{"meta":{"query_hash":"6221cfeba50a","filters":{"venue":"Journal of Computational Biology"},"cohort_total":160,"direct_labels_cover":0,"predictions_cover":160,"exported":160,"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/6221cfeba50a","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Computational+Biology"},"results":[{"id":"W1484399819","doi":"10.1089/cmb.2005.12.129","title":"More Reliable Protein NMR Peak Assignment via Improved 2-Interval Scheduling","year":2005,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Scheduling (production processes); Subsequence; Job shop scheduling; Computer science; Interval (graph theory); Combinatorics; Mathematical optimization; Algorithm; Mathematics; Schedule","score_opus":0.012112642861767222,"score_gpt":0.2743904457364027,"score_spread":0.2622778028746355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1484399819","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061925776,0.0005049661,0.931424,0.00032866906,0.00028484012,0.00012913227,0.00024610106,0.0018856225,0.0032709527],"genre_scores_gemma":[0.34588528,0.00027603505,0.64849573,0.00024231021,0.0001978295,0.00021855441,0.0011164312,0.0005158044,0.00305199],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982528,0.000372356,0.000085508036,0.0004692331,0.00047352418,0.00034651518],"domain_scores_gemma":[0.9974935,0.00093078933,0.00025243356,0.000573662,0.00041039928,0.00033920238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018783564,0.0012253871,0.0018857805,0.0009444823,0.00081666646,0.0013479751,0.002853032,0.0010160872,0.004155962],"category_scores_gemma":[0.0045032385,0.0005170218,0.0010229528,0.0016169247,0.00057318626,0.0016849074,0.0013328805,0.0020251146,0.0012898443],"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":[0.001015401,0.0006720181,0.0013257302,0.00021500827,0.0000661595,0.0002577045,0.00025575754,0.79631186,0.029085523,0.021897875,0.010818654,0.13807832],"study_design_scores_gemma":[0.000049123795,0.00007763553,0.00015528475,0.0000037851748,0.0000067855935,0.00002689473,0.000014774231,0.99183804,0.0018175374,0.0048904154,0.001106988,0.000012728267],"about_ca_topic_score_codex":0.004414738,"about_ca_topic_score_gemma":0.0039931447,"teacher_disagreement_score":0.004414738,"about_ca_system_score_codex":0.0013404557,"about_ca_system_score_gemma":0.0025957292,"threshold_uncertainty_score":0.013903081},"labels":[],"label_agreement":null},{"id":"W1606551583","doi":"10.1089/cmb.2006.13.1355","title":"Optimizing Multiple Spaced Seeds for Homology Search","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Waterloo","funders":"","keywords":"Sensitivity (control systems); Greedy algorithm; Homology (biology); Algorithm; Set (abstract data type); Local search (optimization); Linear programming; Mathematical optimization; Computer science; Mathematics; Search algorithm; Biology; Engineering; Genetics","score_opus":0.0242074479757779,"score_gpt":0.32591470296420705,"score_spread":0.30170725498842915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1606551583","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037430223,0.00021011295,0.9598954,0.00009514502,0.00002151815,0.000056045534,0.000029838886,0.0011867856,0.0010749096],"genre_scores_gemma":[0.32898915,0.00013011543,0.6684777,0.00014999892,0.000029280089,0.00015799559,0.00016668765,0.0003404961,0.0015584702],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894243,0.0003819464,0.000057854384,0.00026964262,0.00026108383,0.0000871425],"domain_scores_gemma":[0.99731076,0.0017063941,0.00025384,0.00029664056,0.0003024405,0.00012991649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015960954,0.0009787369,0.0013620231,0.0012479804,0.0005427586,0.0007848525,0.0013190755,0.0018757855,0.002090732],"category_scores_gemma":[0.007140057,0.0007530169,0.00064186985,0.0012664547,0.0010072485,0.0021187086,0.0014484554,0.001030925,0.0009868273],"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":[0.00036355428,0.00021400748,0.001616394,0.00011886096,0.00007631821,0.00021124711,0.00013810431,0.75636697,0.033249497,0.01680128,0.0029432934,0.18790048],"study_design_scores_gemma":[0.000033724355,0.000062511564,0.000115837574,0.0000049123405,0.000010634451,0.00006422001,0.000012078025,0.98592144,0.005954585,0.007238948,0.000569713,0.0000113690885],"about_ca_topic_score_codex":0.001409728,"about_ca_topic_score_gemma":0.0018267801,"teacher_disagreement_score":0.002090732,"about_ca_system_score_codex":0.0009805752,"about_ca_system_score_gemma":0.0011224828,"threshold_uncertainty_score":0.008441031},"labels":[],"label_agreement":null},{"id":"W1963713243","doi":"10.1089/cmb.2010.0099","title":"Natural Parameter Values for Generalized Gene Adjacency","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Genome; Adjacency list; Value (mathematics); Probabilistic logic; Gene; Natural (archaeology); Class (philosophy); Biology; Expected value; Computational biology; Genetics; Computer science; Mathematics; Combinatorics; Artificial intelligence; Statistics","score_opus":0.010781784142865205,"score_gpt":0.28796840471012203,"score_spread":0.27718662056725685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963713243","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.543058,0.00080491154,0.42947662,0.0027952811,0.000086602726,0.000200308,0.0005339789,0.00080234185,0.02224199],"genre_scores_gemma":[0.94809264,0.00024113471,0.049935505,0.00024408,0.00005340833,0.00035431734,0.00024757307,0.00014738864,0.00068389723],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975574,0.0013174646,0.00009848677,0.00049314916,0.00034483813,0.00018862748],"domain_scores_gemma":[0.9427756,0.048704453,0.0029211533,0.0024929338,0.0013965332,0.0017092595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054873065,0.0006041633,0.00079884566,0.0026483487,0.0012780525,0.0022106133,0.0016357657,0.002599502,0.004506266],"category_scores_gemma":[0.07248765,0.00055134186,0.0006452374,0.0010659101,0.0036559885,0.005760673,0.0022369192,0.0022798479,0.00042358806],"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":[0.00029165563,0.0001463068,0.0069217957,0.00031271813,0.000075553566,0.00031783615,0.00056801905,0.17979972,0.006405469,0.7835379,0.003587393,0.018035622],"study_design_scores_gemma":[0.000073334275,0.00007379858,0.0017216761,0.00007111775,0.000021968415,0.0004295179,0.00020807124,0.2171486,0.0012284549,0.7776109,0.0013153681,0.00009733325],"about_ca_topic_score_codex":0.0004262755,"about_ca_topic_score_gemma":0.0006964875,"teacher_disagreement_score":0.0054873065,"about_ca_system_score_codex":0.0011163614,"about_ca_system_score_gemma":0.0006352911,"threshold_uncertainty_score":0.029020011},"labels":[],"label_agreement":null},{"id":"W1963847479","doi":"10.1089/cmb.2010.0091","title":"Rearrangement Models and Single-Cut Operations","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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 Toronto","funders":"Deutscher Akademischer Austauschdienst","keywords":"Sorting; Join (topology); Set (abstract data type); Computer science; Algorithm; Mathematics; Theoretical computer science; Combinatorics; Programming language","score_opus":0.01894765429857264,"score_gpt":0.26936801227171825,"score_spread":0.2504203579731456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963847479","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13902344,0.0014536327,0.8234567,0.001441305,0.00010757252,0.00008890536,0.0003186667,0.00056975044,0.033540003],"genre_scores_gemma":[0.8203724,0.0010930438,0.16269772,0.00040599212,0.0001525279,0.0001669437,0.0007211823,0.0001593389,0.014230796],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985613,0.00028158902,0.00008511191,0.00041044972,0.00044852128,0.00021296136],"domain_scores_gemma":[0.9975534,0.0013268885,0.00033183536,0.00038859397,0.0002073371,0.00019200708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010362398,0.0005938513,0.00046657847,0.0009985523,0.0007114229,0.0026024783,0.00209887,0.0017156915,0.0077864802],"category_scores_gemma":[0.0035329422,0.0003601618,0.0010335658,0.001275554,0.0022784967,0.0059987996,0.0018894523,0.0022513994,0.0008322527],"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":[0.000042392086,0.000032297936,0.00027290048,0.000049610364,0.000009259403,0.00008387257,0.00010569353,0.019860175,0.0020488794,0.9669154,0.0007363262,0.009843183],"study_design_scores_gemma":[0.000029438057,0.000060736842,0.00015204752,0.000015564303,0.000013946645,0.00028731275,0.00012239158,0.096360534,0.003121104,0.89278674,0.0070294966,0.00002062372],"about_ca_topic_score_codex":0.0012096622,"about_ca_topic_score_gemma":0.0011448419,"teacher_disagreement_score":0.0077864802,"about_ca_system_score_codex":0.0015905595,"about_ca_system_score_gemma":0.0007055414,"threshold_uncertainty_score":0.026048362},"labels":[],"label_agreement":null},{"id":"W1964112927","doi":"10.1089/cmb.2012.0292","title":"Ancestral Genome Organization: An Alignment Approach","year":2013,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Genome; Biology; Evolutionary biology; Computational biology; Computer science; Data science; Genetics; Gene","score_opus":0.011429712418337259,"score_gpt":0.2455299861806244,"score_spread":0.23410027376228715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964112927","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010231441,0.000106428815,0.98708457,0.00015503683,0.000011347622,0.000034252735,0.00018140652,0.00048135035,0.0017140862],"genre_scores_gemma":[0.135508,0.00023058508,0.861411,0.00010145699,0.000032684464,0.00012304146,0.0010017186,0.00027664588,0.0013148512],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991886,0.00024777697,0.000042621097,0.00026777462,0.0001771157,0.000076087854],"domain_scores_gemma":[0.9992048,0.00041227866,0.00009108409,0.00012365788,0.0001216776,0.000046389578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009100357,0.0007592135,0.00087624637,0.0023615551,0.0009412801,0.0014907669,0.0020728754,0.0011960035,0.0053179376],"category_scores_gemma":[0.0035129718,0.0007150719,0.0013928848,0.0024655764,0.0008337374,0.0029289525,0.0015225353,0.0018369247,0.0010327528],"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":[0.0002597299,0.00017414182,0.004820784,0.0003230224,0.00013463979,0.00053801714,0.0004212615,0.4881794,0.021335758,0.20115489,0.0030099098,0.27964848],"study_design_scores_gemma":[0.000030493204,0.00007034252,0.00075455284,0.000036923248,0.000046940604,0.0003247223,0.00009902087,0.8369155,0.006537052,0.1478542,0.007300151,0.000030210404],"about_ca_topic_score_codex":0.0019635388,"about_ca_topic_score_gemma":0.0019040446,"teacher_disagreement_score":0.0053179376,"about_ca_system_score_codex":0.0010591621,"about_ca_system_score_gemma":0.0012117409,"threshold_uncertainty_score":0.017790258},"labels":[],"label_agreement":null},{"id":"W1966241066","doi":"10.1089/cmb.2007.r002","title":"Bayesian Inference of MicroRNA Targets from Sequence and Expression Data","year":2007,"lang":"en","type":"review","venue":"Journal of Computational Biology","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":118,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"microRNA; Biology; Computational biology; Robustness (evolution); Inference; Gene; DNA microarray; Gene expression profiling; Gene expression; Bayesian probability; Regulation of gene expression; Bioinformatics; Artificial intelligence; Computer science; Genetics","score_opus":0.07661162696924576,"score_gpt":0.39470660907499217,"score_spread":0.3180949821057464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966241066","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050310255,0.51305777,0.47465968,0.0018374783,0.00033521926,0.00003229168,0.00027268642,0.00047301047,0.004300901],"genre_scores_gemma":[0.0901852,0.7815323,0.12252378,0.0005900445,0.00073615334,0.00013891784,0.00090265874,0.0001711994,0.0032197784],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999529,0.00017638634,0.00002594355,0.00010093165,0.0001491208,0.000018564888],"domain_scores_gemma":[0.99906343,0.0006834794,0.000062229374,0.0000390239,0.00013165394,0.000020170115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016910793,0.00084244524,0.0013072566,0.0011390299,0.00011346427,0.00096293655,0.0018291328,0.0014516783,0.0006493401],"category_scores_gemma":[0.0033195773,0.0006976673,0.000658346,0.0012848752,0.00081752293,0.001179293,0.0005688019,0.0012760905,0.0008245203],"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":[0.000118884745,0.000049069575,0.0012821063,0.00318491,0.00033941542,0.00022542207,0.00006280687,0.14349346,0.005322111,0.033536006,0.008943429,0.8034424],"study_design_scores_gemma":[0.000109443754,0.00017160576,0.004715331,0.0017581801,0.00040774955,0.0014579037,0.000065999346,0.5662927,0.011445577,0.17811917,0.23519176,0.00026458793],"about_ca_topic_score_codex":0.0017059321,"about_ca_topic_score_gemma":0.0012064438,"teacher_disagreement_score":0.0018291328,"about_ca_system_score_codex":0.0009374803,"about_ca_system_score_gemma":0.0006937443,"threshold_uncertainty_score":0.008943379},"labels":[],"label_agreement":null},{"id":"W1967695819","doi":"10.1089/cmb.2013.0163","title":"Simultaneous Alignment and Folding of Protein Sequences","year":2014,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"RNA and protein synthesis mechanisms","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":"National Institute of General Medical Sciences","keywords":"Pairwise comparison; Structural alignment; Multiple sequence alignment; Computer science; Alignment-free sequence analysis; Sequence alignment; Sequence (biology); Computational biology; Protein structure prediction; Protein folding; Folding (DSP implementation); Theoretical computer science; Protein structure; Algorithm; Artificial intelligence; Biology; Peptide sequence; Genetics; Engineering","score_opus":0.008369427603408643,"score_gpt":0.2523752670893315,"score_spread":0.24400583948592286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967695819","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039114803,0.00047542504,0.95382744,0.00017786103,0.000061305494,0.00007496864,0.00043448253,0.0041445564,0.0016891472],"genre_scores_gemma":[0.16056287,0.000377222,0.8354512,0.00009604288,0.000033647924,0.0001330324,0.0018981856,0.000541956,0.0009059792],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977635,0.0006311003,0.00016966602,0.00084866676,0.0004675426,0.000119581426],"domain_scores_gemma":[0.99786264,0.00073445856,0.0002312902,0.0007260383,0.00035111225,0.00009449987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016150568,0.0011105372,0.0014158512,0.0017223048,0.0011168837,0.0014241991,0.001503368,0.0012579251,0.0033955183],"category_scores_gemma":[0.0060693705,0.0010038213,0.0013263754,0.0024579756,0.0008662398,0.003192454,0.0019489855,0.0016062044,0.0027350113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001010718,0.00021808808,0.00412313,0.0012343882,0.00030818445,0.00057385996,0.0005564874,0.119931355,0.20622574,0.039307512,0.0098187,0.61669177],"study_design_scores_gemma":[0.00008480812,0.0004125049,0.0018493868,0.00007144823,0.00008650085,0.0007841753,0.00029223508,0.757635,0.12342921,0.09570986,0.019580886,0.00006397222],"about_ca_topic_score_codex":0.00060352415,"about_ca_topic_score_gemma":0.001092535,"teacher_disagreement_score":0.0033955183,"about_ca_system_score_codex":0.0005454388,"about_ca_system_score_gemma":0.001296812,"threshold_uncertainty_score":0.011359155},"labels":[],"label_agreement":null},{"id":"W1968904197","doi":"10.1089/cmb.2008.0025","title":"Inferring Ancestral Gene Orders for a Family of Tandemly Arrayed Genes","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","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":"Université de Montréal","funders":"","keywords":"Gene duplication; Biology; Genome; Tandem exon duplication; Gene; Evolutionary biology; Phylogenetics; Genetics; Gene family; Computational biology; Segmental duplication; Gene cluster; Genome evolution","score_opus":0.03223557707972704,"score_gpt":0.28409633442212867,"score_spread":0.25186075734240165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968904197","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71014315,0.0003587164,0.28712103,0.00017414847,0.000008691627,0.00002175535,0.0006661062,0.00037650004,0.0011299311],"genre_scores_gemma":[0.84536666,0.00028357105,0.15190409,0.00003232748,0.000010799741,0.000023534247,0.0017046202,0.00007911065,0.0005952504],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997503,0.000051168412,0.0000126815075,0.00009678569,0.000046442135,0.00004259011],"domain_scores_gemma":[0.99902916,0.0005140349,0.00013125227,0.00013997151,0.00011491726,0.000070669754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007007759,0.00030712783,0.00045871412,0.0023546147,0.00064696616,0.00071231736,0.00057445426,0.0006134289,0.0008586837],"category_scores_gemma":[0.0031251528,0.00032601497,0.0008665534,0.0013704625,0.0005290048,0.0010047135,0.0005297483,0.00071349205,0.0002525739],"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":[0.0007303348,0.00015572,0.22399253,0.0003069628,0.00025278237,0.0010386903,0.001354012,0.43176576,0.048971426,0.053279214,0.0017453199,0.23640728],"study_design_scores_gemma":[0.000033301985,0.000112864356,0.028369674,0.000049877144,0.000103791936,0.0008705132,0.00047727211,0.8968176,0.0099680945,0.059355397,0.0037934333,0.000048125108],"about_ca_topic_score_codex":0.0027456866,"about_ca_topic_score_gemma":0.004105794,"teacher_disagreement_score":0.0027456866,"about_ca_system_score_codex":0.00087955676,"about_ca_system_score_gemma":0.00077872875,"threshold_uncertainty_score":0.006381631},"labels":[],"label_agreement":null},{"id":"W1969554820","doi":"10.1089/cmb.2009.0133","title":"A Near-Linear Time Algorithm for Haplotype Determination on General Pedigrees","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genetic Associations and Epidemiology","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 New Brunswick","funders":"","keywords":"Pedigree chart; Haplotype; Algorithm; Computer science; Mathematics; Combinatorics; Biology; Genetics; Genotype; Gene","score_opus":0.010550771376542893,"score_gpt":0.3040306811532861,"score_spread":0.2934799097767432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969554820","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017746933,0.0002449273,0.97359425,0.0003113475,0.000038933977,0.00015272807,0.0004937052,0.005003863,0.0024132803],"genre_scores_gemma":[0.104886636,0.00011581727,0.88893664,0.00015446494,0.000041168558,0.00027219072,0.0013258758,0.00033709363,0.003930093],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998611,0.00044524527,0.00008444748,0.0004380762,0.0002543421,0.00016692575],"domain_scores_gemma":[0.99752575,0.0015960089,0.00014535962,0.00037473568,0.00025272666,0.00010551021],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013325543,0.0008130772,0.00093274924,0.0009942671,0.0006398159,0.0012731246,0.001677236,0.00087859813,0.0117051],"category_scores_gemma":[0.005076676,0.0006118081,0.0006398692,0.0018926068,0.0004881907,0.0022627779,0.0018631137,0.0008449378,0.003414401],"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":[0.00054999196,0.00020028176,0.0019796425,0.00025562666,0.00009117822,0.00021657624,0.00026817483,0.13440996,0.0050751152,0.030189754,0.024465628,0.8022981],"study_design_scores_gemma":[0.00047905202,0.000091397116,0.0011673666,0.000027410377,0.000039962422,0.00024597265,0.000101278594,0.89159274,0.0019807953,0.09651353,0.0077335173,0.000027018947],"about_ca_topic_score_codex":0.0058754287,"about_ca_topic_score_gemma":0.0074458276,"teacher_disagreement_score":0.0117051,"about_ca_system_score_codex":0.0009699275,"about_ca_system_score_gemma":0.0020897842,"threshold_uncertainty_score":0.03915745},"labels":[],"label_agreement":null},{"id":"W1969595164","doi":"10.1089/cmb.2007.a005","title":"Common Intervals and Symmetric Difference in a Model-Free Phylogenomics, with an Application to Streptophyte Evolution","year":2007,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"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; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Phylogenomics; Biology; Evolutionary biology; Botany; Phylogenetics; Genetics","score_opus":0.009398791714588465,"score_gpt":0.264439563613116,"score_spread":0.25504077189852753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969595164","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054064628,0.00020417402,0.94445735,0.00025979275,0.00002229105,0.000019818111,0.00009399429,0.00020578539,0.0006720631],"genre_scores_gemma":[0.44568968,0.00023806417,0.5522702,0.00011620504,0.00006889209,0.00013756825,0.0003866987,0.00015967347,0.0009329522],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987997,0.0006754508,0.00005217147,0.00022121539,0.00020186658,0.00004971888],"domain_scores_gemma":[0.9936103,0.0051728426,0.0003253861,0.0005038087,0.00020307956,0.00018449317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003042668,0.00038069097,0.000887484,0.0016121768,0.00058636285,0.001138269,0.0018873115,0.001043051,0.0011248303],"category_scores_gemma":[0.013634111,0.00050979486,0.0011517007,0.0016140552,0.0018492707,0.0023066336,0.0025392107,0.0015893914,0.0001869718],"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":[0.00023652974,0.000052238513,0.003067979,0.000056608194,0.000065430984,0.00011740805,0.0001367906,0.79019743,0.0024276804,0.16232076,0.0005369499,0.040784128],"study_design_scores_gemma":[0.000018684304,0.000019879231,0.00018856952,0.0000055048913,0.0000063908733,0.00003337356,0.000010172364,0.93272614,0.00037377095,0.066143654,0.0004647783,0.000009018706],"about_ca_topic_score_codex":0.0024377191,"about_ca_topic_score_gemma":0.0019516737,"teacher_disagreement_score":0.003042668,"about_ca_system_score_codex":0.0010788379,"about_ca_system_score_gemma":0.00077803415,"threshold_uncertainty_score":0.016091347},"labels":[],"label_agreement":null},{"id":"W1970475266","doi":"10.1089/cmb.2009.0091","title":"A Whole Genome Study and Identification of Specific Carcinogenic Regions of the Human Papilloma Viruses","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Cervical Cancer and HPV Research","field":"Medicine","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":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Computational biology; Biology; Identification (biology); Genetics; Monophyly; Carcinogen; Human genome; Genomics; Evolutionary biology; Clade; Phylogenetics; Gene","score_opus":0.06340988668549548,"score_gpt":0.37932183583506146,"score_spread":0.315911949149566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970475266","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9766326,0.0010194621,0.01990974,0.00016190547,0.000012257316,0.000020009165,0.0012205513,0.000097396296,0.0009260796],"genre_scores_gemma":[0.95547295,0.00087784487,0.038982272,0.00006237084,0.000011521141,0.000023520279,0.0038671545,0.000047747013,0.0006546718],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998801,0.000034912267,0.000004076836,0.000050442664,0.000016149312,0.000014374582],"domain_scores_gemma":[0.99964213,0.0002252165,0.000026811225,0.000043789063,0.000034533692,0.000027441982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026921363,0.00020317634,0.00030473908,0.000685189,0.00032085727,0.00031413173,0.00024077094,0.0004137446,0.0013912461],"category_scores_gemma":[0.0015035135,0.00017696655,0.00051763817,0.0010622112,0.00016682115,0.0005037791,0.00026862725,0.00033430662,0.0001740992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021481272,0.0004822639,0.22262253,0.0010345746,0.00081568246,0.001188918,0.0009412482,0.12293062,0.41374427,0.009684275,0.0028258394,0.22158168],"study_design_scores_gemma":[0.00011125041,0.0007255905,0.53774214,0.000080797196,0.0004903344,0.0015548898,0.0010018746,0.36743638,0.059945174,0.0128470985,0.017980207,0.00008426839],"about_ca_topic_score_codex":0.0033193787,"about_ca_topic_score_gemma":0.0037967474,"teacher_disagreement_score":0.0033193787,"about_ca_system_score_codex":0.00021607631,"about_ca_system_score_gemma":0.00034723125,"threshold_uncertainty_score":0.0066001415},"labels":[],"label_agreement":null},{"id":"W1970557025","doi":"10.1089/cmb.2014.0057","title":"Asynchronous Stochastic Boolean Networks as Gene Network Models","year":2014,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Gene Regulatory Network Analysis","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":"University of Alberta","funders":"","keywords":"Asynchronous communication; Boolean network; Gene regulatory network; Computer science; Robustness (evolution); ENCODE; Biological network; Attractor; Stochastic process; Theoretical computer science; Boolean function; Mathematics; Gene; Algorithm; Biology; Computational biology; Genetics","score_opus":0.0065819920977378005,"score_gpt":0.23475709909424486,"score_spread":0.22817510699650706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970557025","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0365662,0.000730921,0.9543547,0.00044204915,0.00006926364,0.000055201046,0.00050197967,0.00022043746,0.0070592514],"genre_scores_gemma":[0.8613004,0.0022530672,0.11929758,0.00032314024,0.00015435305,0.0004922285,0.0008517043,0.00010665022,0.015220865],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927074,0.00030952456,0.000031721444,0.00013186876,0.0001717855,0.00008438827],"domain_scores_gemma":[0.9986388,0.00088075356,0.00020583157,0.000056793044,0.00013641495,0.00008143021],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010482421,0.0007996971,0.0007828783,0.0009963836,0.00035928612,0.0011694595,0.0011827395,0.0009777392,0.003307741],"category_scores_gemma":[0.0034434684,0.0003311719,0.0007622852,0.0011751776,0.00086560444,0.0017379118,0.0007342058,0.0011567324,0.00041623454],"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":[0.000044183165,0.000022466744,0.0004380995,0.00005286757,0.00002327237,0.000091357775,0.000047725396,0.66152704,0.0016972333,0.3293213,0.0006094844,0.006124951],"study_design_scores_gemma":[0.0000064563046,0.00000682752,0.00004439755,0.0000025222416,0.0000048584207,0.000011590954,0.0000050752724,0.9499912,0.00012580681,0.049365047,0.00043231554,0.0000038508333],"about_ca_topic_score_codex":0.004576292,"about_ca_topic_score_gemma":0.003987857,"teacher_disagreement_score":0.004576292,"about_ca_system_score_codex":0.0013429257,"about_ca_system_score_gemma":0.0007537539,"threshold_uncertainty_score":0.011065483},"labels":[],"label_agreement":null},{"id":"W1971276942","doi":"10.1089/cmb.2009.0103","title":"Towards Improved Reconstruction of Ancestral Gene Order in Angiosperm Phylogeny","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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":"University of Ottawa","funders":"","keywords":"Phylogenetics; Evolutionary biology; Biology; Order (exchange); Computational biology; Paleontology; Gene; Genetics; Economics","score_opus":0.00961919351483483,"score_gpt":0.2658073958321393,"score_spread":0.2561882023173045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971276942","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70094705,0.00017238945,0.2970203,0.00012619836,0.000007869088,0.000030611416,0.0001784776,0.0008736434,0.0006435972],"genre_scores_gemma":[0.5872527,0.000117404205,0.41122854,0.000050735303,0.00000750875,0.000043067485,0.000714931,0.00018244663,0.00040267466],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99963486,0.00018225363,0.00002340916,0.00007751336,0.000051988318,0.000030085661],"domain_scores_gemma":[0.99837697,0.00093341013,0.000121347904,0.00028565523,0.00021218177,0.000070395734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020208103,0.00038626738,0.000783854,0.0012829156,0.00046795257,0.0010411692,0.0009009856,0.0006636597,0.00055681576],"category_scores_gemma":[0.0075018066,0.0005895919,0.0005575853,0.00083402905,0.00048177573,0.0007817463,0.0008329481,0.0008376182,0.00027142596],"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":[0.0003844764,0.000112805836,0.034656234,0.00011089775,0.00009030028,0.00019368729,0.00067055033,0.77337074,0.031721372,0.011617665,0.0005577106,0.14651357],"study_design_scores_gemma":[0.000025864701,0.000047994487,0.0020851456,0.000010879393,0.000014818102,0.000036099635,0.00006037238,0.98870635,0.0038021754,0.00474243,0.00045881735,0.000009010238],"about_ca_topic_score_codex":0.0035119639,"about_ca_topic_score_gemma":0.0053945826,"teacher_disagreement_score":0.0035119639,"about_ca_system_score_codex":0.00063332426,"about_ca_system_score_gemma":0.0010802812,"threshold_uncertainty_score":0.010687172},"labels":[],"label_agreement":null},{"id":"W1973255639","doi":"10.1089/cmb.2012.0089","title":"Determining Protein Structures from NOESY Distance Constraints by Semidefinite Programming","year":2012,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Peroxisome Proliferator-Activated Receptors","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":"York University; University of Waterloo","funders":"","keywords":"Semidefinite programming; Mathematical optimization; Euclidean distance; Computer science; Algorithm; Euclidean geometry; Simulated annealing; Mathematics; Artificial intelligence","score_opus":0.00952262510956205,"score_gpt":0.2651261782244295,"score_spread":0.2556035531148675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973255639","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006171725,0.00011282418,0.9898163,0.00029827925,0.000035681427,0.00006874706,0.0001506284,0.00013834704,0.0032074447],"genre_scores_gemma":[0.16906519,0.00049399433,0.8213192,0.0004032774,0.00011329243,0.0008922951,0.0010567153,0.0003763471,0.0062795985],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984674,0.0007362688,0.00005957198,0.00024525225,0.00040278886,0.000088770794],"domain_scores_gemma":[0.9944929,0.004284854,0.00036575782,0.00027601465,0.00045830503,0.00012215436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025425788,0.0017691118,0.0016513286,0.0006343941,0.0005467367,0.0014498961,0.0017007889,0.0014645807,0.004133719],"category_scores_gemma":[0.0061425706,0.0011421645,0.0011508233,0.00079550897,0.0019517258,0.0018459116,0.0018134199,0.0032788804,0.000810551],"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":[0.000038745562,0.00006065281,0.00015754317,0.00012282199,0.000022206821,0.000074599746,0.000037488255,0.953386,0.0009628433,0.029638069,0.0015902006,0.013908846],"study_design_scores_gemma":[0.000017853272,0.000021399952,0.000032031214,0.000007943032,0.0000027933258,0.0000125553815,0.000013852047,0.9749747,0.00040484627,0.02358682,0.0009185083,0.000006764883],"about_ca_topic_score_codex":0.0029616992,"about_ca_topic_score_gemma":0.0037956727,"teacher_disagreement_score":0.004133719,"about_ca_system_score_codex":0.0010600338,"about_ca_system_score_gemma":0.0018696444,"threshold_uncertainty_score":0.013828695},"labels":[],"label_agreement":null},{"id":"W1973260309","doi":"10.1089/cmb.2011.0083","title":"Consistency of Sequence-Based Gene Clusters","year":2011,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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 British Columbia; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft","keywords":"Genome; Gene cluster; Gene; Phylogenetic tree; Consistency (knowledge bases); Biology; Computational biology; Permutation (music); Genomics; Sequence (biology); Phylogenetic network; Gene prediction; Set (abstract data type); Comparative genomics; Genetics; Computer science; Artificial intelligence; Physics","score_opus":0.041981213999927214,"score_gpt":0.2742414387323298,"score_spread":0.2322602247324026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973260309","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2144339,0.00041555343,0.77911276,0.0009663096,0.000031778756,0.00018161703,0.0007249441,0.00078635034,0.0033468925],"genre_scores_gemma":[0.70794886,0.00029222778,0.28610504,0.00024172265,0.000050810908,0.00018741135,0.0026125512,0.00034794753,0.0022134553],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943475,0.0021697497,0.00030277058,0.0015280938,0.0012685014,0.0003835017],"domain_scores_gemma":[0.96492165,0.026368268,0.0018714431,0.0042677606,0.0020407331,0.00053007907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047468916,0.0006076701,0.0011425279,0.0017838752,0.001350133,0.0027234512,0.003516606,0.0016147301,0.0032257668],"category_scores_gemma":[0.03336502,0.0010811193,0.0015832975,0.0023935284,0.0032701558,0.0061318143,0.0028491647,0.0021360859,0.00057473796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012473802,0.00026485918,0.02186365,0.00056434056,0.00025486673,0.0005149528,0.0016143885,0.40269503,0.009695374,0.44886193,0.004726171,0.10769703],"study_design_scores_gemma":[0.00009158939,0.00009421141,0.0011052317,0.00004295817,0.00005184804,0.0002844648,0.00031207417,0.5273168,0.0076549053,0.46046382,0.002543057,0.000039098974],"about_ca_topic_score_codex":0.003115962,"about_ca_topic_score_gemma":0.0024986975,"teacher_disagreement_score":0.0047468916,"about_ca_system_score_codex":0.0017312173,"about_ca_system_score_gemma":0.0019929875,"threshold_uncertainty_score":0.025104284},"labels":[],"label_agreement":null},{"id":"W1976245710","doi":"10.1089/cmb.2005.12.1083","title":"The Statistical Analysis of Spatially Clustered Genes under the Maximum Gap Criterion","year":2005,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Gene expression and cancer classification","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 Ottawa","funders":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Alfred P. Sloan Foundation","keywords":"Pairwise comparison; Genome; Comparative genomics; Computational biology; Identification (biology); Genomics; Biology; Set (abstract data type); Statistical model; Cluster (spacecraft); Statistical analysis; Gene; Genetics; Computer science; Mathematics; Statistics","score_opus":0.02096222089491316,"score_gpt":0.319773445089963,"score_spread":0.29881122419504985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976245710","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14168152,0.0003119012,0.85579693,0.0003702119,0.000027239774,0.000103895945,0.00041870907,0.00043895986,0.0008506457],"genre_scores_gemma":[0.8890708,0.00017151443,0.10799418,0.00022036608,0.0000979176,0.00047096508,0.0011585398,0.00016015883,0.00065567927],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9869704,0.0074172723,0.0005319836,0.002282332,0.0022400103,0.0005579015],"domain_scores_gemma":[0.898393,0.08471585,0.0048504747,0.008309029,0.0027580878,0.00097352307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026491895,0.00062693463,0.0021869952,0.0024543456,0.0013827777,0.0018233305,0.0025436722,0.0017232118,0.0018521282],"category_scores_gemma":[0.08861123,0.000426856,0.0014700426,0.0027501252,0.005413805,0.0027607686,0.0032672505,0.0021973376,0.0002988438],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001682498,0.0002591003,0.08794459,0.00094536325,0.0013245463,0.0012652337,0.0018947637,0.3220113,0.019378219,0.36427566,0.004986565,0.19403216],"study_design_scores_gemma":[0.00006371977,0.00038890596,0.023619102,0.000055211065,0.000090017274,0.0004166165,0.0003146216,0.665814,0.0051610614,0.3022061,0.0018148901,0.00005578724],"about_ca_topic_score_codex":0.0011134975,"about_ca_topic_score_gemma":0.00053707924,"teacher_disagreement_score":0.026491895,"about_ca_system_score_codex":0.0010995284,"about_ca_system_score_gemma":0.001767369,"threshold_uncertainty_score":0.14010423},"labels":[],"label_agreement":null},{"id":"W1976616078","doi":"10.1089/cmb.2007.a004","title":"Paths and Cycles in Breakpoint Graph of Random Multichromosomal Genomes","year":2007,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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 Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Breakpoint; Combinatorics; Genome; Mathematics; Biology; Graph; Genetics; Discrete mathematics; Gene; Chromosome","score_opus":0.006927500281005102,"score_gpt":0.2610461755468781,"score_spread":0.254118675265873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976616078","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9131031,0.00019622706,0.08533095,0.00024125293,0.000009057297,0.00004678748,0.0001770314,0.00023173603,0.00066390197],"genre_scores_gemma":[0.97747225,0.00015584308,0.020792335,0.000041348296,0.000009336871,0.00006616001,0.00042851435,0.00007170474,0.000962555],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993643,0.00022029574,0.000020520203,0.00020094206,0.00010652947,0.00008743008],"domain_scores_gemma":[0.98677826,0.010415881,0.0012898518,0.00056561234,0.0003924737,0.00055801263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016843042,0.000339759,0.00039347072,0.0019436752,0.0004838514,0.0008850789,0.0011647847,0.0010151888,0.0021280553],"category_scores_gemma":[0.01475661,0.0004538597,0.00051709375,0.000923782,0.0014458589,0.0019783182,0.00095854513,0.0007757594,0.00014431615],"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":[0.0005711898,0.00009669109,0.025203612,0.00016094916,0.00012128138,0.0004935609,0.00047237557,0.8050572,0.0090235965,0.14072703,0.0013211934,0.016751245],"study_design_scores_gemma":[0.00006989932,0.00008561843,0.005143783,0.000016928998,0.000025381782,0.00023765505,0.000087766,0.92417186,0.0020362642,0.06740241,0.0006904035,0.000032032254],"about_ca_topic_score_codex":0.003189733,"about_ca_topic_score_gemma":0.0031742984,"teacher_disagreement_score":0.003189733,"about_ca_system_score_codex":0.0013987888,"about_ca_system_score_gemma":0.00047165249,"threshold_uncertainty_score":0.0101489425},"labels":[],"label_agreement":null},{"id":"W1978273076","doi":"10.1089/cmb.2007.r003","title":"A Parameterized Algorithm for Protein Structure Alignment","year":2007,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"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":"University of Waterloo","keywords":"Parameterized complexity; Algorithm; Computer science","score_opus":0.006747070707571181,"score_gpt":0.27536498147432953,"score_spread":0.26861791076675834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978273076","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035434454,0.00013381969,0.991896,0.000110649744,0.000020181376,0.00005162226,0.00012636995,0.0031371787,0.0009806899],"genre_scores_gemma":[0.073997736,0.00028842533,0.92166775,0.00008139942,0.000026907523,0.00021529334,0.0013418224,0.00048902945,0.001891619],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857795,0.0003156962,0.00009990845,0.00044774535,0.0004140581,0.00014475957],"domain_scores_gemma":[0.99860877,0.0004929665,0.0001138024,0.000581424,0.0001416391,0.00006144046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088407414,0.0014001724,0.0014388895,0.0010501656,0.0011283654,0.0016648379,0.0034098937,0.0014951918,0.00768911],"category_scores_gemma":[0.004119903,0.0008066549,0.0012622639,0.0026700206,0.00079421944,0.0039063725,0.0020110838,0.0020463627,0.002852865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050386746,0.00019685627,0.0008088062,0.00032037555,0.00010910395,0.00015138369,0.00022123057,0.31295118,0.013259867,0.06958408,0.014787416,0.5871058],"study_design_scores_gemma":[0.00007138059,0.000049284725,0.00015435804,0.000013052266,0.00001646817,0.00011741776,0.00004065325,0.94757676,0.0028045606,0.040773984,0.008364352,0.00001780199],"about_ca_topic_score_codex":0.00470667,"about_ca_topic_score_gemma":0.004820021,"teacher_disagreement_score":0.00768911,"about_ca_system_score_codex":0.0022254994,"about_ca_system_score_gemma":0.0021048938,"threshold_uncertainty_score":0.025722682},"labels":[],"label_agreement":null},{"id":"W1978802080","doi":"10.1089/cmb.2007.0229","title":"Computing Knock-Out Strategies in Metabolic Networks","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Microbial Metabolic Engineering and Bioproduction","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":"Simon Fraser University","funders":"Simon Fraser University","keywords":"Computation; Computer science; Block (permutation group theory); Computational complexity theory; Metabolic network; Algorithm; Theoretical computer science; Mathematics; Computational