"about_ca_topic_score_codex":0.02176018,"about_ca_topic_score_gemma":0.1308957,"teacher_disagreement_score":0.109340005,"about_ca_system_score_codex":0.00017485232,"about_ca_system_score_gemma":0.00020802298,"threshold_uncertainty_score":0.984754},"labels":[],"label_agreement":null},{"id":"W7071542607","doi":"","title":"Trustees Approve Faculty Recommendation to Streamline Graduation Requirement, Improve Affordability","year":2014,"lang":"en","type":"article","venue":"Digital Commons - Winthrop University (Winthrop University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Graduation (instrument); Resolution (logic); Degree (music); Crunch; Career Pathways; Quarter (Canadian coin)","score_opus":0.01370828514145419,"score_gpt":0.2389196938788315,"score_spread":0.2252114087373773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071542607","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6573442,0.0000045044826,0.20860134,0.0036363627,0.0004230609,0.00094729225,0.000885796,0.00026159422,0.1278958],"genre_scores_gemma":[0.9883587,0.0000133779085,0.0027248857,0.00014632876,0.00010210445,4.3132155e-7,0.002707977,0.00003081876,0.0059153736],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998232,0.00016995906,0.00027873256,0.000635035,0.00024453318,0.00043975675],"domain_scores_gemma":[0.9983638,0.000057268102,0.00025787114,0.00072271633,0.00030296214,0.0002953652],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024564707,0.00036333522,0.0003050782,0.00030649285,0.0005305918,0.0001211235,0.0006393598,0.00022772556,0.00009579588],"category_scores_gemma":[0.000316562,0.0004327031,0.00021375025,0.00047055163,0.0003798291,0.00016933595,0.0008014664,0.00027050803,0.00008240487],"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":[0.008209374,0.006273613,0.15778764,0.0008993432,0.0027218435,0.00009120707,0.007283716,0.008685057,0.06729227,0.06590475,0.11237804,0.5624732],"study_design_scores_gemma":[0.001976013,0.0016273404,0.0028726254,0.00003282691,0.00009718114,0.000008263722,0.004872083,0.0031863928,0.0056563737,0.00010549361,0.97873265,0.0008327358],"about_ca_topic_score_codex":0.0002036257,"about_ca_topic_score_gemma":0.0004837888,"teacher_disagreement_score":0.86635464,"about_ca_system_score_codex":0.0003140572,"about_ca_system_score_gemma":0.000093053626,"threshold_uncertainty_score":0.9998125},"labels":[],"label_agreement":null},{"id":"W7071596846","doi":"","title":"Summary of the Doha Climate Change Conference: 26 November-8 December 2012","year":2012,"lang":"en","type":"report","venue":"UvA-DARE (University of Amsterdam)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"Bundesministerium für Umwelt, Naturschutz, nukleare Sicherheit und Verbraucherschutz; Udenrigsministeriet; New Zealand Foreign Affairs and Trade; Bundesministerium für Wirtschaftliche Zusammenarbeit und Entwicklung; Ministry of Environment; Fox Chase Cancer Center; U.S. Department of State; Ministry of Economy, Trade and Industry; European Commission; Australian Government; Bundesamt für Umwelt; Government of Canada","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Liquation; Diafiltration; Triacetin; Emperipolesis; Durvalumab","score_opus":0.03506088713513812,"score_gpt":0.2549098514482098,"score_spread":0.21984896431307172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071596846","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27978867,0.00629109,0.0009896585,0.0010331689,0.0042031496,0.002094895,0.0028562506,0.00011574348,0.70262736],"genre_scores_gemma":[0.92659235,0.009162651,0.0030835588,0.00032389042,0.0011662245,0.000004035037,0.0019527393,0.0001794031,0.057535138],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981812,0.000115161885,0.00034813824,0.00031226772,0.0006125914,0.00043061978],"domain_scores_gemma":[0.99715847,0.000024947632,0.0010826027,0.0010197444,0.0005926981,0.0001215459],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00048191665,0.0003516545,0.0005507734,0.000110688285,0.00016028747,0.000013225874,0.00089055835,0.00071048,0.00059558544],"category_scores_gemma":[0.00006790909,0.0003289705,0.00041569886,0.0001443898,0.00036481553,0.000029012639,0.0013669286,0.0004392159,0.00003888507],"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":[0.0009724602,0.0010169358,0.2081616,0.013341959,0.002605192,0.00004302079,0.008043241,0.00006221454,0.018590575,0.00083506556,0.6538722,0.09245551],"study_design_scores_gemma":[0.0008095594,0.0002245594,0.046283547,0.00074936415,0.00042745392,0.00006909562,0.0008576281,0.00008285442,0.0010514185,0.000012923879,0.9487826,0.00064895296],"about_ca_topic_score_codex":0.0004981524,"about_ca_topic_score_gemma":0.0009839353,"teacher_disagreement_score":0.6468037,"about_ca_system_score_codex":0.00006134724,"about_ca_system_score_gemma":0.0003916014,"threshold_uncertainty_score":0.99991626},"labels":[],"label_agreement":null},{"id":"W7071601567","doi":"","title":"Tras las huellas vascas en Terranova y Labrador / Henrike Knörr.","year":2000,"lang":"es","type":"article","venue":"Euskal Memoria Digitala (Sancho el Sabio Foundation)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Meaning (existential); Period (music)","score_opus":0.004889021436241712,"score_gpt":0.25733988130975244,"score_spread":0.25245085987351074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071601567","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81876904,0.0008045543,0.00071123696,0.001886145,0.0025986324,0.0010838704,0.00027394245,0.00022837114,0.17364421],"genre_scores_gemma":[0.96541613,0.0009143018,0.0022253192,0.0010907031,0.0038709624,0.000058451853,0.002972509,0.00019789628,0.02325373],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952877,0.00028471122,0.0014063707,0.0011238777,0.0007925195,0.0011047886],"domain_scores_gemma":[0.9971744,0.00017368728,0.0004881588,0.0014617427,0.00026784124,0.00043421],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00058351515,0.0010085818,0.0007493107,0.0001867999,0.00047539469,0.001219123,0.0010283495,0.0007887575,0.0041253557],"category_scores_gemma":[0.00059379294,0.0010449261,0.00050632324,0.0005528006,0.000482131,0.00018216013,0.00028744395,0.00069979846,0.0051359963],"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":[0.0009244101,0.0013267813,0.023612471,0.0009093802,0.001382799,0.000051008275,0.0016660724,0.00081585813,0.013094513,0.004797046,0.014532079,0.93688756],"study_design_scores_gemma":[0.0024712048,0.00081792637,0.023821399,0.00017568651,0.0001715139,0.0001472133,0.0001503807,0.00074083236,0.0055289264,0.00045396877,0.9641155,0.0014054435],"about_ca_topic_score_codex":0.000067402296,"about_ca_topic_score_gemma":0.000048565,"teacher_disagreement_score":0.9495834,"about_ca_system_score_codex":0.00018190393,"about_ca_system_score_gemma":0.00039629004,"threshold_uncertainty_score":0.9998177},"labels":[],"label_agreement":null},{"id":"W7071828285","doi":"","title":"THE TYPE Ia SUPERNOVA RATE IN RADIO AND INFRARED GALAXIES FROM THE CANADA-FRANCE-HAWAII TELESCOPE SUPERNOVA LEGACY SURVEY","year":2010,"lang":"en","type":"article","venue":"Oxford University Research Archive (ORA) (University of Oxford)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Supernova; Infrared; Galaxy; Star formation; Luminous infrared galaxy; Radio galaxy; Telescope; Infrared telescope","score_opus":0.012689153463183564,"score_gpt":0.24030008884371262,"score_spread":0.22761093538052907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071828285","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99113804,0.00011488613,0.00020926095,0.00111418,0.00013449181,0.00035011137,0.00030566257,0.0000108822005,0.0066224635],"genre_scores_gemma":[0.99181914,0.0020602879,0.0011056634,0.000034154626,0.000054572283,1.8574048e-7,0.00041044116,0.000019040084,0.0044964943],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99772733,0.00071341847,0.00016648535,0.00037986398,0.00043183344,0.0005810817],"domain_scores_gemma":[0.99783206,0.0007699897,0.00011052414,0.0007410061,0.0003601572,0.00018623412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014200001,0.00020822315,0.00024828446,0.00014624072,0.0010593423,0.00007645253,0.0015256598,0.00014824464,0.00007199276],"category_scores_gemma":[0.00062314514,0.00018584897,0.0000712186,0.0005451371,0.0013364122,0.000065831046,0.0012112723,0.0010542118,0.0000025397899],"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":[0.0013829309,0.000059202288,0.96537447,0.000039157545,0.00018465712,0.00006473907,0.0013898344,0.000055183726,0.0099928845,0.0013883081,0.016987205,0.0030814444],"study_design_scores_gemma":[0.0008478746,0.00015512081,0.6591313,0.0000175908,0.00000960751,0.0000049340047,0.0044662636,0.00058560574,0.00013934019,0.00009392988,0.33437875,0.0001696788],"about_ca_topic_score_codex":0.24707036,"about_ca_topic_score_gemma":0.83386964,"teacher_disagreement_score":0.5867993,"about_ca_system_score_codex":0.00006447719,"about_ca_system_score_gemma":0.0010725424,"threshold_uncertainty_score":0.8147712},"labels":[],"label_agreement":null},{"id":"W7073617332","doi":"","title":"Crença