biology; Biology; Combinatorics","score_opus":0.010345468351113567,"score_gpt":0.2563395280575266,"score_spread":0.245994059706413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978802080","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41072103,0.00017677696,0.5819499,0.00021414626,0.00002292476,0.000089571935,0.00046473581,0.0017869817,0.0045739706],"genre_scores_gemma":[0.84878993,0.00015254412,0.14868303,0.00007149824,0.000008091531,0.0001520616,0.000625978,0.00019468888,0.0013221885],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99956757,0.00013192049,0.000031612737,0.000102804865,0.00008304711,0.00008306184],"domain_scores_gemma":[0.9978618,0.0016114803,0.00012212119,0.00017239957,0.000121432386,0.00011065902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008691421,0.0011125549,0.0009888762,0.00077821204,0.00046592756,0.001206792,0.0012182716,0.0009076907,0.002128013],"category_scores_gemma":[0.0051309313,0.0006836323,0.00075288344,0.00039261027,0.0011403945,0.0019601395,0.0011883865,0.0010103398,0.00029985153],"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":[0.00016687071,0.000044581706,0.00073935284,0.00006540244,0.00002534222,0.00007775907,0.000046873458,0.9570078,0.0059832237,0.023428585,0.0002647501,0.012149393],"study_design_scores_gemma":[0.00002443897,0.000026616159,0.000091510905,0.000004906503,0.000010983764,0.000010141952,0.000013111975,0.9595568,0.0036424294,0.036409535,0.0002022393,0.0000072677976],"about_ca_topic_score_codex":0.0027502233,"about_ca_topic_score_gemma":0.00399873,"teacher_disagreement_score":0.0027502233,"about_ca_system_score_codex":0.0013851501,"about_ca_system_score_gemma":0.001041448,"threshold_uncertainty_score":0.010050058},"labels":[],"label_agreement":null},{"id":"W1979201422","doi":"10.1089/cmb.2010.0145","title":"Algorithm for Haplotype Inference via Galled-Tree Networks with Simple Galls","year":2012,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","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; University of British Columbia","funders":"","keywords":"Haplotype; Phylogenetic tree; Tree (set theory); Biology; Phylogenetic network; Rank (graph theory); Computer science; Inference; Computational biology; Mathematics; Theoretical computer science; Genetics; Combinatorics; Genotype; Artificial intelligence; Gene","score_opus":0.012905915868547682,"score_gpt":0.2740701020462222,"score_spread":0.2611641861776745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979201422","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010476632,0.0001253393,0.9834985,0.00030830334,0.000045142977,0.00024802607,0.0008706725,0.0028189956,0.0016083958],"genre_scores_gemma":[0.09522891,0.00009317864,0.89878815,0.00018146772,0.000034507713,0.0003820876,0.0030005323,0.00038028887,0.0019108909],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990308,0.00024500155,0.00008387479,0.00027725508,0.00021943123,0.00014360982],"domain_scores_gemma":[0.99616843,0.0021697136,0.00023304872,0.00081043807,0.0004627841,0.00015559194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001581272,0.0009770315,0.0010765601,0.0019037512,0.00087002624,0.001329227,0.002292808,0.0017771738,0.012376438],"category_scores_gemma":[0.009994123,0.00077087333,0.001381193,0.00170463,0.00068036205,0.0028703257,0.0028969736,0.0018990438,0.0034390842],"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":[0.0009543862,0.0003445746,0.004371591,0.0005636606,0.00026873834,0.00027473425,0.0005347029,0.27449512,0.007710126,0.03990485,0.025490226,0.6450872],"study_design_scores_gemma":[0.00020626401,0.00007497616,0.00058584067,0.00003069767,0.00005367429,0.00018465245,0.00008600298,0.9154492,0.0025216409,0.07523203,0.005548247,0.000026673117],"about_ca_topic_score_codex":0.0031742726,"about_ca_topic_score_gemma":0.005275418,"teacher_disagreement_score":0.012376438,"about_ca_system_score_codex":0.0011207093,"about_ca_system_score_gemma":0.0023653868,"threshold_uncertainty_score":0.041403294},"labels":[],"label_agreement":null},{"id":"W1979521110","doi":"10.1089/cmb.2007.0038","title":"A Physical Analogy of the Genetic Toggle Switch","year":2007,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Gene Regulatory Network Analysis","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":"Analogy; Statistical physics; Probability distribution; Computer science; Field (mathematics); Stochastic modelling; Stochastic process; Biological system; Physics; Mathematics; Biology; Statistics","score_opus":0.006131849924920689,"score_gpt":0.2622982573992441,"score_spread":0.25616640747432345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979521110","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20054287,0.00037185417,0.74825656,0.003323008,0.00054199586,0.000092163405,0.000109772176,0.00033426922,0.046427514],"genre_scores_gemma":[0.953419,0.00028544044,0.037181515,0.00059075974,0.0001098152,0.00015500063,0.00003922709,0.00008789606,0.008131272],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99968934,0.00007869417,0.000008274047,0.00006922584,0.000115205155,0.00003926115],"domain_scores_gemma":[0.99962986,0.00016610211,0.000039486735,0.00006439314,0.00003812436,0.000062112595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040372356,0.00019790002,0.00040777828,0.00034791217,0.00068377826,0.0008127805,0.0010291081,0.0013254649,0.0043293103],"category_scores_gemma":[0.0014435339,0.0001844844,0.0007277344,0.00027077924,0.0016660279,0.0014449306,0.0008688237,0.0012760649,0.000342337],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031291336,0.000044439024,0.00034930508,0.000027018072,0.000016053482,0.00018788452,0.00015214627,0.15075387,0.0101921065,0.8348386,0.00068221893,0.002724897],"study_design_scores_gemma":[0.00003468957,0.00006676445,0.0005557752,0.0000118991165,0.00001076977,0.00017453985,0.000044026463,0.6189874,0.0017700784,0.3744252,0.003887221,0.000031624124],"about_ca_topic_score_codex":0.0014907945,"about_ca_topic_score_gemma":0.00051619305,"teacher_disagreement_score":0.0043293103,"about_ca_system_score_codex":0.0005418693,"about_ca_system_score_gemma":0.0006659574,"threshold_uncertainty_score":0.014483035},"labels":[],"label_agreement":null},{"id":"W1982057578","doi":"10.1089/cmb.2004.11.1001","title":"Pooled Genomic Indexing (PGI): Analysis and Design of Experiments","year":2004,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Gene expression and cancer classification","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 de Montréal; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Université de Montréal; National Human Genome Research Institute; Howard Hughes Medical Institute","keywords":"Shotgun sequencing; Pooling; Shotgun; Sequence (biology); clone (Java method); Search engine indexing; Intersection (aeronautics); Genetics; Computational biology; Biology; Sequence-tagged site; Row; Contig; Alignment-free sequence analysis; Probabilistic logic; Sequence analysis; Column (typography); Computer science; Chromosome; Sequence alignment; DNA sequencing; Genome; Artificial intelligence; Gene; Peptide sequence; Gene mapping; Engineering; Database","score_opus":0.019554499999410908,"score_gpt":0.3009634660872478,"score_spread":0.2814089660878369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982057578","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022381768,0.00023781192,0.96408737,0.000120602985,0.00015154814,0.0098632,0.00080851617,0.0014555117,0.00089363585],"genre_scores_gemma":[0.08499375,0.00021673788,0.8505626,0.0002444314,0.000074404896,0.062097475,0.0009108136,0.00026991946,0.00062983594],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.946884,0.038893722,0.0024846003,0.006149539,0.0040601045,0.001527973],"domain_scores_gemma":[0.92809594,0.053620443,0.005058424,0.008402482,0.0040249736,0.00079765084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05169096,0.0034926794,0.004353539,0.0019278206,0.0010725474,0.002927272,0.0029084617,0.0023657333,0.0041548903],"category_scores_gemma":[0.09528127,0.0018526794,0.0036413805,0.0019288522,0.002064285,0.0016779102,0.0022137149,0.0028835917,0.00087870605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.036084913,0.0028955985,0.014109117,0.007210946,0.007889654,0.00048015107,0.0012222304,0.34433308,0.04370258,0.06847781,0.006483795,0.4671101],"study_design_scores_gemma":[0.0066116615,0.018028514,0.0074040955,0.0002911393,0.0030325088,0.00017033567,0.00024012203,0.8223373,0.048213,0.076008625,0.017313061,0.00034957714],"about_ca_topic_score_codex":0.0010580699,"about_ca_topic_score_gemma":0.00075241696,"teacher_disagreement_score":0.05169096,"about_ca_system_score_codex":0.0031551293,"about_ca_system_score_gemma":0.005301754,"threshold_uncertainty_score":0.27337116},"labels":[],"label_agreement":null},{"id":"W1983815263","doi":"10.1089/cmb.2006.13.267","title":"RNA–RNA Interaction Prediction and Antisense RNA Target Search","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":128,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Simon Fraser University","funders":"","keywords":"RNA; Non-coding RNA; Computational biology; Antisense RNA; Biology; Nucleic acid secondary structure; Gene; Nucleic acid structure; Algorithm; Sense (electronics); Genetics; Computer science; Chemistry","score_opus":0.01063543045560723,"score_gpt":0.26713580027726197,"score_spread":0.25650036982165475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983815263","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06532829,0.0002587981,0.9305492,0.00019719798,0.000013844323,0.000053731892,0.00012633699,0.0016406185,0.0018319422],"genre_scores_gemma":[0.4202184,0.00020244549,0.5750962,0.00016372793,0.00003420801,0.0002089773,0.00073690544,0.00021353285,0.003125594],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946743,0.00021248625,0.000023075316,0.000120038596,0.00012148728,0.000055403925],"domain_scores_gemma":[0.9989121,0.0007957123,0.00009391358,0.000054326058,0.00010729605,0.000036615053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001025978,0.00077036326,0.001133496,0.0012073427,0.00041395272,0.0005528637,0.0015765257,0.0014945506,0.0025879792],"category_scores_gemma":[0.0021459812,0.0005843588,0.0007611832,0.0010957244,0.0006132442,0.0011452548,0.0006616388,0.00068602135,0.00075074343],"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":[0.0002053995,0.00016354978,0.0022494476,0.00011089806,0.00007321838,0.00019243638,0.00004566225,0.86032116,0.009141792,0.011787793,0.0021168962,0.11359166],"study_design_scores_gemma":[0.000013510756,0.000021388121,0.00014735373,0.0000020053087,0.00000662606,0.00003099874,0.000007570735,0.99284583,0.0017937054,0.004810871,0.00031610427,0.0000039949105],"about_ca_topic_score_codex":0.0015993372,"about_ca_topic_score_gemma":0.0019337356,"teacher_disagreement_score":0.0025879792,"about_ca_system_score_codex":0.0004526473,"about_ca_system_score_gemma":0.00072085863,"threshold_uncertainty_score":0.008657634},"labels":[],"label_agreement":null},{"id":"W1985113830","doi":"10.1089/cmb.2007.0147","title":"Discovering High-Order Patterns of Gene Expression Levels","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Gene expression and cancer classification","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":"Gene expression; Gene; Biology; Gene cluster; Pair-rule gene; Genetics; Computational biology; Expression (computer science); Regulation of gene expression; Gene expression profiling; Regulator gene; Computer science","score_opus":0.02274656102876796,"score_gpt":0.28096686755892336,"score_spread":0.2582203065301554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985113830","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42761976,0.0013019529,0.5648134,0.000814316,0.000053004624,0.0001216669,0.00202872,0.0012133557,0.0020337524],"genre_scores_gemma":[0.8014196,0.00059609057,0.1943273,0.00013313162,0.000078381825,0.0001441011,0.0022438895,0.00008916672,0.00096836605],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982786,0.00027253613,0.00013976541,0.0005088477,0.00063737575,0.00016286511],"domain_scores_gemma":[0.99448484,0.0034052038,0.0008356769,0.0006027671,0.00052190025,0.00014964576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001186558,0.0005373606,0.0011443268,0.0028311335,0.0005359757,0.0011131555,0.0008214939,0.0005774034,0.0006587552],"category_scores_gemma":[0.007268962,0.0004511547,0.00087300496,0.0024575666,0.0007509739,0.0012095424,0.0007201604,0.0011388985,0.00043833838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007990878,0.0006562118,0.22495973,0.0011248008,0.0005579138,0.0025930288,0.0014807176,0.09679676,0.14345782,0.020066474,0.0049657887,0.5025417],"study_design_scores_gemma":[0.00010138701,0.00036992534,0.16873658,0.00008935647,0.00022978587,0.0018940052,0.0006245364,0.69228756,0.031888004,0.09355797,0.010068564,0.00015238787],"about_ca_topic_score_codex":0.002117073,"about_ca_topic_score_gemma":0.002350011,"teacher_disagreement_score":0.0028311335,"about_ca_system_score_codex":0.0005903724,"about_ca_system_score_gemma":0.0008308751,"threshold_uncertainty_score":0.0062752366},"labels":[],"label_agreement":null},{"id":"W1985474870","doi":"10.1089/cmb.2011.0088","title":"Mapping Association between Long-Range <i>cis</i> -Regulatory Regions and Their Target Genes Using Synteny","year":2011,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Chromatin Dynamics","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":"McGill University and Génome Québec Innovation Centre; McGill University","funders":"Genome Canada","keywords":"Synteny; Biology; Enhancer; Gene; Genome; Genetics; Computational biology; Regulatory sequence; Regulation of gene expression; Transcription factor","score_opus":0.020432127862721822,"score_gpt":0.23256831616129034,"score_spread":0.2121361882985685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985474870","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95849276,0.00049893546,0.039221726,0.00004203372,0.000003862441,0.000023000222,0.00063711783,0.00042608462,0.0006543911],"genre_scores_gemma":[0.9657733,0.00012443597,0.03191251,0.000017897883,0.0000058714654,0.000032020125,0.0016200586,0.000042228898,0.00047182516],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99977773,0.0000388425,0.000011835611,0.00010772927,0.000043299307,0.000020626165],"domain_scores_gemma":[0.99948335,0.0003116014,0.000104917584,0.000024872319,0.00003678822,0.00003840679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032268837,0.00039000835,0.00042318812,0.0010816504,0.0003360036,0.00033799425,0.0002889707,0.00036471503,0.001373467],"category_scores_gemma":[0.0012618743,0.00020274072,0.0004614019,0.00064364326,0.00019929881,0.00021387245,0.00037452648,0.00030306238,0.0003924065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019260928,0.00025226772,0.33383775,0.0005844216,0.0005353327,0.0017054506,0.00059956306,0.08492186,0.40204716,0.0028328635,0.001399442,0.16935779],"study_design_scores_gemma":[0.00014866094,0.00047094683,0.48812273,0.000056422366,0.00038287908,0.0023985398,0.00025423468,0.3985796,0.09824093,0.0064796126,0.004788201,0.000077320394],"about_ca_topic_score_codex":0.002850224,"about_ca_topic_score_gemma":0.0034488842,"teacher_disagreement_score":0.002850224,"about_ca_system_score_codex":0.00022307878,"about_ca_system_score_gemma":0.0003735687,"threshold_uncertainty_score":0.005667269},"labels":[],"label_agreement":null},{"id":"W1985833509","doi":"10.1089/cmb.2010.0123","title":"Finding Nearly Optimal GDT Scores","year":2011,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computation; Conjecture; Heuristic; Mathematics; Algorithm; Statistics; Combinatorics; Set (abstract data type); Computer science; Mathematical optimization","score_opus":0.0318057403196908,"score_gpt":0.28878150794754465,"score_spread":0.25697576762785385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985833509","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3560329,0.0013868299,0.62219536,0.0010643693,0.00017486363,0.00021968443,0.0023769503,0.007480662,0.0090684155],"genre_scores_gemma":[0.5531987,0.0002651087,0.43820897,0.0003555275,0.000056004734,0.00019375856,0.0052508325,0.0009265328,0.0015446417],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960663,0.0007935733,0.00031856305,0.0010938817,0.0011555158,0.0005722442],"domain_scores_gemma":[0.9946473,0.00292426,0.00040292778,0.0008571038,0.0008416959,0.00032661873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034643074,0.0015138268,0.0023406735,0.004012408,0.0010331401,0.002094256,0.0019520192,0.0017255323,0.0039314856],"category_scores_gemma":[0.02013908,0.00078462856,0.0013289403,0.002414695,0.0017167347,0.0024949329,0.0027500207,0.0014043141,0.0017277013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014623747,0.00044366624,0.04239128,0.00079335086,0.00040192148,0.0010652749,0.00060725556,0.30831152,0.031307813,0.055208858,0.04327323,0.5147334],"study_design_scores_gemma":[0.0002515749,0.0002603496,0.0040333695,0.00005748661,0.00008411055,0.0005940407,0.0002931444,0.8942481,0.010086993,0.08418539,0.00584005,0.000065449414],"about_ca_topic_score_codex":0.0018625453,"about_ca_topic_score_gemma":0.0021193044,"teacher_disagreement_score":0.004012408,"about_ca_system_score_codex":0.0014819313,"about_ca_system_score_gemma":0.0025815242,"threshold_uncertainty_score":0.018321276},"labels":[],"label_agreement":null},{"id":"W1986505750","doi":"10.1089/cmb.2009.0165","title":"Detection of Locally Over-Represented GO Terms in Protein-Protein Interaction Networks","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Clinical Research Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Universities Space Research Association","keywords":"Subnetwork; Computer science; Cluster analysis; Biological network; Protein Interaction Networks; Complex network; Clustering coefficient; Gene ontology; Interaction network; Theoretical computer science; Data mining; Artificial intelligence; Machine learning; Protein–protein interaction; Computational biology; Biology; Gene","score_opus":0.005044887690845892,"score_gpt":0.2510740498544096,"score_spread":0.24602916216356374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986505750","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6935824,0.00055513735,0.30385286,0.00021230277,0.000009403182,0.000033000262,0.00035245175,0.0007524049,0.0006500332],"genre_scores_gemma":[0.94994026,0.00015581104,0.048994653,0.000036441586,0.000012542108,0.00004193589,0.00053404993,0.00004621737,0.0002380402],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994247,0.00019636388,0.000030860145,0.0001435098,0.00012986251,0.00007476583],"domain_scores_gemma":[0.9960496,0.0027974953,0.0005154396,0.00033877126,0.00018873416,0.00011007989],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013933562,0.00041928462,0.00066832866,0.003389603,0.00046422498,0.00085495267,0.00067159045,0.00061528856,0.0004431365],"category_scores_gemma":[0.007008626,0.00024596514,0.00052748923,0.0022204935,0.0008739158,0.0009646055,0.0010751545,0.0006281242,0.00010398681],"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":[0.0010262381,0.00023933224,0.15736046,0.0006791761,0.0005101721,0.0012751451,0.0012402475,0.44742373,0.21097358,0.029444916,0.0019845066,0.14784251],"study_design_scores_gemma":[0.000029161129,0.000055598255,0.052533004,0.000024969657,0.0001099732,0.000492472,0.00019310584,0.88566774,0.013168499,0.04663451,0.0010462794,0.0000447367],"about_ca_topic_score_codex":0.002576695,"about_ca_topic_score_gemma":0.0045985975,"teacher_disagreement_score":0.003389603,"about_ca_system_score_codex":0.0006043818,"about_ca_system_score_gemma":0.0004584984,"threshold_uncertainty_score":0.0073689222},"labels":[],"label_agreement":null},{"id":"W1991119060","doi":"10.1089/cmb.2004.11.933","title":"The Role of Unequal Crossover in Alpha-Satellite DNA Evolution: A Computational Analysis","year":2004,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","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":"Simon Fraser University","funders":"","keywords":"Crossover; Satellite; Alpha (finance); Computational biology; Computer science; Biology; Evolutionary biology; Mathematics; Aerospace engineering; Artificial intelligence; Engineering; Statistics","score_opus":0.008642758030217107,"score_gpt":0.23775524134235315,"score_spread":0.22911248331213604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991119060","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94277084,0.00035408343,0.04837751,0.0011997507,0.000029529658,0.00004857829,0.00029049712,0.00021778673,0.006711414],"genre_scores_gemma":[0.96431535,0.00022658761,0.03367075,0.000116983974,0.000020294889,0.00012475786,0.0003675103,0.000034602268,0.0011230927],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997919,0.00010515286,0.000009631141,0.00003023629,0.000028042032,0.00003503102],"domain_scores_gemma":[0.9932815,0.006128218,0.00018772959,0.00014128134,0.00014417109,0.00011712389],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001035689,0.000431736,0.0008341928,0.00062949996,0.0007775141,0.0010223892,0.0012953386,0.0014430612,0.0019380999],"category_scores_gemma":[0.006046464,0.00035677754,0.0007647568,0.00083541736,0.0011123371,0.0014279562,0.0007809489,0.0009048739,0.00011351481],"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":[0.00010460779,0.00007133543,0.004400441,0.00005463982,0.00004349674,0.000085894295,0.000064388194,0.97863585,0.00020841771,0.010552492,0.00033445118,0.0054439576],"study_design_scores_gemma":[0.000015257123,0.000009586238,0.0003295782,0.0000025342545,0.000008837146,0.000009540919,0.000019634525,0.9956489,0.0000627946,0.0037973872,0.00009341701,0.0000025672398],"about_ca_topic_score_codex":0.010750339,"about_ca_topic_score_gemma":0.010326696,"teacher_disagreement_score":0.010750339,"about_ca_system_score_codex":0.0008316875,"about_ca_system_score_gemma":0.0013740845,"threshold_uncertainty_score":0.021375537},"labels":[],"label_agreement":null},{"id":"W1992306462","doi":"10.1089/cmb.2008.21tt","title":"How to Synchronize Biological Clocks","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":47,"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; European Commission","keywords":"Biological clock; Construct (python library); Computer science; Biological network; Synchronization (alternating current); Set (abstract data type); Distributed computing; Theoretical computer science; Computer network; Biology; Computational biology; Programming language; Neuroscience","score_opus":0.01107651730193498,"score_gpt":0.2620000061672376,"score_spread":0.25092348886530264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992306462","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038016878,0.00015307401,0.95802337,0.0003108409,0.00007344774,0.00004631964,0.000031659027,0.0002100749,0.0031343799],"genre_scores_gemma":[0.4661127,0.00034329836,0.5292081,0.00015122157,0.00006473118,0.00023385398,0.00015735807,0.00022960549,0.0034991177],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993382,0.00026159806,0.0000328421,0.00020014924,0.000115837924,0.000051346426],"domain_scores_gemma":[0.9984546,0.00095066475,0.00014000313,0.00018859071,0.00018721448,0.00007893424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015478677,0.0004013073,0.0005687792,0.00045531135,0.00057738746,0.0010802072,0.001153676,0.00092009094,0.003193887],"category_scores_gemma":[0.0076925596,0.00036359162,0.00041581574,0.00033508232,0.0011363947,0.002834354,0.0014330727,0.0008190548,0.000628036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002902633,0.000040156257,0.0020543518,0.00018048125,0.000063830834,0.00012511827,0.00044622747,0.4016765,0.012861775,0.4656467,0.0019390186,0.11467566],"study_design_scores_gemma":[0.000087485416,0.00006923564,0.00017059302,0.00003242565,0.000020350253,0.00007179607,0.000086467415,0.8196212,0.0054682796,0.16566488,0.008687566,0.000019723031],"about_ca_topic_score_codex":0.0009882993,"about_ca_topic_score_gemma":0.0005553346,"teacher_disagreement_score":0.003193887,"about_ca_system_score_codex":0.00047664513,"about_ca_system_score_gemma":0.0007631705,"threshold_uncertainty_score":0.010684609},"labels":[],"label_agreement":null},{"id":"W1994823302","doi":"10.1089/cmb.2011.0128","title":"The Complexity of the Gapped Consecutive-Ones Property Problem for Matrices of Bounded Maximum Degree","year":2011,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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":"University of British Columbia; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bounded function; Degree (music); Combinatorics; Row; Mathematics; Upper and lower bounds; Polynomial; Matrix (chemical analysis); Binary number; Discrete mathematics; Physics; Computer science; Mathematical analysis; Chemistry; Arithmetic","score_opus":0.08174218429878709,"score_gpt":0.2810726362280495,"score_spread":0.1993304519292624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994823302","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5663281,0.0033219538,0.38393584,0.011502087,0.00031678617,0.0006760486,0.009369931,0.0024341603,0.022115072],"genre_scores_gemma":[0.8932323,0.0015249504,0.088506594,0.001092401,0.00038348234,0.000544859,0.007443473,0.00059731357,0.006674715],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951391,0.0014514045,0.0002889248,0.0012926258,0.000872168,0.00095566],"domain_scores_gemma":[0.9528995,0.039515514,0.0026222658,0.002170115,0.001446426,0.0013462303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023259295,0.0019268795,0.0027349163,0.00084585935,0.0018255294,0.005509721,0.0035309219,0.0032767802,0.00888516],"category_scores_gemma":[0.024193859,0.0010109552,0.0018382794,0.0020166507,0.0021953427,0.01029412,0.0031467092,0.0038750449,0.0011643698],"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":[0.0035468428,0.00075074454,0.0061381543,0.0022925423,0.00038620847,0.0010176442,0.0011003735,0.7446222,0.012998277,0.1284802,0.030761981,0.067904815],"study_design_scores_gemma":[0.00039632825,0.00015514281,0.00090671616,0.00007262028,0.00006935167,0.0003710383,0.00025555366,0.7363548,0.0025894288,0.25666767,0.0021072284,0.00005411394],"about_ca_topic_score_codex":0.007684738,"about_ca_topic_score_gemma":0.0061521344,"teacher_disagreement_score":0.00888516,"about_ca_system_score_codex":0.0037056576,"about_ca_system_score_gemma":0.003616247,"threshold_uncertainty_score":0.029723883},"labels":[],"label_agreement":null},{"id":"W1999060916","doi":"10.1089/cmb.2007.0198","title":"Novel and Efficient RNA Secondary Structure Prediction Using Hierarchical Folding","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"RNA and protein synthesis mechanisms","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 British Columbia","funders":"","keywords":"Pseudoknot; Nucleic acid secondary structure; Protein secondary structure; RNA; Nucleic acid structure; Computer science; Computational biology; Energy minimization; Algorithm; Base pair; Folding (DSP implementation); Bioinformatics; Theoretical computer science; Biology; Genetics; DNA; Physics; Engineering","score_opus":0.015793937090755262,"score_gpt":0.2522987994211601,"score_spread":0.23650486233040485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999060916","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024866948,0.0002835972,0.96919525,0.00009322026,0.000033548575,0.000068578905,0.0002036475,0.0045446167,0.00071054616],"genre_scores_gemma":[0.15767232,0.00020524213,0.83913076,0.00009101009,0.000023739183,0.00011056293,0.001041539,0.00031057312,0.0014142455],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99958783,0.00007215638,0.000028846825,0.00011279985,0.0001567873,0.00004155516],"domain_scores_gemma":[0.9993594,0.00024090082,0.00006924868,0.00010865512,0.0001685572,0.000053217685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006339348,0.00096557144,0.000953246,0.0009095282,0.0006502966,0.000817625,0.0013629035,0.00092375866,0.0013094977],"category_scores_gemma":[0.0015093769,0.0005092383,0.0007383533,0.0009221599,0.00046626994,0.001461409,0.001030038,0.0009393977,0.00090152025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023642175,0.00023547758,0.0047110473,0.0002676356,0.00013056188,0.00020676406,0.00016906051,0.4467299,0.059707146,0.0123447515,0.007774815,0.46748635],"study_design_scores_gemma":[0.000012115677,0.000026702108,0.00024037236,0.00000436466,0.0000060766406,0.000028887916,0.000008877741,0.9905014,0.004667566,0.0037038387,0.0007923235,0.000007415692],"about_ca_topic_score_codex":0.0045514666,"about_ca_topic_score_gemma":0.0065362393,"teacher_disagreement_score":0.0045514666,"about_ca_system_score_codex":0.0008050021,"about_ca_system_score_gemma":0.001220178,"threshold_uncertainty_score":0.009049952},"labels":[],"label_agreement":null},{"id":"W2000692739","doi":"10.1089/cmb.2008.0087","title":"Heuristic Approach to Sparse Approximation of Gene Regulatory Networks","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Gene Regulatory Network Analysis","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":"Heuristic; Gene regulatory network; Computational biology; Computer science; Gene; Biology; Mathematics; Artificial intelligence; Mathematical optimization; Genetics; Gene expression","score_opus":0.014543373137551462,"score_gpt":0.2369159129839828,"score_spread":0.22237253984643132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000692739","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011017254,0.00012687405,0.987676,0.0001537529,0.000011980542,0.00002900183,0.000059270355,0.00021845505,0.00070749276],"genre_scores_gemma":[0.29383746,0.00028247436,0.702757,0.00020164692,0.00007364975,0.00041630218,0.0005351552,0.00013198375,0.0017642134],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999338,0.00036570732,0.00002142279,0.00008256044,0.00013061383,0.000061775965],"domain_scores_gemma":[0.9962782,0.0030531713,0.00019141921,0.0001637895,0.00024052022,0.00007289176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016697088,0.0008132678,0.0013870477,0.0012917725,0.0004518668,0.0008734185,0.0014207534,0.0012251117,0.0018369752],"category_scores_gemma":[0.007193897,0.0006106898,0.0006961072,0.0011503258,0.0010500342,0.0008554437,0.0009305913,0.0011924062,0.00034942376],"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":[0.000047245692,0.00002461592,0.00029144294,0.000047103258,0.000018158591,0.00004553781,0.00003308415,0.9687876,0.00077675364,0.012175096,0.00064497226,0.017108416],"study_design_scores_gemma":[0.0000074258896,0.000004934209,0.000022676246,0.0000022465588,0.0000014756748,0.000005272709,0.0000039649376,0.99456584,0.0001000042,0.005164928,0.000119743476,0.0000015458775],"about_ca_topic_score_codex":0.0049842414,"about_ca_topic_score_gemma":0.005787134,"teacher_disagreement_score":0.0049842414,"about_ca_system_score_codex":0.0010710418,"about_ca_system_score_gemma":0.001415188,"threshold_uncertainty_score":0.009910464},"labels":[],"label_agreement":null},{"id":"W2001076853","doi":"10.1089/106652701446170","title":"Comparison of Additive Trees Using Circular Orders","year":2000,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Plant and animal studies","field":"Agricultural and Biological Sciences","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 de Montréal; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Distance matrix; Distance matrices in phylogeny; Mathematics; Tree (set theory); Metric (unit); Matrix (chemical analysis); Combinatorics; Similarity (geometry); Table (database); Tree structure; Distance measures; Algorithm; Topology (electrical circuits); Discrete mathematics; Computer science; Binary tree; Image (mathematics); Artificial intelligence; Data mining","score_opus":0.07513292765423034,"score_gpt":0.3015252342484584,"score_spread":0.22639230659422804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001076853","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2852623,0.00043576112,0.7085684,0.00012769879,0.000047436835,0.000121757774,0.00043156755,0.0009703688,0.0040347716],"genre_scores_gemma":[0.4852002,0.0003103035,0.51142824,0.000045906334,0.000022341042,0.00006659208,0.0015985926,0.00024138487,0.0010864309],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981048,0.0005564571,0.00021214092,0.00038341508,0.0005818221,0.0001613655],"domain_scores_gemma":[0.99064964,0.0056117396,0.0007046069,0.0011359254,0.0015405971,0.0003576017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002348508,0.00044580683,0.0008970919,0.0044898335,0.0008944098,0.0023513518,0.0010743478,0.0007119312,0.0029468772],"category_scores_gemma":[0.01573304,0.00048978126,0.00082436076,0.0022782886,0.0008490236,0.0033853727,0.0014468713,0.00070582924,0.0005899286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017259888,0.00025973617,0.019173156,0.0006222072,0.00027241776,0.000393116,0.0016801197,0.30702755,0.028432956,0.14781745,0.0030606024,0.48953465],"study_design_scores_gemma":[0.00008626614,0.00042017526,0.005878219,0.00007042744,0.00012356818,0.00040888757,0.00096221967,0.8562275,0.017636074,0.10974142,0.008348222,0.00009701929],"about_ca_topic_score_codex":0.0027322243,"about_ca_topic_score_gemma":0.0045173685,"teacher_disagreement_score":0.0044898335,"about_ca_system_score_codex":0.00086282886,"about_ca_system_score_gemma":0.0012264672,"threshold_uncertainty_score":0.012420297},"labels":[],"label_agreement":null},{"id":"W2001390039","doi":"10.1089/cmb.2006.0136","title":"Efficient Algorithms for Counting and Reporting Segregating Sites in Genomic Sequences","year":2007,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","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":"McMaster University","funders":"","keywords":"Set (abstract data type); Sequence (biology); Algorithm; Computer science; Sample (material); Sublinear function; Data set; Biology; Computational biology; Mathematics; Genetics; Artificial intelligence; Combinatorics","score_opus":0.0333006308644674,"score_gpt":0.3234489920134218,"score_spread":0.2901483611489544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001390039","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0090736495,0.00043907884,0.97911876,0.00024256796,0.00006434801,0.0002543625,0.0012325291,0.0091073215,0.00046732608],"genre_scores_gemma":[0.02984694,0.00019199104,0.96579975,0.00008671832,0.00005521843,0.00046382722,0.0027215504,0.00027228653,0.0005619017],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.991787,0.0019137339,0.0011932531,0.0018515461,0.0027387429,0.00051568204],"domain_scores_gemma":[0.9700981,0.018533802,0.0027661794,0.0054366696,0.0025523927,0.00061286875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007008898,0.0024966577,0.0026758641,0.0066096857,0.0016622309,0.004796009,0.0067963083,0.0033017553,0.0041034645],"category_scores_gemma":[0.0361156,0.0017902622,0.0018002979,0.0079267705,0.001602072,0.0061136796,0.00413982,0.0033562945,0.0035868713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009619821,0.00047518633,0.0068664616,0.00061764364,0.00018460088,0.0001996777,0.00043325417,0.082319565,0.025852004,0.020632224,0.016957425,0.84449995],"study_design_scores_gemma":[0.0006015864,0.00019905434,0.0029158855,0.00007510689,0.000106770094,0.00088556,0.00026252982,0.8544909,0.033138253,0.09564704,0.011488883,0.0001884048],"about_ca_topic_score_codex":0.0044891452,"about_ca_topic_score_gemma":0.007502254,"teacher_disagreement_score":0.007008898,"about_ca_system_score_codex":0.0019869457,"about_ca_system_score_gemma":0.0045148027,"threshold_uncertainty_score":0.037066996},"labels":[],"label_agreement":null},{"id":"W2002421352","doi":"10.1089/cmb.2009.0007","title":"Maximal Information Transfer and Behavior Diversity in Random Threshold Networks","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Opinion Dynamics and Social Influence","field":"Physics and Astronomy","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 Calgary","funders":"","keywords":"Pairwise comparison; Information transfer; Diversity (politics); Chaotic; Computer science; Information transmission; Statistical physics; Transmission (telecommunications); Topology (electrical circuits); Theoretical computer science; Mathematics; Physics; Computer network; Artificial intelligence; Telecommunications","score_opus":0.010484154669825345,"score_gpt":0.2601999614000828,"score_spread":0.24971580673025742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002421352","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85699314,0.00032059406,0.1304558,0.00080833654,0.000017606762,0.000059785885,0.0001451042,0.00019194624,0.0110076135],"genre_scores_gemma":[0.9966557,0.0000689275,0.0026579343,0.000037825455,0.000016819526,0.000036616613,0.00003804622,0.000017232218,0.00047084354],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884254,0.00045455122,0.000050257622,0.00019899505,0.00021607424,0.00023760213],"domain_scores_gemma":[0.9891193,0.0072443807,0.0016484502,0.00042321027,0.000491463,0.0010732585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015600867,0.00042320948,0.00074490835,0.0012617169,0.0007979999,0.0012919478,0.0007720032,0.0010074462,0.0015327111],"category_scores_gemma":[0.014897292,0.0004156469,0.0004887296,0.00037862602,0.0022934047,0.0026358087,0.0016808145,0.00074939214,0.00018190726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047305424,0.00017544629,0.0038412376,0.00020859097,0.000108335975,0.0010043399,0.00066316564,0.36110145,0.034329154,0.58799785,0.0014150259,0.008682397],"study_design_scores_gemma":[0.00008029965,0.00014127449,0.0019216958,0.000023563358,0.00002560651,0.00028080182,0.00012575847,0.6035702,0.0043491754,0.38906276,0.00037491551,0.000043938184],"about_ca_topic_score_codex":0.00051969406,"about_ca_topic_score_gemma":0.00029651998,"teacher_disagreement_score":0.0015600867,"about_ca_system_score_codex":0.0010330944,"about_ca_system_score_gemma":0.0004930757,"threshold_uncertainty_score":0.008250654},"labels":[],"label_agreement":null},{"id":"W2003843657","doi":"10.1089/cmb.2013.0085","title":"Using Structural and Evolutionary Information to Detect and Correct Pyrosequencing Errors in Noncoding RNAs","year":2013,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","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":"Agence Nationale de la Recherche","keywords":"Sequence (biology); Pointwise; Algorithm; Computer science; Computational biology; Complement (music); Pipeline (software); Theoretical computer science; Biology; Genetics; Mathematics; Gene","score_opus":0.015177359472025467,"score_gpt":0.2679005415797938,"score_spread":0.25272318210776834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003843657","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16521572,0.00022948942,0.8312818,0.00010702285,0.000048286198,0.000046785506,0.00022600498,0.0021483386,0.0006965767],"genre_scores_gemma":[0.4762394,0.00021503608,0.52195805,0.00006656757,0.000024815721,0.00004859841,0.0005440737,0.00033364966,0.0005697506],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922216,0.00019390309,0.00005815562,0.00019544944,0.00028898066,0.000041391424],"domain_scores_gemma":[0.9980015,0.0010951795,0.00035011448,0.00025277224,0.00025166653,0.00004880146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020192168,0.00067849655,0.0005836602,0.0010294243,0.00043403637,0.0007522244,0.0007004317,0.00091131206,0.00059482735],"category_scores_gemma":[0.011342603,0.0005471504,0.0005784241,0.0008805391,0.0004002198,0.0011284772,0.00074858597,0.0010125615,0.00028071206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005129243,0.00017442062,0.034165036,0.0004896465,0.00019352208,0.0003999147,0.00042977638,0.35025212,0.14004034,0.0116548035,0.0009174432,0.4607701],"study_design_scores_gemma":[0.000019928575,0.000100742574,0.0064508733,0.000033856777,0.00005196125,0.00023672443,0.00005861352,0.9247173,0.055897865,0.01105228,0.0013453906,0.00003437742],"about_ca_topic_score_codex":0.0008851578,"about_ca_topic_score_gemma":0.002231388,"teacher_disagreement_score":0.0020192168,"about_ca_system_score_codex":0.0003852026,"about_ca_system_score_gemma":0.0007409129,"threshold_uncertainty_score":0.010678768},"labels":[],"label_agreement":null},{"id":"W2003921372","doi":"10.1089/cmb.2005.12.812","title":"Chromosomal Breakpoint Reuse in Genome Sequence Rearrangement","year":2005,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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":"Carleton