de auto-eficácia e validação da Chronic Pain Self-Efficacy Scale.","year":2004,"lang":"pt","type":"article","venue":"Americanae (AECID Library)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"McGill Pain Questionnaire; Confidence interval; Population; Rating scale","score_opus":0.005619575066446135,"score_gpt":0.23519354267520803,"score_spread":0.2295739676087619,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7073617332","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9487569,0.0042365105,0.030158484,0.0055343783,0.000670366,0.0009987872,0.00014738698,0.0006499025,0.008847292],"genre_scores_gemma":[0.9599348,0.0015523793,0.02587213,0.0057681594,0.001188134,0.00005056929,0.0008250468,0.0002716851,0.0045371433],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956619,0.000573813,0.0009348754,0.0009262586,0.0004665414,0.0014366021],"domain_scores_gemma":[0.9969647,0.00012300335,0.00065702957,0.0015219686,0.00006037795,0.000672908],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053442403,0.00083315274,0.0007068633,0.00021501747,0.00034624842,0.00020094102,0.0013047833,0.0005688605,0.0007252622],"category_scores_gemma":[0.00030156467,0.00088752166,0.00047696097,0.00082536606,0.00047018647,0.000081240745,0.0006838284,0.00082184095,0.00038494615],"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":[0.0005763526,0.0054148086,0.37335408,0.001992548,0.0035459325,0.0004423286,0.007745773,0.036177933,0.050787725,0.0025613212,0.24302773,0.27437344],"study_design_scores_gemma":[0.0078034597,0.008378579,0.25388527,0.0006391646,0.00068148936,0.00018567289,0.0011331723,0.022873523,0.04451916,0.00027189046,0.65472955,0.004899091],"about_ca_topic_score_codex":0.0021359224,"about_ca_topic_score_gemma":0.00003381288,"teacher_disagreement_score":0.4117018,"about_ca_system_score_codex":0.00027170812,"about_ca_system_score_gemma":0.0019530181,"threshold_uncertainty_score":0.9993575},"labels":[],"label_agreement":null},{"id":"W7074109393","doi":"","title":"Comprehensive Evaluations of Student Performance Estimation via Machine Learning","year":2023,"lang":"en","type":"article","venue":"RePEc: Research Papers in Economics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Perceptron; Decision tree; Support vector machine; Artificial neural network; Random forest; Linear discriminant analysis; Naive Bayes classifier; Convolutional neural network","score_opus":0.02798206735404996,"score_gpt":0.3619625918947426,"score_spread":0.33398052454069266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7074109393","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99190795,0.000038392605,0.00008429268,0.000062683874,0.0000613242,0.00023525151,0.00000639999,0.000018849212,0.0075848624],"genre_scores_gemma":[0.99577934,0.0017978539,0.0012118889,0.00002119674,0.000036562073,0.000039202703,0.00026933174,0.00002042362,0.00082423456],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878466,0.00015441478,0.00035625906,0.00021035963,0.00020163709,0.00029266495],"domain_scores_gemma":[0.9992798,0.000110730456,0.00011413342,0.00031485304,0.00012808626,0.000052372772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009340287,0.00010393782,0.0001502068,0.00022085579,0.0001294401,0.000018598326,0.00023044445,0.00009484708,0.000025941921],"category_scores_gemma":[0.00028452364,0.000110485365,0.000048492642,0.00019044524,0.00012055476,0.000008979976,0.0002586054,0.00031907955,0.000026398171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000584791,0.000061048755,0.14618644,0.00013382928,0.00005469212,0.000001222425,0.00043338697,0.5804666,0.02433168,0.00003459937,0.000029109278,0.24820887],"study_design_scores_gemma":[0.00053624157,0.0002893068,0.19356193,0.00003022319,0.0000041513244,0.0000061200803,0.00031754965,0.79433507,0.0044318596,0.000024850275,0.006322061,0.0001406378],"about_ca_topic_score_codex":0.000010350821,"about_ca_topic_score_gemma":0.000013420342,"teacher_disagreement_score":0.24806823,"about_ca_system_score_codex":0.00006169368,"about_ca_system_score_gemma":0.00008539322,"threshold_uncertainty_score":0.45054623},"labels":[],"label_agreement":null},{"id":"W7074673918","doi":"","title":"Knowing how to acquire for Bern","year":2025,"lang":"en","type":"book-chapter","venue":"Industrias Culturais (Universidade de Coimbra)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Prestige; Enlightenment; Reputation; State (computer science); Humanism; The Republic; Quarter (Canadian coin)","score_opus":0.01941121638168339,"score_gpt":0.2510736073028385,"score_spread":0.23166239092115512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7074673918","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":[0.0007957748,0.0003696816,0.0073235496,0.015690157,0.0007047395,0.0017601737,0.0009895758,0.00014108754,0.97222525],"genre_scores_gemma":[0.002467763,0.000053184347,0.004027975,0.001168865,0.0007423186,0.000021475553,0.0017142228,0.0000757131,0.9897285],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99842024,0.000028934144,0.00025954927,0.0005703391,0.00023593428,0.00048501338],"domain_scores_gemma":[0.9985228,0.00006379941,0.00027722408,0.0006097511,0.00027828934,0.00024810727],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00019954007,0.00051939825,0.00043695825,0.00023927943,0.0002549634,0.00014460336,0.0007291975,0.0015745085,0.00011450894],"category_scores_gemma":[0.00044653338,0.0005596355,0.00037580956,0.000097856355,0.00008705344,0.000015914682,0.00043278115,0.00059352524,0.00004183233],"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":[0.00021775597,0.000020735024,0.000030754785,0.00020549948,0.00066706754,0.000022435537,0.00030438512,0.0002031522,0.009761175,0.024791308,0.92509365,0.03868205],"study_design_scores_gemma":[0.0008650719,0.00028374576,0.00012799061,0.00028070828,0.00017733588,0.00002215541,0.0002218725,0.00012632653,0.0019753666,0.00011048026,0.9951557,0.0006532781],"about_ca_topic_score_codex":0.000018808874,"about_ca_topic_score_gemma":0.000045250228,"teacher_disagreement_score":0.07006199,"about_ca_system_score_codex":0.00017819465,"about_ca_system_score_gemma":0.00029620377,"threshold_uncertainty_score":0.99972165},"labels":[],"label_agreement":null},{"id":"W7083201329","doi":"10.7202/1120132ar","title":"Sexe, genre et droit international du sport","year":2025,"lang":"fr","type":"article","venue":"Revue québécoise de droit international","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"International law; International relations; Customary international law; Human rights","score_opus":0.004719014716444542,"score_gpt":0.25437939005685556,"score_spread":0.24966037534041102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7083201329","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20724322,0.001832314,0.03256553,0.03011284,0.010600325,0.000424902,0.0004836716,0.00008666546,0.71665055],"genre_scores_gemma":[0.77916574,0.0029936694,0.0075767436,0.008528104,0.0025180911,0.000061766186,0.0027289812,0.000072539784,0.19635434],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99783343,0.000059750804,0.00076241925,0.0005366878,0.00036247898,0.00044524684],"domain_scores_gemma":[0.9984698,0.000056737856,0.00036030667,0.0005304536,0.00042328984,0.00015939432],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00063146924,0.0003544628,0.00030673083,0.0002665839,0.00009877754,0.00018879188,0.0011516149,0.00047309184,0.0007938865],"category_scores_gemma":[0.00055287994,0.00048112578,0.00033499944,0.00017392955,0.00015578086,0.000043425312,0.0003874359,0.00056855014,0.00021560673],"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":[0.0003799409,0.000694323,0.09445211,0.0004638364,0.0017415385,0.00019027863,0.00071687606,0.006240475,0.0035798927,0.80742794,0.047659468,0.036453318],"study_design_scores_gemma":[0.000900221,0.00008835756,0.013783643,0.0003686082,0.00008686203,0.00049063674,0.000108097105,0.031825416,0.001102474,0.0038720632,0.9469345,0.0004390738],"about_ca_topic_score_codex":0.00067534536,"about_ca_topic_score_gemma":0.00075269304,"teacher_disagreement_score":0.89927506,"about_ca_system_score_codex":0.0005730956,"about_ca_system_score_gemma":0.0006700931,"threshold_uncertainty_score":0.999764},"labels":[],"label_agreement":null},{"id":"W7084160227","doi":"10.64628/aam.rm6c9c4xx","title":"Nova Scotia’s new pre-primary class gives kids a head start through play-based learning","year":2019,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Mount Saint Vincent University","funders":"","keywords":"Class (philosophy); Head start; Head (geology); Task (project management); Focus (optics)","score_opus":0.011039953519338633,"score_gpt":0.26880004689454884,"score_spread":0.2577600933752102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7084160227","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8521258,0.00022027266,0.033133652,0.0008088643,0.00036484314,0.0003968111,0.0000074620943,0.00010934856,0.1128329],"genre_scores_gemma":[0.9003295,0.00002734869,0.05458807,0.0044035683,0.00029969137,0.0000036882639,0.000586444,0.00006590411,0.039695825],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985746,0.00007108513,0.0003366713,0.00036256728,0.00025646077,0.00039860097],"domain_scores_gemma":[0.9991025,0.000032170723,0.0001468337,0.0005401067,0.00006132069,0.00011707609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019428213,0.00026542792,0.00024383455,0.00004506243,0.00006127186,0.00006359758,0.00031019375,0.0002400551,0.0008300643],"category_scores_gemma":[0.00010841938,0.000236994,0.00013483517,0.00010804285,0.0000662928,0.0000146024295,0.00018669755,0.00035911013,0.00057636533],"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":[0.0008851564,0.00026986655,0.38158354,0.00069047767,0.0003385261,0.000007283523,0.0013481159,0.06697058,0.43232235,0.0012537986,0.10561615,0.00871417],"study_design_scores_gemma":[0.0035435054,0.002011766,0.02851048,0.00011210941,0.000042020427,0.00002595096,0.00020173627,0.011534481,0.07200293,0.00007515647,0.88089514,0.0010446946],"about_ca_topic_score_codex":0.00042146997,"about_ca_topic_score_gemma":0.00014934511,"teacher_disagreement_score":0.775279,"about_ca_system_score_codex":0.000029603794,"about_ca_system_score_gemma":0.0003150045,"threshold_uncertainty_score":0.9664335},"labels":[],"label_agreement":null},{"id":"W7084582566","doi":"10.1386/jcs_00124_5","title":"Pacita Abad","year":2025,"lang":"en","type":"article","venue":"Journal of Curatorial Studies","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University","funders":"","keywords":"Natural (archaeology); Context (archaeology); Exposition (narrative)","score_opus":0.01127605096772747,"score_gpt":0.3516388569143813,"score_spread":0.3403628059466538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7084582566","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9218719,0.025269734,0.0043738885,0.002807994,0.023973811,0.00019326423,0.000007428793,0.000016388834,0.021485578],"genre_scores_gemma":[0.99176675,0.0016050545,0.0022421023,0.0003485574,0.0031826003,0.0000016224815,0.0000017110772,0.0000073438396,0.00084423175],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993539,0.000037662732,0.000332076,0.000051979,0.00012812675,0.00009625937],"domain_scores_gemma":[0.99926955,0.000031141408,0.00023043554,0.000102222,0.00034056298,0.000026069558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003196518,0.00008166207,0.0001781917,0.000044505836,0.00007168417,0.000017058583,0.00013744301,0.000068324654,0.0000031773266],"category_scores_gemma":[0.0012049242,0.000059995207,0.00009082272,0.000080360056,0.000054719425,0.000004832227,0.00008587543,0.00014060106,0.000002551766],"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":[0.000840078,0.0001452107,0.028900739,0.00026993308,0.0029891322,0.000018786408,0.0012426913,0.00043578964,0.08835041,0.00821026,0.8556916,0.012905357],"study_design_scores_gemma":[0.0011837035,0.0005043724,0.0014112807,0.00009143629,0.00008417987,0.000024871824,0.0008001987,0.000015189203,0.019329188,0.0011913122,0.9752237,0.00014057072],"about_ca_topic_score_codex":7.0652175e-7,"about_ca_topic_score_gemma":0.0000024105634,"teacher_disagreement_score":0.119532086,"about_ca_system_score_codex":0.000016079566,"about_ca_system_score_gemma":0.00007667212,"threshold_uncertainty_score":0.24465336},"labels":[],"label_agreement":null},{"id":"W7085840220","doi":"10.6084/m9.figshare.28001726.v2","title":"<b>Oli, M. K., Kenney, A. J., Boonstra, R., Boutin, S., Murray, D. L., Jung, T. S., Hines, J. E., and Charles J. Krebs, C. J. (2025). Data from: </b>Demographic mechanisms of snowshoe hare population cycles in Yukon, Canada. Figshare Repository. DOI: 10.6084/m9.figshare.28001726.To be published in Journal of Animal Ecology.","year":2025,"lang":"en","type":"dataset","venue":"Figshare","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Data file; Elasticity (physics); Population; File format; Matrix (chemical analysis); Data Matrix","score_opus":0.01774513161087635,"score_gpt":0.26793094963581476,"score_spread":0.2501858180249384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7085840220","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013001777,0.0032067918,5.9853863e-7,0.00030194593,0.0002734081,0.0009374133,0.9938458,0.000020051268,0.00011381806],"genre_scores_gemma":[0.006321027,0.00015476428,0.0003953707,0.00059997675,0.00033645632,0.0001607529,0.9918112,0.000060226874,0.00016023264],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943755,0.00038910532,0.0023628215,0.0012214099,0.00083170494,0.0008194258],"domain_scores_gemma":[0.99403054,0.00031135647,0.0023502372,0.0021855398,0.00075078895,0.0003715214],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00039929769,0.00094429834,0.0014327848,0.0009999638,0.00016557032,0.0002864665,0.0030072278,0.0014310209,0.06815896],"category_scores_gemma":[0.01219424,0.0009782384,0.00020583217,0.00077019515,0.000030660296,0.0001300713,0.0027131245,0.0014203021,0.000020594101],"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":[0.00019894046,0.00012063188,0.0009605826,0.0019221181,0.00016519749,0.000118026845,0.000024110333,0.00009252362,0.0002409672,5.987845e-7,0.9959885,0.00016783434],"study_design_scores_gemma":[0.001402413,0.00042663675,0.03150503,0.009745749,0.00014452488,0.00009146319,0.00008249012,0.00058060576,0.00089519966,0.000014580826,0.95401746,0.0010938235],"about_ca_topic_score_codex":0.024081638,"about_ca_topic_score_gemma":0.24759683,"teacher_disagreement_score":0.22351518,"about_ca_system_score_codex":0.00020155915,"about_ca_system_score_gemma":0.0018979637,"threshold_uncertainty_score":0.99986535},"labels":[],"label_agreement":null},{"id":"W7086971055","doi":"10.18739/a2222r79t","title":"Waterfowl Population Status Reports (2021-2025)","year":2025,"lang":"en","type":"dataset","venue":"California Digital Library","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Waterfowl; Wildlife; Population; Wildlife conservation; Service (business); Wildlife management","score_opus":0.0031493888154829498,"score_gpt":0.21563413987086247,"score_spread":0.2124847510553795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7086971055","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005928165,0.00039748993,0.00006255386,0.00008619456,0.00050126587,0.0002624233,0.9926999,0.000051791176,0.0053455597],"genre_scores_gemma":[0.00076890935,0.00024995487,0.0002534248,0.0005758493,0.00043682384,0.000022934053,0.9919622,0.000032264736,0.005697649],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998092,0.000039305498,0.00067965727,0.0005099063,0.00023936965,0.00043978315],"domain_scores_gemma":[0.9983454,0.000020994645,0.00035425377,0.0010678843,0.0000317127,0.00017975758],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000065187,0.00042003638,0.00033376756,0.00014718408,0.000087922635,0.0004400085,0.00032662964,0.00057956146,0.00043588394],"category_scores_gemma":[0.0003059405,0.00038232145,0.00019239228,0.00015277963,0.000057540317,0.000036090452,0.0008138082,0.00037286157,0.00021674426],"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":[0.000037544825,0.00004248924,0.0046245717,0.00024281102,0.0000667172,0.000044966873,0.0000012702833,0.00002814117,0.000007679382,0.000001949477,0.9930777,0.0018241496],"study_design_scores_gemma":[0.00012781449,0.0000663831,0.000113962866,0.00009220603,0.000036275756,0.0000369316,0.0000044440753,0.000030329196,0.0002410981,0.00007749198,0.9987542,0.00041888314],"about_ca_topic_score_codex":0.000018080895,"about_ca_topic_score_gemma":0.0000016997199,"teacher_disagreement_score":0.00567647,"about_ca_system_score_codex":0.000021595966,"about_ca_system_score_gemma":0.00024740308,"threshold_uncertainty_score":0.99986285},"labels":[],"label_agreement":null},{"id":"W7094941570","doi":"10.5683/sp3/h0aelt","title":"CLARE: Cognitive Load Assessment in REaltime with Multimodal Data","year":2023,"lang":"","type":"dataset","venue":"Borealis","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Cognitive load; Cognition; Gaze; Cognitive Assessment System; Data collection","score_opus":0.02107162470859449,"score_gpt":0.33184978211190486,"score_spread":0.3107781574033104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7094941570","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003017917,0.0001993681,0.00084960856,0.00037714912,0.00020320065,0.0012855359,0.99454767,0.000042357602,0.0021933503],"genre_scores_gemma":[0.0015220676,0.0027796738,0.0030831185,0.00055724446,0.00051071134,0.00012916815,0.9909654,0.00014646715,0.00030611054],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9944438,0.00045261893,0.0012497165,0.001689463,0.0011005135,0.0010638968],"domain_scores_gemma":[0.9941916,0.00021548558,0.00094173977,0.0038957696,0.0004296542,0.00032578493],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0016425109,0.0010273395,0.00094325986,0.00023897074,0.00020441017,0.00021112185,0.0023670946,0.0013124053,0.00006145114],"category_scores_gemma":[0.0012953585,0.0009506289,0.00012255152,0.000464556,0.0004161866,0.000028980734,0.0029015895,0.0019379053,0.00023481538],"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":[0.000529146,0.00036035295,0.0013070722,0.00057768135,0.0005311027,0.0002519062,0.0001054784,0.00015967617,0.000040633546,0.0000069111375,0.99108064,0.0050494093],"study_design_scores_gemma":[0.00377075,0.0014089482,0.009913979,0.00097024883,0.00042373885,0.00008503002,0.0005019963,0.017875295,0.00005642655,0.0000074351133,0.9635513,0.0014348935],"about_ca_topic_score_codex":0.07758338,"about_ca_topic_score_gemma":0.120032996,"teacher_disagreement_score":0.042449612,"about_ca_system_score_codex":0.00023601744,"about_ca_system_score_gemma":0.0026991742,"threshold_uncertainty_score":0.9999841},"labels":[],"label_agreement":null},{"id":"W7095154267","doi":"","title":"Criteria","year":2010,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Term (time); Service (business); Subject (documents); Government (linguistics); Work (physics)","score_opus":0.0037223849919705274,"score_gpt":0.27169326288031087,"score_spread":0.26797087788834034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095154267","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8143448,0.0000052599767,0.002871908,0.000195158,0.0002851941,0.00003566615,0.0000013706626,0.00002037711,0.18224026],"genre_scores_gemma":[0.9713194,0.0000022338977,0.022988454,0.0006058173,0.00018610866,0.000002209548,0.000030083005,0.00000642604,0.0048592943],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.999747,0.000005290757,0.00006494042,0.000065045206,0.0000369037,0.000080836144],"domain_scores_gemma":[0.9997286,0.0000021500737,0.000015850985,0.00020082651,0.000020174488,0.000032364063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007273376,0.00004458482,0.000029470286,0.000009816868,0.000025001533,0.000015002129,0.00009375534,0.00006217956,0.00058167934],"category_scores_gemma":[0.000082328865,0.00003706091,0.000020962654,0.000016594819,0.000023914938,7.8555337e-7,0.00005107761,0.000079355596,0.00009298387],"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":[0.000004473501,0.000008443458,0.0034711624,0.0000039528213,0.0000045532984,2.1490322e-7,0.000013973232,0.0000016924097,0.9723461,0.0014442825,0.020444855,0.0022562821],"study_design_scores_gemma":[0.00016160213,0.000069198926,0.005714685,7.1331505e-7,0.000002274623,0.000027011665,0.0000126018285,0.00093992177,0.18248118,0.00009277416,0.8103768,0.000121228455],"about_ca_topic_score_codex":0.0000039629012,"about_ca_topic_score_gemma":0.000020256135,"teacher_disagreement_score":0.78993195,"about_ca_system_score_codex":4.539156e-7,"about_ca_system_score_gemma":0.000010379304,"threshold_uncertainty_score":0.6368981},"labels":[],"label_agreement":null},{"id":"W7095368055","doi":"","title":"Review of the Weighting Methodology for the Canadian Community Health Survey","year":2015,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sample (material); Community health; Weighting; Public health; Survey sampling; Survey data collection; Survey methodology","score_opus":0.2021307153959405,"score_gpt":0.4084479534218202,"score_spread":0.20631723802587973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095368055","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15656807,0.3100515,0.23318626,0.12497954,0.0063298433,0.015283032,0.0016902259,0.0001274989,0.15178405],"genre_scores_gemma":[0.7693693,0.0074364473,0.08854079,0.12977016,0.00028158005,0.000082730185,0.001010816,0.00006429576,0.0034438754],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980347,0.0014717563,0.00022608036,0.0000510366,0.00006116304,0.00015523958],"domain_scores_gemma":[0.9987253,0.0003145177,0.00016314664,0.00053496443,0.00018390911,0.000078170604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008599469,0.00006313037,0.00013026367,0.00000985829,0.00025997427,0.0000058684327,0.00042756766,0.000054416672,0.0000072488274],"category_scores_gemma":[0.0044111866,0.00003235109,0.000055929664,0.00007243303,0.00007893923,8.6008475e-7,0.00011939731,0.00017148249,0.0000011636105],"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":[0.000059273272,0.000054295735,0.077149615,0.0042509227,0.00024267401,5.122737e-8,0.001056857,0.00024203424,0.00051603914,0.0047981283,0.8886444,0.022985714],"study_design_scores_gemma":[0.00050981157,0.00045277856,0.04006388,0.000474062,0.00003302322,0.000022148943,0.0003646207,0.0010945501,0.002809434,0.00025960163,0.95370513,0.0002109268],"about_ca_topic_score_codex":0.36657357,"about_ca_topic_score_gemma":0.8593019,"teacher_disagreement_score":0.61280125,"about_ca_system_score_codex":0.00002245858,"about_ca_system_score_gemma":0.00062729366,"threshold_uncertainty_score":0.63764447},"labels":[],"label_agreement":null},{"id":"W7095469748","doi":"","title":"The Structural Influences of Patients in French, Canadian and American Hospitals","year":2007,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"MEDLINE; Government (linguistics); Health care; Public health","score_opus":0.001726503922595811,"score_gpt":0.22814148706435772,"score_spread":0.2264149831417619,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095469748","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99747646,0.000040095827,0.000010259715,0.000058191872,0.000028328162,0.000057742316,0.0000043794166,0.0000012823864,0.002323263],"genre_scores_gemma":[0.9991183,0.000022703776,0.0006564889,0.000109629356,0.000009496979,6.145734e-7,0.000013216599,0.000002499841,0.00006704738],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99959624,0.0000100210855,0.00014149974,0.000057284975,0.00005403223,0.00014093064],"domain_scores_gemma":[0.9997444,0.0000146479415,0.00006049575,0.000096626296,0.000031686584,0.000052131065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001289973,0.000048400972,0.000049744795,0.000029099716,0.00004007328,0.000009041043,0.000089594745,0.000026909123,0.0000033352637],"category_scores_gemma":[0.00011156554,0.000031538013,0.000010273926,0.000058457437,0.0001435584,0.0000017459597,0.000029953968,0.000041990013,3.9864452e-7],"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":[0.0000032547043,0.000001042048,0.9836948,0.0000023456776,0.0000041943567,1.5574041e-7,0.000089377594,0.000009368741,0.00016751884,0.000040891682,0.0000896586,0.01589741],"study_design_scores_gemma":[0.00008664627,0.00009235609,0.9958338,0.0000015098911,9.351106e-7,5.195958e-7,0.00015935535,0.000063946085,0.0010057698,0.000025214198,0.0026829292,0.000046985362],"about_ca_topic_score_codex":0.07022357,"about_ca_topic_score_gemma":0.35738692,"teacher_disagreement_score":0.28716335,"about_ca_system_score_codex":0.0000065953577,"about_ca_system_score_gemma":0.000029535611,"threshold_uncertainty_score":0.93596786},"labels":[],"label_agreement":null},{"id":"W7095769137","doi":"","title":"Canada-US Security Relations","year":2004,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Ballistic missile; Aerospace; Government (linguistics); National security; Joint (building); Control (management)","score_opus":0.002294319134625334,"score_gpt":0.20559912577888742,"score_spread":0.2033048066442621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095769137","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79827166,0.0000604816,0.0060220324,0.0018461169,0.00013671193,0.00009655043,0.000015406416,0.000023420733,0.19352761],"genre_scores_gemma":[0.9929032,0.0000052336172,0.0034902026,0.001268535,0.000056275378,0.0000023480338,0.00007858157,0.0000058127894,0.0021898493],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99963224,0.0000075310713,0.00009778104,0.00007787842,0.000077903074,0.000106656466],"domain_scores_gemma":[0.9997203,0.0000028202448,0.000027534128,0.00017391721,0.000028466666,0.000047009074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000044753117,0.000057054447,0.000039216175,0.000009108354,0.000057726862,0.000008034701,0.00008159507,0.000051300718,0.00008004214],"category_scores_gemma":[0.00007245786,0.000052113235,0.000019914018,0.000036911584,0.00001668484,0.0000011935498,0.000041854353,0.00006903759,0.000022579474],"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":[0.00008846703,0.00029772168,0.15877418,0.00012484005,0.00032134322,0.000029516674,0.00074347435,0.089768626,0.052610476,0.11061965,0.5837786,0.0028430875],"study_design_scores_gemma":[0.0006330339,0.000098639626,0.016711054,0.000005804075,0.000009478039,0.000035331504,0.000058802812,0.0006232931,0.027521005,0.00091370917,0.9531234,0.00026643317],"about_ca_topic_score_codex":0.17110254,"about_ca_topic_score_gemma":0.5487448,"teacher_disagreement_score":0.37764224,"about_ca_system_score_codex":0.000028290362,"about_ca_system_score_gemma":0.00041195648,"threshold_uncertainty_score":0.83441716},"labels":[],"label_agreement":null},{"id":"W7097495227","doi":"","title":"The