University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Breakpoint; Genome; Biology; Computational biology; Sequence (biology); Genetics; Identification (biology); Gene; Reuse; Computer science; Chromosome","score_opus":0.01606047862208839,"score_gpt":0.2841884439062238,"score_spread":0.2681279652841354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003921372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50023043,0.00060783926,0.4970161,0.0002615924,0.000015412565,0.00006720014,0.00005286721,0.00045409848,0.0012945206],"genre_scores_gemma":[0.91287917,0.00027665662,0.0858002,0.00008455046,0.00001904541,0.00008932216,0.0001455901,0.00013459373,0.0005709043],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99381554,0.0033052217,0.00035052327,0.00091869826,0.0012815815,0.00032831973],"domain_scores_gemma":[0.93093276,0.054947767,0.0047655697,0.0069502327,0.0018653966,0.0005383703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012048721,0.0003324616,0.00095755345,0.0018952515,0.000664956,0.0015153916,0.0014067219,0.0012656112,0.0009499282],"category_scores_gemma":[0.086448856,0.0005198504,0.0007985168,0.001808678,0.002364228,0.0031182556,0.0030267427,0.0010732828,0.00021269785],"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":[0.0009618098,0.00011987652,0.069180705,0.00025524842,0.00030984968,0.00031883953,0.0012830731,0.64032763,0.014155484,0.13805771,0.00047783417,0.13455188],"study_design_scores_gemma":[0.0000681734,0.00017323841,0.0068285028,0.00004468048,0.00007447339,0.00038688997,0.00012407942,0.86805004,0.012591393,0.10995343,0.0016487851,0.000056264653],"about_ca_topic_score_codex":0.0017832512,"about_ca_topic_score_gemma":0.0020384602,"teacher_disagreement_score":0.012048721,"about_ca_system_score_codex":0.0012968403,"about_ca_system_score_gemma":0.0010546558,"threshold_uncertainty_score":0.063720465},"labels":[],"label_agreement":null},{"id":"W2004998616","doi":"10.1089/cmb.2009.0031","title":"Towards Improved Assessment of Functional Similarity in Large-Scale Screens: A Study on Indel Length","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","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":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Indel; Sequence alignment; Computer science; Hidden Markov model; Similarity (geometry); Markov chain; Multiple sequence alignment; Sequence (biology); Alignment-free sequence analysis; Computational biology; Algorithm; Structural alignment; Biology; Genetics; Artificial intelligence; Gene; Machine learning; Peptide sequence; Image (mathematics)","score_opus":0.017585471397804735,"score_gpt":0.3092551470240396,"score_spread":0.29166967562623486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004998616","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5273446,0.0020212163,0.4658544,0.00018132421,0.00002113684,0.00017546161,0.00042188462,0.0026896494,0.0012904844],"genre_scores_gemma":[0.7329132,0.0006925334,0.26460996,0.000121405465,0.000015852806,0.00011421163,0.0005959237,0.00029758387,0.0006393822],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983699,0.0005531937,0.0001140386,0.0003541204,0.00052882597,0.0000800635],"domain_scores_gemma":[0.9945852,0.0035838934,0.0007147956,0.00050918304,0.00043807758,0.00016879347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027937547,0.0006869186,0.0010892485,0.0015398206,0.00029715788,0.00091711426,0.00079866673,0.0008367056,0.0007057297],"category_scores_gemma":[0.008795622,0.00029529282,0.0005011948,0.0009198814,0.0005024457,0.0012548735,0.0008967295,0.0009944708,0.0002855672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077769166,0.0004563017,0.020854458,0.00061706244,0.00020592948,0.00040607,0.00019583124,0.051923428,0.7281849,0.003798214,0.00037425495,0.19220595],"study_design_scores_gemma":[0.000061547944,0.0013326135,0.03149765,0.00005343117,0.00024997944,0.0012174414,0.0001438022,0.6234311,0.33441845,0.0057341373,0.0017333926,0.00012649767],"about_ca_topic_score_codex":0.00050364225,"about_ca_topic_score_gemma":0.00068224047,"teacher_disagreement_score":0.0027937547,"about_ca_system_score_codex":0.00041111693,"about_ca_system_score_gemma":0.000384106,"threshold_uncertainty_score":0.014774978},"labels":[],"label_agreement":null},{"id":"W2006716451","doi":"10.1089/cmb.2010.0113","title":"Minimal Conflicting Sets for the Consecutive Ones Property in Ancestral Genome Reconstruction","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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":"Simon Fraser University","funders":"","keywords":"Row; Monotone polygon; Logical matrix; Set (abstract data type); Combinatorics; Bounded function; Block matrix; Mathematics; Function (biology); Genome; Property (philosophy); Matrix (chemical analysis); Computer science; Discrete mathematics; Biology; Genetics; Group (periodic table)","score_opus":0.022886922461080095,"score_gpt":0.3087363574746885,"score_spread":0.28584943501360843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006716451","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3736979,0.00019469496,0.62261146,0.00049076386,0.0000146647535,0.00013873054,0.0005760065,0.0006211986,0.0016545851],"genre_scores_gemma":[0.581124,0.00006651775,0.41611162,0.00011779083,0.000018928724,0.0001298299,0.0018067549,0.00011407938,0.0005104854],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888915,0.0005077878,0.00007565536,0.00021285602,0.00022527082,0.00008933793],"domain_scores_gemma":[0.9874478,0.010393458,0.0006707114,0.0007421946,0.00054417585,0.0002016315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002580693,0.0004322378,0.0005350378,0.0012126883,0.00077309494,0.0010588131,0.0010410219,0.0008395715,0.002768974],"category_scores_gemma":[0.018066587,0.00054291,0.0008715384,0.00093105604,0.0010323112,0.0016034333,0.0010689512,0.0010809911,0.00023634508],"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":[0.0015640205,0.00046336773,0.041140687,0.0003624522,0.00016789006,0.00072785263,0.000850243,0.6442428,0.018309971,0.084032424,0.004413174,0.2037251],"study_design_scores_gemma":[0.00006939225,0.000078630816,0.0020932192,0.00001842255,0.00002587236,0.00022985572,0.000111568326,0.9340234,0.0050005866,0.057554368,0.00077607867,0.00001866392],"about_ca_topic_score_codex":0.0017672132,"about_ca_topic_score_gemma":0.0025317639,"teacher_disagreement_score":0.002768974,"about_ca_system_score_codex":0.0005806554,"about_ca_system_score_gemma":0.0010454117,"threshold_uncertainty_score":0.013648152},"labels":[],"label_agreement":null},{"id":"W2007492229","doi":"10.1089/106652704773416966","title":"From a Phylogenetic Tree to a Reticulated Network","year":2004,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":79,"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 du Québec à Montréal","funders":"","keywords":"Reticulate; Reticulate evolution; Phylogenetic tree; Phylogenetic network; Biology; Phylogenetics; Evolutionary biology; Tree (set theory); Most recent common ancestor; Ancestor; Paleontology; Genetics; Gene; Combinatorics; Mathematics; Geography","score_opus":0.009135419365097668,"score_gpt":0.2517320367021659,"score_spread":0.2425966173370682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007492229","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019470345,0.00039691024,0.9770015,0.0003590136,0.000029217634,0.000045434303,0.00030619308,0.0007189086,0.0016725078],"genre_scores_gemma":[0.15542372,0.0008477507,0.8404355,0.00017787536,0.000043905355,0.00013651101,0.0011161362,0.00043735994,0.0013812969],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998811,0.00059404917,0.000054730783,0.00032461216,0.00016380394,0.000051786792],"domain_scores_gemma":[0.9960731,0.002528335,0.00030311386,0.00061986607,0.0003197328,0.00015577643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019520574,0.0006021661,0.0006457862,0.002158619,0.0011207414,0.0021947173,0.0016842594,0.00115476,0.004364779],"category_scores_gemma":[0.013384712,0.0009022119,0.0008054191,0.0015686817,0.0017278484,0.0057107676,0.0021382407,0.001626624,0.0014456366],"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":[0.00021880493,0.000055847777,0.0039626486,0.0007109846,0.00017778217,0.00067741185,0.0022691085,0.35010412,0.012265649,0.4256738,0.007041648,0.19684222],"study_design_scores_gemma":[0.000017362647,0.000038648803,0.0006628598,0.000072433,0.00003470326,0.0002891631,0.00015479837,0.52161396,0.0017636261,0.46084583,0.01447851,0.000028110471],"about_ca_topic_score_codex":0.0016776978,"about_ca_topic_score_gemma":0.0019054444,"teacher_disagreement_score":0.004364779,"about_ca_system_score_codex":0.0013052486,"about_ca_system_score_gemma":0.0007002552,"threshold_uncertainty_score":0.014601648},"labels":[],"label_agreement":null},{"id":"W2008288996","doi":"10.1089/10665270252935511","title":"A General Edit Distance between RNA Structures","year":2002,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":207,"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; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Edit distance; RNA; Similarity (geometry); Set (abstract data type); Computer science; Computation; Nucleic acid secondary structure; Arc (geometry); Algorithm; Mathematics; Theoretical computer science; Artificial intelligence; Geometry; Biology; Genetics; Programming language","score_opus":0.01613724710562217,"score_gpt":0.2617552788092111,"score_spread":0.24561803170358895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008288996","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033835117,0.0006785732,0.9608782,0.00017570151,0.0000877555,0.000082262275,0.0008993304,0.0005438966,0.0028192236],"genre_scores_gemma":[0.40400696,0.0009327774,0.58662176,0.00018085526,0.00017227633,0.0001882975,0.0021772797,0.00017192903,0.0055477964],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997815,0.00038534234,0.0001860072,0.00089583546,0.00063752895,0.00008022371],"domain_scores_gemma":[0.99780494,0.00092710165,0.00023663635,0.0004972245,0.00041980855,0.00011439341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010210105,0.000701651,0.0008245961,0.0021975625,0.00057906035,0.0015358631,0.0018015656,0.001203756,0.0026292733],"category_scores_gemma":[0.0054612583,0.00024524622,0.00080403185,0.0024354255,0.00084589206,0.0032458093,0.0013473692,0.00079716847,0.00085596874],"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":[0.0003269419,0.00017413833,0.004661139,0.00071420247,0.0002882837,0.00079639826,0.0003746529,0.24179974,0.038867358,0.23762605,0.006289026,0.46808204],"study_design_scores_gemma":[0.00004380014,0.0004834671,0.0027311386,0.00006363275,0.000090774614,0.0023269947,0.00013494199,0.6471317,0.020813964,0.29818636,0.027881017,0.00011224123],"about_ca_topic_score_codex":0.0008098477,"about_ca_topic_score_gemma":0.0009402627,"teacher_disagreement_score":0.0026292733,"about_ca_system_score_codex":0.0006440808,"about_ca_system_score_gemma":0.0006750733,"threshold_uncertainty_score":0.008795798},"labels":[],"label_agreement":null},{"id":"W2013476107","doi":"10.1089/cmb.2006.13.1005","title":"The Distribution of Genomic Distance between Random Genomes","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Combinatorics; Breakpoint; Random graph; Probability distribution; Distribution (mathematics); Mathematics; Biology; Graph; Computational biology; Genetics; Gene; Statistics","score_opus":0.0060786303690669044,"score_gpt":0.2405020344163715,"score_spread":0.23442340404730458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013476107","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63159484,0.0007299188,0.36168957,0.0022033418,0.000060220995,0.00010276559,0.00057797437,0.00049051887,0.00255082],"genre_scores_gemma":[0.97788846,0.0004119893,0.01894078,0.00019537883,0.000082378414,0.00012607065,0.00065252953,0.00010135356,0.0016009845],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965581,0.001641805,0.00009656511,0.00086853054,0.00047866403,0.00035628738],"domain_scores_gemma":[0.91501355,0.073860645,0.00432218,0.003399695,0.0018432334,0.0015607205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008313745,0.00058527186,0.0012664921,0.0024203807,0.00068036723,0.002510884,0.002760086,0.0022257334,0.0029561003],"category_scores_gemma":[0.06952317,0.00093996676,0.0005957017,0.0016201192,0.0045988266,0.00563081,0.0018668,0.0024534971,0.00056857534],"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":[0.0009925003,0.00018442063,0.034640793,0.0002496032,0.0001618387,0.0007487929,0.00046408907,0.56135595,0.007471198,0.3686987,0.0026155275,0.02241659],"study_design_scores_gemma":[0.00011159434,0.00011571784,0.0043317103,0.000032912878,0.000023067942,0.00022549709,0.00010167382,0.9066166,0.0019002326,0.08595257,0.0005251411,0.0000632662],"about_ca_topic_score_codex":0.0021803116,"about_ca_topic_score_gemma":0.0012754507,"teacher_disagreement_score":0.008313745,"about_ca_system_score_codex":0.0022324708,"about_ca_system_score_gemma":0.0007971787,"threshold_uncertainty_score":0.043967783},"labels":[],"label_agreement":null},{"id":"W2016167735","doi":"10.1089/cmb.2011.0108","title":"A 2-Approximation for the Minimum Duplication Speciation Problem","year":2011,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","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":"Simon Fraser University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Genetic algorithm; Gene duplication; Inference; Set (abstract data type); Generalization; Mathematics; Approximation algorithm; Combinatorics; Computer science; Mathematical optimization; Artificial intelligence; Biology; Gene; Evolutionary biology; Genetics","score_opus":0.0262975366789249,"score_gpt":0.26108095322314806,"score_spread":0.23478341654422316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016167735","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12305518,0.0028279272,0.849624,0.004410881,0.0004024179,0.00061363983,0.0043776305,0.0046872473,0.010001072],"genre_scores_gemma":[0.24424143,0.0008432317,0.7432782,0.00079084124,0.00025991243,0.0005183044,0.0064535714,0.0006748093,0.002939625],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978498,0.0005680893,0.000119779645,0.0006952471,0.00040226805,0.00036476925],"domain_scores_gemma":[0.9947678,0.0036001736,0.00036117143,0.0006556663,0.00031191006,0.0003032581],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023244836,0.0023040585,0.002819655,0.0020347193,0.001357106,0.0028880797,0.004154685,0.0036686135,0.010346178],"category_scores_gemma":[0.0110852625,0.0011617844,0.002576233,0.0034969605,0.0010177642,0.0065978304,0.0023006913,0.0038390409,0.0019229706],"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":[0.0019888857,0.0010672075,0.004424879,0.0015551031,0.00045465215,0.0005136377,0.0006658922,0.6337942,0.007412733,0.040472444,0.048049435,0.259601],"study_design_scores_gemma":[0.0004137433,0.0001633889,0.00087520696,0.000060409864,0.00009287441,0.00042628255,0.00019002275,0.89006954,0.0015788687,0.100754514,0.005338794,0.000036401234],"about_ca_topic_score_codex":0.0035873316,"about_ca_topic_score_gemma":0.004862627,"teacher_disagreement_score":0.010346178,"about_ca_system_score_codex":0.0024440608,"about_ca_system_score_gemma":0.0030635202,"threshold_uncertainty_score":0.034611404},"labels":[],"label_agreement":null},{"id":"W2020163930","doi":"10.1089/cmb.2011.0116","title":"Restricted DCJ Model: Rearrangement Problems with Chromosome Reincorporation","year":2011,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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 Ottawa","funders":"Universität Bielefeld; Univerzita Komenského v Bratislave","keywords":"Sorting; Combinatorics; Constraint (computer-aided design); Chromosome; Genome; Mathematics; Time complexity; Computer science; Algorithm; Discrete mathematics; Biology; Genetics; Gene","score_opus":0.02783604522470315,"score_gpt":0.23956346261886585,"score_spread":0.2117274173941627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020163930","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.100118935,0.000612297,0.8886854,0.0010336844,0.00008985025,0.00018899857,0.00045530606,0.001092929,0.007722563],"genre_scores_gemma":[0.5005555,0.0007266101,0.48479602,0.00048729888,0.00016623951,0.0003764753,0.0021875699,0.00041657852,0.0102876015],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884796,0.00027373427,0.00005605529,0.000398816,0.00021865436,0.0002047955],"domain_scores_gemma":[0.9968162,0.00194917,0.00029123275,0.0005120127,0.00021004613,0.00022131047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011148704,0.00095708546,0.0013732689,0.0007794306,0.0012294768,0.002154321,0.0032701509,0.0019680911,0.0063508055],"category_scores_gemma":[0.004924482,0.0006012927,0.0016207905,0.0017774251,0.0014640172,0.0045205993,0.0021634684,0.0027740705,0.0008620137],"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":[0.000838808,0.0004232949,0.0020201127,0.00060090516,0.00013504246,0.0005289027,0.00038098925,0.6305492,0.009360646,0.2336573,0.011680382,0.10982446],"study_design_scores_gemma":[0.00013623133,0.00016426618,0.0003796867,0.000024215242,0.000041538144,0.0005266589,0.00018303089,0.76030105,0.0058674263,0.22536325,0.0069710277,0.000041657317],"about_ca_topic_score_codex":0.0025382603,"about_ca_topic_score_gemma":0.0023628091,"teacher_disagreement_score":0.0063508055,"about_ca_system_score_codex":0.0014169295,"about_ca_system_score_gemma":0.0012529936,"threshold_uncertainty_score":0.021245599},"labels":[],"label_agreement":null},{"id":"W2020892353","doi":"10.1089/cmb.2009.0039","title":"On the Maximal Interval Subgraph of a Tree","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"","keywords":"Tree (set theory); Mathematics; Combinatorics; Interval (graph theory); Induced subgraph isomorphism problem; Interval tree; Subgraph isomorphism problem; Time complexity; Algorithm; Computational complexity theory; Discrete mathematics; Computer science; Tree structure; Graph; Binary tree; Line graph","score_opus":0.013870780396049845,"score_gpt":0.26742344192832346,"score_spread":0.2535526615322736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020892353","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23610507,0.0009037085,0.7518269,0.0009378276,0.000041128555,0.000082247585,0.00064973504,0.0005057864,0.008947628],"genre_scores_gemma":[0.5592474,0.0013096319,0.4303753,0.00024025736,0.00016247628,0.0001570052,0.0024522769,0.00028753656,0.0057682144],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99952865,0.00016431417,0.000020668575,0.00011886141,0.00010514051,0.0000625019],"domain_scores_gemma":[0.997855,0.0015845376,0.00017725908,0.00017728985,0.00012779565,0.00007816552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005491367,0.00036995343,0.00079162396,0.0011115972,0.0006120717,0.0009119501,0.0006446157,0.00058604014,0.0033375763],"category_scores_gemma":[0.0042065782,0.00030258225,0.00062752137,0.0022624838,0.0008735865,0.0026319968,0.001012113,0.00071955257,0.0005165223],"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":[0.000547746,0.00017233769,0.0031892161,0.00077019626,0.000103295424,0.00076231913,0.00094555144,0.2940895,0.023260571,0.4003124,0.016098127,0.2597488],"study_design_scores_gemma":[0.00005371157,0.0000790257,0.0012154506,0.000051230778,0.000032924374,0.00039221326,0.00021383904,0.5099832,0.0042840578,0.47794235,0.005732262,0.000019712703],"about_ca_topic_score_codex":0.0014974802,"about_ca_topic_score_gemma":0.0012689135,"teacher_disagreement_score":0.0033375763,"about_ca_system_score_codex":0.00057481247,"about_ca_system_score_gemma":0.00036261562,"threshold_uncertainty_score":0.011165261},"labels":[],"label_agreement":null},{"id":"W2021281986","doi":"10.1089/cmb.2006.13.1419","title":"Approximating Subtree Distances Between Phylogenies","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":50,"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 British Columbia; Graduate Center; National Science Foundation","keywords":"Tree (set theory); Approximation algorithm; Algorithm; Type (biology); Scheme (mathematics); Computer science; Mathematics; Combinatorics; Biology","score_opus":0.012095741316089299,"score_gpt":0.25926230497714375,"score_spread":0.24716656366105447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021281986","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048840582,0.00063216675,0.94709396,0.0002511978,0.00007990082,0.000049753602,0.00024550426,0.0009832381,0.0018237821],"genre_scores_gemma":[0.22884497,0.00046877872,0.76696414,0.00011807983,0.000060470997,0.00011786729,0.0012964655,0.0002561044,0.001873188],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984659,0.00030377507,0.000120705874,0.00032636835,0.00062116905,0.00016206512],"domain_scores_gemma":[0.99621385,0.0020313477,0.00030312545,0.0008933652,0.00042526503,0.00013311273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012592654,0.00077503826,0.0009736518,0.0019148808,0.0006198546,0.0013307445,0.0021499128,0.0013514766,0.0024322835],"category_scores_gemma":[0.013119925,0.00052507006,0.0009789319,0.0025603303,0.0008624804,0.0022787515,0.0023739652,0.0022490614,0.0010690312],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049236265,0.0001367903,0.0036962614,0.00030231668,0.00012648164,0.00024872422,0.00047799273,0.42057514,0.009772863,0.08399488,0.0062238933,0.4739522],"study_design_scores_gemma":[0.000046581597,0.000089959285,0.00062003604,0.000028713475,0.000030271445,0.0002817558,0.00007476959,0.9056756,0.0050665555,0.08370345,0.0043606474,0.000021569216],"about_ca_topic_score_codex":0.001963323,"about_ca_topic_score_gemma":0.0025511333,"teacher_disagreement_score":0.0024322835,"about_ca_system_score_codex":0.0010796562,"about_ca_system_score_gemma":0.0010013707,"threshold_uncertainty_score":0.008136809},"labels":[],"label_agreement":null},{"id":"W2022846158","doi":"10.1089/10665270360688129","title":"Tests for Gene Clustering","year":2003,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"is_retracted":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":"National Human Genome Research Institute","keywords":"Genome; Biology; Gene; Gene duplication; Comparative genomics; Horizontal gene transfer; Gene cluster; Genetics; Genomics; Evolutionary biology; Gene family; Computational biology; Genome evolution","score_opus":0.019888695644746702,"score_gpt":0.29794481290654184,"score_spread":0.27805611726179513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022846158","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7126497,0.0012134903,0.26808128,0.002042044,0.00032036172,0.00051831995,0.0032012046,0.0020362742,0.009937338],"genre_scores_gemma":[0.9455726,0.0000733995,0.0500828,0.00025865666,0.000104432314,0.00032158,0.0028971985,0.00023325245,0.00045605743],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94041204,0.03446022,0.0030958361,0.010948522,0.00841237,0.0026710376],"domain_scores_gemma":[0.5703571,0.39104718,0.0097966,0.017886637,0.007436914,0.0034755836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033834055,0.0017444645,0.0024426663,0.00726632,0.0033164173,0.004318326,0.005739363,0.0045784106,0.0074162213],"category_scores_gemma":[0.24578106,0.00068127725,0.0036227677,0.007370237,0.008626021,0.0049080015,0.004011575,0.004191911,0.0008197547],"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":[0.008357933,0.0009364958,0.54654586,0.001546138,0.008163648,0.0014775443,0.0018478485,0.15344313,0.009955445,0.08027362,0.009327758,0.17812449],"study_design_scores_gemma":[0.0009061079,0.002297132,0.15052825,0.0002180458,0.0013146151,0.0022793664,0.0024766203,0.64063925,0.013993229,0.17766437,0.007464046,0.00021895496],"about_ca_topic_score_codex":0.0012407522,"about_ca_topic_score_gemma":0.0008429813,"teacher_disagreement_score":0.033834055,"about_ca_system_score_codex":0.0016933806,"about_ca_system_score_gemma":0.0023010308,"threshold_uncertainty_score":0.17893374},"labels":[],"label_agreement":null},{"id":"W2024827079","doi":"10.1089/cmb.2009.0067","title":"Two Lower Bounds for Self-Assemblies at Temperature 1","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Advanced biosensing and bioanalysis techniques","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":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Tile; Square (algebra); Combinatorics; Upper and lower bounds; Domain (mathematical analysis); Mathematics; Discrete mathematics; Computer science; Geometry; Materials science; Mathematical analysis","score_opus":0.005450051418784046,"score_gpt":0.29836028117791136,"score_spread":0.29291022975912734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024827079","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11881426,0.0056274775,0.8099157,0.004860203,0.0009558736,0.00018546102,0.00072793965,0.0020972518,0.056815807],"genre_scores_gemma":[0.66551083,0.002480323,0.30014318,0.0023706534,0.000898365,0.0012373388,0.0016108232,0.0014905363,0.024257926],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995605,0.00074364495,0.00019593658,0.0010217549,0.0012583062,0.0011753449],"domain_scores_gemma":[0.98003346,0.011315482,0.0020240713,0.0031754395,0.0017851528,0.0016664054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032902872,0.0026875585,0.00200522,0.0018040265,0.0020093848,0.0029009944,0.004554224,0.0036589287,0.011069967],"category_scores_gemma":[0.019490536,0.0015794465,0.0029633092,0.0008430358,0.0029449863,0.00789796,0.004294942,0.0076479185,0.0037675912],"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":[0.0014069942,0.0008280859,0.0047141504,0.0013685013,0.00018873117,0.0007797768,0.0009802064,0.23374446,0.08265153,0.5890588,0.018522521,0.06575621],"study_design_scores_gemma":[0.00009419551,0.00045120955,0.0019146253,0.00021962971,0.00012352587,0.0006720848,0.00015253611,0.5254183,0.05510567,0.39977375,0.015909106,0.00016529115],"about_ca_topic_score_codex":0.0007578846,"about_ca_topic_score_gemma":0.00073907344,"teacher_disagreement_score":0.011069967,"about_ca_system_score_codex":0.0023823257,"about_ca_system_score_gemma":0.00088428735,"threshold_uncertainty_score":0.037032664},"labels":[],"label_agreement":null},{"id":"W2026888821","doi":"10.1089/cmb.2006.13.1630","title":"A General Modeling Strategy for Gene Regulatory Networks with Stochastic Dynamics","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Gene Regulatory Network Analysis","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":"University of Calgary","funders":"Fundação para a Ciência e a Tecnologia; Natural Sciences and Engineering Research Council of Canada; Government of Alberta","keywords":"Gene; Gene regulatory network; Genetic network; Stochastic modelling; Computer science; Computational biology; Translation (biology); Genetics; Transcription (linguistics); Regulation of gene expression; Stochastic process; Activator (genetics); Biology; Gene expression; Mathematics; Messenger RNA","score_opus":0.008581990317334634,"score_gpt":0.24164874193117683,"score_spread":0.2330667516138422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026888821","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009717864,0.000099364726,0.9878593,0.00014723466,0.00002019229,0.0000408983,0.00007764479,0.00012063687,0.0019168265],"genre_scores_gemma":[0.56934583,0.001053888,0.41372862,0.0002864993,0.00008186195,0.0010461285,0.00043612492,0.00019577878,0.013825269],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997111,0.0000870947,0.000014694762,0.00007447459,0.00008365724,0.000029000725],"domain_scores_gemma":[0.99976724,0.00011881169,0.000030627096,0.000020479747,0.000039596664,0.000023231527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062495284,0.00091294514,0.00091598846,0.00054022187,0.0005147426,0.00092221354,0.0017087026,0.0013604771,0.0019075105],"category_scores_gemma":[0.0013313302,0.00046944342,0.0014810122,0.0005578508,0.000679849,0.0010300409,0.00069118344,0.0010568168,0.0005159582],"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":[0.0000060785865,0.000009699954,0.000120528486,0.0000150291435,0.000018060722,0.00005717221,0.000026946656,0.9424362,0.0018738693,0.052822582,0.00016488106,0.0024489767],"study_design_scores_gemma":[0.0000035270903,0.0000061883707,0.00002062328,0.0000016612165,0.000004183633,0.000011573709,0.0000023550467,0.9888948,0.00014657516,0.010364119,0.00054023415,0.0000041122953],"about_ca_topic_score_codex":0.006945193,"about_ca_topic_score_gemma":0.0045333356,"teacher_disagreement_score":0.006945193,"about_ca_system_score_codex":0.0010792593,"about_ca_system_score_gemma":0.0012384864,"threshold_uncertainty_score":0.013809562},"labels":[],"label_agreement":null},{"id":"W2028382411","doi":"10.1089/cmb.2011.0086","title":"Theory and Practice of Ultra-Perfection","year":2011,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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; Université du Québec à Montréal","funders":"","keywords":"Perfection; Extant taxon; Epistemology; Computer science; Evolutionary biology; Philosophy; Biology","score_opus":0.015535623767214325,"score_gpt":0.27790593920380113,"score_spread":0.2623703154365868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028382411","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021271095,0.0037597714,0.9291008,0.008481344,0.00026956017,0.000084719824,0.00053735025,0.0004707777,0.03602457],"genre_scores_gemma":[0.64150006,0.0036546038,0.3437979,0.002585526,0.0009111516,0.000545458,0.0010063641,0.0004972101,0.0055017923],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98714185,0.006627362,0.0008075635,0.002996535,0.0018980777,0.00052851817],"domain_scores_gemma":[0.9554934,0.032619882,0.0022578982,0.007475631,0.0014882082,0.0006650384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016408348,0.00094770663,0.0019297575,0.004325571,0.0027457308,0.0067556994,0.0038880815,0.0029189417,0.009339636],"category_scores_gemma":[0.07031822,0.0009624716,0.0020779765,0.0040812804,0.0181064,0.013476497,0.0068602297,0.005304199,0.0016995547],"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":[0.000015018089,0.0000072477987,0.0012426454,0.0001202249,0.00003624518,0.000049541148,0.00031220625,0.008943447,0.00012664126,0.97265327,0.001817332,0.014676179],"study_design_scores_gemma":[0.0000054656393,0.000005154328,0.00014368264,0.000035792873,0.0000043359196,0.000049293034,0.000033700988,0.0075135455,0.00010852222,0.9889557,0.0031376637,0.0000070716933],"about_ca_topic_score_codex":0.001956732,"about_ca_topic_score_gemma":0.001281994,"teacher_disagreement_score":0.016408348,"about_ca_system_score_codex":0.0033451938,"about_ca_system_score_gemma":0.0026558405,"threshold_uncertainty_score":0.08677673},"labels":[],"label_agreement":null},{"id":"W2029399461","doi":"10.1089/cmb.2004.11.800","title":"ThurGood: Evaluating Assembly-to-Assembly Mapping","year":2004,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","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":"Queen's University","funders":"","keywords":"Focus (optics); Ranking (information retrieval); Computer science; Sequence assembly; Computational biology; Artificial intelligence; Biology; Genetics; Gene","score_opus":0.03034881183755104,"score_gpt":0.3214108486167955,"score_spread":0.2910620367792444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029399461","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27025732,0.0052731633,0.61919165,0.0010094851,0.0015346687,0.0013150612,0.013200869,0.07533547,0.012882349],"genre_scores_gemma":[0.3150759,0.0006377497,0.64727545,0.0003467542,0.00013923798,0.0008811612,0.027095202,0.0062100403,0.002338573],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97703105,0.010158303,0.002067622,0.0028491877,0.00700558,0.00088820857],"domain_scores_gemma":[0.9407539,0.03717904,0.0026223059,0.0073619327,0.010807186,0.0012756546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021299476,0.004431175,0.002673043,0.010035902,0.0024431844,0.004534704,0.0038582894,0.0033617618,0.0056652483],"category_scores_gemma":[0.08055679,0.0008666459,0.0022240756,0.006656289,0.0016766286,0.004473765,0.0039428254,0.0018157441,0.0020740111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0049390136,0.0010805209,0.062039707,0.0035942118,0.002908513,0.00080052635,0.0010792197,0.2490132,0.03354404,0.018348157,0.07007464,0.5525782],"study_design_scores_gemma":[0.0005974648,0.001837517,0.010378927,0.00015232062,0.0005136964,0.00046483104,0.0005621915,0.90434474,0.046934605,0.019025568,0.014994866,0.0001931877],"about_ca_topic_score_codex":0.009108553,"about_ca_topic_score_gemma":0.011753061,"teacher_disagreement_score":0.021299476,"about_ca_system_score_codex":0.0025190054,"about_ca_system_score_gemma":0.0034675521,"threshold_uncertainty_score":0.11264378},"labels":[],"label_agreement":null},{"id":"W2033292629","doi":"10.1089/cmb.2009.0238","title":"Ray: Simultaneous Assembly of Reads from a Mix of High-Throughput Sequencing Technologies","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":559,"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 universitaire de Québec","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Compute Canada","keywords":"Contig; Sequence assembly; Hybrid genome assembly; Computer science; Software; DNA sequencing; Reference genome; Genome; Throughput; Computational biology; Sequence (biology); Data mining; Biology; Genetics; Gene; Transcriptome; Operating system","score_opus":0.00983358367180499,"score_gpt":0.2552465525768091,"score_spread":0.24541296890500414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033292629","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048821934,0.0013681112,0.90587234,0.0001626749,0.00028534356,0.0012336738,0.005037334,0.03340289,0.0038156377],"genre_scores_gemma":[0.043068808,0.00069529616,0.93572646,0.00022861271,0.00007730413,0.0012359335,0.011874237,0.0023998483,0.004693482],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967069,0.00083310175,0.00035438323,0.00082104775,0.0010982417,0.00018626473],"domain_scores_gemma":[0.9981893,0.0005702222,0.00026201195,0.00051307474,0.00031412786,0.00015124083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003592884,0.0022616563,0.0020694977,0.0017309174,0.00072951446,0.002002626,0.0017704371,0.0010304556,0.0052714637],"category_scores_gemma":[0.004242675,0.0018310542,0.0019133012,0.0012624586,0.00040480995,0.0013497497,0.0023213252,0.002168122,0.006704054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025315396,0.00029769161,0.0044118087,0.0018895173,0.0010639894,0.00049689185,0.00064698077,0.012216762,0.7763137,0.0053510545,0.015301508,0.17947851],"study_design_scores_gemma":[0.00044588695,0.0015492178,0.0057322485,0.00015098625,0.00056376006,0.0010095986,0.00015923876,0.09497274,0.7909293,0.004915841,0.099260256,0.0003109646],"about_ca_topic_score_codex":0.00050477963,"about_ca_topic_score_gemma":0.0009179854,"teacher_disagreement_score":0.0052714637,"about_ca_system_score_codex":0.00043180748,"about_ca_system_score_gemma":0.00074241165,"threshold_uncertainty_score":0.019001186},"labels":[],"label_agreement":null},{"id":"W2034206030","doi":"10.1089/10665270252935421","title":"Algorithms for Phylogenetic Footprinting","year":2002,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":177,"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; Defense Advanced Research Projects Agency; National Science Foundation","keywords":"Substring; Phylogenetic tree; Footprinting; Computational biology; Biology; Dynamic programming; Set (abstract data type); Computer science; Phylogenetic network; Conserved sequence; Theoretical computer science; Genetics; Algorithm; DNA; Gene; Base sequence","score_opus":0.029776873719534424,"score_gpt":0.2799829105839355,"score_spread":0.25020603686440107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034206030","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007680181,0.00022687344,0.9925775,0.00014367595,0.000045417502,0.00008147466,0.0004437821,0.0037654142,0.0019477574],"genre_scores_gemma":[0.013744881,0.0003220666,0.9809522,0.00011988446,0.000062148574,0.0003827297,0.0016781463,0.001077194,0.0016606457],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99709976,0.0007886176,0.0002810916,0.000707907,0.00085880427,0.00026381598],"domain_scores_gemma":[0.9933542,0.0036858863,0.00030410057,0.0014252532,0.0010448543,0.00018567519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035742603,0.0023787925,0.0019898838,0.004020083,0.0023318522,0.0034547793,0.0047415486,0.0026781312,0.027511856],"category_scores_gemma":[0.018407755,0.0017876261,0.0030575886,0.005329884,0.0015413396,0.0061663054,0.0050364933,0.004265813,0.014181309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018012973,0.0002039917,0.0017530489,0.000662756,0.00020927242,0.00016834702,0.00038121318,0.16430981,0.002813467,0.2137553,0.0393786,0.5761841],"study_design_scores_gemma":[0.000092989656,0.000031790812,0.00021688158,0.00008893161,0.00003683518,0.0001972133,0.00009013579,0.46097383,0.0016250281,0.49316972,0.043439023,0.000037598205],"about_ca_topic_score_codex":0.0027956152,"about_ca_topic_score_gemma":0.0036111102,"teacher_disagreement_score":0.027511856,"about_ca_system_score_codex":0.0017810261,"about_ca_system_score_gemma":0.0023881465,"threshold_uncertainty_score":0.09203637},"labels":[],"label_agreement":null},{"id":"W2034206612","doi":"10.1089/cmb.2008.0054","title":"Gene Family Evolution by Duplication, Speciation, and Loss","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","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":"Computer Research Institute of Montréal; Université de Montréal; Simon Fraser University; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University","keywords":"Gene duplication; Genetic algorithm; Gene family; Biology; Tree rearrangement; Gene; Heuristic; Tree (set theory); Evolutionary biology; Phylogenetics; Computational biology; Genetics; Computer science; Mathematics; Genome; Combinatorics; Artificial intelligence","score_opus":0.008717990535582093,"score_gpt":0.23062074681318978,"score_spread":0.2219027562776077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034206612","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8444986,0.0009201063,0.15120865,0.001073905,0.000018265824,0.00006871927,0.00051058497,0.00019376756,0.00150744],"genre_scores_gemma":[0.90640396,0.0003857311,0.09111402,0.00016885586,0.000034037566,0.00008685666,0.000896989,0.00008660124,0.0008229534],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870574,0.00042673573,0.00009030248,0.00049767597,0.00017748619,0.00010203105],"domain_scores_gemma":[0.98831356,0.008722304,0.0013954929,0.0009661168,0.0002839874,0.00031849032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003906649,0.00043102505,0.001201861,0.0014991623,0.0011739944,0.0014035365,0.0017731105,0.0014026312,0.0017798448],"category_scores_gemma":[0.01895287,0.000599481,0.0012768332,0.002285021,0.0022876095,0.0048398073,0.0014335376,0.0015347032,0.00021549896],"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":[0.0012543065,0.00025051762,0.2076209,0.0007666069,0.00038693435,0.0009952011,0.0018219698,0.5245085,0.0147862015,0.11490057,0.0047267224,0.12798165],"study_design_scores_gemma":[0.00014404215,0.00013316207,0.018652126,0.0000416492,0.0001053698,0.0015359939,0.00039395064,0.7591922,0.0036899904,0.21254507,0.003521272,0.00004510392],"about_ca_topic_score_codex":0.0015898593,"about_ca_topic_score_gemma":0.002562963,"teacher_disagreement_score":0.003906649,"about_ca_system_score_codex":0.0014100093,"about_ca_system_score_gemma":0.00060109526,"threshold_uncertainty_score":0.02066058},"labels":[],"label_agreement":null},{"id":"W2034369306","doi":"10.1089/cmb.2011.0136","title":"Genome Halving and Double Distance with Losses","year":2011,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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 de Montréal","funders":"","keywords":"Genome; Gene duplication; Tree (set theory); Phylogenetic tree; Gene; Gene rearrangement; Biology; Combinatorics; Genome evolution; Node (physics); Segmental duplication; Genetics; Mathematics; Computational biology; Computer science; Gene family; Physics","score_opus":0.01705976222796272,"score_gpt":0.24128566552039846,"score_spread":0.22422590329243575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034369306","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11801069,0.0004364701,0.87690705,0.00048614453,0.00005416008,0.00007728218,0.00022335206,0.0013390598,0.0024657412],"genre_scores_gemma":[0.40814656,0.00016324513,0.58666456,0.0001429414,0.0000370541,0.00012498164,0.0007879552,0.00033770222,0.0035949568],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902713,0.00019976718,0.000047259327,0.00032650103,0.00025907572,0.00014032848],"domain_scores_gemma":[0.9974431,0.0014183364,0.00021548568,0.0004767496,0.0002855873,0.00016071704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001036419,0.0007129459,0.001133373,0.0008815167,0.00067910046,0.0013295119,0.002217951,0.0011745056,0.003458322],"category_scores_gemma":[0.005160284,0.00045777496,0.0008390813,0.0010666212,0.0012041149,0.0022254824,0.0023783974,0.0016184973,0.00064543454],"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":[0.00086372945,0.00016650147,0.0044834344,0.00032104345,0.00009618646,0.00040017863,0.00041661412,0.5755779,0.012435876,0.08321264,0.00555858,0.31646737],"study_design_scores_gemma":[0.00007095562,0.00012906503,0.0005511666,0.000016721166,0.000019383022,0.000281094,0.0001229851,0.908035,0.009017623,0.07853736,0.0031932024,0.000025351206],"about_ca_topic_score_codex":0.002119841,"about_ca_topic_score_gemma":0.0024222662,"teacher_disagreement_score":0.003458322,"about_ca_system_score_codex":0.00090409437,"about_ca_system_score_gemma":0.0012581107,"threshold_uncertainty_score":0.011569262},"labels":[],"label_agreement":null},{"id":"W2035522779","doi":"10.1089/cmb.2006.13.1289","title":"Wavelet Analysis of DNA Walks","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Fractal and DNA sequence analysis","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 New Brunswick","funders":"U.S. National Library of Medicine; National Institutes of Health","keywords":"Computational biology; Wavelet; Intron; Biology; Genome; DNA sequencing; Genetics; genomic DNA; Sequence analysis; DNA; Computer science; Gene; Artificial intelligence","score_opus":0.005689296584836071,"score_gpt":0.2539969995628238,"score_spread":0.2483077029779877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035522779","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20115314,0.0007682553,0.79148644,0.00027747743,0.000096016025,0.00003626447,0.00026556157,0.0002665914,0.005650206],"genre_scores_gemma":[0.90171564,0.0011649346,0.08774983,0.00011520387,0.000113359405,0.00006471441,0.00064410595,0.00016652617,0.00826567],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998099,0.000046719662,0.000008637343,0.000036890546,0.000062110325,0.000035780376],"domain_scores_gemma":[0.9993622,0.0002551661,0.00010101783,0.000055733206,0.00014659803,0.00007926659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033128873,0.0002879232,0.00034673142,0.0014343276,0.00028252442,0.00075384334,0.00028345714,0.00044750268,0.0019529995],"category_scores_gemma":[0.0023713568,0.00017636972,0.0003857511,0.0007748714,0.00058621564,0.0007424672,0.0005623756,0.00057431246,0.00041550724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026017523,0.000052578904,0.002764643,0.00021381573,0.00006269772,0.0005521234,0.00040617856,0.17503448,0.07089527,0.6266892,0.004317749,0.11875106],"study_design_scores_gemma":[0.000015215241,0.000052897045,0.0023680928,0.000024704217,0.000010792668,0.00025837394,0.00007893371,0.8163842,0.005172479,0.17034718,0.0052584847,0.000028637174],"about_ca_topic_score_codex":0.00047691213,"about_ca_topic_score_gemma":0.00030344314,"teacher_disagreement_score":0.0019529995,"about_ca_system_score_codex":0.00028265401,"about_ca_system_score_gemma":0.00022571508,"threshold_uncertainty_score":0.006533444},"labels":[],"label_agreement":null},{"id":"W2035596374","doi":"10.1089/cmb.2009.0047","title":"Maximum Likelihood Genome Assembly","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":129,"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":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Genome; De Bruijn graph; De Bruijn sequence; Contig; Hybrid genome assembly; Sequence assembly; Computational biology; Biology; Genetics; Computer science; Algorithm; Mathematics; Combinatorics; Gene","score_opus":0.009191157194856088,"score_gpt":0.25706119320850007,"score_spread":0.247870036013644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035596374","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049906587,0.00023457776,0.9862141,0.000122121,0.00006025357,0.00011996906,0.0015826692,0.0038961347,0.002779506],"genre_scores_gemma":[0.05191153,0.00025387935,0.93434256,0.00011513055,0.000030909523,0.000321692,0.007346047,0.0013865097,0.0042918106],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984946,0.00045477616,0.000079272366,0.00053149404,0.00031859748,0.00012112782],"domain_scores_gemma":[0.998094,0.00089865376,0.00014645657,0.00041957208,0.0003681942,0.00007307679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014668222,0.0016811226,0.0016955353,0.001675711,0.0012941671,0.001947961,0.0030290359,0.0021867277,0.011666094],"category_scores_gemma":[0.0068922355,0.0012768096,0.002014368,0.0017509944,0.00065067445,0.0016773216,0.0021812473,0.00200291,0.008093952],"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":[0.0009728312,0.00036066314,0.0048770085,0.0015897808,0.0004513798,0.0009904291,0.00063245377,0.39893216,0.0734472,0.09078088,0.035047222,0.39191797],"study_design_scores_gemma":[0.00008865822,0.00007293849,0.00068227865,0.000055974622,0.000055229353,0.0003576179,0.00007307461,0.89319265,0.020354511,0.054009907,0.030980611,0.00007656072],"about_ca_topic_score_codex":0.0016904732,"about_ca_topic_score_gemma":0.0020364416,"teacher_disagreement_score":0.011666094,"about_ca_system_score_codex":0.0009806864,"about_ca_system_score_gemma":0.0014870005,"threshold_uncertainty_score":0.039026976},"labels":[],"label_agreement":null},{"id":"W2038639639","doi":"10.1089/cmb.2010.0126","title":"Combinatorial Structure of Genome Rearrangements Scenarios","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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":"Simon Fraser University","funders":"","keywords":"Bijection, injection and surjection; Enumeration; Genome; Set (abstract data type); sort; Combinatorics; Mathematics; Construct (python library); Component (thermodynamics); Computer science; Biology; Genetics; Physics; Bijection; Gene; Arithmetic","score_opus":0.005735136830741955,"score_gpt":0.25104857336194397,"score_spread":0.24531343653120202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038639639","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38466945,0.0011078567,0.56194806,0.0019005025,0.00010193736,0.00047095274,0.0016599416,0.0005418726,0.047599554],"genre_scores_gemma":[0.8379594,0.00065738003,0.15156074,0.00031744997,0.00013598774,0.0005892562,0.002901884,0.0001821714,0.0056958026],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99716324,0.00088501145,0.00022782011,0.00064884685,0.00074143615,0.000333631],"domain_scores_gemma":[0.98751545,0.008609841,0.0010972338,0.00091809704,0.0010532682,0.00080610835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021076298,0.00062451104,0.0009683805,0.0041520083,0.002538113,0.004909173,0.0022438008,0.0027456915,0.010760482],"category_scores_gemma":[0.017528517,0.0009662174,0.001372989,0.0034618392,0.0028694374,0.0077014756,0.0033856314,0.0025903855,0.0010159938],"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":[0.000085668325,0.000059427137,0.002211714,0.00018395497,0.000028622157,0.00018192873,0.00026765236,0.028389841,0.0018194781,0.9465942,0.0018168367,0.018360743],"study_design_scores_gemma":[0.000031002593,0.00004907318,0.00074597134,0.00005084228,0.00002560473,0.0006261311,0.00024067794,0.08402724,0.0018128367,0.9071211,0.005239655,0.000029853512],"about_ca_topic_score_codex":0.00039893386,"about_ca_topic_score_gemma":0.00044222188,"teacher_disagreement_score":0.010760482,"about_ca_system_score_codex":0.0014529887,"about_ca_system_score_gemma":0.0007668772,"threshold_uncertainty_score":0.03599739},"labels":[],"label_agreement":null},{"id":"W2038963639","doi":"10.1089/cmb.2010.0251","title":"Towards Fully Automated Structure-Based NMR Resonance Assignment of <sup>15</sup> N-Labeled Proteins From Automatically Picked Peaks","year":2011,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Protein Structure and Dynamics","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":"University of Waterloo","funders":"","keywords":"Algorithm; Set (abstract data type); Computer science; Resonance (particle physics); Data set; Integer programming; Biological system; Artificial intelligence; Physics; Biology","score_opus":0.010130420327557394,"score_gpt":0.24734576025060354,"score_spread":0.23721533992304614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038963639","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023141488,0.00026368452,0.94285053,0.00021551106,0.000053624124,0.000087362714,0.0006252034,0.031948045,0.00081463123],"genre_scores_gemma":[0.04354488,0.00011696533,0.9517382,0.00019649077,0.000025818703,0.00009038803,0.0018351206,0.0015401844,0.0009118848],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997638,0.0005883053,0.00017714332,0.0008068438,0.00064861,0.00014103256],"domain_scores_gemma":[0.99517316,0.0018413126,0.00060791284,0.0011444391,0.0010475161,0.00018569296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031432617,0.0021578686,0.0017641439,0.0014387586,0.000970428,0.002342789,0.003378924,0.0020498508,0.0033130902],"category_scores_gemma":[0.00602079,0.001186739,0.0018641568,0.0018821321,0.000871249,0.0026185587,0.0019735328,0.0029280763,0.003809402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023111885,0.00086237537,0.0043744566,0.00068483176,0.00028935765,0.00043187395,0.0004526527,0.066542506,0.19091685,0.006949858,0.026269754,0.6999142],"study_design_scores_gemma":[0.00010383757,0.000110051726,0.0008567585,0.000028008364,0.00003966815,0.00021837425,0.00010693622,0.905996,0.07479233,0.010129173,0.0075478563,0.000071022696],"about_ca_topic_score_codex":0.0031382993,"about_ca_topic_score_gemma":0.0031519663,"teacher_disagreement_score":0.003378924,"about_ca_system_score_codex":0.000848994,"about_ca_system_score_gemma":0.002138959,"threshold_uncertainty_score":0.016623378},"labels":[],"label_agreement":null},{"id":"W2039885142","doi":"10.1089/cmb.2012.0078","title":"LoopWeaver: Loop Modeling by the Weighted Scaling of Verified Proteins","year":2013,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Protein Structure and Dynamics","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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts; Compute Canada","keywords":"Scaling; Loop (graph theory); Computer science; Limit (mathematics); Algorithm; Mathematics; Geometry; Combinatorics; Mathematical analysis","score_opus":0.006924101297147768,"score_gpt":0.23889115119529825,"score_spread":0.23196704989815048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039885142","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041429944,0.00019542003,0.9318494,0.00007494163,0.00007067103,0.00010714855,0.0004566092,0.024142431,0.0016734572],"genre_scores_gemma":[0.24587739,0.00023433582,0.74519634,0.000090076785,0.000022118982,0.0003034142,0.001623985,0.00473908,0.0019132573],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989336,0.00030175305,0.00007589432,0.00023347417,0.00038989427,0.00006541931],"domain_scores_gemma":[0.997865,0.00074922637,0.00027629317,0.0007474186,0.00029210662,0.000069878304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020030483,0.0012742019,0.0010351336,0.0010342479,0.0006952947,0.00096499664,0.0026411428,0.0008031237,0.006493761],"category_scores_gemma":[0.007413063,0.0008074393,0.0009871301,0.0010348231,0.00047123298,0.0021694119,0.0015129851,0.0009786838,0.0018672255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011383034,0.00036867056,0.009117777,0.0008882177,0.00044116532,0.00068192446,0.00059400854,0.36821645,0.07614849,0.041460894,0.018739168,0.48220488],"study_design_scores_gemma":[0.000069692076,0.00013417187,0.00043035354,0.00003706518,0.000037926573,0.00015977646,0.000048427843,0.947497,0.028821578,0.011503669,0.01122115,0.000039052353],"about_ca_topic_score_codex":0.0021547854,"about_ca_topic_score_gemma":0.0022938454,"teacher_disagreement_score":0.006493761,"about_ca_system_score_codex":0.00041306778,"about_ca_system_score_gemma":0.0012483204,"threshold_uncertainty_score":0.021723747},"labels":[],"label_agreement":null},{"id":"W2042452585","doi":"10.1089/cmb.2008.0175","title":"Fast and Accurate Calculation of a Computationally Intensive Statistic for Mapping Disease Genes","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genetic Mapping and Diversity in Plants and Animals","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":"National Institutes of Health","keywords":"Numerical integration; Computer science; Statistic; Grid; Matching (statistics); Function (biology); Mathematical optimization; Variety (cybernetics); Algorithm; Class (philosophy); Mathematics; Artificial intelligence; Statistics","score_opus":0.019757833401928937,"score_gpt":0.28187330329921606,"score_spread":0.2621154698972871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042452585","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051773004,0.000057099693,0.9924736,0.000092425624,0.00003034639,0.000029449022,0.000064164204,0.0009592994,0.0011163957],"genre_scores_gemma":[0.09959515,0.00013228411,0.8978989,0.00007654842,0.00003070544,0.00017222934,0.0002851147,0.00035556266,0.0014534105],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994172,0.0001719192,0.000037964423,0.000064890686,0.00027116496,0.000036892132],"domain_scores_gemma":[0.9962196,0.0025420159,0.00021009686,0.00048234084,0.00046113197,0.00008481317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018556702,0.0006848517,0.0007885198,0.00092847156,0.0005609876,0.00088104856,0.0013084661,0.0009191341,0.005474402],"category_scores_gemma":[0.011475417,0.00033313263,0.0005653304,0.001022171,0.00067274255,0.0010918175,0.0007954456,0.001512934,0.0022385644],"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":[0.00016091076,0.00012437518,0.0033497976,0.00026267522,0.000061103856,0.00024357864,0.00021038782,0.57995546,0.019573065,0.078478694,0.00819178,0.30938816],"study_design_scores_gemma":[0.000026812777,0.000026121937,0.0004970112,0.000012922593,0.0000077549275,0.000088383196,0.000027721637,0.9786471,0.0026811769,0.015723975,0.002247081,0.000013917172],"about_ca_topic_score_codex":0.004029086,"about_ca_topic_score_gemma":0.0057995487,"teacher_disagreement_score":0.005474402,"about_ca_system_score_codex":0.00076577417,"about_ca_system_score_gemma":0.0025947886,"threshold_uncertainty_score":0.018313646},"labels":[],"label_agreement":null},{"id":"W2042756476","doi":"10.1089/cmb.2010.0108","title":"Mosaic Graphs and Comparative Genomics in Phage Communities","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Bacteriophages and microbial interactions","field":"Environmental Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"National Center for Research Resources; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Genome; Biology; Metagenomics; Comparative genomics; Genomics; Bacterial genome size; Genetics; Computational biology; Mosaic; Recombination; Horizontal gene transfer; Evolutionary biology; Gene; Geography","score_opus":0.021567881096635134,"score_gpt":0.28279490331409723,"score_spread":0.2612270222174621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042756476","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5830113,0.0032926737,0.40121552,0.0011538658,0.00005612643,0.00009258169,0.0010306552,0.00067884213,0.009468411],"genre_scores_gemma":[0.87149924,0.00068843784,0.12570927,0.00011752583,0.000047430683,0.000109749184,0.0010539445,0.00006988421,0.0007044566],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858886,0.00083242194,0.000052746527,0.00027204448,0.00017145919,0.00008248187],"domain_scores_gemma":[0.9919205,0.006349007,0.0006540246,0.0004904874,0.00026326132,0.00032283054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021503586,0.0003480598,0.00049608253,0.0060996837,0.0012978703,0.0014923264,0.00066940696,0.00089859666,0.0020267998],"category_scores_gemma":[0.012700769,0.00039045085,0.0008552709,0.005444997,0.0030978967,0.0029592952,0.0020000068,0.00066409406,0.00015181847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043431524,0.00010695097,0.018978607,0.00051853707,0.00025609927,0.00058405806,0.003391516,0.16120197,0.010510299,0.726251,0.0016251128,0.07614155],"study_design_scores_gemma":[0.000038220125,0.000048424597,0.0073930863,0.00005386407,0.000047127913,0.00028930392,0.00050751184,0.17323633,0.0014115747,0.8099687,0.0069665294,0.000039282884],"about_ca_topic_score_codex":0.0034829644,"about_ca_topic_score_gemma":0.003213025,"teacher_disagreement_score":0.0060996837,"about_ca_system_score_codex":0.0015486623,"about_ca_system_score_gemma":0.000674071,"threshold_uncertainty_score":0.011372328},"labels":[],"label_agreement":null},{"id":"W2044487872","doi":"10.1089/cmb.2008.0202","title":"Inverse Protein Folding in 3D Hexagonal Prism Lattice under HPC Model","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Protein Structure and Dynamics","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":"Simon Fraser University","funders":"","keywords":"Hexagonal prism; Inverse; Conjecture; Hexagonal crystal system; Protein design; Lattice (music); Protein structure prediction; Protein folding; Protein structure; Simple (philosophy); Combinatorics; Amino acid; Mathematics; Crystallography; Geometry; Physics; Chemistry","score_opus":0.011310177154034552,"score_gpt":0.2731153592604306,"score_spread":0.2618051821063961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044487872","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6421544,0.00021770483,0.34296885,0.00040571584,0.000042116233,0.000050463965,0.00023984043,0.00025849885,0.0136624295],"genre_scores_gemma":[0.9304489,0.0001828895,0.06618432,0.000092153314,0.000015974216,0.00007180459,0.00023702602,0.00004817456,0.0027188195],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997211,0.000075499454,0.00001632918,0.0000495011,0.00009725492,0.000040250252],"domain_scores_gemma":[0.9997112,0.000066647335,0.000060727318,0.00007557363,0.000050834216,0.000034928882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037086502,0.00022769718,0.00042712057,0.00021173472,0.0003299938,0.00048065724,0.00048633327,0.0006096294,0.0009884533],"category_scores_gemma":[0.0008615929,0.00016566619,0.0006704837,0.00023087117,0.0008701879,0.0007222208,0.0006441149,0.00049554725,0.00016811666],"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":[0.00013108611,0.000034673994,0.0016285274,0.00009344014,0.000026329775,0.00043092872,0.00015733874,0.5708615,0.021778846,0.39456308,0.00080864626,0.009485569],"study_design_scores_gemma":[0.00004044476,0.00010488682,0.0003566347,0.000006406068,0.0000064048154,0.00016632097,0.00004486405,0.84755784,0.004151623,0.14604215,0.001506923,0.00001554333],"about_ca_topic_score_codex":0.0016600903,"about_ca_topic_score_gemma":0.0007738781,"teacher_disagreement_score":0.0016600903,"about_ca_system_score_codex":0.00048005808,"about_ca_system_score_gemma":0.00042399124,"threshold_uncertainty_score":0.003483057},"labels":[],"label_agreement":null},{"id":"W2044506914","doi":"10.1089/cmb.2009.0094","title":"Genetic Map Refinement Using a Comparative Genomic Approach","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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":"McGill University; Université de Montréal","funders":"","keywords":"Directed acyclic graph; Phylogenetic tree; Heuristics; Tree (set theory); Set (abstract data type); Phylogenetic network; Biology; Gene mapping; Graph; Computational biology; Genetics; Computer science; Mathematics; Combinatorics; Algorithm; Gene; Theoretical computer science; Chromosome","score_opus":0.03135141223604313,"score_gpt":0.30297317240939275,"score_spread":0.2716217601733496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044506914","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018570751,0.00016936749,0.97737885,0.00009604435,0.000027706077,0.00017087892,0.00026587216,0.002168584,0.001151957],"genre_scores_gemma":[0.037560556,0.0001135699,0.9607691,0.000046955964,0.0000099724575,0.00012290015,0.00066788914,0.00027234055,0.00043679183],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977642,0.000809913,0.00014434081,0.0006987792,0.0004419991,0.0001406791],"domain_scores_gemma":[0.9958799,0.0021844534,0.00025725982,0.0008301637,0.0007683781,0.00007993591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003853015,0.0014126243,0.0018443896,0.0045417505,0.0012788202,0.0017273288,0.0027259067,0.0011813573,0.0050993613],"category_scores_gemma":[0.015512232,0.0009849023,0.0017311012,0.0037832265,0.0011359098,0.001675195,0.0018441149,0.0018374772,0.00097417796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006213528,0.00038272733,0.004483038,0.0006600032,0.00042119325,0.0008732689,0.0010272964,0.34488544,0.07608199,0.06211932,0.003684112,0.50476027],"study_design_scores_gemma":[0.00017254431,0.00028051963,0.0031988677,0.00009285034,0.00022428496,0.00058465364,0.00037165437,0.89563847,0.024064528,0.050974347,0.024300307,0.000096965516],"about_ca_topic_score_codex":0.008550901,"about_ca_topic_score_gemma":0.011021764,"teacher_disagreement_score":0.008550901,"about_ca_system_score_codex":0.0016454103,"about_ca_system_score_gemma":0.002180631,"threshold_uncertainty_score":0.02037692},"labels":[],"label_agreement":null},{"id":"W2045430208","doi":"10.1089/106652701752236232","title":"Unfolding of Microarray Data","year":2001,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; Ontario Institute for Cancer Research","funders":"","keywords":"Microarray databases; DNA microarray; Microarray analysis techniques; Microarray; Robustness (evolution); Outlier; Computer science; Data mining; Gene chip analysis; Inference; Computational biology; Biology; Artificial intelligence; Genetics; Gene expression; Gene","score_opus":0.03968641451553621,"score_gpt":0.3339513396237907,"score_spread":0.29426492510825447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045430208","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011284002,0.00017782167,0.98539263,0.00021171148,0.000052190255,0.00011197641,0.001087466,0.0013464929,0.00033564022],"genre_scores_gemma":[0.1602102,0.00083709724,0.82863003,0.00034335422,0.00017205556,0.0006940061,0.007585119,0.0006468642,0.0008811421],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99292845,0.0030630727,0.00040821437,0.0013883465,0.0019347365,0.00027722452],"domain_scores_gemma":[0.9850462,0.008044217,0.0008339071,0.0043698065,0.0014780433,0.0002277376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0071033705,0.0013257994,0.00153703,0.0019387752,0.0008139372,0.001960106,0.0013623617,0.0009184736,0.0017862074],"category_scores_gemma":[0.032909404,0.000828655,0.002070666,0.0024742137,0.0010021238,0.00180622,0.0020661356,0.0024637687,0.00160029],"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":[0.0006998148,0.00022714918,0.009791202,0.000961265,0.00048235856,0.00046227418,0.00077419274,0.45677948,0.14605415,0.046416707,0.007941857,0.3294096],"study_design_scores_gemma":[0.000023936087,0.00018426664,0.0047911317,0.00003630197,0.000047177764,0.00026732025,0.00015322931,0.8599372,0.030089088,0.09226058,0.012132592,0.00007722892],"about_ca_topic_score_codex":0.0009539294,"about_ca_topic_score_gemma":0.0007677488,"teacher_disagreement_score":0.0071033705,"about_ca_system_score_codex":0.0010668382,"about_ca_system_score_gemma":0.0011419099,"threshold_uncertainty_score":0.03756666},"labels":[],"label_agreement":null},{"id":"W2045444967","doi":"10.1089/cmb.2005.12.1328","title":"Structure-Approximating Inverse Protein Folding Problem in the 2D HP Model","year":2005,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Protein Structure and Dynamics","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":"Simon Fraser University","funders":"","keywords":"Inverse; Protein structure; Protein folding; Protein structure prediction; Fold (higher-order function); Stability (learning theory); Sequence (biology); Computer science; Protein design; Folding (DSP implementation); Computational biology; Mathematics; Biology; Biochemistry; Engineering; Machine learning; Geometry","score_opus":0.009101872440230755,"score_gpt":0.2593196454700624,"score_spread":0.25021777302983167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045444967","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09960091,0.0004242805,0.8889631,0.0012005796,0.000053926964,0.000037369584,0.0002338976,0.00018367115,0.009302198],"genre_scores_gemma":[0.7709644,0.00054914644,0.21686819,0.00038354262,0.00007932139,0.00024392197,0.0004239592,0.00015461701,0.010332868],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997876,0.0000934766,0.0000075588378,0.00004312315,0.000045656067,0.000022636337],"domain_scores_gemma":[0.99931276,0.00047961742,0.00005904514,0.0000488687,0.00005775745,0.000041837182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007136899,0.00044500455,0.0010354473,0.00037060576,0.00033586365,0.00081891625,0.00094650063,0.001833318,0.0021027855],"category_scores_gemma":[0.0020601617,0.0004955938,0.0005810875,0.0003521152,0.0011558563,0.0013052201,0.00095532037,0.0010750183,0.00026876046],"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":[0.000028922337,0.0000146505445,0.0001732511,0.000035081208,0.0000068726586,0.000093534894,0.000032047803,0.9617447,0.00052132976,0.034158383,0.0004616805,0.0027294385],"study_design_scores_gemma":[0.000006720868,0.0000057404395,0.000021025187,0.0000015957098,9.615154e-7,0.000011870862,0.0000043528466,0.9899159,0.000077054654,0.009759283,0.000193382,0.0000020786013],"about_ca_topic_score_codex":0.005094571,"about_ca_topic_score_gemma":0.0020639885,"teacher_disagreement_score":0.005094571,"about_ca_system_score_codex":0.0008591396,"about_ca_system_score_gemma":0.0007321862,"threshold_uncertainty_score":0.010129809},"labels":[],"label_agreement":null},{"id":"W2046060480","doi":"10.1089/cmb.2005.12.777","title":"Wrap-and-Pack: A New Paradigm for Beta Structural Motif Recognition with Application to Recognizing Beta Trefoils","year":2005,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"RNA and protein synthesis mechanisms","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":"Artificial Intelligence in Medicine (Canada)","funders":"National Institute of General Medical Sciences; National Institutes of Health; National Science Foundation","keywords":"BETA (programming language); Computational biology; Computer science; Biology; Genetics; Artificial intelligence","score_opus":0.017404705841974566,"score_gpt":0.27566441496696226,"score_spread":0.2582597091249877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046060480","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009233794,0.00011687094,0.9861703,0.000112487935,0.000034720153,0.00005670643,0.00010907375,0.003534249,0.0006317772],"genre_scores_gemma":[0.08748476,0.0002448917,0.90908045,0.0002075368,0.000047673733,0.00026502143,0.0004217126,0.0005773181,0.0016706056],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997174,0.00007452443,0.000022630558,0.000076722354,0.0000805918,0.000028065704],"domain_scores_gemma":[0.99930525,0.0003240386,0.00006722646,0.00016015487,0.00008173906,0.00006163801],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012976632,0.0011233445,0.0010807218,0.0009756948,0.00046047487,0.0010658554,0.0018242941,0.00093802443,0.0029370403],"category_scores_gemma":[0.0025698717,0.00063078006,0.0010350854,0.00073941547,0.00079208234,0.0020735068,0.0015263116,0.0015475965,0.0012622434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005941047,0.0002940786,0.006057204,0.0004322756,0.0003106267,0.00042877623,0.00028483703,0.2504446,0.027394056,0.04547146,0.016285663,0.6520023],"study_design_scores_gemma":[0.000039579492,0.000103865386,0.00034235316,0.000020860009,0.00002379241,0.00020242787,0.000033980188,0.94575316,0.008615131,0.03863179,0.006208489,0.000024606165],"about_ca_topic_score_codex":0.0010860654,"about_ca_topic_score_gemma":0.0013826677,"teacher_disagreement_score":0.0029370403,"about_ca_system_score_codex":0.00030100523,"about_ca_system_score_gemma":0.00071616995,"threshold_uncertainty_score":0.009825408},"labels":[],"label_agreement":null},{"id":"W2046437109","doi":"10.1089/cmb.2008.0096","title":"Stable Structure-Approximating Inverse Protein Folding in 2D Hydrophobic-Polar-Cysteine (HPC) Model","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Protein Structure and Dynamics","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":"Simon Fraser University","funders":"","keywords":"Protein structure prediction; Cysteine; Inverse; Amino acid; Protein design; Protein structure; Folding (DSP implementation); Protein folding; Sequence (biology); Polar; Function (biology); Stability (learning theory); Computer science; Combinatorics; Mathematics; Chemistry; Physics; Geometry; Biology","score_opus":0.010764013905599605,"score_gpt":0.24353479646729428,"score_spread":0.23277078256169467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046437109","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.466664,0.0010735606,0.51437277,0.000928845,0.000081200786,0.0000763072,0.00024778332,0.00020135987,0.016354205],"genre_scores_gemma":[0.93397254,0.0007760804,0.056578618,0.00024203068,0.00006734339,0.00017909016,0.00030606022,0.00009744544,0.0077808094],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998215,0.000048942376,0.00000901184,0.000038169324,0.000050403545,0.00003192142],"domain_scores_gemma":[0.99972516,0.00009800352,0.000059954986,0.00003827496,0.000039215185,0.00003938857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037342968,0.0006752843,0.0008864031,0.00060169655,0.0005516888,0.00074047176,0.0008257916,0.0013606936,0.0015114414],"category_scores_gemma":[0.0009810793,0.00031620258,0.0013019225,0.00029996762,0.0011907042,0.0010238688,0.0009315951,0.0009323143,0.00027021344],"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":[0.00011681776,0.00006732018,0.0014294485,0.00013313885,0.00004335865,0.00030188225,0.00020389746,0.651388,0.011469813,0.32800794,0.0011572147,0.0056810644],"study_design_scores_gemma":[0.00001842649,0.00004802725,0.00017225696,0.000006330374,0.0000062669124,0.000044948385,0.000020952037,0.9404285,0.00051265204,0.058127735,0.00060355937,0.0000103593775],"about_ca_topic_score_codex":0.0025028286,"about_ca_topic_score_gemma":0.0011274784,"teacher_disagreement_score":0.0025028286,"about_ca_system_score_codex":0.00084853347,"about_ca_system_score_gemma":0.00044009418,"threshold_uncertainty_score":0.0061565638},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036651,0.00039282304,0.96185523,0.00013516448,0.000014389837,0.000021107118,0.000042496362,0.0004222104,0.0004654957],"genre_scores_gemma":[0.71450114,0.0005033953,0.28245834,0.00008030309,0.000053777127,0.00011208479,0.00038043028,0.00010162392,0.0018089793],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99885094,0.00049136,0.000072601644,0.00016824299,0.00033854262,0.000078230776],"domain_scores_gemma":[0.9968599,0.0014806474,0.00039468476,0.0006229714,0.00052693905,0.000114908784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019640387,0.0005682335,0.0007048683,0.0009317922,0.00024789,0.0007856592,0.001246562,0.00086084934,0.0007993227],"category_scores_gemma":[0.009207773,0.0002860659,0.0005955963,0.0008972748,0.0006682233,0.0025556413,0.0008907591,0.0012204075,0.00058828655],"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":[0.0004100783,0.0002999436,0.0031069429,0.00015911346,0.0000971853,0.00013240817,0.000108794426,0.62984973,0.010708479,0.063992456,0.0021130876,0.28902173],"study_design_scores_gemma":[0.0000053635426,0.000016721022,0.00022315286,0.000002414499,0.0000024244714,0.000019425102,0.0000043001983,0.9922694,0.00097206695,0.0062436536,0.00023536394,0.000005799942],"about_ca_topic_score_codex":0.001231746,"about_ca_topic_score_gemma":0.00086642796,"teacher_disagreement_score":0.0019640387,"about_ca_system_score_codex":0.0007144364,"about_ca_system_score_gemma":0.00074308476,"threshold_uncertainty_score":0.010386944},"labels":[],"label_agreement":null},{"id":"W2050243856","doi":"10.1089/cmb.2009.0095","title":"Space of Gene/Species Trees Reconciliations and Parsimonious Models","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"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; Simon Fraser University","keywords":"Tree (set theory); Space (punctuation); Computer science; Mutation; Gene duplication; Family tree; Mathematics; Gene; Combinatorics; Biology; Genetics","score_opus":0.01963970999811997,"score_gpt":0.2529601758186593,"score_spread":0.23332046582053934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050243856","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19512813,0.0022177554,0.78743815,0.0021760808,0.000067229026,0.00017777643,0.0018263706,0.0018638141,0.009104666],"genre_scores_gemma":[0.6919405,0.00081826653,0.29963055,0.0003493127,0.00013222554,0.00037448632,0.0030497275,0.00058345124,0.0031215362],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962249,0.0022596861,0.00017697913,0.0005343048,0.00056426943,0.00023993575],"domain_scores_gemma":[0.98274225,0.013419893,0.0011081917,0.00169624,0.0005262159,0.0005072363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050282804,0.0010123758,0.001902408,0.0037786218,0.0018089905,0.0038804952,0.0038360443,0.0029750313,0.006504023],"category_scores_gemma":[0.027834928,0.0010120127,0.002050721,0.0039104195,0.0026919383,0.006046636,0.003238784,0.0025148976,0.0008555643],"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":[0.00035758156,0.00008251456,0.0014026271,0.00020003281,0.00010453104,0.00018814385,0.0003343877,0.78526294,0.00062337465,0.1730948,0.0030290822,0.035319984],"study_design_scores_gemma":[0.000045174915,0.00003407618,0.00019173678,0.000021550193,0.000021036814,0.00008535493,0.000051398423,0.71399003,0.00035924083,0.28392962,0.0012503439,0.000020485868],"about_ca_topic_score_codex":0.0012246117,"about_ca_topic_score_gemma":0.0013778533,"teacher_disagreement_score":0.006504023,"about_ca_system_score_codex":0.0022327257,"about_ca_system_score_gemma":0.0014411076,"threshold_uncertainty_score":0.026592374},"labels":[],"label_agreement":null},{"id":"W2051551591","doi":"10.1089/cmb.2006.13.1340","title":"On the Similarity of Sets of Permutations and Its Applications to Genome Comparison","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Genome; Chaining; Similarity (geometry); Generalization; Key (lock); Feature (linguistics); Computer science; Combinatorics; Mathematics; Computational biology; Theoretical computer science; Biology; Gene; Genetics; Artificial intelligence","score_opus":0.01775467834541102,"score_gpt":0.30163803439926734,"score_spread":0.28388335605385634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051551591","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055382982,0.001660963,0.9316987,0.0007789861,0.00010797239,0.00009956848,0.0002462671,0.00039390277,0.00963071],"genre_scores_gemma":[0.46596143,0.0017266924,0.528211,0.00035821495,0.00037071432,0.00026488805,0.0007232629,0.00024220326,0.0021416366],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99567574,0.0018705835,0.0003483229,0.0009259707,0.0010256923,0.00015366563],"domain_scores_gemma":[0.98090166,0.014728313,0.0012151948,0.0017935084,0.0009824448,0.00037894485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031528987,0.0005350556,0.0012793159,0.0062692487,0.001620211,0.0029049474,0.0018617513,0.0016161837,0.003810564],"category_scores_gemma":[0.034952935,0.0004852444,0.0010775909,0.009557774,0.0042039882,0.00798796,0.0043782294,0.002193735,0.0005436593],"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":[0.00015486368,0.00006991206,0.0029228546,0.0001971792,0.000063809974,0.00017149467,0.0007156728,0.041939955,0.0028623894,0.77627903,0.0014904896,0.17313239],"study_design_scores_gemma":[0.000017744384,0.00007028441,0.00095071644,0.000054937434,0.000021500928,0.00032890492,0.0001619641,0.09038201,0.0013734871,0.90128815,0.005318718,0.00003166505],"about_ca_topic_score_codex":0.0013450987,"about_ca_topic_score_gemma":0.0007527321,"teacher_disagreement_score":0.0062692487,"about_ca_system_score_codex":0.0012441629,"about_ca_system_score_gemma":0.0006501448,"threshold_uncertainty_score":0.01667428},"labels":[],"label_agreement":null},{"id":"W2052541209","doi":"10.1089/cmb.2008.03tt","title":"The Effect of Insertions and Deletions on Wirings in Protein-Protein Interaction Networks: A Large-Scale Study","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Bioinformatics and Genomic Networks","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; Simon Fraser University","funders":"","keywords":"Indel; Biology; Computational biology; Genetics; INDEL Mutation; Sequence (biology); Protein Interaction Networks; Protein–protein interaction; Evolutionary biology; Gene","score_opus":0.0041442959538678225,"score_gpt":0.2601894752652332,"score_spread":0.2560451793113654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052541209","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99577516,0.00031795193,0.0035553633,0.000022783333,0.0000030037413,0.000004579822,0.00006671203,0.000034911776,0.00021959624],"genre_scores_gemma":[0.9970372,0.00021247353,0.0024093816,0.0000058466594,0.0000059704175,0.0000056023428,0.00019653008,0.000012203941,0.00011483773],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9995459,0.00014602732,0.000026314072,0.00014066578,0.00008719024,0.000053836357],"domain_scores_gemma":[0.99402255,0.004056427,0.00091876695,0.0004956257,0.00023821832,0.0002683753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065871596,0.00024720246,0.00028814565,0.0013626134,0.00042344976,0.00045022907,0.000357132,0.0003758814,0.00065535144],"category_scores_gemma":[0.0042136386,0.00014921192,0.00049319933,0.0012666464,0.00067146594,0.0009041107,0.0005117157,0.0003957468,0.00010201336],"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":[0.0005548498,0.00044832562,0.601015,0.00061640545,0.0010468054,0.0024591358,0.00084503816,0.16967455,0.13179934,0.005448497,0.0009485922,0.08514351],"study_design_scores_gemma":[0.00002598805,0.0004227663,0.67710966,0.00003513723,0.0003431699,0.0017612306,0.00076286856,0.2914539,0.019830935,0.0054201605,0.0027687196,0.0000655217],"about_ca_topic_score_codex":0.0012029966,"about_ca_topic_score_gemma":0.00203769,"teacher_disagreement_score":0.0013626134,"about_ca_system_score_codex":0.00020081166,"about_ca_system_score_gemma":0.0001414943,"threshold_uncertainty_score":0.0034837127},"labels":[],"label_agreement":null},{"id":"W2052915966","doi":"10.1089/106652704773416911","title":"Use of Runs Statistics for Pattern Recognition in Genomic DNA Sequences","year":2004,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; University of Manitoba; Manitoba Health Research Council","keywords":"Hidden Markov model; Bivariate analysis; Expectation–maximization algorithm; Mathematics; Statistic; Binary number; Statistics; Probabilistic logic; Sufficient statistic; Markov chain; Pattern recognition (psychology); Computer science; Algorithm; Artificial intelligence; Maximum likelihood","score_opus":0.0690596579144282,"score_gpt":0.3219836843225449,"score_spread":0.25292402640811673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052915966","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004747389,0.00011470496,0.9945775,0.0000391589,0.000008206718,0.0000074725804,0.000022107904,0.0001827008,0.00030074015],"genre_scores_gemma":[0.30740947,0.0005031658,0.6900559,0.00009722478,0.00007001316,0.00015290268,0.00024195173,0.0002803372,0.001189055],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998083,0.0009745797,0.0001251165,0.00043806012,0.00031747573,0.000061737],"domain_scores_gemma":[0.9876066,0.00962467,0.00090676313,0.0012340166,0.00045956904,0.00016828485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003793949,0.00069426844,0.0008315484,0.0018072685,0.00040593353,0.001401064,0.0011850739,0.0010941505,0.0018371153],"category_scores_gemma":[0.022131547,0.0005616415,0.00084463716,0.001145162,0.0022475028,0.0033229492,0.0012838733,0.0018191793,0.000573764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017009475,0.000050511513,0.00623453,0.00022933519,0.000106994485,0.0003874775,0.00056813617,0.2982465,0.024035074,0.5024833,0.0008375411,0.16665047],"study_design_scores_gemma":[0.000009795868,0.00007952969,0.0011440414,0.00004312061,0.000016822236,0.00029422223,0.000049219834,0.75042284,0.009575822,0.23594855,0.0023595856,0.000056538232],"about_ca_topic_score_codex":0.0006265485,"about_ca_topic_score_gemma":0.0005880842,"teacher_disagreement_score":0.003793949,"about_ca_system_score_codex":0.0007149595,"about_ca_system_score_gemma":0.00058760314,"threshold_uncertainty_score":0.020064592},"labels":[],"label_agreement":null},{"id":"W2054028885","doi":"10.1089/cmb.2006.0108","title":"Parsing