Use of Internal and External Functional Domains to Improve Transmembrane Protein Topology Prediction","year":2008,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Transmembrane protein; Transmembrane domain; Membrane topology; Topology (electrical circuits); Domain (mathematical analysis); Membrane protein; Protein structure","score_opus":0.011449055085927699,"score_gpt":0.22524008708401466,"score_spread":0.21379103199808697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097495227","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8862303,0.00003431265,0.11276028,0.00021618532,0.000109400666,0.00019101641,0.000012197538,0.00000776415,0.00043852907],"genre_scores_gemma":[0.98752344,0.000043844782,0.008103689,0.0002917057,0.00012655,0.000020836576,0.000010982435,0.000007766035,0.0038711955],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999438,0.00003188835,0.00019901879,0.00011593568,0.00009883911,0.00011630975],"domain_scores_gemma":[0.9996723,0.000018963852,0.00005490363,0.00015255269,0.00005119243,0.000050113693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000097993754,0.000076566685,0.00006750691,0.000021910357,0.00010319125,0.000011558698,0.00007558813,0.000068866,0.000023271106],"category_scores_gemma":[0.000086126325,0.000051884832,0.00003563298,0.000026834452,0.00013813897,0.000005181773,0.00005611014,0.00008365167,0.0000022218978],"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":[0.00047327264,0.00003050385,0.009509067,0.000019889007,0.0000475601,0.0000012557798,0.00012799648,0.0004516558,0.9818357,0.0007102529,0.0012023647,0.0055904794],"study_design_scores_gemma":[0.002343697,0.003156416,0.098681994,0.000038154234,0.000029473846,0.0006754313,0.00010317228,0.01009258,0.6702911,0.00016936456,0.21405767,0.0003608918],"about_ca_topic_score_codex":0.000047274312,"about_ca_topic_score_gemma":0.000033080967,"teacher_disagreement_score":0.31154454,"about_ca_system_score_codex":0.0000050723606,"about_ca_system_score_gemma":0.00002604354,"threshold_uncertainty_score":0.2115802},"labels":[],"label_agreement":null},{"id":"W7098164046","doi":"","title":"FACULTÉ DES ÉTUDES SUPÉRIEURES","year":2014,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Term (time); Context (archaeology)","score_opus":0.009465576246912955,"score_gpt":0.26046707514694845,"score_spread":0.2510014989000355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7098164046","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77427614,0.000042706546,0.025744721,0.00010058907,0.00004924045,0.000057822686,0.0000020912757,0.000045211327,0.19968146],"genre_scores_gemma":[0.98192924,0.000013643826,0.014224859,0.0005724779,0.00010298196,0.0000034281463,0.00004699215,0.000010406801,0.0030959595],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995552,0.00002535933,0.000105110055,0.000104278704,0.00006996852,0.00014011045],"domain_scores_gemma":[0.9996822,0.000008661771,0.000028243989,0.00019698894,0.00003681173,0.000047076213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012724016,0.00008335598,0.000061083716,0.000014999081,0.00006174675,0.00002349833,0.00013603696,0.00006407279,0.000077422395],"category_scores_gemma":[0.00020640568,0.00006520933,0.000039071536,0.000029905232,0.000064347245,0.0000018350197,0.00007795071,0.000048072052,0.000060669816],"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":[0.00011702449,0.00019960332,0.1474338,0.0002864356,0.00022100357,0.0000018459099,0.0010938738,0.002815921,0.6181359,0.078725316,0.06793544,0.08303381],"study_design_scores_gemma":[0.00046423567,0.00043346322,0.02309022,0.000009200695,0.000011425923,0.000026164511,0.0001364362,0.0035735634,0.118990764,0.00043266546,0.852493,0.0003388504],"about_ca_topic_score_codex":0.000011073418,"about_ca_topic_score_gemma":0.000040394112,"teacher_disagreement_score":0.7845576,"about_ca_system_score_codex":0.0000026200455,"about_ca_system_score_gemma":0.000009844006,"threshold_uncertainty_score":0.26591593},"labels":[],"label_agreement":null},{"id":"W7098770417","doi":"","title":"Canadian Acute Respiratory Illness and Flu Scale (CARIFS)","year":2016,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Malay; Intraclass correlation; Respiratory illness; Reliability (semiconductor); Asthma; Severity of illness; Scale (ratio); Concordance","score_opus":0.0034718705965036765,"score_gpt":0.223599696670242,"score_spread":0.22012782607373832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7098770417","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9628951,0.00010711984,0.0016450495,0.00093149766,0.00012218923,0.00010329374,0.00004010986,0.00002019578,0.03413545],"genre_scores_gemma":[0.9879577,0.00004826645,0.0014054326,0.0019794183,0.000106084735,0.000006826364,0.000015787373,0.000015309417,0.008465143],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99946296,0.000021196813,0.00010919996,0.00014456679,0.00005862796,0.00020345082],"domain_scores_gemma":[0.9995057,0.0000062005806,0.000027142418,0.00024668837,0.00003618677,0.00017805483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011727527,0.00008979495,0.00006764709,0.000039462368,0.000092456285,0.00001848202,0.00011172207,0.000116721036,0.0001200603],"category_scores_gemma":[0.000042045172,0.000059320857,0.00002291813,0.000031510514,0.000060728955,0.0000036239533,0.00006865609,0.000042842734,0.000044211414],"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":[0.000060345315,0.000020946905,0.16267069,0.000044485158,0.00017232247,0.000012505106,0.00027439097,0.0000055965465,0.62162113,0.0016314427,0.08781339,0.12567274],"study_design_scores_gemma":[0.0005899466,0.00016481023,0.013823815,0.000014694125,0.000017169117,0.000031488937,0.000058596343,0.00005919804,0.09302439,0.00006147379,0.89182436,0.00033006663],"about_ca_topic_score_codex":0.0028672796,"about_ca_topic_score_gemma":0.043021806,"teacher_disagreement_score":0.804011,"about_ca_system_score_codex":0.000018397794,"about_ca_system_score_gemma":0.00010409037,"threshold_uncertainty_score":0.9744406},"labels":[],"label_agreement":null},{"id":"W7099462896","doi":"","title":"ice: remote guidance ultrasound to diagnose injury on the","year":2011,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Space medicine; Space (punctuation); Aviation medicine; Aerospace; Passions; Space exploration; Duration (music)","score_opus":0.015352685699516028,"score_gpt":0.26529227988424503,"score_spread":0.249939594184729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099462896","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7668112,0.000035477777,0.0048473235,0.0008406631,0.00016498152,0.0002494197,0.000008392241,0.000033300177,0.22700927],"genre_scores_gemma":[0.97435653,0.0000402316,0.011424036,0.008636828,0.00013016837,0.000008433411,0.000011888703,0.000017095806,0.005374796],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993746,0.00004240864,0.00014999797,0.00015343032,0.00010324566,0.00017629217],"domain_scores_gemma":[0.9992541,0.000041581883,0.000047770896,0.0005518957,0.000040150902,0.000064467946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024606468,0.00011275629,0.000064009415,0.000018836598,0.00007680171,0.000018128796,0.00031320323,0.00007400747,0.00033690853],"category_scores_gemma":[0.00071870233,0.00007194026,0.000043793065,0.000070139315,0.000040037965,0.0000016617764,0.000097620155,0.00010509558,0.000307424],"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":[0.0004914317,0.0002329675,0.020138962,0.000048796956,0.00015626864,0.000006406975,0.0022981113,0.00011917956,0.3303434,0.018653259,0.590711,0.036800224],"study_design_scores_gemma":[0.0001959138,0.0010106969,0.016280962,0.000028781977,0.000011057595,0.000016218602,0.00016435156,0.00019672247,0.5475585,0.00042438146,0.43372577,0.00038666622],"about_ca_topic_score_codex":0.000058912145,"about_ca_topic_score_gemma":0.00002867726,"teacher_disagreement_score":0.22163448,"about_ca_system_score_codex":0.0000063665634,"about_ca_system_score_gemma":0.000016725864,"threshold_uncertainty_score":0.3951416},"labels":[],"label_agreement":null},{"id":"W7100489758","doi":"","title":"1 Rensselaer Working Papers in Economics","year":2009,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Investment (military); Exchange rate; Consumption (sociology); Ambiguity; Investment goods; Quarter (Canadian coin); Econometric model; Real gross domestic product; National