Nucleic Acid Pseudoknotted Secondary Structure: Algorithm and Applications","year":2007,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"RNA and protein synthesis mechanisms","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 British Columbia","funders":"","keywords":"Algorithm; Parsing; Nucleic acid secondary structure; Pseudoknot; Protein secondary structure; Computer science; Generality; Dynamic programming; Nucleic acid structure; Energy (signal processing); Artificial intelligence; Mathematics; RNA; Biology; Statistics","score_opus":0.006073057763412786,"score_gpt":0.25270201741132264,"score_spread":0.24662895964790985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054028885","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008688298,0.00022638842,0.9871842,0.00022731784,0.000027807917,0.000050628965,0.00008238365,0.002586527,0.00092637166],"genre_scores_gemma":[0.0642271,0.00025390147,0.9334869,0.000098897566,0.000023931478,0.0001075831,0.00034839977,0.00027489028,0.0011784578],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994881,0.00011343571,0.000046679426,0.00015548758,0.0001448342,0.000051362356],"domain_scores_gemma":[0.99870634,0.000830033,0.00007944903,0.00014514592,0.00020056631,0.00003850127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000702154,0.00081223,0.00079459633,0.00089448056,0.0006269965,0.0010203745,0.0016007081,0.001730036,0.003013478],"category_scores_gemma":[0.0028665792,0.00042412506,0.00066714885,0.0019508343,0.000827,0.0018156827,0.00075349933,0.0009878771,0.0011920462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002948806,0.0002558417,0.0018843636,0.00039449637,0.000052614716,0.000328017,0.0002680451,0.31712934,0.021342404,0.059141118,0.009361813,0.58954704],"study_design_scores_gemma":[0.000045391724,0.000039918024,0.00024033965,0.000019164021,0.000012511603,0.00015004039,0.00003564523,0.9489238,0.009994507,0.037428617,0.0030856188,0.000024434232],"about_ca_topic_score_codex":0.0029318444,"about_ca_topic_score_gemma":0.0028701758,"teacher_disagreement_score":0.003013478,"about_ca_system_score_codex":0.0009827698,"about_ca_system_score_gemma":0.0014521222,"threshold_uncertainty_score":0.010081112},"labels":[],"label_agreement":null},{"id":"W2054206457","doi":"10.1089/cmb.2004.11.945","title":"Towards Quality Control for DNA Microarrays","year":2004,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Gene expression and cancer classification","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":"McGill University","funders":"","keywords":"DNA microarray; Computational biology; Oligomer restriction; Oligonucleotide; Hybridization probe; Biology; Nucleic acid thermodynamics; Genetics; Biological system; Computer science; DNA; Gene; Base sequence; Gene expression","score_opus":0.021876852584909852,"score_gpt":0.33458642804707356,"score_spread":0.3127095754621637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054206457","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011131436,0.00058957137,0.99717844,0.00027342848,0.00005926358,0.0000348182,0.000045374134,0.00045869476,0.000247341],"genre_scores_gemma":[0.041939605,0.0009258679,0.9540615,0.00043810002,0.00026042084,0.00041024844,0.0005353795,0.00045837217,0.00097049365],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9567803,0.015844742,0.0023962073,0.0062676664,0.017504824,0.0012062391],"domain_scores_gemma":[0.9322017,0.030966893,0.0055449023,0.015781669,0.014467509,0.0010373571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04077421,0.0019878254,0.0024350618,0.0038687605,0.0013037781,0.00569247,0.0051099705,0.0029535524,0.0016313142],"category_scores_gemma":[0.09021864,0.0015787398,0.001987293,0.0035440573,0.0055305785,0.00454235,0.005068595,0.0062555005,0.0012536765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040537262,0.00014544874,0.003473911,0.0011519113,0.00028161795,0.00024316525,0.00059275975,0.11196925,0.0650989,0.37060708,0.006943017,0.43908766],"study_design_scores_gemma":[0.00007899488,0.0002112624,0.0013242402,0.00020549851,0.00007586851,0.00026847748,0.00010903592,0.48548168,0.04593676,0.43986976,0.026309367,0.00012900734],"about_ca_topic_score_codex":0.0020336786,"about_ca_topic_score_gemma":0.001120506,"teacher_disagreement_score":0.04077421,"about_ca_system_score_codex":0.0029735535,"about_ca_system_score_gemma":0.0028923454,"threshold_uncertainty_score":0.2156372},"labels":[],"label_agreement":null},{"id":"W2054453573","doi":"10.1089/cmb.2007.0208","title":"New, Improved, and Practical k-Stem Sequence Similarity Measures for Probe Design","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of British Columbia","keywords":"Nearest neighbor search; Similarity (geometry); k-nearest neighbors algorithm; Sequence (biology); Computer science; Oligomer restriction; Data mining; Bit array; Algorithm; Pattern recognition (psychology); Oligonucleotide; Mathematics; Artificial intelligence; Biology; Genetics; Gene","score_opus":0.048645072579860414,"score_gpt":0.3051138640791153,"score_spread":0.2564687914992549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054453573","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014257652,0.00024207745,0.9835722,0.00006816956,0.000033163647,0.00009191851,0.00011078484,0.0008254076,0.0007985022],"genre_scores_gemma":[0.118396394,0.00016678234,0.87956977,0.00013216099,0.000045987083,0.0004315557,0.00036203285,0.00022749357,0.0006678025],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99448204,0.0014814084,0.0005193331,0.0008291013,0.0025252122,0.00016278104],"domain_scores_gemma":[0.9907306,0.0046084584,0.0013206854,0.001112971,0.001941319,0.00028608466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003277662,0.0010059768,0.0012971825,0.0019544647,0.0005984212,0.0016226294,0.0019242842,0.0015118056,0.0022950931],"category_scores_gemma":[0.019237677,0.0004999223,0.0008206204,0.0019591313,0.0013146576,0.0038503306,0.0016010145,0.0019090598,0.0013744705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008221006,0.00055214437,0.006385787,0.0009920324,0.00016229563,0.0002002154,0.00042238017,0.12892382,0.20075607,0.0883155,0.0038224687,0.5686453],"study_design_scores_gemma":[0.000098928016,0.0010254958,0.0017798814,0.00007148038,0.00006850863,0.0005293094,0.00010971416,0.8081781,0.11707551,0.06141549,0.00949042,0.00015703842],"about_ca_topic_score_codex":0.000367819,"about_ca_topic_score_gemma":0.00065718306,"teacher_disagreement_score":0.003277662,"about_ca_system_score_codex":0.0010153024,"about_ca_system_score_gemma":0.0010223137,"threshold_uncertainty_score":0.017334104},"labels":[],"label_agreement":null},{"id":"W2054547415","doi":"10.1089/106652701300099119","title":"Perfect Phylogenetic Networks with Recombination","year":2001,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":216,"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":"Phylogenetic tree; Phylogenetic network; Recombination; Phylogenetics; Tree (set theory); Time complexity; Mathematics; Evolutionary biology; Biology; Combinatorics; Computer science; Genetics; Gene","score_opus":0.007125730998609258,"score_gpt":0.2408557460107803,"score_spread":0.23373001501217106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054547415","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06675501,0.0006502388,0.92484593,0.00083831564,0.000039177765,0.00006946025,0.0005688018,0.00039688605,0.005836207],"genre_scores_gemma":[0.6304662,0.0009481537,0.36144805,0.00022273783,0.00007224498,0.00016992594,0.0016792801,0.00012250949,0.0048708776],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986696,0.0004848796,0.00006008064,0.0004529186,0.00019544944,0.00013698444],"domain_scores_gemma":[0.997012,0.0016589677,0.00048405447,0.0005158909,0.00013950757,0.00018945654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014498989,0.00045047037,0.0008006437,0.00069946516,0.0008810641,0.0017873793,0.0013429424,0.0013368605,0.0044431775],"category_scores_gemma":[0.0062906113,0.0004440577,0.0007353244,0.0014929076,0.0011611765,0.006117053,0.0019199289,0.0013133992,0.0004853471],"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":[0.00028839541,0.0000715794,0.0018323147,0.00035363567,0.00006574775,0.0002665974,0.00024122492,0.38797942,0.0050801663,0.5067789,0.0050342283,0.09200776],"study_design_scores_gemma":[0.000041237952,0.00007643755,0.00042987164,0.000029816334,0.000033082484,0.00032148187,0.00009024101,0.47412822,0.0023025637,0.5106915,0.011833301,0.00002206109],"about_ca_topic_score_codex":0.00078863214,"about_ca_topic_score_gemma":0.00095758535,"teacher_disagreement_score":0.0044431775,"about_ca_system_score_codex":0.0008755982,"about_ca_system_score_gemma":0.0007657019,"threshold_uncertainty_score":0.014863908},"labels":[],"label_agreement":null},{"id":"W2056251063","doi":"10.1089/cmb.2014.0156","title":"PASTA: Ultra-Large Multiple Sequence Alignment for Nucleotide and Amino-Acid Sequences","year":2014,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":463,"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; National Human Genome Research Institute; Howard Hughes Medical Institute; National Science Foundation; National Institutes of Health; National Institute on Aging; University of Alberta; Pennsylvania Department of Health","keywords":"Scalability; Multiple sequence alignment; Parallelizable manifold; Computer science; Sequence (biology); Alignment-free sequence analysis; Sequence alignment; Tree (set theory); Algorithm; Computational biology; Data mining; Biology; Mathematics; Peptide sequence; Genetics","score_opus":0.017049347721773037,"score_gpt":0.2699171632434254,"score_spread":0.2528678155216524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056251063","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006321382,0.002684684,0.9233872,0.00043914624,0.0005921589,0.00013990172,0.0047038337,0.059296772,0.0024349734],"genre_scores_gemma":[0.024359366,0.0013763908,0.9526307,0.00028920718,0.00018053698,0.0005243854,0.013569813,0.0051802145,0.0018893257],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987226,0.00046514475,0.00013111843,0.00031203395,0.00030215146,0.00006697385],"domain_scores_gemma":[0.99825746,0.0006545579,0.00024422564,0.00047299676,0.00025305056,0.000117838346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017792815,0.0021863116,0.0019408367,0.0020414684,0.0017426354,0.0023577341,0.0031897982,0.0015984426,0.009685293],"category_scores_gemma":[0.0074421004,0.001542999,0.0019173312,0.002626024,0.00071116904,0.0036430901,0.0021459176,0.0043893307,0.011548713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001656685,0.00035036053,0.0045790025,0.003997467,0.0017182638,0.0015512601,0.0009213295,0.0680927,0.12449797,0.06317033,0.19610244,0.53336227],"study_design_scores_gemma":[0.00034403554,0.0003557925,0.0016955951,0.00042677514,0.0002582981,0.0020214848,0.00016240506,0.5128191,0.04901577,0.08398648,0.34864935,0.00026488802],"about_ca_topic_score_codex":0.001060265,"about_ca_topic_score_gemma":0.0017565548,"teacher_disagreement_score":0.009685293,"about_ca_system_score_codex":0.00061374943,"about_ca_system_score_gemma":0.0015436132,"threshold_uncertainty_score":0.032400608},"labels":[],"label_agreement":null},{"id":"W2058730888","doi":"10.1089/cmb.2010.0184","title":"Gene Prediction Based on DNA Spectral Analysis: A Literature Review","year":2011,"lang":"en","type":"review","venue":"Journal of Computational Biology","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"is_retracted":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":"ENCODE; Digital signal processing; Genetic code; Computational biology; Computer science; DNA; Coding (social sciences); Biology; Gene; Genetics; Mathematics","score_opus":0.018661564649076888,"score_gpt":0.30827490507033456,"score_spread":0.2896133404212577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058730888","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00056911295,0.991426,0.005220941,0.0003266874,0.00021371036,0.0000130258395,0.00008800449,0.000052279807,0.0020903368],"genre_scores_gemma":[0.0028603855,0.9906737,0.005047123,0.00014221876,0.00024446184,0.000017619743,0.00017574808,0.000012523507,0.0008263025],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99976295,0.000032512748,0.000034265788,0.00007131156,0.00008480992,0.0000140800685],"domain_scores_gemma":[0.99895525,0.0006176518,0.00006828901,0.000029083005,0.00029686204,0.000032929165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073516706,0.0009100726,0.0014039617,0.004237599,0.00030306037,0.0010289287,0.0012653045,0.000933848,0.002991112],"category_scores_gemma":[0.0015836909,0.0004397069,0.00065800163,0.0052110166,0.00044974568,0.0014530553,0.00053311524,0.0008703322,0.0023244217],"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":[0.000044021162,0.000052960277,0.00046570768,0.009504401,0.00008720689,0.00019106717,0.000054639542,0.0014649916,0.0013451835,0.0028204273,0.013452381,0.970517],"study_design_scores_gemma":[0.000024556519,0.00015972598,0.0028695152,0.010722989,0.0005066483,0.0034151978,0.00020806938,0.0035318825,0.005145879,0.009530232,0.96375763,0.00012767225],"about_ca_topic_score_codex":0.0021285494,"about_ca_topic_score_gemma":0.0016401346,"teacher_disagreement_score":0.004237599,"about_ca_system_score_codex":0.0005580891,"about_ca_system_score_gemma":0.0011556079,"threshold_uncertainty_score":0.010006249},"labels":[],"label_agreement":null},{"id":"W2061327015","doi":"10.1089/106652703322756104","title":"Mining the Biomedical Literature in the Genomic Era: An Overview","year":2003,"lang":"en","type":"review","venue":"Journal of Computational Biology","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":264,"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":"Data science; Computer science; Biomedical text mining; sort; Genomics; Genome; Data mining; Text mining; Information retrieval; Biology","score_opus":0.06706577458925418,"score_gpt":0.38961169413093805,"score_spread":0.3225459195416839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061327015","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026380452,0.9376332,0.043916147,0.007508941,0.0005460501,0.00010626557,0.00045979396,0.0004016832,0.0067898147],"genre_scores_gemma":[0.0082109645,0.9190524,0.06789776,0.0014365035,0.0007262246,0.000082748666,0.00063938,0.000040910934,0.0019131389],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99865687,0.00037651384,0.00019117889,0.00017609654,0.0005567112,0.000042617598],"domain_scores_gemma":[0.9945779,0.0037484479,0.0003416917,0.00018082824,0.0009720536,0.0001790595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028242306,0.0005836831,0.0012332721,0.015155518,0.00085394393,0.0032440373,0.0014876598,0.0014163892,0.0023119806],"category_scores_gemma":[0.005903593,0.0004126323,0.00083309814,0.016818259,0.0011709951,0.006688852,0.0010920491,0.0009199887,0.0024074088],"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":[0.000030242316,0.00006137912,0.0010161083,0.007914093,0.00009193821,0.00045879695,0.0003075393,0.0008408768,0.0015208424,0.008288426,0.01664144,0.96282834],"study_design_scores_gemma":[0.000021153977,0.000076894656,0.0041926205,0.008263817,0.00018031607,0.0048652384,0.0009504853,0.0024179416,0.002161783,0.035950508,0.94085735,0.00006192469],"about_ca_topic_score_codex":0.0025795286,"about_ca_topic_score_gemma":0.0043647042,"teacher_disagreement_score":0.015155518,"about_ca_system_score_codex":0.000890231,"about_ca_system_score_gemma":0.002592921,"threshold_uncertainty_score":0.014936149},"labels":[],"label_agreement":null},{"id":"W2062252710","doi":"10.1089/cmb.2014.0192","title":"Principal Component Analysis of Binding Energies for Single-Point Mutants of hT2R16 Bound to an Agonist Correlate with Experimental Mutant Cell Response","year":2014,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Biochemical Analysis and Sensing Techniques","field":"Nursing","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":"Lakehead University; Thunder Bay Regional Research Institute","funders":"National Institute on Deafness and Other Communication Disorders; National Institutes of Health","keywords":"Mutant; Principal component analysis; Agonist; Biology; Chemistry; Computational biology; Genetics; Receptor; Computer science; Gene; Artificial intelligence","score_opus":0.01985265323225235,"score_gpt":0.29711105357519757,"score_spread":0.27725840034294524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062252710","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9749486,0.000060003335,0.023924489,0.000043622935,0.000008042649,0.000013041367,0.00012092581,0.00024443134,0.00063688436],"genre_scores_gemma":[0.9955745,0.000045167293,0.0039970907,0.000005532411,7.434721e-7,0.000017257147,0.00014712343,0.000021819116,0.00019078537],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999181,0.000017519382,0.000004941639,0.000016632843,0.000028214794,0.00001454566],"domain_scores_gemma":[0.9997881,0.00012100227,0.000019589343,0.00002572403,0.000033286382,0.000012376849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022045853,0.0003417714,0.00025953213,0.00030567253,0.00016784531,0.00021249616,0.00022675845,0.00023570348,0.0010229587],"category_scores_gemma":[0.0008650783,0.00012938298,0.00034864747,0.00026203287,0.00022401875,0.000157968,0.00013271604,0.00031314977,0.0001713443],"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":[0.00058550097,0.00017568999,0.012578761,0.00013275213,0.00011674237,0.00010102391,0.000091064314,0.6193245,0.3399259,0.002492836,0.0005163023,0.023958938],"study_design_scores_gemma":[0.000011086663,0.00008218893,0.011325568,0.0000023544144,0.000016594571,0.00004809388,0.000021097016,0.9440892,0.04378778,0.00043165236,0.00016423504,0.000020136156],"about_ca_topic_score_codex":0.0029031234,"about_ca_topic_score_gemma":0.0019979188,"teacher_disagreement_score":0.0029031234,"about_ca_system_score_codex":0.0003609665,"about_ca_system_score_gemma":0.00033896038,"threshold_uncertainty_score":0.005772412},"labels":[],"label_agreement":null},{"id":"W2062347965","doi":"10.1089/cmb.2011.0133","title":"Listing All Parsimonious Reversal Sequences: New Algorithms and Perspectives","year":2011,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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 Ottawa; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sorting; Perspective (graphical); Listing (finance); Computer science; Genome; Algorithm; Genomics; Sequence (biology); Theoretical computer science; Biology; Artificial intelligence; Genetics; Gene","score_opus":0.05445580679385164,"score_gpt":0.28472176222363027,"score_spread":0.23026595542977862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062347965","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012161638,0.0042832275,0.97451854,0.0020084428,0.00027558568,0.00010838349,0.00014109016,0.0012894477,0.005213655],"genre_scores_gemma":[0.049963705,0.0025958763,0.94256985,0.00054857496,0.0006137212,0.00015678939,0.000427449,0.0005494571,0.002574635],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956873,0.0018482109,0.00028389518,0.0009375785,0.0009651943,0.00027771256],"domain_scores_gemma":[0.9767427,0.018414995,0.0008118663,0.0022721025,0.0013033435,0.0004548781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056742355,0.0023543513,0.002411754,0.003444853,0.0015509651,0.004198713,0.005391127,0.0039926064,0.0066967797],"category_scores_gemma":[0.027400298,0.0011828803,0.0017984291,0.005557175,0.002904801,0.016008703,0.0030012939,0.0072190054,0.0023508663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051415956,0.00046876143,0.001999222,0.0006389758,0.00011280528,0.00016042714,0.0004878766,0.1438499,0.004014689,0.32948452,0.011366548,0.5069021],"study_design_scores_gemma":[0.00012992251,0.00017520807,0.0003241705,0.00010661532,0.00005284378,0.00036087024,0.00017339835,0.56809914,0.0023024057,0.4154449,0.012751006,0.00007942981],"about_ca_topic_score_codex":0.0026438471,"about_ca_topic_score_gemma":0.0030864875,"teacher_disagreement_score":0.0066967797,"about_ca_system_score_codex":0.0018922079,"about_ca_system_score_gemma":0.0024133376,"threshold_uncertainty_score":0.030008554},"labels":[],"label_agreement":null},{"id":"W2064296763","doi":"10.1089/cmb.2006.13.554","title":"Stability of Rearrangement Measures in the Comparison of Genome Sequences","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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":"","keywords":"Genome; Biology; Evolutionary biology; Gene rearrangement; Tree (set theory); Computational biology; Genetics; Mathematics; Combinatorics; Gene","score_opus":0.030405882720506743,"score_gpt":0.3033162470871048,"score_spread":0.27291036436659805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064296763","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6003475,0.001830345,0.39310926,0.00036998556,0.000063027204,0.00014636274,0.0013815964,0.0011821429,0.0015697513],"genre_scores_gemma":[0.9051006,0.00027484942,0.09124842,0.000100806625,0.00010816106,0.00024634687,0.0023245113,0.00028008464,0.00031626047],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98740387,0.0052199787,0.0010840284,0.0030742784,0.0028750875,0.0003428039],"domain_scores_gemma":[0.8137041,0.15422459,0.013844448,0.011111815,0.0054895063,0.001625569],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022730952,0.0006366331,0.0011630629,0.010661329,0.0009987197,0.003197531,0.0018324187,0.0014078632,0.0009523646],"category_scores_gemma":[0.15172575,0.00054105796,0.0008627669,0.0056408118,0.0038798314,0.0046816515,0.0024867733,0.0020486931,0.0003042267],"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":[0.0019634585,0.0002658394,0.30305284,0.0009995366,0.0016093019,0.00051001506,0.0021444645,0.37462637,0.032444034,0.08372848,0.002129143,0.19652648],"study_design_scores_gemma":[0.00007184998,0.00058426516,0.077297226,0.00012901386,0.00018788493,0.0008665047,0.00060210907,0.7800738,0.017947797,0.119330764,0.0027172696,0.00019157089],"about_ca_topic_score_codex":0.0007903651,"about_ca_topic_score_gemma":0.00073603285,"teacher_disagreement_score":0.022730952,"about_ca_system_score_codex":0.0014824796,"about_ca_system_score_gemma":0.000653114,"threshold_uncertainty_score":0.120214164},"labels":[],"label_agreement":null},{"id":"W2065117387","doi":"10.1089/cmb.2008.0224","title":"On the Parameterized Complexity of Pooling Design","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Advanced biosensing and bioanalysis techniques","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":"Parameterized complexity; Pooling; Separable space; Integer (computer science); Matrix (chemical analysis); Combinatorics; Binary number; Function (biology); Mathematics; Computational complexity theory; Discrete mathematics; Disjunct; Computer science; Algorithm; Artificial intelligence; Arithmetic; Biology","score_opus":0.04487972586313298,"score_gpt":0.3227692446525396,"score_spread":0.2778895187894066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065117387","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15287994,0.0010117323,0.82806766,0.0038741461,0.00009454636,0.00035456254,0.0012269791,0.0015056921,0.010984669],"genre_scores_gemma":[0.63690305,0.0012288216,0.34872025,0.0009874658,0.00027364667,0.0012987052,0.0026588517,0.00070548634,0.0072237286],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9915656,0.0036411323,0.0006217352,0.0017013116,0.0015101229,0.00096002856],"domain_scores_gemma":[0.94371414,0.04481794,0.0029543096,0.0061481595,0.001599037,0.00076637586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005531979,0.001598216,0.002136821,0.000856817,0.0012813513,0.0044946764,0.002821043,0.002350531,0.009422759],"category_scores_gemma":[0.03885386,0.0012930108,0.0022508488,0.002171869,0.0025514693,0.010090568,0.0035310928,0.0033281012,0.0009556349],"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":[0.0010716975,0.00038729078,0.004602571,0.0007883297,0.00024421487,0.00040899275,0.00041498538,0.71149504,0.008458379,0.1474144,0.009199231,0.11551476],"study_design_scores_gemma":[0.00013469397,0.00012366875,0.00067496154,0.000033982356,0.000054668628,0.00013475333,0.00007079371,0.8025767,0.002281014,0.19177881,0.0021025343,0.000033446348],"about_ca_topic_score_codex":0.003085776,"about_ca_topic_score_gemma":0.0026459843,"teacher_disagreement_score":0.009422759,"about_ca_system_score_codex":0.0035376593,"about_ca_system_score_gemma":0.0035713539,"threshold_uncertainty_score":0.031522214},"labels":[],"label_agreement":null},{"id":"W2065400176","doi":"10.1089/cmb.2007.a006","title":"Exact and Heuristic Algorithms for the Indel Maximum Likelihood Problem","year":2007,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université du Québec à Montréal","funders":"","keywords":"Indel; Algorithm; Heuristic; Tree (set theory); Markov chain; Viterbi algorithm; Hidden Markov model; Phylogenetic tree; Computer science; Mathematics; Biology; Artificial intelligence; Genetics; Combinatorics; Machine learning; Gene; Decoding methods","score_opus":0.013906141597825812,"score_gpt":0.27932563023353707,"score_spread":0.26541948863571124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065400176","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013189913,0.0002910056,0.99599314,0.00016094674,0.000038409824,0.000063057654,0.00008602371,0.0006703384,0.0013780014],"genre_scores_gemma":[0.023993967,0.00032639247,0.9730338,0.00012824374,0.000108530694,0.00035618932,0.00037753893,0.0002633605,0.0014119694],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981117,0.0008372837,0.00011512651,0.0002925703,0.00046887138,0.00017427621],"domain_scores_gemma":[0.9926293,0.0058162673,0.00030682885,0.0005688188,0.0005474366,0.00013136186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003662029,0.0017057711,0.0017881928,0.002519765,0.0011109457,0.0022270235,0.0041119694,0.002833214,0.010495359],"category_scores_gemma":[0.01800748,0.0010997782,0.0013486466,0.003535001,0.0013990992,0.0034180149,0.0028239484,0.0034147762,0.003937101],"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":[0.0001874201,0.00021053315,0.0008007824,0.0003630904,0.00009385637,0.00017647042,0.00024766685,0.52846456,0.00130393,0.10111711,0.011973316,0.35506126],"study_design_scores_gemma":[0.00009817275,0.000028433476,0.00012454945,0.000030630366,0.000015942891,0.00008465248,0.000053667198,0.8513949,0.0005017089,0.14395939,0.0036817205,0.000026242127],"about_ca_topic_score_codex":0.0037778767,"about_ca_topic_score_gemma":0.005060512,"teacher_disagreement_score":0.010495359,"about_ca_system_score_codex":0.00167369,"about_ca_system_score_gemma":0.0024186738,"threshold_uncertainty_score":0.035110474},"labels":[],"label_agreement":null},{"id":"W2065576510","doi":"10.1089/cmb.2007.0185","title":"On the Sparse Reconstruction of Gene Networks","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Gene Regulatory Network Analysis","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 Calgary","funders":"","keywords":"Greedy algorithm; Heuristic; Computer science; Noise (video); Algorithm; Iterative method; Mathematical optimization; Computational biology; Theoretical computer science; Pattern recognition (psychology); Mathematics; Artificial intelligence; Biology","score_opus":0.013229108107174608,"score_gpt":0.2320361408289565,"score_spread":0.21880703272178187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065576510","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004019281,0.00015537957,0.99475574,0.00015351386,0.000016496173,0.000011082339,0.000026930202,0.000088889035,0.00077264453],"genre_scores_gemma":[0.20745006,0.0014155579,0.786134,0.00031711062,0.00018888284,0.00022700682,0.00036184682,0.00021922978,0.0036864069],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999343,0.00036271216,0.000013752873,0.00006269265,0.00016589458,0.00005193251],"domain_scores_gemma":[0.9969368,0.0024007987,0.00013521755,0.00024749833,0.00019549027,0.000084118044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016874712,0.0007210239,0.00087581354,0.00097317644,0.00047289458,0.0008479979,0.0010528484,0.0012377641,0.0017347431],"category_scores_gemma":[0.0090096425,0.0005051613,0.0008572821,0.0011598439,0.0020242347,0.0014145189,0.0014176213,0.0015103711,0.00054558675],"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":[0.000086737906,0.000024585303,0.00029762718,0.000100151505,0.000035534824,0.00011533667,0.000090199,0.8304437,0.0046234415,0.12784512,0.0016833756,0.034654234],"study_design_scores_gemma":[0.000011611545,0.000012433715,0.000055154418,0.00000768877,0.0000039614874,0.000030764553,0.000008279583,0.9545703,0.00065510295,0.043883495,0.00075419835,0.000007000544],"about_ca_topic_score_codex":0.0030200721,"about_ca_topic_score_gemma":0.002542892,"teacher_disagreement_score":0.0030200721,"about_ca_system_score_codex":0.00066207815,"about_ca_system_score_gemma":0.0007773842,"threshold_uncertainty_score":0.008924305},"labels":[],"label_agreement":null},{"id":"W2068396445","doi":"10.1089/cmb.2006.13.567","title":"On Sorting by Translocations","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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":"Université du Québec à Montréal","funders":"","keywords":"Sorting; Chromosomal translocation; Sorting algorithm; Genome; Chromosome; Computer science; Algorithm; Computational biology; Biology; Mathematics; Genetics; Gene","score_opus":0.005620043957935987,"score_gpt":0.250474535487991,"score_spread":0.24485449153005498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068396445","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034021877,0.0032751847,0.93183255,0.0036688622,0.00068409,0.00013716368,0.0002873009,0.0014490923,0.024643922],"genre_scores_gemma":[0.32214,0.00942413,0.629141,0.0032304334,0.0011812473,0.00035825474,0.0015716333,0.0016005002,0.031352863],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969837,0.0008428889,0.00021370171,0.0006913715,0.0008589983,0.00040924957],"domain_scores_gemma":[0.9943252,0.0038925742,0.00028370184,0.0007715434,0.0005513089,0.00017565188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002881999,0.0010878065,0.0014861921,0.0019113945,0.0023833592,0.003039651,0.0020763187,0.002303632,0.01198689],"category_scores_gemma":[0.016049925,0.0006181882,0.0017207348,0.00501953,0.005589408,0.012779253,0.0050746677,0.003919002,0.0028841167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019703491,0.00004933649,0.0004631003,0.0002572841,0.000020512602,0.00012383996,0.00031803627,0.037612636,0.0031223833,0.8282742,0.007769436,0.1217921],"study_design_scores_gemma":[0.00005906422,0.000042140102,0.00012294683,0.000047713937,0.0000143181,0.0001319008,0.00007467029,0.046787646,0.0023000345,0.9297373,0.020656709,0.000025560532],"about_ca_topic_score_codex":0.003100907,"about_ca_topic_score_gemma":0.0023303395,"teacher_disagreement_score":0.01198689,"about_ca_system_score_codex":0.0022550935,"about_ca_system_score_gemma":0.0017043297,"threshold_uncertainty_score":0.040100098},"labels":[],"label_agreement":null},{"id":"W2069393486","doi":"10.1089/cmb.2005.12.971","title":"Finding Cancer Biomarkers from Mass Spectrometry Data by Decision Lists","year":2005,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; USable; Biomarker; Cancer; Computational biology; Machine learning; Biomarker discovery; Cancer biomarkers; Decision tree; Artificial intelligence; Data mining; Proteomics; Bioinformatics; Medicine; Biology","score_opus":0.026119018219900487,"score_gpt":0.3591833970151411,"score_spread":0.33306437879524065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069393486","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051425114,0.0021727404,0.94097006,0.0015979479,0.000085857944,0.00028908657,0.0015515569,0.0012152328,0.0006924128],"genre_scores_gemma":[0.40955478,0.0015921121,0.5818883,0.0005829499,0.0002972951,0.00046930098,0.004467129,0.0001127853,0.0010353113],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99501795,0.0023385484,0.00049926323,0.000690454,0.0012518528,0.00020193576],"domain_scores_gemma":[0.96973175,0.026229596,0.0018027511,0.00067813357,0.0012806031,0.00027710202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0071127727,0.0020046846,0.0023475394,0.0054955753,0.0010504088,0.0039025613,0.001622264,0.0019831595,0.0018573614],"category_scores_gemma":[0.022755263,0.00091262587,0.0019166041,0.0039913114,0.0012337762,0.0041996525,0.0013274394,0.0019821613,0.00084594556],"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":[0.0011920731,0.0004499107,0.016026566,0.001471171,0.00041009884,0.0007858642,0.00029708253,0.5369448,0.0072743455,0.014298242,0.005576913,0.41527286],"study_design_scores_gemma":[0.000087270324,0.00015711281,0.0011597491,0.000085216765,0.000099562574,0.00014968279,0.00007215113,0.92510325,0.004944729,0.06605139,0.0020197178,0.00007010729],"about_ca_topic_score_codex":0.0020399282,"about_ca_topic_score_gemma":0.0024283435,"teacher_disagreement_score":0.0071127727,"about_ca_system_score_codex":0.0011236458,"about_ca_system_score_gemma":0.001966213,"threshold_uncertainty_score":0.037616372},"labels":[],"label_agreement":null},{"id":"W2072014857","doi":"10.1089/cmb.2009.0117","title":"Haplotype Inferring via Galled-Tree Networks Is NP-Complete","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genetic Mapping and Diversity in Plants and Animals","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":"Simon Fraser University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Haplotype; Phylogenetic tree; Tree (set theory); Phylogenetic network; Biology; International HapMap Project; Computational biology; Computer science; Genetics; Theoretical computer science; Combinatorics; Mathematics; Genotype; Gene","score_opus":0.011824991485407001,"score_gpt":0.2456756754351442,"score_spread":0.2338506839497372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072014857","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1047498,0.00119118,0.87045276,0.0054747346,0.00009368958,0.00044639717,0.007877158,0.0021856523,0.007528661],"genre_scores_gemma":[0.39736342,0.0015475013,0.57653314,0.0010867191,0.0001428353,0.0006010455,0.016458165,0.0005017504,0.0057654483],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99848926,0.00045397898,0.000100187906,0.0005073266,0.0002675951,0.00018162146],"domain_scores_gemma":[0.98215485,0.015396551,0.00066829735,0.0009595591,0.00048002874,0.0003407642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015852721,0.0009669882,0.0014285301,0.0009843403,0.0012224324,0.002709599,0.002074466,0.0021112906,0.0077113495],"category_scores_gemma":[0.01207945,0.0009977729,0.0017746852,0.0019265917,0.0011560565,0.0073536187,0.0021135411,0.002277995,0.0009837473],"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":[0.0005784965,0.00029947687,0.005323815,0.0012885568,0.00027931624,0.0005686954,0.00069026026,0.7032063,0.0037366631,0.055808924,0.02536029,0.20285924],"study_design_scores_gemma":[0.000087945824,0.000037244645,0.0007800866,0.000047154255,0.00006357874,0.00025268842,0.0001933175,0.80856794,0.0013864444,0.18292348,0.005634145,0.000025950514],"about_ca_topic_score_codex":0.00587566,"about_ca_topic_score_gemma":0.009956695,"teacher_disagreement_score":0.0077113495,"about_ca_system_score_codex":0.0017217777,"about_ca_system_score_gemma":0.0018586764,"threshold_uncertainty_score":0.02579701},"labels":[],"label_agreement":null},{"id":"W2072483773","doi":"10.1089/cmb.2009.0088","title":"Computation of Perfect DCJ Rearrangement Scenarios with Linear and Circular Chromosomes","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Agence Nationale de la Recherche","keywords":"Computation; Computer science; Mathematics; Biology; Algorithm","score_opus":0.008552402600034597,"score_gpt":0.2568928983666118,"score_spread":0.24834049576657719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072483773","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59721464,0.00029711978,0.39128116,0.000678582,0.00003283513,0.00010284712,0.00090178987,0.0014308442,0.008060222],"genre_scores_gemma":[0.85565764,0.00014088502,0.14066775,0.00009569146,0.00001607489,0.000060434613,0.0016534475,0.00013019673,0.0015779044],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992736,0.00014277625,0.000045384037,0.00027384254,0.000120867706,0.00014348017],"domain_scores_gemma":[0.9973455,0.0015722042,0.000313994,0.00043794894,0.00015525047,0.00017513288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070262025,0.0005242292,0.00061947136,0.0005204342,0.0007600181,0.0016274049,0.0013294189,0.001285895,0.003511777],"category_scores_gemma":[0.0046036313,0.0005302067,0.00072282297,0.0011679021,0.00096598273,0.0030380085,0.0015322143,0.00074530917,0.0003761549],"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":[0.0005360581,0.000115973606,0.004183152,0.0003239092,0.00007167229,0.0004213278,0.00019642824,0.8409057,0.01208603,0.093508,0.0022928712,0.045358915],"study_design_scores_gemma":[0.000049502258,0.00007700761,0.00050267373,0.000014840738,0.000020503981,0.00023889595,0.00017332728,0.90722877,0.008526258,0.081140436,0.002010139,0.000017553848],"about_ca_topic_score_codex":0.0018127149,"about_ca_topic_score_gemma":0.0021369462,"teacher_disagreement_score":0.003511777,"about_ca_system_score_codex":0.0011833677,"about_ca_system_score_gemma":0.000889994,"threshold_uncertainty_score":0.0117480755},"labels":[],"label_agreement":null},{"id":"W2073141486","doi":"10.1089/cmb.2010.0260","title":"Pathway-Based Functional Analysis of Metagenomes","year":2011,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"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","keywords":"Metagenomics; Computational biology; Biology; Ranking (information retrieval); Computer science; Pathway analysis; Gene; Data science; Machine learning; Genetics; Gene expression","score_opus":0.03234882831146196,"score_gpt":0.24692981790528434,"score_spread":0.21458098959382238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073141486","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22804564,0.0003403848,0.7655604,0.0003492053,0.000032281045,0.00012050605,0.0024829558,0.0013004293,0.0017682298],"genre_scores_gemma":[0.80030966,0.00037132355,0.19613007,0.00004996735,0.000015386808,0.00023105265,0.0019255417,0.00013077415,0.00083633297],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995851,0.00019117525,0.000022458264,0.00007445618,0.000090530455,0.00003627604],"domain_scores_gemma":[0.99842924,0.0010256462,0.0001047295,0.00015436948,0.00020766087,0.00007830536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012110601,0.000817155,0.0006166794,0.0015667195,0.0005287575,0.0011977444,0.0011639367,0.0006792338,0.0024306353],"category_scores_gemma":[0.004484334,0.00031140575,0.0016899632,0.0010390611,0.00040851563,0.0012070852,0.00075269403,0.0007600681,0.0003008612],"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":[0.00012445597,0.00004257705,0.0031112984,0.00008252053,0.00007244037,0.000036347854,0.0000296757,0.9720144,0.0026296133,0.008514431,0.00017983723,0.013162381],"study_design_scores_gemma":[0.00000531593,0.000010445853,0.00038403165,0.0000022651145,0.0000058183914,0.000011096893,0.000006856532,0.99283665,0.000667884,0.005913094,0.0001515647,0.0000049787513],"about_ca_topic_score_codex":0.00856307,"about_ca_topic_score_gemma":0.006159019,"teacher_disagreement_score":0.00856307,"about_ca_system_score_codex":0.0011522454,"about_ca_system_score_gemma":0.0015712102,"threshold_uncertainty_score":0.017026484},"labels":[],"label_agreement":null},{"id":"W2073512309","doi":"10.1089/cmb.2006.13.979","title":"An <i>O</i> ( <i>n</i> log <i>n</i> )-Time Algorithm for the Restriction Scaffold Assignment Problem","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Complexity and Algorithms in Graphs","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; McGill University","funders":"","keywords":"Computer science; Algorithm; Scaffold; Combinatorics; Mathematics; Programming language","score_opus":0.01202318925585627,"score_gpt":0.2583048064252301,"score_spread":0.24628161716937386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073512309","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020681472,0.00045390017,0.9460441,0.00170138,0.00021542776,0.0010874106,0.0012932996,0.013473054,0.015049993],"genre_scores_gemma":[0.049148887,0.00028004203,0.9398547,0.00022689636,0.000101810685,0.0008862028,0.0027811883,0.0007066618,0.006013586],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982486,0.00027768844,0.00011763384,0.00066413864,0.00034097387,0.00035095913],"domain_scores_gemma":[0.99651426,0.0017955747,0.00033415842,0.0007759664,0.00027973845,0.00030025328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016350975,0.0033646165,0.0025944037,0.002044278,0.0023064043,0.003838554,0.006713059,0.003344555,0.025955636],"category_scores_gemma":[0.0050562983,0.0013837393,0.0027775986,0.0039066635,0.0016464823,0.0066136415,0.0043965406,0.0036275818,0.008840228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010962335,0.0011011205,0.0021911585,0.0014731289,0.00024225458,0.00028519912,0.0005042287,0.07579736,0.016397823,0.036011633,0.09004767,0.7748522],"study_design_scores_gemma":[0.0019029947,0.0008130842,0.0023310175,0.0001953575,0.00030918865,0.0015653011,0.0008093793,0.7617485,0.018116942,0.16185853,0.050130375,0.00021935934],"about_ca_topic_score_codex":0.007075232,"about_ca_topic_score_gemma":0.009691231,"teacher_disagreement_score":0.025955636,"about_ca_system_score_codex":0.0032735036,"about_ca_system_score_gemma":0.0055079185,"threshold_uncertainty_score":0.08683032},"labels":[],"label_agreement":null},{"id":"W2073783012","doi":"10.1089/cmb.2008.0002","title":"Pathway Analysis of Microarray Data via Regression","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Covariate; Phenotype; Microarray analysis techniques; Computational biology; Gene expression profiling; Test statistic; Regression; Biological pathway; Microarray; Regression analysis; Biology; Computer science; Statistical hypothesis testing; Statistics; Gene; Gene expression; Genetics; Mathematics; Machine learning","score_opus":0.02183032745076579,"score_gpt":0.2775139254295046,"score_spread":0.2556835979787388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073783012","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010718847,0.0002980345,0.98417085,0.00012987807,0.000024913841,0.000084740386,0.0017436716,0.0024724074,0.000356689],"genre_scores_gemma":[0.23881304,0.0010504785,0.750243,0.00008746577,0.000071842136,0.00092587556,0.0060352427,0.0005722374,0.0022008845],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99753404,0.0010549016,0.00016265226,0.0005922377,0.0005053657,0.00015078539],"domain_scores_gemma":[0.9965062,0.0022256707,0.00033251985,0.00043829042,0.00042596585,0.00007137699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037273336,0.0010932231,0.0015509999,0.002715227,0.00032693814,0.0014585784,0.0009903456,0.00044217738,0.004184389],"category_scores_gemma":[0.010298629,0.0005090025,0.0017692753,0.0037113994,0.00042657656,0.0010515677,0.0010823683,0.0015924886,0.0016157735],"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":[0.0007097503,0.00024576817,0.014102745,0.0010631309,0.0011858408,0.00023485182,0.00022263054,0.4065564,0.044341333,0.032500774,0.007967421,0.49086937],"study_design_scores_gemma":[0.000037807666,0.00008660734,0.004819696,0.000022735463,0.000060360675,0.000082872146,0.000040129962,0.9588691,0.007028672,0.024054922,0.004843911,0.00005321936],"about_ca_topic_score_codex":0.0021455756,"about_ca_topic_score_gemma":0.0021187954,"teacher_disagreement_score":0.004184389,"about_ca_system_score_codex":0.0006020419,"about_ca_system_score_gemma":0.0011771214,"threshold_uncertainty_score":0.01971227},"labels":[],"label_agreement":null},{"id":"W2074993099","doi":"10.1089/10665270152530818","title":"On Combinatorial DNA Word Design","year":2001,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Advanced biosensing and bioanalysis techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":236,"is_retracted":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":"Alphabet; Word (group theory); DNA computing; Combinatorics; Heuristic; Code (set theory); Discrete mathematics; Computer science; Coding (social sciences); Dynamic programming; Constraint (computer-aided design); Complement (music); Algorithm; Mathematics; Computation; Biology; Genetics; Set (abstract data type)","score_opus":0.014473723184892153,"score_gpt":0.29749736186493075,"score_spread":0.2830236386800386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074993099","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009804489,0.0027843087,0.9689839,0.00074253225,0.00025783118,0.00013538956,0.0002074308,0.00025694387,0.016827088],"genre_scores_gemma":[0.14903344,0.006920289,0.8239378,0.0010552568,0.00077209243,0.0010443074,0.0012687336,0.0004413283,0.015526794],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976926,0.0008186825,0.00015142269,0.0005289507,0.00058364624,0.00022474426],"domain_scores_gemma":[0.9943036,0.0043990063,0.00028854105,0.0004632099,0.00038638982,0.00015930101],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019438788,0.0017278297,0.0016714361,0.0018208451,0.0011049359,0.0029613683,0.0021139504,0.0021669783,0.0078119375],"category_scores_gemma":[0.010104691,0.0009378939,0.001534384,0.0035270066,0.003270759,0.0040167742,0.0024257472,0.0025549703,0.0020271083],"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":[0.000119365905,0.00012995694,0.000474143,0.0006627687,0.00006828384,0.00022413126,0.00015885693,0.31897914,0.0023299751,0.5601402,0.0071477587,0.10956536],"study_design_scores_gemma":[0.000057533958,0.00009815973,0.00007548091,0.00007125021,0.000023207322,0.00015886135,0.00004404455,0.24721828,0.0012269036,0.7336746,0.017323628,0.000028059605],"about_ca_topic_score_codex":0.00089085125,"about_ca_topic_score_gemma":0.00097473635,"teacher_disagreement_score":0.0078119375,"about_ca_system_score_codex":0.001537289,"about_ca_system_score_gemma":0.001063856,"threshold_uncertainty_score":0.026133537},"labels":[],"label_agreement":null},{"id":"W2077735595","doi":"10.1089/cmb.2006.13.200","title":"GenRate: A Generative Model that Reveals Novel Transcripts in Genome-Tiling Microarray Data","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Gene expression and cancer classification","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":"Tiling array; DNA microarray; Genome; Generative model; Cluster analysis; Computational biology; Biology; Microarray; Hierarchical clustering; Computer science; Microarray analysis techniques; Generative grammar; Microarray databases; Gene; Genetics; Data mining; Artificial intelligence; Gene expression","score_opus":0.058067648367697004,"score_gpt":0.31259989269332134,"score_spread":0.2545322443256243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077735595","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044057075,0.00014455908,0.9524578,0.00029152623,0.00002834047,0.00004802178,0.0006356882,0.0018298037,0.00050725584],"genre_scores_gemma":[0.54076034,0.000398468,0.4482804,0.0005974914,0.000108942564,0.00039545872,0.0045666676,0.00083277305,0.004059546],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910235,0.00038142598,0.000035324276,0.00024936057,0.0001564755,0.00007502966],"domain_scores_gemma":[0.99594456,0.003079815,0.00023910929,0.00043130523,0.00019576243,0.000109380795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003476266,0.00084521965,0.0012154967,0.0011875683,0.0005138791,0.001135131,0.0020403478,0.0014208772,0.0020072947],"category_scores_gemma":[0.007648338,0.00078386813,0.0018957115,0.0009442276,0.0012908955,0.0010697652,0.0012162206,0.0016365726,0.00064266956],"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":[0.00037839133,0.000086943226,0.009380198,0.00011777426,0.00016181258,0.00026429805,0.00019675854,0.86111134,0.008454849,0.025850799,0.004456036,0.08954085],"study_design_scores_gemma":[0.000011854992,0.00000984273,0.00025403843,0.0000036234353,0.000008709961,0.00005098757,0.0000054313446,0.9894037,0.0007290605,0.009170581,0.00034389808,0.000008283359],"about_ca_topic_score_codex":0.0036681078,"about_ca_topic_score_gemma":0.009059463,"teacher_disagreement_score":0.0036681078,"about_ca_system_score_codex":0.0010753144,"about_ca_system_score_gemma":0.0009869824,"threshold_uncertainty_score":0.018384457},"labels":[],"label_agreement":null},{"id":"W2081112743","doi":"10.1089/106652703322756195","title":"A Transition Probability Model for Amino Acid Substitutions from Blocks","year":2003,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":140,"is_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; Ontario Institute for Cancer Research","funders":"","keywords":"Substitution (logic); Sequence (biology); Distance matrices in phylogeny; Sequence alignment; Function (biology); Stochastic matrix; Matrix (chemical analysis); Protein sequencing; Computer science; Protein evolution; Algorithm; Evolutionary algorithm; Mathematics; Peptide sequence; Combinatorics; Biology; Genetics; Artificial intelligence; Machine learning; Chemistry","score_opus":0.023874447168447593,"score_gpt":0.26311787450956814,"score_spread":0.23924342734112056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081112743","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045085646,0.00067208754,0.9391358,0.0010923538,0.00022833633,0.00015592732,0.0012546779,0.0007855513,0.011589602],"genre_scores_gemma":[0.75365615,0.0020660793,0.16356029,0.00069169357,0.00049580366,0.0012304939,0.0023582971,0.00057281315,0.07536843],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988821,0.0002789804,0.00005255702,0.00034696766,0.00023707126,0.00020232153],"domain_scores_gemma":[0.9958792,0.0026974545,0.000356773,0.00041110403,0.0004173948,0.00023806472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00198656,0.0007196104,0.0016509009,0.0016357858,0.0009961966,0.0021395567,0.003391224,0.0024792193,0.0132743195],"category_scores_gemma":[0.0075808815,0.00082488055,0.0015336681,0.0017463355,0.0018296132,0.0044341185,0.0014163528,0.0029517077,0.004466276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002127001,0.00013703712,0.0029743158,0.00019708482,0.000097461394,0.00057164294,0.00050759694,0.24873765,0.005437119,0.7030964,0.008254901,0.029776094],"study_design_scores_gemma":[0.0000564241,0.000056425506,0.0005474046,0.000025119936,0.000039325063,0.0002828557,0.000026702372,0.80952793,0.00048173484,0.18399772,0.004915052,0.000043208423],"about_ca_topic_score_codex":0.005342313,"about_ca_topic_score_gemma":0.0035024532,"teacher_disagreement_score":0.0132743195,"about_ca_system_score_codex":0.0011196358,"about_ca_system_score_gemma":0.0010527109,"threshold_uncertainty_score":0.04440701},"labels":[],"label_agreement":null},{"id":"W2081163014","doi":"10.1089/cmb.2008.0003","title":"Linear Time Probabilistic Algorithms for the Singular Haplotype Reconstruction Problem from SNP Fragments","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Gene expression and cancer classification","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 Regina","funders":"","keywords":"Probabilistic logic; Haplotype; Algorithm; SNP; Probabilistic analysis of algorithms; Computer science; Computational biology; Mathematics; Biology; Genetics; Artificial intelligence; Single-nucleotide polymorphism; Gene; Genotype","score_opus":0.031321084303404516,"score_gpt":0.2924202296880671,"score_spread":0.26109914538466256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081163014","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014669349,0.00006386408,0.99766904,0.00011789969,0.000008393922,0.00003893507,0.000030083478,0.00033822475,0.00026659665],"genre_scores_gemma":[0.063440986,0.00017402829,0.9342154,0.00013844964,0.000060410268,0.00039677366,0.00043989433,0.00019199828,0.0009420031],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99559456,0.0016535928,0.00029810276,0.0010998775,0.0009902023,0.00036364855],"domain_scores_gemma":[0.97478163,0.020570898,0.0011919371,0.0020991052,0.0010138878,0.00034258192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006616051,0.0016340215,0.0015856066,0.0013396306,0.0014958036,0.002237112,0.004921025,0.002721041,0.005389036],"category_scores_gemma":[0.025654571,0.0012252722,0.001776204,0.0019771012,0.0022783633,0.004960291,0.0041925795,0.0037888826,0.0016362882],"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":[0.00035390034,0.00019532735,0.0010733487,0.00028750143,0.00010018066,0.000092980445,0.00025120514,0.7279651,0.0017429055,0.10821011,0.0040213666,0.15570602],"study_design_scores_gemma":[0.00006489484,0.00003175349,0.00010465903,0.000013630319,0.000013470441,0.00006085491,0.000030465706,0.9033703,0.00084090966,0.094509326,0.0009425014,0.000017298964],"about_ca_topic_score_codex":0.003663813,"about_ca_topic_score_gemma":0.004555283,"teacher_disagreement_score":0.006616051,"about_ca_system_score_codex":0.0024015892,"about_ca_system_score_gemma":0.0035213549,"threshold_uncertainty_score":0.034989476},"labels":[],"label_agreement":null},{"id":"W2083479074","doi":"10.1089/cmb.2008.0219","title":"An <i>O</i> ( <i>n</i> <sup>5</sup> ) Algorithm for MFE Prediction of Kissing Hairpins and 4-Chains in Nucleic Acids","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Nucleic acid; Algorithm; Function (biology); Computer science; Nucleic acid secondary structure; Nucleic acid structure; Class (philosophy); Protein secondary structure; RNA; Computational biology; Mathematics; Biology; Artificial intelligence; Genetics; Biochemistry","score_opus":0.010552622680376565,"score_gpt":0.261910987315347,"score_spread":0.25135836463497047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083479074","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059018685,0.00019429924,0.9878757,0.00016811477,0.00006834517,0.00015746825,0.00023353829,0.004183738,0.0012169423],"genre_scores_gemma":[0.017007064,0.00007149685,0.9804453,0.00007758637,0.000028100834,0.0002453366,0.0004698925,0.0003798926,0.0012752925],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928504,0.00017009971,0.00008997737,0.0001651582,0.0002088791,0.000080946316],"domain_scores_gemma":[0.9982755,0.0010700064,0.00013729755,0.00022516615,0.00022232757,0.00006968434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016109224,0.0016523029,0.0010831996,0.001366874,0.0011371397,0.0012891288,0.002495664,0.0021870201,0.013342362],"category_scores_gemma":[0.004687728,0.0008681415,0.0014221151,0.0015496839,0.0008740995,0.0027035088,0.002250093,0.0020243514,0.0041023716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007464906,0.0003344298,0.0016992649,0.00041143276,0.00016084411,0.00022345096,0.00021882665,0.099173196,0.011902483,0.015151884,0.019992579,0.8499851],"study_design_scores_gemma":[0.00041651205,0.00020741139,0.0006497332,0.000059576367,0.00005695996,0.0003010752,0.00007209456,0.94250095,0.0130035905,0.028011717,0.014661128,0.000059324524],"about_ca_topic_score_codex":0.0025404778,"about_ca_topic_score_gemma":0.005124597,"teacher_disagreement_score":0.013342362,"about_ca_system_score_codex":0.00086822704,"about_ca_system_score_gemma":0.0016405759,"threshold_uncertainty_score":0.04463458},"labels":[],"label_agreement":null},{"id":"W2083760725","doi":"10.1089/cmb.2009.0140","title":"A Bayesian Network Model of Proteins' Association with Promyelocytic Leukemia (PML) Nuclear Bodies","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Chromatin Dynamics","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":"Dalhousie University","funders":"","keywords":"Promyelocytic leukemia protein; Acute promyelocytic leukemia; Bayesian network; Computational biology; Leukemia; Association (psychology); Bayesian probability; Biology; Computer science; Genetics; Artificial intelligence; Psychology; Gene","score_opus":0.003907895730455847,"score_gpt":0.20686339783157925,"score_spread":0.2029555021011234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083760725","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23696287,0.00076560344,0.74881834,0.0021823922,0.000072955874,0.0000907413,0.002183733,0.0006019868,0.008321457],"genre_scores_gemma":[0.9312719,0.0008662862,0.055318024,0.00019955674,0.00010078344,0.00026239047,0.001562533,0.00007660856,0.010341994],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996239,0.00013573765,0.000012930325,0.00011909015,0.0000569032,0.000051331528],"domain_scores_gemma":[0.99846977,0.0010538155,0.00019351186,0.00004302583,0.00014501983,0.000094899304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014718728,0.0006368069,0.00086693134,0.0012707144,0.0005370304,0.0012134365,0.0016687227,0.0015995296,0.0038070758],"category_scores_gemma":[0.004901197,0.0006629861,0.0007932936,0.0012261342,0.000896457,0.0018524262,0.0006271307,0.0009420894,0.00053360994],"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":[0.00011109458,0.000025677044,0.0021898772,0.000027061818,0.00003114131,0.00007205785,0.000042526495,0.9681826,0.0006269468,0.020999271,0.00088391535,0.0068078972],"study_design_scores_gemma":[0.000014218747,0.0000072537186,0.0003810787,0.000004249529,0.000008160228,0.000015405585,0.0000035684568,0.9909712,0.000057682286,0.008345019,0.00018492919,0.0000071827335],"about_ca_topic_score_codex":0.021721547,"about_ca_topic_score_gemma":0.014929234,"teacher_disagreement_score":0.021721547,"about_ca_system_score_codex":0.0014906604,"about_ca_system_score_gemma":0.0010008152,"threshold_uncertainty_score":0.04319024},"labels":[],"label_agreement":null},{"id":"W2084401130","doi":"10.1089/cmb.2010.0250","title":"Admixture Aberration Analysis: Application to Mapping in Admixed Population Using Pooled DNA","year":2011,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Molecular Biology Techniques and Applications","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":"Azrieli Foundation; Israel Science Foundation","keywords":"Genotyping; Locus (genetics); Computational biology; Biology; Java; Genetic admixture; Population; Genetics; Gene; Computer science; Genotype; Medicine","score_opus":0.02007450093623693,"score_gpt":0.30158751492578645,"score_spread":0.28151301398954953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084401130","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09464981,0.00009638782,0.90389156,0.0001159522,0.000024534804,0.0000524603,0.00016225218,0.0006522066,0.0003549078],"genre_scores_gemma":[0.45251969,0.00006599656,0.546332,0.00003801509,0.000018309061,0.00010241223,0.000158385,0.00008277507,0.00068240875],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99936134,0.0003894271,0.000027382834,0.000115123315,0.000080461214,0.000026321788],"domain_scores_gemma":[0.99670875,0.0024224604,0.00020570608,0.00038772915,0.00018743206,0.00008794244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002894801,0.00048047327,0.00071438303,0.0011437965,0.00057267403,0.0004261124,0.0009253214,0.00048084694,0.0018130766],"category_scores_gemma":[0.0088540735,0.0002586749,0.0008122637,0.0012287023,0.0003817984,0.00043788506,0.0009213156,0.0006010231,0.0001632099],"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":[0.0005361963,0.0001499901,0.053933345,0.00019099325,0.0010190498,0.0006913271,0.00054062,0.68488276,0.01315266,0.019236704,0.0020533865,0.22361301],"study_design_scores_gemma":[0.00005445427,0.00007332314,0.0050981385,0.000006666709,0.00006830344,0.00015948032,0.000029252677,0.9755107,0.0027241006,0.015202714,0.0010466907,0.000026112277],"about_ca_topic_score_codex":0.00843703,"about_ca_topic_score_gemma":0.0064845113,"teacher_disagreement_score":0.00843703,"about_ca_system_score_codex":0.00037680796,"about_ca_system_score_gemma":0.000695476,"threshold_uncertainty_score":0.016775846},"labels":[],"label_agreement":null},{"id":"W2086121836","doi":"10.1089/cmb.2009.0032","title":"Protein-Protein Interaction Network Evaluation for Identifying Potential Drug Targets","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Computational Drug Discovery Methods","field":"Computer Science","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":"Simon Fraser University","funders":"","keywords":"Drug; Protein–protein interaction; Computational biology; Computer science; Biology; Pharmacology; Genetics","score_opus":0.03731551870322106,"score_gpt":0.37694203795660575,"score_spread":0.3396265192533847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086121836","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48218903,0.0045835874,0.48216635,0.0020175872,0.00009489165,0.00072428084,0.0076147555,0.003189358,0.017420096],"genre_scores_gemma":[0.8421992,0.0009083545,0.15123679,0.00010924776,0.000028036711,0.00027674594,0.0035773255,0.000089861336,0.0015745473],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918,0.00032636547,0.000045235083,0.00011622167,0.00026305532,0.00006907137],"domain_scores_gemma":[0.9975683,0.0017318125,0.000246108,0.00012102169,0.00022144472,0.00011125132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014843796,0.0011105605,0.00084932294,0.003406782,0.00038978516,0.0009735609,0.0006597583,0.00085649337,0.004662389],"category_scores_gemma":[0.006489684,0.00023425126,0.0006969469,0.0020833018,0.0003799253,0.0012678553,0.0008033327,0.000541495,0.00045386856],"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":[0.0013006108,0.00029996593,0.020549152,0.00067911914,0.00033815144,0.00023936327,0.00005993786,0.8127122,0.01206988,0.011163756,0.0049130623,0.13567486],"study_design_scores_gemma":[0.000021128808,0.00008142413,0.001934739,0.000011484783,0.000037651156,0.000065908775,0.000022693921,0.9907527,0.002142353,0.0038651035,0.001057645,0.000007225996],"about_ca_topic_score_codex":0.0026655444,"about_ca_topic_score_gemma":0.0027019624,"teacher_disagreement_score":0.004662389,"about_ca_system_score_codex":0.0012476447,"about_ca_system_score_gemma":0.00090441096,"threshold_uncertainty_score":0.015597284},"labels":[],"label_agreement":null},{"id":"W2088586122","doi":"10.1089/cmb.2008.0118","title":"Descendants of Whole Genome Duplication within Gene Order Phylogeny","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Genome; Phylogenetics; Gene duplication; Biology; Evolutionary biology; Genomics; Genetic algorithm; Genetics; Computational biology; Gene","score_opus":0.016306235639022143,"score_gpt":0.2577301740039923,"score_spread":0.24142393836497014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088586122","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7186205,0.0003277871,0.2770245,0.00017126394,0.000019281511,0.00004037046,0.0003586262,0.000478969,0.0029586237],"genre_scores_gemma":[0.8622728,0.00016929733,0.13348815,0.00005194734,0.000011707602,0.000037615264,0.0014836561,0.00010688136,0.002377954],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99972624,0.00005232984,0.000014342329,0.00012421388,0.00005510985,0.000027896474],"domain_scores_gemma":[0.99937123,0.00030167657,0.000079508296,0.00013409804,0.000061631734,0.000051924373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094728044,0.00021023037,0.00045744306,0.00077257503,0.0005279145,0.0009170889,0.000608918,0.00032862936,0.0019017345],"category_scores_gemma":[0.002761378,0.000277806,0.00056766946,0.00073435454,0.0004278779,0.0006897476,0.00082731294,0.00066893117,0.00030118437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00091776095,0.00014387527,0.16742481,0.00043805665,0.00037540292,0.0011301708,0.0012156769,0.26763234,0.07777432,0.15188193,0.002205221,0.3288604],"study_design_scores_gemma":[0.00006138566,0.00020527697,0.054346345,0.000061564475,0.00014223366,0.0017630141,0.0006289084,0.78412306,0.032759864,0.11255995,0.013294244,0.00005420056],"about_ca_topic_score_codex":0.0011837386,"about_ca_topic_score_gemma":0.0030237727,"teacher_disagreement_score":0.0019017345,"about_ca_system_score_codex":0.00053542166,"about_ca_system_score_gemma":0.0005542651,"threshold_uncertainty_score":0.0063619614},"labels":[],"label_agreement":null},{"id":"W2092120709","doi":"10.1089/cmb.2007.a007","title":"Duplication and Inversion History of a Tandemly Repeated Genes Family","year":2007,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","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":"Université de Montréal","funders":"","keywords":"Phylogenetic tree; Biology; Gene duplication; Phylogenetics; Gene; Chromosomal inversion; Gene family; Genetics; Breakpoint; Chromosome; Segmental duplication; Inference; Maximum parsimony; Evolutionary biology; Genome; Karyotype; Computer science; Artificial intelligence","score_opus":0.014768631216696925,"score_gpt":0.2472926858771418,"score_spread":0.23252405466044487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092120709","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98200834,0.00011297801,0.016950702,0.000062935724,0.000001902714,0.0000048032157,0.00010448528,0.00003448853,0.00071947754],"genre_scores_gemma":[0.9867487,0.0000587558,0.012657337,0.000009420249,0.000002984466,0.000006479236,0.00023121119,0.000009476457,0.0002757591],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998166,0.00004190453,0.000010292422,0.000060029757,0.000046269302,0.00002504504],"domain_scores_gemma":[0.99856657,0.0008349746,0.00027471015,0.00008510196,0.00012748009,0.000111209396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046652087,0.00010726771,0.00030088014,0.000707554,0.0004699769,0.00044996096,0.00048530518,0.00042785346,0.0011511266],"category_scores_gemma":[0.0040362542,0.00019615515,0.00022841193,0.00072059967,0.00046238248,0.00086117757,0.00027913027,0.0004275324,0.00018170998],"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":[0.001002808,0.00015687894,0.22380623,0.00030458812,0.00015706493,0.0023471517,0.00078197516,0.38494208,0.24711066,0.060549088,0.0008516628,0.077989765],"study_design_scores_gemma":[0.00007621827,0.0003584576,0.08279686,0.000045721692,0.00012060912,0.0028775434,0.00037205592,0.8190663,0.027278436,0.06379347,0.0031474358,0.000066945926],"about_ca_topic_score_codex":0.001027967,"about_ca_topic_score_gemma":0.0013116278,"teacher_disagreement_score":0.0011511266,"about_ca_system_score_codex":0.0005214093,"about_ca_system_score_gemma":0.00040747752,"threshold_uncertainty_score":0.0038508773},"labels":[],"label_agreement":null},{"id":"W2105179267","doi":"10.1089/cmb.2006.13.929","title":"Enhancing the Prediction of Transcription Factor Binding Sites by Incorporating Structural Properties and Nucleotide Covariations","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Chromatin Dynamics","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 Toronto","funders":"","keywords":"Transcription factor; Computational biology; Genetics; Binding site; DNA binding site; Biology; Nucleotide; Evolutionary biology; Computer science; Promoter; Gene","score_opus":0.01078744981732247,"score_gpt":0.2128727327305383,"score_spread":0.20208528291321584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105179267","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15836425,0.00022681468,0.83863044,0.00008237024,0.00002552064,0.00004933214,0.00028396887,0.0017286015,0.0006087321],"genre_scores_gemma":[0.50279725,0.000307465,0.4946064,0.00006229349,0.000035024794,0.00006913969,0.0010316044,0.00032966115,0.0007611889],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993112,0.00017971001,0.000050641647,0.0001879141,0.00022514001,0.000045346078],"domain_scores_gemma":[0.995902,0.002948498,0.0003258586,0.00034133016,0.00031503252,0.00016720881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014481904,0.0008376984,0.0012644647,0.001065806,0.0002940432,0.00086330675,0.0009449382,0.0011864365,0.0009061581],"category_scores_gemma":[0.00808001,0.0007467015,0.0007495068,0.0009578454,0.00039578057,0.0009279082,0.00064441696,0.0012364114,0.00090684084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011409203,0.00047973508,0.053042166,0.00036804288,0.00026411816,0.0006371856,0.00023876828,0.35087326,0.22784176,0.005754783,0.000984954,0.35837424],"study_design_scores_gemma":[0.000050746155,0.00015464288,0.0032909063,0.000015533544,0.00005557203,0.00032877288,0.000025506039,0.95196444,0.039117523,0.0041844426,0.0007678135,0.000044048382],"about_ca_topic_score_codex":0.0020136577,"about_ca_topic_score_gemma":0.003630323,"teacher_disagreement_score":0.0020136577,"about_ca_system_score_codex":0.0002650369,"about_ca_system_score_gemma":0.0010207915,"threshold_uncertainty_score":0.007658839},"labels":[],"label_agreement":null},{"id":"W2122316710","doi":"10.1089/cmb.2014.0160","title":"On the Representation of De Bruijn Graphs","year":2015,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"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; Canada's Michael Smith Genome Sciences Centre","funders":"Division of Biological Infrastructure","keywords":"De Bruijn sequence; De Bruijn graph; Bottleneck; Computer science; Theoretical computer science; Data structure; Graph; Representation (politics); Mathematics; Discrete mathematics; Programming language","score_opus":0.030731782023773087,"score_gpt":0.30024953807546445,"score_spread":0.26951775605169137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122316710","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018493105,0.00027280775,0.9738689,0.000254584,0.000050049064,0.000055097255,0.0007044846,0.0010212546,0.0052797687],"genre_scores_gemma":[0.14866321,0.00061461516,0.84266114,0.00019825937,0.000092150476,0.00025796934,0.0025065788,0.0008129886,0.004193176],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998949,0.00032083088,0.00012781039,0.00021591723,0.0002847225,0.00010172262],"domain_scores_gemma":[0.9970161,0.0015389782,0.00031844806,0.00060872093,0.0004445967,0.00007325011],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009432341,0.00087911193,0.00067363173,0.0024872168,0.0008401093,0.002297185,0.0011687451,0.0009859415,0.003734269],"category_scores_gemma":[0.006982544,0.0005377582,0.0008793225,0.0029379353,0.0012981083,0.0033041947,0.0012641035,0.0014575357,0.0015831717],"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":[0.00015753102,0.00009355326,0.0009506757,0.00036870138,0.00002932349,0.00020712294,0.000535337,0.14895032,0.014950769,0.6635433,0.00689806,0.16331531],"study_design_scores_gemma":[0.000024421402,0.00006144917,0.0002962565,0.000104194165,0.000017382908,0.00024993593,0.000118720745,0.35564485,0.0075873025,0.6124699,0.023386002,0.000039631155],"about_ca_topic_score_codex":0.0018658193,"about_ca_topic_score_gemma":0.0023271877,"teacher_disagreement_score":0.003734269,"about_ca_system_score_codex":0.0008041192,"about_ca_system_score_gemma":0.0007402118,"threshold_uncertainty_score":0.012492359},"labels":[],"label_agreement":null},{"id":"W2124824180","doi":"10.1089/cmb.2012.0233","title":"Simultaneously Learning DNA Motif Along with Its Position and Sequence Rank Preferences Through Expectation Maximization Algorithm","year":2013,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"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":"Ministry of Education, India; Ministry of Earth Sciences; National University of Singapore; Canadian Occupational Therapy Foundation","keywords":"Motif (music); Sequence motif; Computer science; False positive paradox; Chromatin immunoprecipitation; Computational biology; DNA binding site; Artificial intelligence; Algorithm; Data mining; Biology; Genetics; DNA; Gene","score_opus":0.00857171474557676,"score_gpt":0.23632398282998113,"score_spread":0.22775226808440438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124824180","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021641651,0.00013292313,0.977394,0.00008490837,0.000008258987,0.000024215875,0.00004461965,0.00048153024,0.00018793262],"genre_scores_gemma":[0.29581997,0.00020854818,0.7014798,0.00021308006,0.000036869827,0.00019658593,0.0007031354,0.00012490636,0.0012171263],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991104,0.00037541747,0.000057774618,0.00024919593,0.00012996339,0.00007732049],"domain_scores_gemma":[0.9978156,0.0016909286,0.00012389908,0.00010041732,0.00020637906,0.000062707375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002238068,0.0011312044,0.0013956525,0.00073437754,0.0003110215,0.0006168034,0.0014509492,0.0012020956,0.00090551033],"category_scores_gemma":[0.004358397,0.0007372083,0.0009540683,0.00088118453,0.0005180553,0.0011472721,0.0007951061,0.0013734945,0.00042463315],"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":[0.0003092182,0.00018465969,0.004354948,0.00015026965,0.00016591857,0.00011925142,0.000098864024,0.7820372,0.011622553,0.0053991545,0.0013968993,0.1941611],"study_design_scores_gemma":[0.000009711825,0.000017555918,0.00010526752,0.0000016625626,0.0000059841386,0.00001627562,0.0000034235788,0.9972644,0.0009218723,0.0015397852,0.00011004023,0.0000040157984],"about_ca_topic_score_codex":0.0022346908,"about_ca_topic_score_gemma":0.0028341424,"teacher_disagreement_score":0.002238068,"about_ca_system_score_codex":0.000558996,"about_ca_system_score_gemma":0.0009951423,"threshold_uncertainty_score":0.011836171},"labels":[],"label_agreement":null},{"id":"W2127421473","doi":"10.1089/cmb.2013.0042","title":"IDBA-MT: <i>De Novo</i> Assembler for Metatranscriptomic Data Generated from Next-Generation Sequencing Technology","year":2013,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","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":"Amgen (Canada); University of Toronto","funders":"","keywords":"Contig; Sequence assembly; Computational biology; DNA sequencing; Genome; Biology; Computer science; Transcriptome; Genetics; Gene","score_opus":0.08796824590738316,"score_gpt":0.29473647663191455,"score_spread":0.20676823072453138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127421473","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0175131,0.0016712687,0.910246,0.00029356265,0.00046061364,0.00041373627,0.0043780203,0.061024234,0.0039993566],"genre_scores_gemma":[0.038205694,0.0010840904,0.9322991,0.0003145333,0.000071429764,0.00070827047,0.015572741,0.0069221053,0.0048220158],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985967,0.00032531752,0.00019511298,0.00032391326,0.00044622557,0.000112718524],"domain_scores_gemma":[0.99888855,0.00027947858,0.00022831769,0.00026408266,0.00023552192,0.00010409544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015475339,0.0020494314,0.0016678968,0.001451576,0.0011641402,0.0018565234,0.001843476,0.0011042656,0.0047502513],"category_scores_gemma":[0.0027965487,0.0014085727,0.0016770646,0.0012336716,0.00048704792,0.0010247784,0.001281648,0.0034157026,0.0067078653],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072112284,0.00017894754,0.001736555,0.0016547495,0.00031254542,0.00053613377,0.00047360497,0.004565328,0.83311814,0.006232676,0.028930195,0.121540025],"study_design_scores_gemma":[0.00010806561,0.00029176436,0.001586423,0.00012442879,0.00015316713,0.001142405,0.000092322494,0.05515642,0.71564615,0.0029750625,0.22252615,0.00019771494],"about_ca_topic_score_codex":0.0010487989,"about_ca_topic_score_gemma":0.0015346666,"teacher_disagreement_score":0.0047502513,"about_ca_system_score_codex":0.000789495,"about_ca_system_score_gemma":0.0011012035,"threshold_uncertainty_score":0.015891194},"labels":[],"label_agreement":null},{"id":"W2156501361","doi":"10.1089/cmb.2007.0062","title":"Locality and Gaps in RNA Comparison","year":2007,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Edmond de Rothschild Foundation; Russian Foundation for Basic Research","keywords":"Locality; Computation; Affine transformation; Smith–Waterman algorithm; Algorithm; Metric (unit); String (physics); Sequence (biology); RNA; Computer science; Multiple sequence alignment; Mathematics; Sequence alignment; Biology","score_opus":0.013436072819467662,"score_gpt":0.30363343712928076,"score_spread":0.2901973643098131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156501361","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08794026,0.003917057,0.9011952,0.0003966845,0.000080490536,0.00009760025,0.0001765348,0.0015394122,0.0046568443],"genre_scores_gemma":[0.50079465,0.0011267496,0.4939797,0.00016337914,0.00012758854,0.00029526275,0.000521711,0.0004274327,0.0025635494],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99378645,0.0030295579,0.0003883809,0.0010471853,0.0014871091,0.00026130796],"domain_scores_gemma":[0.9865328,0.00908752,0.0015862207,0.0015167685,0.0008702953,0.00040640662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003654625,0.0006559326,0.0016155104,0.003154279,0.0011331955,0.001875532,0.0018003389,0.001440475,0.002325863],"category_scores_gemma":[0.020597976,0.00048532255,0.00072265044,0.0036366624,0.0026619898,0.005493741,0.0042105727,0.0010542425,0.00086891773],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088233396,0.00012905982,0.010573033,0.0011601412,0.00017501287,0.00046051785,0.0008029689,0.21121533,0.027117508,0.20936798,0.003839093,0.53427714],"study_design_scores_gemma":[0.00006791842,0.000549817,0.004722594,0.00012596093,0.00007334236,0.0010249583,0.0004914939,0.50029033,0.029872058,0.44770566,0.014961405,0.00011447051],"about_ca_topic_score_codex":0.0007479638,"about_ca_topic_score_gemma":0.0008703736,"teacher_disagreement_score":0.003654625,"about_ca_system_score_codex":0.0011422465,"about_ca_system_score_gemma":0.0009803566,"threshold_uncertainty_score":0.01932776},"labels":[],"label_agreement":null},{"id":"W2161936690","doi":"10.1089/cmb.2008.0221","title":"Parallel GPU Implementation of Iterative PCA Algorithms","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":119,"is_retracted":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":"Principal component analysis; Orthogonalization; Graphics processing unit; Computer science; Algorithm; Orthogonality; CUDA; Graphics; Parallel computing; Artificial intelligence; Mathematics; Computer graphics (images)","score_opus":0.019470933568587052,"score_gpt":0.35851686782559833,"score_spread":0.3390459342570113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161936690","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03715222,0.00031437696,0.92973506,0.000273084,0.00016645963,0.00010076078,0.0005076502,0.01101492,0.020735469],"genre_scores_gemma":[0.22463703,0.000238803,0.7632648,0.00011581286,0.00004179438,0.00030743377,0.001066082,0.0009885379,0.009339651],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994881,0.000102790225,0.00002965665,0.00007184556,0.00022481875,0.000082705716],"domain_scores_gemma":[0.99925965,0.00015241232,0.000031982265,0.00013631764,0.00038008392,0.00003959276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039056962,0.0009240597,0.0008103974,0.00064945617,0.00064074097,0.0012456017,0.0014815335,0.00075837475,0.010923301],"category_scores_gemma":[0.0021779712,0.0003507404,0.0006145088,0.0012966822,0.00031931346,0.00075846334,0.00085738546,0.00080758746,0.0030693072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000683618,0.00027460032,0.0033399037,0.00030029588,0.00018781109,0.00047647915,0.00042980546,0.42775983,0.03116797,0.04542587,0.03927669,0.45067707],"study_design_scores_gemma":[0.00005577177,0.000029722285,0.0003278198,0.000008365091,0.0000100296875,0.00006618704,0.000032192787,0.97743064,0.0070566633,0.005985863,0.008982384,0.000014375266],"about_ca_topic_score_codex":0.010819959,"about_ca_topic_score_gemma":0.010221614,"teacher_disagreement_score":0.010923301,"about_ca_system_score_codex":0.00077855994,"about_ca_system_score_gemma":0.0014535527,"threshold_uncertainty_score":0.036542058},"labels":[],"label_agreement":null},{"id":"W2171285552","doi":"10.1089/cmb.2007.a002","title":"Gene Maps Linearization Using Genomic Rearrangement Distances","year":2007,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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":"Université de Montréal; McGill University","funders":"","keywords":"Genome; Linearization; Mathematics; Dynamic programming; Bounded function; Heuristic; Breakpoint; Combinatorics; Algorithm; Biology; Gene; Genetics; Mathematical optimization; Chromosome; Nonlinear system","score_opus":0.01605486950027104,"score_gpt":0.2870756702324307,"score_spread":0.2710208007321597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171285552","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058358863,0.00019782824,0.93429375,0.00025610471,0.000016693868,0.00014827604,0.00023704459,0.0008852031,0.0056062373],"genre_scores_gemma":[0.32636648,0.0003270786,0.6655664,0.00011863236,0.000038794748,0.000344105,0.0010674144,0.00031350486,0.005857679],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999435,0.00015443099,0.000026190935,0.00017050188,0.00014255983,0.00007121723],"domain_scores_gemma":[0.9986964,0.0008531543,0.00013145228,0.00012305101,0.00014538456,0.00005066458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006151839,0.0007282936,0.000610803,0.0010242157,0.000556738,0.00091002695,0.0009855824,0.00065113977,0.0047961115],"category_scores_gemma":[0.0036497512,0.0004405563,0.0008840317,0.0009469485,0.0007275722,0.0014201123,0.0016466461,0.0009867572,0.0010659127],"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":[0.00022578717,0.00011238103,0.0017021031,0.00024381082,0.000045437577,0.00023077789,0.00045035483,0.71558654,0.014940399,0.05046363,0.0033259282,0.21267278],"study_design_scores_gemma":[0.00007869586,0.0001948282,0.0006525614,0.000036085472,0.00003769745,0.00020620471,0.00022330304,0.90465146,0.009910663,0.07531656,0.0086581735,0.00003363629],"about_ca_topic_score_codex":0.0036392775,"about_ca_topic_score_gemma":0.0031481977,"teacher_disagreement_score":0.0047961115,"about_ca_system_score_codex":0.0011069893,"about_ca_system_score_gemma":0.0010486735,"threshold_uncertainty_score":0.016044617},"labels":[],"label_agreement":null},{"id":"W2176627438","doi":"10.1089/cmb.2014.0283","title":"Chaining Sequence/Structure Seeds for Computing RNA Similarity","year":2015,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"RNA and protein synthesis mechanisms","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":"Chaining; Search engine indexing; Computer science; Set (abstract data type); Pipeline (software); Computation; Benchmark (surveying); Sequence (biology); Similarity (geometry); Algorithm; RNA; Computational biology; Data mining; Artificial intelligence; Biology; Genetics","score_opus":0.0452231961673456,"score_gpt":0.32048954754549497,"score_spread":0.27526635137814937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2176627438","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045012668,0.00044759247,0.9377193,0.000051797324,0.00006232774,0.00021322806,0.0010251881,0.013104593,0.0023633875],"genre_scores_gemma":[0.16194713,0.00014082824,0.83255494,0.00004760436,0.0000392762,0.00022380454,0.0027838813,0.000965838,0.0012966879],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987006,0.00015799724,0.00010277959,0.00040555518,0.00055327243,0.00007986624],"domain_scores_gemma":[0.99769753,0.0007272093,0.00029097835,0.0005997693,0.000549304,0.00013503453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009699307,0.0009914133,0.0013574938,0.004496979,0.0007130549,0.0012871142,0.0015805614,0.0008426664,0.006770325],"category_scores_gemma":[0.0058562923,0.00065623806,0.0008503351,0.0038729894,0.0010108718,0.0020619584,0.0016559449,0.0008801574,0.002755516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010429989,0.00023365964,0.009540435,0.00071848795,0.00023660024,0.0004262498,0.00026038292,0.059156362,0.10742943,0.022680437,0.009440568,0.7888343],"study_design_scores_gemma":[0.0001444578,0.00036214283,0.0042036334,0.00003737719,0.000082569815,0.0007581922,0.000103977036,0.87102234,0.078964375,0.032546647,0.011683008,0.000091280075],"about_ca_topic_score_codex":0.0023285511,"about_ca_topic_score_gemma":0.0036772664,"teacher_disagreement_score":0.006770325,"about_ca_system_score_codex":0.00086221413,"about_ca_system_score_gemma":0.0013730614,"threshold_uncertainty_score":0.02264893},"labels":[],"label_agreement":null},{"id":"W2253609413","doi":"10.1089/cmb.2015.0189","title":"Deep Feature Selection: Theory and Application to Identify Enhancers and Promoters","year":2016,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":207,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Canada","keywords":"Artificial intelligence; Deep learning; Computer science; Feature selection; Feature (linguistics); Artificial neural network; Machine learning; Nonlinear system; Selection (genetic algorithm); Linear model; Pattern recognition (psychology)","score_opus":0.002544613022489751,"score_gpt":0.2572304031433438,"score_spread":0.254685790120854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2253609413","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007017225,0.0007504381,0.99090964,0.00025391774,0.000036651,0.000022985027,0.000104488165,0.0003261615,0.0005784294],"genre_scores_gemma":[0.54398334,0.0026866712,0.44598365,0.0005360133,0.00029866336,0.00035934753,0.00094275916,0.00016033476,0.005049093],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99963796,0.000089065776,0.000027108328,0.000086400294,0.000112199414,0.000047233058],"domain_scores_gemma":[0.99893016,0.0006678352,0.00009458644,0.00006175559,0.00020764304,0.000038002818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011338217,0.000756607,0.001004579,0.0013802008,0.00031307095,0.0006871111,0.00090732746,0.00090070534,0.0014072505],"category_scores_gemma":[0.0027086614,0.0003854151,0.0008698377,0.0015268298,0.0006753358,0.0009634385,0.0009037098,0.0011229411,0.00030643906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013433892,0.00009369535,0.0041301297,0.00021332216,0.0001332232,0.00020094111,0.00010769572,0.42291972,0.010250402,0.0452656,0.0063400865,0.51021075],"study_design_scores_gemma":[0.000011913258,0.000028468798,0.000543634,0.000015004719,0.000019703291,0.000058050096,0.000008532864,0.9737207,0.0020686914,0.021844065,0.0016709478,0.0000103073135],"about_ca_topic_score_codex":0.002848326,"about_ca_topic_score_gemma":0.0020423594,"teacher_disagreement_score":0.002848326,"about_ca_system_score_codex":0.00070328114,"about_ca_system_score_gemma":0.0007003306,"threshold_uncertainty_score":0.0059962273},"labels":[],"label_agreement":null},{"id":"W2366192345","doi":"10.1089/cmb.2010.0121","title":"A Statistically Fair Comparison of Ancestral Genome Reconstructions, Based on Breakpoint and Rearrangement Distances","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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":"Breakpoint; Genome; Evolutionary biology; Biology; Algorithm; Mathematics; Computer science; Computational biology; Genetics; Chromosome; Gene","score_opus":0.010238726149141007,"score_gpt":0.2954890485433716,"score_spread":0.2852503223942306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2366192345","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39790064,0.0016228703,0.59255666,0.0011342326,0.00020416614,0.00020099836,0.0008265812,0.000954804,0.0045990404],"genre_scores_gemma":[0.81515217,0.00036118293,0.18153039,0.0002486532,0.00007115607,0.00024429095,0.0013804941,0.00039053036,0.00062115246],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98157376,0.011176319,0.0013315483,0.0022752022,0.0030417505,0.0006013641],"domain_scores_gemma":[0.87770027,0.09508055,0.005790576,0.013832618,0.0056968937,0.0018990777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.049966425,0.0011780615,0.0021774375,0.0058487435,0.0014259707,0.004223446,0.001890361,0.0034285726,0.0021837084],"category_scores_gemma":[0.18253104,0.00069836684,0.0015697867,0.0026939565,0.005891077,0.005697797,0.0045347535,0.0026433622,0.0003938858],"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":[0.0024599242,0.00016289315,0.04419287,0.00043154796,0.0011854137,0.0002452951,0.0006208148,0.767371,0.0084698675,0.11215943,0.001348219,0.06135283],"study_design_scores_gemma":[0.00027809033,0.0010107411,0.021405095,0.00018435773,0.00022834525,0.0005189781,0.0005838337,0.77341133,0.014577696,0.18474245,0.0028346663,0.00022448566],"about_ca_topic_score_codex":0.00097139244,"about_ca_topic_score_gemma":0.0013922063,"teacher_disagreement_score":0.049966425,"about_ca_system_score_codex":0.0019960126,"about_ca_system_score_gemma":0.0017355997,"threshold_uncertainty_score":0.26425087},"labels":[],"label_agreement":null},{"id":"W2369729543","doi":"10.1089/cmb.2010.0092","title":"Yeast Ancestral Genome Reconstructions: The Possibilities of Computational Methods II","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Centre National de la Recherche Scientifique; Agence Nationale de la Recherche","keywords":"Genome; Yeast; Biology; Computational biology; Evolutionary biology; Genetics; Gene","score_opus":0.017120286307819903,"score_gpt":0.3258122984228377,"score_spread":0.3086920121150178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2369729543","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02687388,0.0029979094,0.9632943,0.002924137,0.00023784574,0.00007089919,0.00034667313,0.0010706403,0.0021837594],"genre_scores_gemma":[0.3664156,0.0024158412,0.6271534,0.00058907986,0.00038194915,0.0004462186,0.0008891727,0.00084810716,0.00086070533],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957195,0.0030863364,0.00018962711,0.00032113655,0.00057894894,0.00010444726],"domain_scores_gemma":[0.9714968,0.02339842,0.00057071843,0.0033456276,0.0009231867,0.0002653027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011486239,0.000880524,0.0012813109,0.0019852729,0.0008973462,0.0024109592,0.0020776747,0.0019415212,0.0021737225],"category_scores_gemma":[0.05730147,0.0009800727,0.0018242238,0.0016234415,0.002355055,0.0030362844,0.0024163993,0.0039413422,0.0005698981],"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":[0.0004082898,0.00011705684,0.006513263,0.00055625173,0.00059681025,0.00014798387,0.0003291075,0.60725754,0.0017442617,0.26444474,0.0037847797,0.11409995],"study_design_scores_gemma":[0.000031749078,0.000020444293,0.00047101852,0.00007552233,0.000017674967,0.00003037914,0.000032183638,0.8346744,0.000547781,0.16205703,0.0020156447,0.000026145932],"about_ca_topic_score_codex":0.0022464884,"about_ca_topic_score_gemma":0.001195613,"teacher_disagreement_score":0.011486239,"about_ca_system_score_codex":0.00090769277,"about_ca_system_score_gemma":0.0011592855,"threshold_uncertainty_score":0.060745716},"labels":[],"label_agreement":null},{"id":"W2382695984","doi":"10.1089/cmb.2011.0157","title":"A Probabilistic Model for Sequence Alignment with Context-Sensitive Indels","year":2011,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","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":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Indel; Context (archaeology); Probabilistic logic; Sequence (biology); Computer science; Multiple sequence alignment; Computational biology; Artificial intelligence; Sequence alignment; Biology; Genetics; Peptide sequence; Gene","score_opus":0.05103565228086833,"score_gpt":0.27530089033077626,"score_spread":0.22426523804990794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2382695984","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046054786,0.0002581404,0.99234277,0.0003319574,0.0000748277,0.00006576403,0.00042778964,0.0006964276,0.0011969059],"genre_scores_gemma":[0.3435114,0.0017812668,0.6268494,0.00074341404,0.00052041083,0.0020883174,0.0027438807,0.0013130958,0.020448802],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99680305,0.0010419525,0.0002241532,0.0010011438,0.0006800137,0.00024966232],"domain_scores_gemma":[0.9930224,0.005252541,0.00051303377,0.00054324674,0.0004894296,0.00017943999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004821247,0.0014602504,0.0025378368,0.0025787079,0.001523533,0.0027391047,0.0062605003,0.004385084,0.0067634536],"category_scores_gemma":[0.013582955,0.0018528767,0.0030878657,0.0035127369,0.0025521053,0.0055131107,0.0023027654,0.003704225,0.0038120938],"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":[0.000119929224,0.000056909284,0.0009571312,0.00018153279,0.00011007864,0.0004430016,0.0002485624,0.7700414,0.0026808525,0.19996314,0.0022433181,0.02295415],"study_design_scores_gemma":[0.000023581466,0.000027664339,0.000107050975,0.000012160469,0.000023312266,0.00013177935,0.000008814901,0.8903654,0.00026080868,0.107139334,0.0018686551,0.00003151191],"about_ca_topic_score_codex":0.004820435,"about_ca_topic_score_gemma":0.0051258025,"teacher_disagreement_score":0.0067634536,"about_ca_system_score_codex":0.0016487797,"about_ca_system_score_gemma":0.0019457827,"threshold_uncertainty_score":0.025497437},"labels":[],"label_agreement":null},{"id":"W2385435022","doi":"10.1089/cmb.2011.0087","title":"Genome Aliquoting Revisited","year":2011,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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 Ottawa","funders":"","keywords":"Genome; Breakpoint; Polyploid; Approximation algorithm; Ancestor; Combinatorics; Mathematics; Biology; Computer science; Algorithm; Genetics; Gene; Chromosome","score_opus":0.02241927681391968,"score_gpt":0.2626114851712909,"score_spread":0.24019220835737123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2385435022","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.102018006,0.0028372344,0.8764442,0.0026659288,0.00045150812,0.00016401605,0.00051699154,0.0027778777,0.012124291],"genre_scores_gemma":[0.489454,0.0018562413,0.49452093,0.0011020695,0.00025391195,0.00019260168,0.0013814853,0.0006757967,0.010563042],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986104,0.00021606585,0.00007250198,0.00052331266,0.0003873478,0.0001903426],"domain_scores_gemma":[0.9964742,0.0019058638,0.0002736466,0.0008621926,0.00029394412,0.00019001932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012399541,0.0007429244,0.0013577318,0.0007420396,0.001209252,0.002244921,0.00326466,0.0015591892,0.008350565],"category_scores_gemma":[0.0063525476,0.00046997334,0.0014306356,0.001812023,0.0013822253,0.0054542106,0.0034189082,0.004050035,0.0011183491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009862926,0.00025397554,0.0039105923,0.00073914794,0.0001591694,0.0008182613,0.000857358,0.19176649,0.036036015,0.31752026,0.017307788,0.42964455],"study_design_scores_gemma":[0.0001980375,0.00042092218,0.0019688369,0.00016044731,0.00020142314,0.0015882832,0.00046227712,0.54885393,0.0633237,0.31222895,0.07049103,0.00010210116],"about_ca_topic_score_codex":0.0027827928,"about_ca_topic_score_gemma":0.0019373539,"teacher_disagreement_score":0.008350565,"about_ca_system_score_codex":0.0015028236,"about_ca_system_score_gemma":0.0014595761,"threshold_uncertainty_score":0.027935386},"labels":[],"label_agreement":null},{"id":"W2570688054","doi":"10.1089/cmb.2016.0148","title":"Clonality Inference from Single Tumor Samples Using Low-Coverage Sequence Data","year":2017,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Cancer Genomics and Diagnostics","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 British Columbia; Simon Fraser University","funders":"","keywords":"Deep sequencing; Tumor heterogeneity; Inference; DNA sequencing; Biology; Computational biology; Solid tumor; Sample (material); Sequence (biology); Single cell sequencing; Genetics; Cancer; Computer science; Artificial intelligence; Mutation; Exome sequencing; Genome; Gene","score_opus":0.11867702055789363,"score_gpt":0.3722387631576175,"score_spread":0.25356174259972386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2570688054","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.413429,0.00095139426,0.57775146,0.00026717855,0.0000355737,0.0000946232,0.0033666496,0.00298164,0.0011224777],"genre_scores_gemma":[0.78747404,0.00042553368,0.20266373,0.00023977016,0.000034842247,0.00012925295,0.008043184,0.00031444104,0.0006750965],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992606,0.00019289667,0.00005361065,0.00026495007,0.00016109007,0.00006686253],"domain_scores_gemma":[0.9960061,0.0027199958,0.00035657748,0.00046737381,0.0003029504,0.00014701941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018993465,0.00073638005,0.00095038395,0.001753721,0.00047791124,0.0013260974,0.0008510197,0.0010076045,0.00086465024],"category_scores_gemma":[0.009069596,0.00055378664,0.000992634,0.0010264193,0.00059182453,0.0010879345,0.0012129385,0.0012343234,0.00038752396],"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":[0.0008629391,0.00017524108,0.12639832,0.00065907673,0.0006522076,0.0010051657,0.00053543964,0.5221542,0.18329929,0.0076987077,0.0029761093,0.15358329],"study_design_scores_gemma":[0.000026510686,0.00005696976,0.008904634,0.00002752606,0.000053471307,0.00031935037,0.000058198413,0.95506555,0.023303935,0.010256694,0.0018975738,0.000029677143],"about_ca_topic_score_codex":0.0033791296,"about_ca_topic_score_gemma":0.0055039525,"teacher_disagreement_score":0.0033791296,"about_ca_system_score_codex":0.00057404273,"about_ca_system_score_gemma":0.00083865086,"threshold_uncertainty_score":0.010044813},"labels":[],"label_agreement":null},{"id":"W2589346540","doi":"10.1089/cmb.2016.0173","title":"<i>Drosophila</i> H2A and H2A.Z Nucleosome Sequences Reveal Different Nucleosome Positioning Sequence Patterns","year":2016,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Chromatin Dynamics","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 Ottawa","funders":"","keywords":"Nucleosome; Histone; Biology; DNA; Linker DNA; Genetics; Biophysics","score_opus":0.009782321814461087,"score_gpt":0.2468630646043983,"score_spread":0.2370807427899372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2589346540","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9808111,0.004870441,0.0046649356,0.00016442058,0.000058761474,0.000018000113,0.0038901092,0.00015170625,0.005370494],"genre_scores_gemma":[0.9871683,0.00088961795,0.0043087807,0.00025029396,0.000025586602,0.000019895819,0.0044831154,0.00004069258,0.0028138906],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99993145,0.0000054352745,0.0000046149917,0.000024118113,0.000019037034,0.000015300828],"domain_scores_gemma":[0.99990034,0.000009102436,0.00004093657,0.000007118685,0.000019170071,0.000023381817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006048546,0.00017525392,0.00010764088,0.00036889635,0.0001553256,0.00029285613,0.000119835684,0.0001951647,0.001683756],"category_scores_gemma":[0.00011416515,0.0001070225,0.00016931839,0.00028229665,0.00014711452,0.00014301568,0.00012503896,0.00017548769,0.00052924914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025116818,0.000011976178,0.011837978,0.00012621704,0.000039115206,0.00011895842,0.000066032124,0.00010770371,0.9811101,0.0003188095,0.00068586407,0.005326097],"study_design_scores_gemma":[0.000030644136,0.00021302742,0.54949176,0.000032962158,0.00011456114,0.0022402853,0.00027591063,0.0018293825,0.42045847,0.00042939538,0.024850257,0.00003339211],"about_ca_topic_score_codex":0.0034049484,"about_ca_topic_score_gemma":0.0061428095,"teacher_disagreement_score":0.0034049484,"about_ca_system_score_codex":0.00024651425,"about_ca_system_score_gemma":0.00007215636,"threshold_uncertainty_score":0.006770253},"labels":[],"label_agreement":null},{"id":"W2607286649","doi":"10.1089/cmb.2017.0021","title":"Zseq: An Approach for Preprocessing Next-Generation Sequencing Data","year":2017,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"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","keywords":"Preprocessor; Sequence (biology); DNA sequencing; Sequence assembly; Computer science; Computational biology; Genome; Biology; Discriminative model; Genomics; Algorithm; Genetics; Artificial intelligence; DNA; Gene","score_opus":0.21618993806313613,"score_gpt":0.36352727991060885,"score_spread":0.1473373418474727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607286649","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014246744,0.0015985533,0.9238418,0.00022382857,0.00033752882,0.0005239295,0.023676936,0.032516852,0.0030338797],"genre_scores_gemma":[0.024202017,0.0010592665,0.92769164,0.00041162584,0.000093253635,0.0014246936,0.03707463,0.0045012403,0.0035416717],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981481,0.00026528223,0.00018845033,0.0005985878,0.0006649089,0.00013470647],"domain_scores_gemma":[0.9988387,0.00044689229,0.00014865048,0.00015520275,0.00035758052,0.000053040778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002412484,0.0019111043,0.0015041942,0.003384996,0.0017097619,0.0024682928,0.0019715352,0.0010176891,0.009948754],"category_scores_gemma":[0.003976141,0.0014079906,0.0018254564,0.0029564982,0.00048705164,0.001288993,0.0016437272,0.002663008,0.0053819306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013888195,0.00023304256,0.008020926,0.0035040611,0.0011816173,0.00079470227,0.001118347,0.015026111,0.48766553,0.013952948,0.06725066,0.39986318],"study_design_scores_gemma":[0.00021469861,0.0004034127,0.014883081,0.00025697149,0.00048912404,0.0011929213,0.00038319945,0.11241239,0.464564,0.023436904,0.38122633,0.0005369549],"about_ca_topic_score_codex":0.0031368257,"about_ca_topic_score_gemma":0.0047012004,"teacher_disagreement_score":0.009948754,"about_ca_system_score_codex":0.0012240753,"about_ca_system_score_gemma":0.0020264275,"threshold_uncertainty_score":0.033281922},"labels":[],"label_agreement":null},{"id":"W2703483445","doi":"10.1089/cmb.2017.0010","title":"An Integrative Approach for Identifying Network Biomarkers of Breast Cancer Subtypes Using Genomic, Interactomic, and Transcriptomic Data","year":2017,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Bioinformatics and Genomic Networks","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":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Breast cancer; Biomarker; Biomarker discovery; Computational biology; Transcriptome; Cancer; Gene; Disease; Selection (genetic algorithm); Gene regulatory network; Feature selection; Cancer biomarkers; Biology; Bioinformatics; Machine learning; Computer science; Medicine; Proteomics; Genetics; Gene expression; Internal medicine","score_opus":0.04154260487771495,"score_gpt":0.3472950090392283,"score_spread":0.30575240416151334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2703483445","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.096864074,0.0005535936,0.89810485,0.00054865045,0.000026926624,0.00021582968,0.0010810891,0.0012149194,0.0013901066],"genre_scores_gemma":[0.43613476,0.0003571534,0.55946153,0.00015287045,0.00004771569,0.00031547292,0.002381401,0.000110098896,0.0010389898],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99952483,0.00015184667,0.000028302555,0.00014365275,0.00010888775,0.000042376654],"domain_scores_gemma":[0.99929106,0.00031045414,0.00010101459,0.000087293876,0.00015188372,0.000058211845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014394157,0.0011199227,0.001000106,0.0035495365,0.0005904433,0.0010826684,0.00092590164,0.0005197293,0.0011354911],"category_scores_gemma":[0.0029030212,0.00036396374,0.0013899633,0.002075483,0.0003616342,0.00096298754,0.0012173199,0.0007196417,0.00027673985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005063793,0.0005569264,0.07483159,0.00035119147,0.0015503048,0.00054588524,0.00043274846,0.40801468,0.046141222,0.017193507,0.0030805848,0.44679493],"study_design_scores_gemma":[0.000016882883,0.000070020134,0.007911203,0.00001476921,0.00017295394,0.00009838214,0.00006298024,0.9792956,0.0023450307,0.008926609,0.0010657823,0.000019647607],"about_ca_topic_score_codex":0.0074566826,"about_ca_topic_score_gemma":0.013033346,"teacher_disagreement_score":0.0074566826,"about_ca_system_score_codex":0.00093259325,"about_ca_system_score_gemma":0.0013291903,"threshold_uncertainty_score":0.014826596},"labels":[],"label_agreement":null},{"id":"W2722338676","doi":"10.1089/cmb.2017.0034","title":"On Stable States in a Topologically Driven Protein Folding Model","year":2017,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Protein Structure and Dynamics","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":"Protein folding; Simple (philosophy); Folding (DSP implementation); Computer science; Sequence (biology); Stability (learning theory); Polynomial; Theoretical computer science; Topology (electrical circuits); Statistical physics; Biological system; Mathematics; Physics; Combinatorics; Chemistry; Biology","score_opus":0.012194337501774923,"score_gpt":0.29034240909391457,"score_spread":0.27814807159213967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2722338676","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5669095,0.00061522616,0.40441373,0.0020142375,0.00005987231,0.000089628185,0.000320265,0.00039594228,0.025181599],"genre_scores_gemma":[0.98200893,0.00027935344,0.014788031,0.00010566155,0.00002927399,0.0001092404,0.00015439888,0.000059658712,0.0024653324],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996971,0.00013761653,0.000011443946,0.000034049222,0.00005941451,0.00006041073],"domain_scores_gemma":[0.99840254,0.0010028764,0.00018268982,0.00012112486,0.0001324947,0.0001583185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084170466,0.00056242675,0.00080988125,0.0009065826,0.00092750555,0.0014125784,0.0012875636,0.0018287731,0.0025331841],"category_scores_gemma":[0.0036954326,0.00034883228,0.00067896326,0.00063124736,0.002212582,0.001871816,0.0013981663,0.0010028778,0.00033276476],"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":[0.00007200952,0.000049051654,0.00052779436,0.00003642408,0.00001353393,0.00015977351,0.00011066216,0.72552997,0.0017483635,0.2695696,0.0005077323,0.001675042],"study_design_scores_gemma":[0.000011975794,0.000017361232,0.000046093697,0.0000040455575,0.0000026931755,0.000010609217,0.00001698306,0.9124205,0.00014728575,0.08717464,0.00014182525,0.0000060059665],"about_ca_topic_score_codex":0.0022504025,"about_ca_topic_score_gemma":0.0014018927,"teacher_disagreement_score":0.0025331841,"about_ca_system_score_codex":0.0012619765,"about_ca_system_score_gemma":0.000779632,"threshold_uncertainty_score":0.009156346},"labels":[],"label_agreement":null},{"id":"W2736869029","doi":"10.1089/cmb.2017.0085","title":"T-GOWler: Discovering Generalized Process Models Within Texts","year":2017,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Business Process Modeling and Analysis","field":"Business, Management and Accounting","cited_by":0,"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":"Workflow; Computer science; Ontology; Abstraction; Workflow technology; Semantics (computer science); Workflow management system; Task (project management); Workflow engine; Process (computing); Process mining; Domain (mathematical analysis); Software engineering; Data mining; Database; Programming language; Business process management; Work in process; Business process; Engineering; Systems engineering","score_opus":0.03765193441540742,"score_gpt":0.29893769591874225,"score_spread":0.2612857615033348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736869029","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02153387,0.00013508115,0.964261,0.00028980774,0.000020347425,0.0003423048,0.0029176336,0.009422958,0.0010770559],"genre_scores_gemma":[0.110235855,0.00024655325,0.8780478,0.00009721623,0.000018866798,0.00044161789,0.008476428,0.00076712604,0.0016685576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971398,0.0007484912,0.00029321568,0.0009859132,0.0006837983,0.00014873399],"domain_scores_gemma":[0.9931636,0.00422611,0.0008324947,0.0011240495,0.00048035014,0.00017342233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023383775,0.0013892793,0.0007541587,0.004668447,0.0010047447,0.003114736,0.0017753484,0.0016502464,0.0034844654],"category_scores_gemma":[0.015394542,0.00083138124,0.00279738,0.0034791166,0.0012007824,0.0068459725,0.0027663736,0.0016155635,0.0018810029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007863729,0.0005811379,0.025462816,0.0032700312,0.00060243154,0.0046747946,0.009411392,0.07816493,0.04440975,0.12712723,0.019868292,0.6856409],"study_design_scores_gemma":[0.00012946576,0.00016325942,0.0036839847,0.0003069403,0.00017386833,0.0012105003,0.0017621772,0.6849618,0.033708736,0.22327861,0.050502535,0.00011803897],"about_ca_topic_score_codex":0.004410781,"about_ca_topic_score_gemma":0.0051733013,"teacher_disagreement_score":0.004668447,"about_ca_system_score_codex":0.0008964601,"about_ca_system_score_gemma":0.002231922,"threshold_uncertainty_score":0.0123666525},"labels":[],"label_agreement":null},{"id":"W2737577208","doi":"10.1089/cmb.2017.29008.abd","title":"Preface: Selected Papers from the Workshop Bioinformatics and Artificial Intelligence Joined with the International Joint Conference on Artificial Intelligence","year":2017,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genetics, Bioinformatics, and Biomedical Research","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 du Québec à Montréal","funders":"","keywords":"Artificial intelligence; Computer science; Joint (building); Library science; Engineering","score_opus":0.0568442888526676,"score_gpt":0.3210732096720632,"score_spread":0.2642289208193956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2737577208","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012625001,0.053028032,0.0051803836,0.045838043,0.8123575,0.00057905517,0.0028271284,0.00061043585,0.07831687],"genre_scores_gemma":[0.0073348726,0.059369072,0.0041336166,0.017342526,0.5000042,0.0006135922,0.009812336,0.001433651,0.3999562],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99822694,0.00024625452,0.0001407865,0.00025910832,0.00095930946,0.00016759452],"domain_scores_gemma":[0.9884509,0.0016582642,0.00046753066,0.00031245075,0.0065993913,0.0025113656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002991267,0.0021210893,0.0016796746,0.005700264,0.0029745293,0.009316924,0.0017437332,0.0024270827,0.091751434],"category_scores_gemma":[0.008277131,0.00064792536,0.0017976244,0.0065841526,0.0007020841,0.004357727,0.0026346282,0.0048333076,0.07313953],"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":[0.000055973334,0.00003108933,0.000049955026,0.00019416495,0.0000075026182,0.00003687002,0.000038628692,0.000067938505,0.00027495896,0.00040636086,0.97885877,0.01997788],"study_design_scores_gemma":[0.000017351646,0.000054496664,0.0008854666,0.00034960365,0.000014287116,0.00008938709,0.00013551307,0.00011537021,0.00023415989,0.0012031584,0.9968772,0.000023964803],"about_ca_topic_score_codex":0.0026187717,"about_ca_topic_score_gemma":0.004148664,"teacher_disagreement_score":0.091751434,"about_ca_system_score_codex":0.0029138513,"about_ca_system_score_gemma":0.0022601946,"threshold_uncertainty_score":0.30693913},"labels":[],"label_agreement":null},{"id":"W2795286085","doi":"10.1089/cmb.2011.0181","title":"An Unbiased Adaptive Sampling Algorithm for the Exploration of RNA Mutational Landscapes Under Evolutionary Pressure","year":2011,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Sequence (biology); Algorithm; Sampling (signal processing); Sequence space; Sample (material); Computer science; Computational biology; Mutation; Sequence analysis; Biology; Genetics; Mathematics; Physics; Gene","score_opus":0.060912380696834044,"score_gpt":0.29905870055902695,"score_spread":0.2381463198621929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795286085","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019966334,0.00021695072,0.9785155,0.0001381961,0.000031952295,0.000067690766,0.000042581996,0.00041075575,0.00061003515],"genre_scores_gemma":[0.2589635,0.00019253383,0.73763174,0.00026643608,0.000077157296,0.00059621484,0.00039655538,0.00022635766,0.0016494243],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989912,0.00051533006,0.00004989563,0.00014239775,0.00020753953,0.00009356644],"domain_scores_gemma":[0.99640226,0.0027224277,0.0001536712,0.00016854912,0.0004019592,0.0001511271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002816396,0.0009862037,0.0014125542,0.0012816003,0.00069534045,0.0008502031,0.0017837851,0.0014960491,0.0016170917],"category_scores_gemma":[0.009519963,0.0006783385,0.0008776075,0.0009897122,0.0012320593,0.0010088066,0.0012848226,0.0013870371,0.00034177158],"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":[0.00015817341,0.000049836308,0.0016395424,0.00006610586,0.000105058374,0.000089431844,0.00012097081,0.9192047,0.0029957544,0.015224109,0.0009840924,0.05936229],"study_design_scores_gemma":[0.0000149819,0.000014309059,0.000056831184,0.0000032821351,0.0000037546697,0.000007958056,0.0000039757037,0.9959966,0.00019779759,0.0035247062,0.00017239548,0.000003405],"about_ca_topic_score_codex":0.005714083,"about_ca_topic_score_gemma":0.006713234,"teacher_disagreement_score":0.005714083,"about_ca_system_score_codex":0.001092369,"about_ca_system_score_gemma":0.0015993027,"threshold_uncertainty_score":0.014894664},"labels":[],"label_agreement":null},{"id":"W2884798430","doi":"10.1089/cmb.2018.0068","title":"Dynamic Alignment-Free and Reference-Free Read Compression","year":2018,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Menzies Centre for Australian Studies, King's College London, University of London","keywords":"Computer science; Free water; Environmental science","score_opus":0.01813697689699842,"score_gpt":0.2940232905158488,"score_spread":0.2758863136188504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884798430","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044046145,0.0025977797,0.9361342,0.00042766676,0.0004549104,0.00022771119,0.0014039272,0.009696485,0.005011281],"genre_scores_gemma":[0.20801544,0.0013701427,0.7747545,0.00040808666,0.00023673275,0.00033332483,0.0059056086,0.0010531831,0.007922926],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990225,0.00013347605,0.00008399512,0.00022287981,0.00045962824,0.00007756463],"domain_scores_gemma":[0.9978435,0.0006714685,0.00014624062,0.0007188509,0.00056871853,0.00005126689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006554511,0.0010361257,0.00065076014,0.0018118825,0.00046382335,0.0007069532,0.0016927264,0.0009383175,0.0027040218],"category_scores_gemma":[0.0037105705,0.00025609677,0.0006878279,0.001885787,0.0005143846,0.0013963464,0.0009826187,0.0009809157,0.0016041273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000539332,0.00016110127,0.0009797638,0.0004912585,0.00007596558,0.000456298,0.00029868883,0.054580145,0.113124475,0.01287163,0.01657068,0.7998507],"study_design_scores_gemma":[0.00016042675,0.00038908655,0.0018714522,0.000095990516,0.000102940765,0.0020906487,0.00019238619,0.5446744,0.38743111,0.014114869,0.048723795,0.00015281334],"about_ca_topic_score_codex":0.0014992701,"about_ca_topic_score_gemma":0.0019835238,"teacher_disagreement_score":0.0027040218,"about_ca_system_score_codex":0.00043526155,"about_ca_system_score_gemma":0.00081297406,"threshold_uncertainty_score":0.009045839},"labels":[],"label_agreement":null},{"id":"W2901105999","doi":"10.1089/cmb.2011.0176","title":"Efficient Traversal of Beta-Sheet Protein Folding Pathways Using Ensemble Models","year":2011,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Protein Structure and Dynamics","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":"McGill University","funders":"","keywords":"Folding (DSP implementation); Computer science; Protein folding; Markov chain; Algorithm; Computation; Tree traversal; Molecular dynamics; Sequence (biology); Population; Biological system; Statistical physics; Physics; Chemistry; Computational chemistry; Machine learning; Engineering; Biology","score_opus":0.03550505397159789,"score_gpt":0.2545912468452549,"score_spread":0.21908619287365702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901105999","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24443297,0.00018457683,0.7493318,0.00010065527,0.000015046063,0.00006306431,0.00040468696,0.002066181,0.0034010573],"genre_scores_gemma":[0.7223919,0.00035816702,0.27367947,0.00004426627,0.000012566619,0.000229226,0.0010154025,0.00033850234,0.0019304452],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998609,0.000041521223,0.0000072725766,0.000028909297,0.00004229072,0.000019079327],"domain_scores_gemma":[0.9996234,0.00018222409,0.00003580251,0.00007683552,0.000048174876,0.000033607663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034948357,0.0005401228,0.0005481743,0.00049349444,0.00052426365,0.0005799587,0.00081499974,0.0006776345,0.0013199734],"category_scores_gemma":[0.0012528284,0.00042073082,0.0006977667,0.0004077754,0.00030969473,0.0010624299,0.0006424014,0.00072545395,0.00029480335],"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":[0.00006180691,0.000025028252,0.0013366165,0.000025589256,0.000024294122,0.00005890152,0.000056750752,0.9686627,0.00434435,0.0077314144,0.00028708106,0.017385498],"study_design_scores_gemma":[0.0000026895577,0.0000047139865,0.000044986173,0.0000013992739,0.0000012801869,0.0000047605013,0.000002834696,0.9977081,0.0005068683,0.0015383165,0.00018252479,0.0000014936943],"about_ca_topic_score_codex":0.006891256,"about_ca_topic_score_gemma":0.009839965,"teacher_disagreement_score":0.006891256,"about_ca_system_score_codex":0.0007788616,"about_ca_system_score_gemma":0.0012805638,"threshold_uncertainty_score":0.013702273},"labels":[],"label_agreement":null},{"id":"W2943381976","doi":"10.1089/cmb.2018.0239","title":"Toward an Alignment-Free Method for Feature Extraction and Accurate Classification of Viral Sequences","year":2019,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","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":"Université du Québec à Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Biology; Virus; Subsequence; Computational biology; Genetics; Mathematics","score_opus":0.03237791519115444,"score_gpt":0.3414660170478026,"score_spread":0.30908810185664815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943381976","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026191466,0.00024252605,0.9714769,0.00009871668,0.000021471611,0.000080088954,0.00020123707,0.001421365,0.00026608832],"genre_scores_gemma":[0.14778265,0.00016658603,0.84909075,0.00010072474,0.000033296623,0.0002033749,0.0013925569,0.00012378064,0.0011063098],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985971,0.00031390513,0.00014540118,0.00039116564,0.00039958922,0.00015282896],"domain_scores_gemma":[0.9980356,0.00085363927,0.00021016733,0.00018852795,0.0006464529,0.000065568216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016153866,0.0012330561,0.0013748026,0.0028275077,0.00065444584,0.00091393717,0.0012589422,0.0013369552,0.001135112],"category_scores_gemma":[0.0038339656,0.00040667018,0.0013004508,0.0016490465,0.00047872943,0.001274373,0.00068602787,0.001586644,0.001031392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003649092,0.0002908203,0.004991408,0.00014669738,0.000108794186,0.00014543755,0.00011844055,0.059201982,0.07152548,0.0021117725,0.0029198406,0.85807437],"study_design_scores_gemma":[0.000027873511,0.0001313929,0.0022692946,0.000014724494,0.0000263596,0.00018887836,0.000043757278,0.9731616,0.020064222,0.0020221693,0.0020213816,0.000028360771],"about_ca_topic_score_codex":0.004719334,"about_ca_topic_score_gemma":0.004352543,"teacher_disagreement_score":0.004719334,"about_ca_system_score_codex":0.0005387392,"about_ca_system_score_gemma":0.0014362583,"threshold_uncertainty_score":0.009383738},"labels":[],"label_agreement":null},{"id":"W2951332226","doi":"10.1089/cmb.2019.0309","title":"Efficient Construction of a Complete Index for Pan-Genomics Read Alignment","year":2020,"lang":"en","type":"preprint","venue":"Journal of Computational Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences","keywords":"String (physics); Search engine indexing; Computer science; Rank (graph theory); Sample (material); Suffix array; Compressed suffix array; Index (typography); Data structure; Suffix; Database index; Space (punctuation); Data mining; String searching algorithm; Information retrieval; Mathematics; Combinatorics; World Wide Web; Programming