accounts","score_opus":0.005101010121118638,"score_gpt":0.22123059992450464,"score_spread":0.216129589803386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100489758","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5489378,0.00003597526,0.00012730777,0.00036907307,0.000053689248,0.000052495423,3.1564778e-7,0.000013046201,0.45041028],"genre_scores_gemma":[0.990641,0.00009720875,0.0058272295,0.0016146685,0.00006384911,0.0000010947432,0.0000217015,0.0000052766854,0.001727971],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995919,0.00001027924,0.00013554451,0.00010507061,0.000023809718,0.0001333897],"domain_scores_gemma":[0.99976397,0.0000037467148,0.000032722142,0.00016708743,0.0000045722945,0.000027893871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009011857,0.0000690429,0.000060730643,0.000026732618,0.000017908422,0.00001392587,0.00009067046,0.000076469805,0.000032069674],"category_scores_gemma":[0.000030534084,0.00006486251,0.000028478664,0.00003260497,0.000011585617,8.737218e-7,0.000023707631,0.00006886636,0.000011813614],"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":[0.00019861638,0.00018441454,0.14064507,0.000019114988,0.00006079073,0.000008422516,0.0005016968,0.01709401,0.14686559,0.01951583,0.006512516,0.6683939],"study_design_scores_gemma":[0.0010459797,0.00036682392,0.06657947,0.000020885223,0.00000659892,0.000028608452,0.00014669045,0.007479762,0.018039418,0.00045041277,0.9052973,0.0005380743],"about_ca_topic_score_codex":0.000002940211,"about_ca_topic_score_gemma":0.000032343858,"teacher_disagreement_score":0.89878476,"about_ca_system_score_codex":0.000008433751,"about_ca_system_score_gemma":0.000013900085,"threshold_uncertainty_score":0.26450163},"labels":[],"label_agreement":null},{"id":"W7100556838","doi":"","title":"Research Article Knowledge of Signs and Symptoms of Heart Attack and Stroke among Singapore Residents","year":2016,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Stroke (engine); Signs and symptoms; Population; Heart disease; Vital signs; Heart rate","score_opus":0.021963458193271338,"score_gpt":0.3410886975748948,"score_spread":0.31912523938162346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100556838","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99566185,0.0002169982,0.0002300766,0.00009995704,0.000014835803,0.00009790202,0.000008170862,0.000004655623,0.0036655383],"genre_scores_gemma":[0.99606824,0.000042869593,0.00086088415,0.000011415501,0.000024135026,0.000002210522,0.0000025490654,0.000008738038,0.0029789612],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992631,0.00008706181,0.0002186444,0.00014064614,0.00011974562,0.00017079493],"domain_scores_gemma":[0.999417,0.00007594165,0.000058766625,0.00022857278,0.0001484804,0.0000712056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005242772,0.00007088707,0.00011914134,0.00005824228,0.000040813815,0.000009606907,0.000084086896,0.00009078573,0.000026472853],"category_scores_gemma":[0.00024485463,0.000048396552,0.000023485456,0.000059934762,0.0003921762,0.0000066341413,0.0002250894,0.000065703294,0.000003683128],"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":[0.000032541982,0.000028947708,0.35939756,0.0000675737,0.000021123866,1.3533315e-7,0.0001309634,0.000002226564,0.63657254,0.00012021317,0.0011168229,0.0025093462],"study_design_scores_gemma":[0.00090226455,0.0013302102,0.3648911,0.000109456654,0.000010707129,0.00000776967,0.00026091293,0.00041133518,0.6296165,0.000061893435,0.0022628794,0.00013493907],"about_ca_topic_score_codex":0.00004337253,"about_ca_topic_score_gemma":0.00004854025,"teacher_disagreement_score":0.0069560218,"about_ca_system_score_codex":0.0000045739816,"about_ca_system_score_gemma":0.000029384059,"threshold_uncertainty_score":0.19735542},"labels":[],"label_agreement":null},{"id":"W7100764032","doi":"","title":"Foxe/Baffin Sector of the Laurentide Ice","year":2014,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Promotion (chess); Work (physics)","score_opus":0.004139318647969007,"score_gpt":0.21426849037843407,"score_spread":0.21012917173046505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100764032","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8982471,0.00003854374,0.009648253,0.00034648567,0.00021496278,0.00010610491,0.0000038277417,0.000014974251,0.091379724],"genre_scores_gemma":[0.9922909,0.000003913233,0.0026030154,0.00048847887,0.00008792971,0.000001914982,0.000011897128,0.000007660534,0.0045042913],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995739,0.000041592728,0.00012989118,0.00007620852,0.0000850709,0.00009335529],"domain_scores_gemma":[0.9995157,0.000011996052,0.00007568464,0.0003415779,0.00003407154,0.000020953737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014379862,0.0000627075,0.00006193994,0.000009599682,0.00003128947,0.0000067233045,0.00021824712,0.00005773635,0.000093108785],"category_scores_gemma":[0.0001940792,0.000039259743,0.000060949744,0.00004361857,0.00003958311,9.641359e-7,0.00012100157,0.00005862345,0.000014484981],"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":[0.000051767827,0.000109512126,0.08965238,0.00019303548,0.00011429881,1.213793e-7,0.0002578585,0.0013425397,0.7942575,0.0120391,0.08946334,0.012518546],"study_design_scores_gemma":[0.00046185096,0.00016508358,0.027273878,0.000014924554,0.000017163515,0.0000074088302,0.00003891228,0.0044825063,0.47209197,0.00014327266,0.49512318,0.0001798391],"about_ca_topic_score_codex":0.000020992868,"about_ca_topic_score_gemma":0.000084921296,"teacher_disagreement_score":0.40565985,"about_ca_system_score_codex":0.0000020239413,"about_ca_system_score_gemma":0.000015332605,"threshold_uncertainty_score":0.16009659},"labels":[],"label_agreement":null},{"id":"W7101397496","doi":"10.5281/zenodo.17458967","title":"Zero-Shot Protein Segmentation (ZPS) Data and Embeddings","year":2025,"lang":"","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"UniProt; Parsing; Segmentation; Human proteome project; Search engine indexing; Proteome; Human proteins; File format","score_opus":0.027445033480563114,"score_gpt":0.2919406257354329,"score_spread":0.2644955922548698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7101397496","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032249573,0.00084242463,0.015627194,0.0009601373,0.00036662156,0.003212304,0.9487823,0.00031683687,0.026667222],"genre_scores_gemma":[0.005042505,0.001410256,0.0021564192,0.00033461658,0.00025977273,1.9808188e-7,0.9875871,0.00081782514,0.0023913016],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959932,0.00070277666,0.0007891845,0.0012932569,0.0005815755,0.00063998863],"domain_scores_gemma":[0.99592656,0.000024793651,0.00056683936,0.0025426652,0.0006499153,0.0002892564],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0015337017,0.00053537154,0.00039460658,0.0003541103,0.002817345,0.0018555315,0.0035738726,0.00049431395,0.0039502596],"category_scores_gemma":[0.0026764595,0.0006093638,0.00007236968,0.00049158937,0.0004240676,0.000073591495,0.012700212,0.0009127002,0.0009318951],"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":[0.00016163646,0.00014962477,0.0000013124111,0.0011014938,0.00021474289,0.0000071038285,0.00021264708,0.000033257915,0.010767252,0.00011169123,0.9357111,0.051528133],"study_design_scores_gemma":[0.00090504007,0.00063894194,0.0000131450415,0.0002521445,0.00012091307,0.0001274637,0.00024330262,0.0021775,0.001435215,0.000023726407,0.99350667,0.00055594655],"about_ca_topic_score_codex":0.000032203126,"about_ca_topic_score_gemma":8.3269543e-7,"teacher_disagreement_score":0.057795558,"about_ca_system_score_codex":0.00011516257,"about_ca_system_score_gemma":0.000031772986,"threshold_uncertainty_score":0.999846},"labels":[],"label_agreement":null},{"id":"W7108637041","doi":"10.5376/cmb.2025.15.0011","title":"Deep Learning for Predicting Gene Expression from Genomic Sequences","year":2025,"lang":"","type":"article","venue":"Computational Molecular Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interpretability; Deep learning; Genomics; Functional genomics; Gene regulatory network; Gene; Gene expression; Regulation of gene expression; Expression quantitative trait loci","score_opus":0.006501902357756156,"score_gpt":0.28395418978749554,"score_spread":0.2774522874297394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7108637041","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2018938,0.006108705,0.789201,0.00036642695,0.0007554855,0.0005657901,0.00011929519,0.00003960536,0.0009498679],"genre_scores_gemma":[0.8397025,0.00010360184,0.15207343,0.0008925809,0.00032290636,0.00008528494,0.006599824,0.00004202306,0.00017786295],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99701685,0.00044915927,0.00088029663,0.00091464916,0.00015740028,0.0005816388],"domain_scores_gemma":[0.99822277,0.00037808766,0.00051650085,0.00038948224,0.00036879015,0.00012437736],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039269487,0.00047790853,0.00046277512,0.00019517202,0.00050692825,0.00010000257,0.0006032086,0.0007077731,0.000042584215],"category_scores_gemma":[0.00092826557,0.00051867607,0.00030993248,0.0001932402,0.0003138539,0.000009644437,0.0005771692,0.00044914224,0.000018190725],"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":[0.00020134603,0.00005749315,0.016271599,0.000104337974,0.0003966419,0.000003213024,0.00011902252,0.39139557,0.5786194,0.003347234,0.00011443411,0.009369667],"study_design_scores_gemma":[0.0030376965,0.0009923545,0.0041375444,0.00022802362,0.0002687022,0.000023117322,0.00023127485,0.811218,0.077169,0.08201254,0.019642878,0.0010388346],"about_ca_topic_score_codex":0.00003970323,"about_ca_topic_score_gemma":0.0000064670135,"teacher_disagreement_score":0.6378087,"about_ca_system_score_codex":0.000085939115,"about_ca_system_score_gemma":0.0004052242,"threshold_uncertainty_score":0.9997265},"labels":[],"label_agreement":null},{"id":"W7111352857","doi":"10.1051/bioconf/202516301001/pdf","title":"TooT-SS: Transfer Learning using ProtBERT-BFD Language Model for Predicting Specific Substrates of Transport Proteins","year":2025,"lang":"en","type":"article","venue":"Springer Link (Chiba Institute of Technology)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University; Genome Canada","keywords":"Construct (python library); Language model; Class (philosophy); Artificial neural network; Transfer of learning; Transfer (computing); Deep learning","score_opus":0.012043072152386189,"score_gpt":0.2540567325972173,"score_spread":0.24201366044483108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7111352857","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77913284,0.00044055594,0.21804413,0.00016477903,0.00016678477,0.0010217896,0.00002972391,0.00009505448,0.00090433226],"genre_scores_gemma":[0.900997,0.000070021,0.09829194,0.000017820103,0.00006666071,0.000094999756,0.00006455505,0.000029924062,0.00036711444],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99828964,0.000019745894,0.00086266914,0.0003572953,0.00014200105,0.00032867043],"domain_scores_gemma":[0.99904394,0.000013392388,0.0002551875,0.00048367472,0.0001685101,0.000035287096],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005591433,0.00026568712,0.00050033577,0.00035872683,0.00012688595,0.000010469634,0.0004396373,0.00050596026,0.0000040655314],"category_scores_gemma":[0.00032948385,0.00025788305,0.00023553323,0.00033559417,0.00031864308,0.000020586995,0.000088317385,0.00045129578,4.795307e-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":[0.00013920797,0.00009747931,0.024676798,0.0010515474,0.00022755923,0.0000016144186,0.00037761405,0.063278034,0.8955329,0.00591371,0.0000117165,0.008691806],"study_design_scores_gemma":[0.0011187675,0.00027448472,0.0006410289,0.0004914031,0.0001174804,0.0000070973397,0.00022185405,0.100977376,0.8862614,0.0002281252,0.009337833,0.00032316378],"about_ca_topic_score_codex":0.000021931344,"about_ca_topic_score_gemma":0.00004213806,"teacher_disagreement_score":0.12186411,"about_ca_system_score_codex":0.000024984853,"about_ca_system_score_gemma":0.00021017778,"threshold_uncertainty_score":0.99998736},"labels":[],"label_agreement":null},{"id":"W7114907792","doi":"10.1093/bib/bbaf631.068","title":"Prediction of protein binding residues for metal ions, nucleic acids, and small molecules","year":2025,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Small molecule; Nucleic acid; Binding site; Cysteine; Ligand (biochemistry); Protein–protein interaction; Python (programming language); Peptide; Plasma protein binding","score_opus":0.011374807117741236,"score_gpt":0.2391244631498523,"score_spread":0.22774965603211106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7114907792","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9387528,0.0005804328,0.055481784,0.00049267896,0.00010111457,0.0010926403,0.00013901581,0.000041604944,0.0033179598],"genre_scores_gemma":[0.52237093,0.0003668556,0.47445026,0.0008692385,0.00006672625,0.00016761635,0.00059740286,0.000044950015,0.001066047],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988783,0.000020911257,0.00063068455,0.00013933104,0.00010471338,0.00022605283],"domain_scores_gemma":[0.9993479,0.000031535426,0.0002502583,0.00024854406,0.000085216314,0.00003650944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004298535,0.00016769012,0.000216891,0.00020838462,0.00009699522,0.00003967956,0.00017679493,0.0001908726,0.0000017990179],"category_scores_gemma":[0.00054331176,0.00016554697,0.00006655177,0.00017899837,0.00011591813,0.000017653563,0.00017080706,0.00012343723,0.0000010108057],"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":[0.0016806448,0.00074728415,0.12212967,0.01980453,0.0012313715,0.000004320472,0.008115143,0.0030527073,0.61550164,0.07398257,0.018139293,0.13561085],"study_design_scores_gemma":[0.00861195,0.0020790144,0.0350747,0.0024078763,0.0002885259,0.000067762405,0.0030963488,0.25995666,0.5287742,0.0035030537,0.15468983,0.0014500909],"about_ca_topic_score_codex":0.000027922006,"about_ca_topic_score_gemma":0.00002746881,"teacher_disagreement_score":0.41896847,"about_ca_system_score_codex":0.000017756287,"about_ca_system_score_gemma":0.00007833016,"threshold_uncertainty_score":0.67508096},"labels":[],"label_agreement":null},{"id":"W7117296782","doi":"10.1021/acs.jproteome.5c00506","title":"Protein Language Models: Applications and Perspectives","year":2025,"lang":"en","type":"article","venue":"Journal of Proteome Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Centre hospitalier de l'Université Laval","funders":"","keywords":"Key (lock); Sequence (biology); Protein sequencing; Drug discovery; Proteomics; Language model","score_opus":0.031509319623001,"score_gpt":0.37993761860480757,"score_spread":0.34842829898180655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117296782","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8730633,0.009274884,0.089549966,0.0037903038,0.000024291776,0.0015807842,0.0000061709256,0.000009442444,0.022700844],"genre_scores_gemma":[0.9782702,0.00021883509,0.01784192,0.000020976559,0.00014209782,0.00007188607,0.0000019449292,0.000007774501,0.003424364],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992374,0.00011413486,0.00018679695,0.00008930484,0.00022682278,0.00014551403],"domain_scores_gemma":[0.9992899,0.000018857325,0.000077579585,0.00016990807,0.00039179152,0.000051990242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011955146,0.000054728833,0.00008773611,0.00019035542,0.00009908647,0.000044186418,0.00020054309,0.000068585694,0.0000076006822],"category_scores_gemma":[0.0003216873,0.00004386448,0.000036198115,0.00018061633,0.0001186126,0.000008253121,0.00014374928,0.0003745667,0.0000022370502],"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":[0.00019268513,0.00014185015,0.00041088337,0.00033183466,0.00012467953,0.0000055705905,0.001651655,0.00018118838,0.9674278,0.012047765,0.0015818841,0.015902244],"study_design_scores_gemma":[0.006523256,0.0052933493,0.005648982,0.0011913135,0.00008550128,0.0005125929,0.046140213,0.022222906,0.6267854,0.050396577,0.23412687,0.0010730507],"about_ca_topic_score_codex":0.0000066169573,"about_ca_topic_score_gemma":0.0000020850784,"teacher_disagreement_score":0.34064236,"about_ca_system_score_codex":0.000023526572,"about_ca_system_score_gemma":0.00017419893,"threshold_uncertainty_score":0.17887415},"labels":[],"label_agreement":null},{"id":"W7117545961","doi":"10.18280/ts.420633","title":"Advancing Protein Sequence Signal Analysis in Bioinformatics Through SFA: A Refined Structure-Based Fingerprint Alignment Algorithm","year":2025,"lang":"","type":"article","venue":"Traitement du signal","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Fingerprint (computing); Pattern recognition (psychology); Sequence (biology); Multiple sequence alignment; Protein sequencing; SIGNAL (programming language); Sequence analysis","score_opus":0.007183428570310759,"score_gpt":0.26420106091102824,"score_spread":0.2570176323407175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117545961","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19259411,0.00052722736,0.8012633,0.0011157477,0.00021911101,0.002179182,0.00044454812,0.000061825755,0.0015949561],"genre_scores_gemma":[0.81037056,0.000059016857,0.18650714,0.0016964959,0.00012342566,0.00013780087,0.0008681731,0.000039787443,0.0001976225],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940648,0.00037109287,0.0024450417,0.0009157925,0.00091989426,0.0012833844],"domain_scores_gemma":[0.9974826,0.00012488781,0.0009582327,0.0009498407,0.00026706624,0.0002173648],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001185424,0.00097184227,0.0010461186,0.0007257535,0.00033916679,0.00025486262,0.0008998316,0.00057244505,0.00075580494],"category_scores_gemma":[0.00019129374,0.0009847732,0.0005743426,0.001932643,0.0002963325,0.00006137024,0.00044946128,0.00077744917,0.000013044297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010226436,0.0013006679,0.00887682,0.002708727,0.0049407585,0.000080529186,0.003594712,0.6116389,0.21035641,0.0011859192,0.0007939776,0.15349993],"study_design_scores_gemma":[0.003607437,0.00087477546,0.0009444347,0.00061962474,0.00090323,0.000005787199,0.0007251042,0.8570795,0.12222008,0.0002799339,0.01160799,0.0011321285],"about_ca_topic_score_codex":0.00017210585,"about_ca_topic_score_gemma":0.00024299497,"teacher_disagreement_score":0.61777645,"about_ca_system_score_codex":0.0006210593,"about_ca_system_score_gemma":0.0010291314,"threshold_uncertainty_score":0.99926025},"labels":[],"label_agreement":null},{"id":"W7126423661","doi":"10.21428/594757db.26effc01","title":"TransformerChrome: Transformer-based Model for Prediction ofGene Expression from Histone Modifications","year":2024,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Health Network; University of Manitoba","funders":"","keywords":"Histone; Epigenetics; Gene expression; Chromatin; Regulation of gene expression; Gene; Epigenome; Mechanism (biology)","score_opus":0.018519343558433835,"score_gpt":0.3019168851220438,"score_spread":0.28339754156360997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126423661","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":[0.04448379,0.00041380525,0.9498316,0.00053075596,0.0001571662,0.00042443583,0.00096955046,0.00011885336,0.003070066],"genre_scores_gemma":[0.9379713,0.00008464452,0.055311214,0.00018204299,0.00013959578,0.00020455424,0.0035252522,0.00003847481,0.0025429009],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990908,0.000014741523,0.00029099706,0.00028170279,0.0001340705,0.00018770613],"domain_scores_gemma":[0.9995569,0.000024560362,0.00002730291,0.00026662287,0.000051622883,0.000072983305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012677342,0.00015623367,0.000108576896,0.00006686193,0.00011070372,0.000037906626,0.00013862253,0.0001835536,0.00006852192],"category_scores_gemma":[0.000022102582,0.0001354479,0.00014837302,0.00007153586,0.00004482256,0.000011541126,0.000006270101,0.000103898936,0.00001181138],"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":[0.00008603326,0.000056834586,0.000014807824,0.0001266869,0.000037424375,1.3327978e-7,0.00027339096,0.050686944,0.9332582,0.00034154518,0.008041875,0.007076127],"study_design_scores_gemma":[0.00036182386,0.00010287146,0.000033702556,0.000026569976,0.000034275236,8.7142774e-7,0.000018883835,0.7113583,0.2600413,0.00021418033,0.02768423,0.00012297259],"about_ca_topic_score_codex":0.0000137183615,"about_ca_topic_score_gemma":0.000031581567,"teacher_disagreement_score":0.89452034,"about_ca_system_score_codex":0.000031901993,"about_ca_system_score_gemma":0.00014172561,"threshold_uncertainty_score":0.5523405},"labels":[],"label_agreement":null},{"id":"W71331043","doi":"10.2174/138920311796957621","title":"Editorial [Hot Topic: Machine Learning Models in Protein Bioinformatics (Guest Editors: Lukasz Kurgan &amp; Yaoqi Zhou)]","year":2011,"lang":"en","type":"editorial","venue":"Current Protein and Peptide Science","topic":"Machine Learning in Bioinformatics","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":"University of Alberta","funders":"","keywords":"Automatic summarization; Computational biology; Structural bioinformatics; Computer science; Bioinformatics; Field (mathematics); Function (biology); Data science; Artificial intelligence; Protein structure; Biology; Genetics; Biochemistry","score_opus":0.019142571673450216,"score_gpt":0.2773190226497393,"score_spread":0.25817645097628905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W71331043","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003537237,0.00086880114,0.0015048741,0.000034890585,0.990203,0.001598808,0.00013032273,0.0000823714,0.0020396526],"genre_scores_gemma":[0.0011947923,0.0004778178,0.0054132664,0.000010713332,0.9896901,0.00021011029,0.0009885582,0.00006741048,0.0019472041],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952243,0.00016686677,0.0010604477,0.00093446556,0.0016338576,0.0009800903],"domain_scores_gemma":[0.9973732,0.000058122852,0.0007698414,0.0008768437,0.00054675754,0.00037519162],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002388589,0.00074057543,0.0005955159,0.00042073548,0.00046058215,0.00041018034,0.0013802415,0.001009381,0.00003351742],"category_scores_gemma":[0.003384767,0.0006726429,0.00014204581,0.00049271365,0.00084713986,0.00013623541,0.0010939629,0.0025648477,0.000047239075],"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":[0.00018536599,0.00014270048,0.00015211078,0.0011654198,0.00002303502,0.0000014809876,0.00097533764,0.00015482822,0.0059754485,0.000121776524,0.9869591,0.004143377],"study_design_scores_gemma":[0.0007909226,0.0003915333,0.000008075642,0.000723335,0.000017995522,0.000003031364,0.000033351233,0.002597623,0.0017021894,0.00014497263,0.9927491,0.00083787],"about_ca_topic_score_codex":0.0002546694,"about_ca_topic_score_gemma":0.00014636274,"teacher_disagreement_score":0.0057899808,"about_ca_system_score_codex":0.000117374206,"about_ca_system_score_gemma":0.0011889451,"threshold_uncertainty_score":0.99973625},"labels":[],"label_agreement":null},{"id":"W7162040634","doi":"10.1109/iccta68914.2025.11520011","title":"Survey of Emerging Trends in Artificial Intelligence for Bioinformatics","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Applications of artificial intelligence; Field (mathematics); Key (lock); Big data","score_opus":0.027509203392411197,"score_gpt":0.3414731639385911,"score_spread":0.3139639605461799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7162040634","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05878471,0.0010031505,0.8900864,0.0007810769,0.0011891288,0.00076317845,0.00029695206,0.000020161095,0.047075246],"genre_scores_gemma":[0.97490543,0.00020003357,0.022060823,0.00020245498,0.000038047423,0.000018082508,0.0006004679,0.000018092685,0.001956595],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99713326,0.000115932686,0.0018384707,0.00027691445,0.00016324916,0.00047220077],"domain_scores_gemma":[0.9984338,0.00017773865,0.00042909806,0.00056971365,0.0003280789,0.00006153866],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017155726,0.0003104509,0.00046408747,0.0006194669,0.000081237005,0.000049394297,0.0004941095,0.0003846001,0.00011301842],"category_scores_gemma":[0.00126712,0.00031726854,0.00018362582,0.0011529716,0.00017872971,0.000011004788,0.00029267799,0.0002252016,0.000005095934],"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":[0.00046353065,0.0002925589,0.017966876,0.0009923293,0.00018888105,3.0137593e-7,0.00071947585,0.007974349,0.0014596985,0.0084069725,0.0020387203,0.9594963],"study_design_scores_gemma":[0.0004673932,0.0005839208,0.012714517,0.00019747451,0.000060956012,0.0000013897379,0.0010234291,0.91985774,0.05616018,0.00058421755,0.0077842465,0.0005645065],"about_ca_topic_score_codex":0.0002718411,"about_ca_topic_score_gemma":0.0016254976,"teacher_disagreement_score":0.9589318,"about_ca_system_score_codex":0.000036198522,"about_ca_system_score_gemma":0.00026074616,"threshold_uncertainty_score":0.99992794},"labels":[],"label_agreement":null},{"id":"W73842674","doi":"10.1007/978-3-642-36657-4_15","title":"Neural Networks in Bioinformatics","year":2013,"lang":"en","type":"book-chapter","venue":"Intelligent systems reference library","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","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 Guelph","funders":"","keywords":"Artificial neural network; Computer science; Artificial intelligence; Generalization; Structural bioinformatics; Multidisciplinary approach; Machine learning; Data science; Bioinformatics; Biology; Mathematics; Protein structure","score_opus":0.018274311391564897,"score_gpt":0.22963298873070337,"score_spread":0.21135867733913846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W73842674","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":[0.00080949924,0.004180221,0.0038022276,0.00007187971,0.0011343476,0.0011203436,0.00007992382,0.0001213324,0.98868024],"genre_scores_gemma":[0.07236269,0.0040335106,0.0014952682,0.0006791985,0.0010602934,0.000096634285,0.004161882,0.00026167443,0.91584885],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975532,0.00005220849,0.0012433144,0.00039345273,0.00029691603,0.0004608931],"domain_scores_gemma":[0.99822694,0.00003983778,0.0006067999,0.0008908905,0.000058101195,0.00017740268],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013958837,0.00060319674,0.0005567934,0.00024645374,0.000051781743,0.00022844925,0.00076931075,0.0010987592,0.0006702482],"category_scores_gemma":[0.000030297533,0.0005332017,0.0001608605,0.00005412297,0.00010753601,0.00004498866,0.00048466108,0.00090582983,0.0007280158],"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":[0.0004335239,0.00021999163,0.007790605,0.005362584,0.0011665022,0.00014801473,0.00092159363,0.14260915,0.00021456661,0.25071278,0.45649418,0.1339265],"study_design_scores_gemma":[0.0001737765,0.00025861312,0.000057912774,0.0005987402,0.000020768613,0.00006920469,0.00006235082,0.17148349,0.00010365211,0.0002785844,0.8260159,0.00087700033],"about_ca_topic_score_codex":0.000026881986,"about_ca_topic_score_gemma":0.0000054212583,"teacher_disagreement_score":0.3695217,"about_ca_system_score_codex":0.000029560799,"about_ca_system_score_gemma":0.00009442627,"threshold_uncertainty_score":0.99971193},"labels":[],"label_agreement":null}]}