language","score_opus":0.03835700790850998,"score_gpt":0.29696711672646436,"score_spread":0.2586101088179544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951332226","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022150341,0.0011206146,0.9487873,0.00022594321,0.00027426114,0.00025271927,0.0046605547,0.0177839,0.004744384],"genre_scores_gemma":[0.05398333,0.000415687,0.92294955,0.00016043863,0.00017422042,0.00032959043,0.01671887,0.001591901,0.0036763807],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99765885,0.00025620172,0.00032210373,0.0005161748,0.0010406356,0.000206077],"domain_scores_gemma":[0.996145,0.0006930748,0.00022252712,0.0014495709,0.0012880068,0.00020181833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013890835,0.001031622,0.0019901036,0.0038846687,0.0011408775,0.0025694256,0.0021325,0.0012066931,0.005631907],"category_scores_gemma":[0.008801332,0.00078612723,0.0012059652,0.0060498905,0.00064676796,0.0048255157,0.0034360362,0.0021814487,0.009092192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005948395,0.0003178537,0.0041053537,0.00075759843,0.000121206096,0.0004243046,0.0005751784,0.01691737,0.09436843,0.032454807,0.04845808,0.80090505],"study_design_scores_gemma":[0.00025033476,0.0006071486,0.0051150233,0.00018369567,0.00017668465,0.0017777561,0.00048768247,0.5898419,0.148283,0.08765018,0.16538803,0.00023853603],"about_ca_topic_score_codex":0.0016595252,"about_ca_topic_score_gemma":0.0029764657,"teacher_disagreement_score":0.005631907,"about_ca_system_score_codex":0.00087270886,"about_ca_system_score_gemma":0.0029294437,"threshold_uncertainty_score":0.018840551},"labels":[],"label_agreement":null},{"id":"W2952149733","doi":"10.1089/cmb.2019.29020.abd","title":"Selected Papers from the Workshop on Computational Biology: Joint with the International Joint Conference on Artificial Intelligence and the International Conference on Machine Learning, 2018","year":2019,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genetics, Bioinformatics, and Biomedical Research","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 du Québec à Montréal","funders":"","keywords":"Library science; Artificial intelligence; Computer science; Operations research; Engineering","score_opus":0.04208591819186735,"score_gpt":0.2997319721082747,"score_spread":0.2576460539164073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952149733","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045318366,0.099340975,0.026553655,0.09833416,0.6140745,0.0011319785,0.010520213,0.0018814121,0.14363122],"genre_scores_gemma":[0.0121299345,0.06386824,0.011900072,0.009424947,0.13823818,0.0006068247,0.016983902,0.00256284,0.7442851],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99771583,0.00029833734,0.00014413545,0.0004176728,0.001181803,0.0002423202],"domain_scores_gemma":[0.987703,0.0012309909,0.0002781066,0.00036810074,0.0070473994,0.0033723942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039656083,0.0018960689,0.0021256963,0.004847259,0.0021185935,0.007630957,0.002006924,0.0018905633,0.16035157],"category_scores_gemma":[0.0070208185,0.00042416347,0.0015093618,0.0044448525,0.0005840434,0.003795847,0.0034211285,0.0029339222,0.08036314],"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":[0.00009303913,0.00004556108,0.00016933937,0.00036019704,0.00001696278,0.000052256168,0.000042071824,0.00018308309,0.0005970224,0.0008113745,0.9373579,0.060271215],"study_design_scores_gemma":[0.000039055263,0.000047299887,0.0007505908,0.00034259446,0.000029534009,0.00007258997,0.00013193703,0.0004167182,0.0007020681,0.002339242,0.9951024,0.000025968944],"about_ca_topic_score_codex":0.00254743,"about_ca_topic_score_gemma":0.0071715126,"teacher_disagreement_score":0.16035157,"about_ca_system_score_codex":0.0022497645,"about_ca_system_score_gemma":0.0041694483,"threshold_uncertainty_score":0.53642946},"labels":[],"label_agreement":null},{"id":"W2954689167","doi":"10.1089/cmb.2017.0063","title":"Two-Exponential Models of Gene Expression Patterns for Noisy Experimental Data","year":2018,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Developmental Biology and Gene Regulation","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":"British Columbia Institute of Technology","funders":"National Institute of General Medical Sciences; National Institutes of Health; Russian Foundation for Basic Research","keywords":"Robustness (evolution); Segmentation; Messenger RNA; Drosophila embryogenesis; Embryo; Developmental biology; Pattern recognition (psychology); Translation (biology)","score_opus":0.033733372244685846,"score_gpt":0.3335397560351929,"score_spread":0.29980638379050706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954689167","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033644587,0.0006495026,0.9607427,0.0010954277,0.00007473413,0.00019508535,0.0008867161,0.0007423919,0.001968864],"genre_scores_gemma":[0.72754425,0.002828132,0.21336971,0.0012154732,0.0002412506,0.0035080588,0.004316826,0.0009535415,0.046022724],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99623054,0.001355427,0.00024248245,0.0011805913,0.00064107036,0.00034986937],"domain_scores_gemma":[0.9730452,0.021277169,0.0017759649,0.0020038292,0.0016040084,0.0002937459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01382713,0.0021720538,0.0022957276,0.0022180693,0.00062212645,0.0023878454,0.004536521,0.0041688327,0.003930571],"category_scores_gemma":[0.03761819,0.0022156031,0.0028203884,0.0020355908,0.0034522929,0.0034766493,0.0018180142,0.0040643103,0.0022645753],"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":[0.00020091518,0.00006486682,0.0031772547,0.0002490964,0.00013364959,0.00029105885,0.00039657872,0.9158357,0.0041245176,0.06115293,0.0010710056,0.013302499],"study_design_scores_gemma":[0.00001600483,0.0000145089825,0.0004954081,0.000009764196,0.0000144731475,0.00004361689,0.000013521253,0.9868547,0.00032128632,0.011757248,0.00044260977,0.00001684115],"about_ca_topic_score_codex":0.010589262,"about_ca_topic_score_gemma":0.007843419,"teacher_disagreement_score":0.01382713,"about_ca_system_score_codex":0.0037460877,"about_ca_system_score_gemma":0.0013873165,"threshold_uncertainty_score":0.07312572},"labels":[],"label_agreement":null},{"id":"W2977115588","doi":"10.1089/cmb.2019.0237","title":"Analysis of Gene Expression in Bladder Cancer: Possible Involvement of Mitosis and Complement and Coagulation Cascades Signaling Pathway","year":2019,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Ferroptosis and cancer prognosis","field":"Medicine","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":"Ministry of Agriculture","funders":"","keywords":"microRNA; Biology; Microarray analysis techniques; Gene; Cell cycle; Transcription factor; Gene regulatory network; Downregulation and upregulation; Cancer research; Cell biology; Gene expression; Computational biology; Genetics","score_opus":0.029448062526904576,"score_gpt":0.31434390198590406,"score_spread":0.2848958394589995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2977115588","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9840979,0.007751535,0.0025716124,0.00012723928,0.000025029014,0.0000360446,0.0038859602,0.00007743817,0.0014273559],"genre_scores_gemma":[0.98835665,0.0025730547,0.003932779,0.00010934183,0.000015417869,0.00006961812,0.0038187373,0.000012613999,0.0011117356],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99984026,0.000015854082,0.000011529185,0.00005392385,0.000037446545,0.00004093876],"domain_scores_gemma":[0.9999093,0.000016964597,0.0000325653,0.000004629537,0.000019744264,0.000016764203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015826272,0.00026470106,0.00036751703,0.0010773097,0.0002849504,0.00031666536,0.000098861856,0.00017595635,0.0008663508],"category_scores_gemma":[0.00019185196,0.00010057225,0.00039499468,0.0016970986,0.00012019823,0.00017198396,0.00024154925,0.00020602508,0.00013510106],"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":[0.0011982567,0.00010379145,0.23282796,0.001428328,0.00037621666,0.0007104854,0.00032518033,0.0012773458,0.7096083,0.00052610354,0.0013729724,0.050245054],"study_design_scores_gemma":[0.000026240356,0.00029372296,0.9187287,0.000060910887,0.00045754327,0.0011651057,0.00033733377,0.006103443,0.065567635,0.0005946563,0.0066367337,0.000027866035],"about_ca_topic_score_codex":0.0012752053,"about_ca_topic_score_gemma":0.0017058898,"teacher_disagreement_score":0.0012752053,"about_ca_system_score_codex":0.0002901141,"about_ca_system_score_gemma":0.00032802712,"threshold_uncertainty_score":0.0028982162},"labels":[],"label_agreement":null},{"id":"W2995082003","doi":"10.1089/cmb.2018.0160","title":"Exploring a <i>Drosophila</i> Transcription Factor Interaction Network to Identify Cis-Regulatory Modules","year":2019,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Chromatin Dynamics","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":"Enhancer; Transcription factor; Computational biology; Cis-regulatory module; Binding site; Biology; Gene; Promoter; Regulatory sequence; Genetics; DNA binding site; Genome; Gene expression","score_opus":0.03081525007038616,"score_gpt":0.2786376347258311,"score_spread":0.24782238465544493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995082003","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94746023,0.00076075434,0.047571912,0.00012401078,0.000004995771,0.000025681727,0.001136655,0.00031455606,0.0026012945],"genre_scores_gemma":[0.9654165,0.00042359304,0.031406567,0.000030716303,0.0000031532602,0.00003203554,0.0017483782,0.000025137693,0.0009140696],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99992275,0.000014005308,0.0000030581816,0.000030344332,0.000016187472,0.000013595346],"domain_scores_gemma":[0.99992096,0.000028812137,0.000024592606,0.0000048636116,0.000011702544,0.000009137693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012252915,0.00024142285,0.00027152922,0.001149825,0.00026221309,0.00032086644,0.00028227404,0.00019622494,0.0009545679],"category_scores_gemma":[0.00023276827,0.00012962404,0.00029315447,0.00084619346,0.00012666588,0.00027331096,0.0002028403,0.00014694265,0.00012884877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005934115,0.0002787621,0.15809944,0.001044865,0.0006449578,0.0012305708,0.0005271719,0.29826185,0.42450795,0.015897056,0.0036940984,0.09521999],"study_design_scores_gemma":[0.000017157769,0.00007040483,0.081389226,0.000030112104,0.00012437988,0.00038569598,0.00021803963,0.88878435,0.01908479,0.0051174564,0.004755566,0.000022765254],"about_ca_topic_score_codex":0.0068254354,"about_ca_topic_score_gemma":0.009096567,"teacher_disagreement_score":0.0068254354,"about_ca_system_score_codex":0.00045017267,"about_ca_system_score_gemma":0.0003044809,"threshold_uncertainty_score":0.013571441},"labels":[],"label_agreement":null},{"id":"W3011135697","doi":"10.1089/cmb.2019.0464","title":"A Nested 2-Level Cross-Validation Ensemble Learning Pipeline Suggests a Negative Pressure Against Crosstalk snoRNA-mRNA Interactions in <i>Saccharomyces cerevisiae</i>","year":2020,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"RNA and protein synthesis mechanisms","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":"RNA; Small nucleolar RNA; Non-coding RNA; Biology; Computational biology; Saccharomyces cerevisiae; Messenger RNA; Nucleic acid structure; Crosstalk; Genetics; microRNA; Gene","score_opus":0.030283530106179755,"score_gpt":0.313153475961422,"score_spread":0.2828699458552423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011135697","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49845767,0.0006617293,0.49387303,0.00052306324,0.00014830545,0.00015125459,0.000501835,0.003968294,0.0017147362],"genre_scores_gemma":[0.8950075,0.000067077846,0.10121095,0.00030353063,0.00002323296,0.00010815635,0.0015596609,0.00012500184,0.0015948772],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979724,0.0008282129,0.00012184481,0.000608965,0.00022509928,0.00024353569],"domain_scores_gemma":[0.99704653,0.0016211271,0.00013065519,0.00036592825,0.0006832595,0.0001525131],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007658094,0.0013808873,0.0010766494,0.0007345498,0.00078743516,0.0011418832,0.0015110221,0.00155741,0.0013276822],"category_scores_gemma":[0.007146418,0.00044741947,0.001048704,0.00039115423,0.00050868234,0.0008236145,0.0010810286,0.0018830855,0.00045630414],"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":[0.0010005774,0.0006821243,0.026407536,0.0001282466,0.00089597644,0.00024532247,0.00010449268,0.7799602,0.01964822,0.0015100661,0.0036823384,0.16573492],"study_design_scores_gemma":[0.000010339696,0.000076128286,0.0013997209,0.0000056324507,0.000024975778,0.000016287582,0.00000531476,0.99609643,0.0020029885,0.00023270985,0.000121747944,0.000007822129],"about_ca_topic_score_codex":0.008163983,"about_ca_topic_score_gemma":0.010431335,"teacher_disagreement_score":0.008163983,"about_ca_system_score_codex":0.00072219677,"about_ca_system_score_gemma":0.0015888285,"threshold_uncertainty_score":0.040500343},"labels":[],"label_agreement":null},{"id":"W3012186082","doi":"10.1089/cmb.2019.0440","title":"Kinship Solutions for Partially Observed Multiphenotype Data","year":2020,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genetic and phenotypic traits in livestock","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":"Library science; License; Download; Computer science; World Wide Web","score_opus":0.16252084542629877,"score_gpt":0.32154901406171393,"score_spread":0.15902816863541516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012186082","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024611732,0.00020863516,0.97284275,0.00056956743,0.000046670106,0.00008573703,0.0004975952,0.00042288873,0.0007143836],"genre_scores_gemma":[0.18512805,0.0002657723,0.8081956,0.000279197,0.000105122046,0.0004342126,0.002251541,0.00024687397,0.0030935756],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879104,0.0006298217,0.00006976608,0.00023836766,0.00017126149,0.00009976684],"domain_scores_gemma":[0.9900538,0.007322667,0.0005470399,0.0010220079,0.0007232925,0.0003312119],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033079814,0.0010246763,0.0010662422,0.0013169266,0.000735083,0.0010994624,0.0019359824,0.0015940428,0.005197468],"category_scores_gemma":[0.019622155,0.0008694548,0.0013383044,0.0013683367,0.00075412926,0.0021874364,0.002614251,0.0022560896,0.0010031463],"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":[0.0002488346,0.00015410261,0.003999745,0.00027208237,0.00024297024,0.000348545,0.00035884866,0.7595328,0.001431169,0.061250336,0.008387796,0.16377273],"study_design_scores_gemma":[0.000037073754,0.00002037823,0.00035464644,0.000012159882,0.000008660219,0.00004297642,0.00005004086,0.9445563,0.00025078052,0.05380624,0.00084864005,0.000012175803],"about_ca_topic_score_codex":0.0064406097,"about_ca_topic_score_gemma":0.008435821,"teacher_disagreement_score":0.0064406097,"about_ca_system_score_codex":0.00068292744,"about_ca_system_score_gemma":0.0020109678,"threshold_uncertainty_score":0.0174945},"labels":[],"label_agreement":null},{"id":"W3093225483","doi":"10.1089/cmb.2020.0252","title":"Diagnosis of Autism Spectrum Disorder Based on Functional Brain Networks with Deep Learning","year":2020,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":134,"is_retracted":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":"Autoencoder; Autism spectrum disorder; Artificial intelligence; Computer science; Deep learning; Machine learning; Benchmark (surveying); Artificial neural network; Functional magnetic resonance imaging; Autism; Pattern recognition (psychology); Set (abstract data type); Neuroscience; Psychology","score_opus":0.02267701052063384,"score_gpt":0.24594205749326942,"score_spread":0.22326504697263558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093225483","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42297482,0.0029636603,0.5635123,0.0014137321,0.00014223145,0.00024271967,0.0015112958,0.0014571752,0.0057819905],"genre_scores_gemma":[0.9138885,0.0007571232,0.08296313,0.00015548372,0.000054219363,0.00010847198,0.0010863057,0.000035930232,0.00095088145],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999689,0.00006612954,0.000027420561,0.00009916699,0.000084162166,0.000034251196],"domain_scores_gemma":[0.9996061,0.00014590846,0.00008656727,0.0000308223,0.00010401475,0.00002666438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048736934,0.00072897755,0.00030571304,0.001326544,0.00021029054,0.00031706624,0.00041197828,0.0006703045,0.0006827254],"category_scores_gemma":[0.0018220528,0.0001712837,0.00039075656,0.00032618723,0.00028855968,0.0005749626,0.00065953005,0.0005662833,0.00024401354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064976426,0.00040312047,0.1062647,0.000383146,0.00031275133,0.0017919703,0.00022803344,0.1386281,0.059341207,0.0049494645,0.00913339,0.67791444],"study_design_scores_gemma":[0.000022647213,0.000098693934,0.024469122,0.00006573932,0.00005756915,0.00087934587,0.000064698215,0.9534807,0.013711899,0.005803464,0.0013173927,0.000028683662],"about_ca_topic_score_codex":0.0035954334,"about_ca_topic_score_gemma":0.0060875826,"teacher_disagreement_score":0.0035954334,"about_ca_system_score_codex":0.0004283863,"about_ca_system_score_gemma":0.00037192524,"threshold_uncertainty_score":0.0071490407},"labels":[],"label_agreement":null},{"id":"W3159758719","doi":"10.1089/cmb.2020.0375","title":"Estimating Genetic Similarity Matrices Using Phylogenies","year":2021,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genetic diversity and population structure","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":"Simon Fraser University","funders":"","keywords":"Phylogenetic tree; Similarity (geometry); Genetic similarity; Heritability; Biology; Tree (set theory); Genotype; Genetic analysis; Distance matrices in phylogeny; Evolutionary biology; Statistics; Genetics; Mathematics; Computer science; Artificial intelligence; Genetic diversity; Bioinformatics; Gene; Combinatorics; Population","score_opus":0.020161116588817963,"score_gpt":0.2904591659925219,"score_spread":0.27029804940370394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159758719","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09005663,0.00023094665,0.9075063,0.00019459456,0.000015442962,0.00006499053,0.00051552226,0.00062752457,0.0007880727],"genre_scores_gemma":[0.49413842,0.00022889928,0.502688,0.00009881897,0.000034636956,0.00018709798,0.001691878,0.00019254089,0.0007397223],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972711,0.0012293431,0.0001437472,0.00070695113,0.0005148909,0.00013400256],"domain_scores_gemma":[0.98687464,0.009443979,0.0011701873,0.0012149824,0.0009894127,0.00030684326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032062817,0.000779577,0.001215388,0.0070397723,0.0012131232,0.002184569,0.0017279915,0.001335081,0.001671012],"category_scores_gemma":[0.028163237,0.00084276963,0.0013396326,0.0045010243,0.0010918326,0.0023720823,0.0025605238,0.0019735657,0.00060930056],"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":[0.00014292297,0.0001417457,0.03160335,0.000213456,0.00049996417,0.00029586806,0.00063240284,0.7723445,0.0047319117,0.04757162,0.0021229105,0.13969925],"study_design_scores_gemma":[0.00001748945,0.00001367472,0.0029089143,0.000015366122,0.0000177533,0.000060641778,0.000057858277,0.95169026,0.0005636945,0.04397031,0.0006622211,0.000021800102],"about_ca_topic_score_codex":0.008935496,"about_ca_topic_score_gemma":0.008858016,"teacher_disagreement_score":0.008935496,"about_ca_system_score_codex":0.0013807951,"about_ca_system_score_gemma":0.0013064594,"threshold_uncertainty_score":0.017767012},"labels":[],"label_agreement":null},{"id":"W3177371828","doi":"10.1089/cmb.2020.0543","title":"Essential Protein Prediction Based on node2vec and XGBoost","year":2021,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Computational Drug Discovery Methods","field":"Computer Science","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":"University of Saskatchewan","funders":"","keywords":"Computer science; Biological network; Identification (biology); Computational biology; Construct (python library); Boosting (machine learning); Artificial intelligence; Machine learning; Data mining; Biology","score_opus":0.012354933124775768,"score_gpt":0.29120016656305575,"score_spread":0.27884523343828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177371828","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26035404,0.001817049,0.72142017,0.0006695058,0.0003183941,0.00033532592,0.0024073413,0.009293723,0.0033844442],"genre_scores_gemma":[0.7073848,0.00064178393,0.279507,0.00038088005,0.000099104174,0.00028920572,0.0067053596,0.00032556982,0.0046662],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996605,0.00006237117,0.000023310135,0.00009783656,0.000087270775,0.00006866811],"domain_scores_gemma":[0.99971026,0.00010871845,0.000029024051,0.000023682553,0.00009415558,0.000034035358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006629169,0.0010203978,0.001110478,0.0019179435,0.00052971044,0.00055121654,0.001004267,0.0009789491,0.0016219777],"category_scores_gemma":[0.0010655664,0.0004449817,0.0009021487,0.0011659265,0.00036471366,0.00070766656,0.00051177543,0.0008069297,0.00043398736],"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":[0.00091184134,0.0005628741,0.014560775,0.0003659387,0.00031911425,0.0004101365,0.00007870318,0.61471486,0.008198058,0.0048690797,0.02171776,0.3332909],"study_design_scores_gemma":[0.000010663044,0.000022496122,0.00025657017,0.0000029986222,0.000009595297,0.000024297424,0.0000052146947,0.99782807,0.0007518795,0.00075521757,0.00032939645,0.000003618281],"about_ca_topic_score_codex":0.008539319,"about_ca_topic_score_gemma":0.010347926,"teacher_disagreement_score":0.008539319,"about_ca_system_score_codex":0.0007385,"about_ca_system_score_gemma":0.0015918828,"threshold_uncertainty_score":0.016979218},"labels":[],"label_agreement":null},{"id":"W3186101535","doi":"10.1089/cmb.2021.0258","title":"Metabolic Pathway Prediction Using Non-Negative Matrix Factorization with Improved Precision","year":2021,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Bioinformatics and Genomic Networks","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":"Genome British Columbia; University of British Columbia","funders":"","keywords":"Non-negative matrix factorization; Inference; Computer science; Probabilistic logic; Cluster analysis; Matrix decomposition; Metabolic pathway; Graph; Artificial intelligence; Computational biology; Genome; Machine learning; Data mining; Biology; Theoretical computer science; Gene; Genetics; Eigenvalues and eigenvectors","score_opus":0.007880491162377858,"score_gpt":0.25339708613146755,"score_spread":0.2455165949690897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186101535","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06054049,0.0014137673,0.9275858,0.0004240481,0.00013232674,0.000093060524,0.0014985515,0.0070008556,0.0013110996],"genre_scores_gemma":[0.39029333,0.00039526983,0.60299665,0.00023441331,0.000119545075,0.00010716902,0.004521577,0.00020795943,0.0011241863],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824524,0.00051846413,0.000104547464,0.0005004215,0.00048057814,0.00015078326],"domain_scores_gemma":[0.9941707,0.0034346033,0.00044879652,0.00076731393,0.001047939,0.00013061894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040332326,0.0016485443,0.0015915388,0.0023968313,0.00079494587,0.001396268,0.0012595563,0.0016752421,0.0016022619],"category_scores_gemma":[0.012717235,0.00047568965,0.0015300368,0.0015376917,0.00049690454,0.0025544236,0.0010767212,0.0019001847,0.0013624325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008766848,0.00050816423,0.013839909,0.0004084098,0.0005007188,0.00034320258,0.00019968815,0.4358455,0.019676011,0.0064380234,0.01598348,0.5053803],"study_design_scores_gemma":[0.00002146737,0.00002486523,0.0004857936,0.000008222478,0.000012612038,0.000041164258,0.000011929103,0.9938775,0.0017777187,0.0031800538,0.0005462318,0.000012495597],"about_ca_topic_score_codex":0.012840734,"about_ca_topic_score_gemma":0.014723466,"teacher_disagreement_score":0.012840734,"about_ca_system_score_codex":0.000731087,"about_ca_system_score_gemma":0.0014580457,"threshold_uncertainty_score":0.025532007},"labels":[],"label_agreement":null},{"id":"W3203344580","doi":"10.1089/cmb.2021.0468","title":"Escape from Parsimony of a Double-Cut-and-Join Genome Evolution Process","year":2023,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","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":"Genome; Genome evolution; Join (topology); Mathematics; Tree (set theory); Combinatorics; Computer science; Biology; Evolutionary biology; Algorithm; Genetics; Gene","score_opus":0.014499664592782298,"score_gpt":0.27818453764423773,"score_spread":0.26368487305145544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203344580","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7329738,0.00037337706,0.26104748,0.0011150346,0.000026446962,0.000050027716,0.00020588088,0.00024332119,0.003964582],"genre_scores_gemma":[0.96245414,0.0002786297,0.033517934,0.0001163234,0.000021571128,0.00011288535,0.00031263308,0.00012068642,0.0030652646],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993426,0.00030467717,0.000021221822,0.00013257809,0.000081448365,0.00011747393],"domain_scores_gemma":[0.9926323,0.0057025286,0.0006492065,0.0004499915,0.00020423818,0.00036169557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028549496,0.0006480983,0.0012362666,0.0012063932,0.0010281052,0.0016942573,0.0018244383,0.0023459084,0.0023359815],"category_scores_gemma":[0.013579512,0.0006296298,0.0015821966,0.00076313625,0.002112387,0.002853154,0.0016817732,0.0017944137,0.00030636546],"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":[0.00021149052,0.000052899963,0.004011649,0.0000655769,0.000077521785,0.00028138194,0.0002951339,0.8996118,0.0019780286,0.08818285,0.00060341996,0.0046282057],"study_design_scores_gemma":[0.000025285013,0.000030397534,0.00035627346,0.000005858415,0.000014578514,0.000047130085,0.000031006653,0.9649555,0.0003007474,0.034010172,0.00020963361,0.000013415456],"about_ca_topic_score_codex":0.0039424994,"about_ca_topic_score_gemma":0.0028451465,"teacher_disagreement_score":0.0039424994,"about_ca_system_score_codex":0.0017326865,"about_ca_system_score_gemma":0.00073741097,"threshold_uncertainty_score":0.015098572},"labels":[],"label_agreement":null},{"id":"W3213516359","doi":"10.1089/cmb.2021.0340","title":"Ancestral Flowering Plant Chromosomes and Gene Orders Based on Generalized Adjacencies and Chromosomal Gene Co-Occurrences","year":2021,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; University of Ottawa","funders":"","keywords":"Contig; Genome; Biology; Genetics; Phylogenetics; Chromosome; Evolutionary biology; Gene","score_opus":0.02357044913788481,"score_gpt":0.2529241851261971,"score_spread":0.22935373598831227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213516359","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7970584,0.000466214,0.17100936,0.00017798493,0.00003265983,0.00013099403,0.014054606,0.009210984,0.007858764],"genre_scores_gemma":[0.6451267,0.00045462736,0.3222467,0.00005595845,0.000017923847,0.000113490256,0.026135873,0.002961882,0.002886847],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99969757,0.000031620617,0.000018181341,0.00014937755,0.0000652823,0.00003792875],"domain_scores_gemma":[0.99917656,0.00030209657,0.000121934136,0.000213977,0.0001412409,0.000044123604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061697036,0.00050084735,0.0004135926,0.002642834,0.0006850469,0.0019571641,0.00047803222,0.00036170104,0.0064456407],"category_scores_gemma":[0.0030499701,0.00044897228,0.00094591867,0.002807071,0.00050511264,0.0010105483,0.00089040323,0.00071785017,0.0012303547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019534305,0.00019834364,0.18716107,0.0012412408,0.0005122929,0.00096361653,0.0050449492,0.05339886,0.35558182,0.034629226,0.0074792583,0.35183594],"study_design_scores_gemma":[0.00014974376,0.00045154622,0.4542984,0.0002579978,0.00050526235,0.0013237199,0.002175546,0.34005085,0.09399917,0.053275943,0.053285953,0.00022586905],"about_ca_topic_score_codex":0.0039330022,"about_ca_topic_score_gemma":0.008469984,"teacher_disagreement_score":0.0064456407,"about_ca_system_score_codex":0.00059395126,"about_ca_system_score_gemma":0.0006465338,"threshold_uncertainty_score":0.021562815},"labels":[],"label_agreement":null},{"id":"W4205262153","doi":"10.1089/cmb.2021.0445","title":"Finding Maximal Exact Matches Using the r-Index","year":2022,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","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":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute","keywords":"Set (abstract data type); Sequence (biology); Computer science; Data structure; Index (typography); Key (lock); Space (punctuation); Code (set theory); k-mer; Algorithm; Theoretical computer science; Data set; Genome; Programming language; Artificial intelligence; Biology","score_opus":0.026058600660260656,"score_gpt":0.28366591471717423,"score_spread":0.25760731405691356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205262153","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037374407,0.0007859806,0.9028548,0.000429236,0.00013242355,0.00021178644,0.0061447127,0.04588981,0.006176833],"genre_scores_gemma":[0.1156223,0.00026801374,0.8684711,0.00015611245,0.00006870733,0.00044247918,0.0091710575,0.0042333924,0.0015668132],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939851,0.0011512556,0.00094954355,0.0017081836,0.0017540193,0.00045178397],"domain_scores_gemma":[0.9896031,0.004743941,0.0011504436,0.002979225,0.0011550849,0.0003682302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004036806,0.0018532666,0.0022951902,0.0041770204,0.0014029453,0.004114288,0.0036956049,0.0018434295,0.008290975],"category_scores_gemma":[0.029369438,0.0012557871,0.002225151,0.0044762096,0.0019544314,0.0071897847,0.005419032,0.0019466096,0.010822184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030712446,0.0005280008,0.023228122,0.003098116,0.00061744323,0.001245627,0.0021876094,0.051885728,0.09461392,0.14909929,0.06959559,0.6008293],"study_design_scores_gemma":[0.0004165999,0.00073266577,0.004963347,0.0003814989,0.00020322869,0.0017915237,0.0007313467,0.46742785,0.14633086,0.295347,0.0812365,0.00043756625],"about_ca_topic_score_codex":0.0011275859,"about_ca_topic_score_gemma":0.0013363957,"teacher_disagreement_score":0.008290975,"about_ca_system_score_codex":0.0008434364,"about_ca_system_score_gemma":0.0023962874,"threshold_uncertainty_score":0.027736068},"labels":[],"label_agreement":null},{"id":"W4205330988","doi":"10.1089/cmb.2021.0290","title":"MONI: A Pangenomic Index for Finding Maximal Exact Matches","year":2022,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":90,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute","keywords":"Parsing; Computer science; Index (typography); Trie; Prefix; Matching (statistics); Pattern matching; Algorithm; Sequence (biology); Tree (set theory); Theoretical computer science; Mathematics; Data structure; Artificial intelligence; Combinatorics; Statistics; Biology","score_opus":0.020620484825903746,"score_gpt":0.2744811594893764,"score_spread":0.2538606746634727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205330988","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027345309,0.0043269065,0.81811064,0.0010415551,0.00057489204,0.0005875892,0.031089583,0.098393016,0.018530596],"genre_scores_gemma":[0.060227193,0.0010713025,0.88384926,0.00048163076,0.00015203403,0.00060045475,0.04260216,0.005031294,0.0059846668],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980336,0.000261658,0.00026296612,0.0006536056,0.00060918066,0.0001790689],"domain_scores_gemma":[0.9969311,0.0008616473,0.00032810972,0.0011403286,0.0005407315,0.00019804983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022875704,0.0015119958,0.001750136,0.0071087023,0.0018251202,0.0032557177,0.0031435813,0.0015405905,0.013884343],"category_scores_gemma":[0.009245951,0.0011801657,0.0014865071,0.0076445355,0.00094289804,0.006970549,0.004433132,0.0017086448,0.007864751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002060927,0.00024190468,0.008193855,0.0016826965,0.00036393106,0.00056118565,0.0008286829,0.010112696,0.048070375,0.0659872,0.14331903,0.7185774],"study_design_scores_gemma":[0.00048452782,0.0004528808,0.0053921,0.00039171593,0.00035961714,0.00214509,0.0005444182,0.28288236,0.08756409,0.1809408,0.43846166,0.0003808372],"about_ca_topic_score_codex":0.0034663016,"about_ca_topic_score_gemma":0.0049456037,"teacher_disagreement_score":0.013884343,"about_ca_system_score_codex":0.0016804353,"about_ca_system_score_gemma":0.0027587332,"threshold_uncertainty_score":0.046447754},"labels":[],"label_agreement":null},{"id":"W4206241082","doi":"10.1089/cmb.2021.0436","title":"flopp: Extremely Fast Long-Read Polyploid Haplotype Phasing by Uniform Tree Partitioning","year":2022,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","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":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Polyploid; Phaser; Haplotype; Probabilistic logic; Ploidy; Computer science; Algorithm; Tree (set theory); Metric (unit); Biology; Biological system; Theoretical computer science; Mathematics; Combinatorics; Artificial intelligence; Genetics; Physics; Genotype","score_opus":0.013714826045500953,"score_gpt":0.2547400289230975,"score_spread":0.24102520287759654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206241082","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008943707,0.0001641132,0.9886903,0.00007491898,0.00001925413,0.00003151226,0.00018028005,0.0015730314,0.0003228166],"genre_scores_gemma":[0.09301849,0.00014257866,0.9039486,0.0001417534,0.000028347755,0.00018129998,0.0010468184,0.0006109667,0.0008811847],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994373,0.00018396368,0.000034337965,0.00019172537,0.00011432667,0.000038334358],"domain_scores_gemma":[0.9982033,0.0011360436,0.00016632777,0.00028455313,0.00014150422,0.0000683274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014251501,0.00082857086,0.00092118647,0.0007330239,0.0006041592,0.0009096941,0.0016979495,0.0013126095,0.0020968136],"category_scores_gemma":[0.006183506,0.0006749131,0.00094413135,0.0010514365,0.0006522692,0.0019497697,0.0019999412,0.0015131199,0.0007542429],"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":[0.0004836765,0.000108544715,0.0040238146,0.00055222237,0.00038194552,0.00038384943,0.00049594755,0.46880504,0.0470065,0.03265849,0.010574471,0.4345254],"study_design_scores_gemma":[0.000052969703,0.00005699911,0.000649328,0.00001865744,0.000018483668,0.00019465745,0.000040399576,0.9598082,0.009713011,0.02578315,0.0036351753,0.00002906159],"about_ca_topic_score_codex":0.0024273517,"about_ca_topic_score_gemma":0.0041806796,"teacher_disagreement_score":0.0024273517,"about_ca_system_score_codex":0.0004990513,"about_ca_system_score_gemma":0.0010503032,"threshold_uncertainty_score":0.0075370073},"labels":[],"label_agreement":null},{"id":"W4233853535","doi":"10.1089/106652700750050925","title":"Early Eukaryote Evolution Based on Mitochondrial Gene Order Breakpoints","year":2000,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"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; Université de Montréal","funders":"","keywords":"Genome; Breakpoint; Phylogenetic tree; Eukaryote; Biology; Phylogenetics; Evolutionary biology; Gene; Genetics; Computational biology; Synteny; Phylogenetic network","score_opus":0.005654480235721184,"score_gpt":0.236491253388888,"score_spread":0.2308367731531668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233853535","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76509607,0.0002379162,0.23277698,0.00013870027,0.00001034586,0.000028931734,0.00013390358,0.00020329507,0.0013739725],"genre_scores_gemma":[0.8488719,0.00018974181,0.14982882,0.000026899539,0.000008410773,0.000039587718,0.0003784166,0.0001199192,0.00053636177],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99960285,0.0001342658,0.000020736074,0.00011474904,0.000076048804,0.000051350962],"domain_scores_gemma":[0.99843436,0.00096309197,0.00025677087,0.00015520254,0.000095950185,0.00009468178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011583815,0.00029323273,0.0005918152,0.001158468,0.00065326184,0.0013419943,0.0007712818,0.0007874116,0.0015468738],"category_scores_gemma":[0.0068080374,0.00042420856,0.0007487194,0.0011230685,0.00089776394,0.001300244,0.0010711026,0.001094958,0.00020293819],"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":[0.00088079605,0.00013711496,0.0484066,0.00021143198,0.0001708146,0.00036398036,0.0006835693,0.74875313,0.041667435,0.06057125,0.0004603759,0.09769344],"study_design_scores_gemma":[0.00007751927,0.00026925295,0.02892307,0.000054145927,0.00007316406,0.0002623844,0.00034260596,0.8518319,0.0150369,0.10102536,0.0020471578,0.000056492605],"about_ca_topic_score_codex":0.0013540663,"about_ca_topic_score_gemma":0.0023615058,"teacher_disagreement_score":0.0015468738,"about_ca_system_score_codex":0.00086828705,"about_ca_system_score_gemma":0.0005015566,"threshold_uncertainty_score":0.006299913},"labels":[],"label_agreement":null},{"id":"W4290660596","doi":"10.1089/cmb.2021.0520","title":"Computing Maximal Covers for Protein Sequences","year":2022,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Substring; Cover (algebra); String (physics); Context (archaeology); Computer science; Software; Fragment (logic); Sequence (biology); Theoretical computer science; Biology; Algorithm; Mathematics; Data structure; Genetics; Programming language; Engineering","score_opus":0.021160806813030897,"score_gpt":0.2910424347732892,"score_spread":0.26988162796025833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290660596","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19461569,0.0014394232,0.7853441,0.00038506894,0.00007027006,0.00013010208,0.004173029,0.0079176435,0.005924541],"genre_scores_gemma":[0.465532,0.00073699217,0.5139869,0.00020855221,0.00013137923,0.0003334289,0.014484532,0.0013972803,0.0031890208],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986852,0.00023371214,0.0001114595,0.00033293405,0.0004907498,0.00014598995],"domain_scores_gemma":[0.99660134,0.0022054554,0.0002531191,0.0005398432,0.0002757641,0.00012442803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009878475,0.00095813384,0.0011304682,0.002669867,0.0008003417,0.0016148307,0.0011013678,0.0011959336,0.004591714],"category_scores_gemma":[0.009361102,0.0006852758,0.0013528082,0.0027062704,0.0010401461,0.0038043167,0.0023765652,0.0008065822,0.0016297766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018240652,0.0001506955,0.012896297,0.001599775,0.000326553,0.0008819152,0.0013979207,0.32416558,0.039569393,0.09619051,0.02684402,0.4941533],"study_design_scores_gemma":[0.0000568112,0.00018153944,0.0016447044,0.00011800936,0.000059363403,0.000634087,0.0003138846,0.7622413,0.030568622,0.18967764,0.014460875,0.00004316535],"about_ca_topic_score_codex":0.0008881722,"about_ca_topic_score_gemma":0.0014399608,"teacher_disagreement_score":0.004591714,"about_ca_system_score_codex":0.0008426403,"about_ca_system_score_gemma":0.0010059442,"threshold_uncertainty_score":0.015360773},"labels":[],"label_agreement":null},{"id":"W4293457048","doi":"10.1089/cmb.2022.0251","title":"UNIFAN: A Tool for Unsupervised Single-Cell Clustering and Annotation","year":2022,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Single-cell and spatial transcriptomics","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":"Christie (Canada); McGill University Health Centre","funders":"National Institutes of Health","keywords":"Annotation; Cluster analysis; Computer science; Focus (optics); Software; Cluster (spacecraft); Process (computing); Computational biology; Data mining; Artificial intelligence; Biology","score_opus":0.01678411128139971,"score_gpt":0.24142870114196632,"score_spread":0.22464458986056662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293457048","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031946532,0.0003171416,0.68769294,0.0001228828,0.00024742342,0.0001705403,0.027982935,0.27823108,0.0020403452],"genre_scores_gemma":[0.027996283,0.00048809813,0.81902635,0.00037035186,0.000086941276,0.0020253866,0.091182135,0.052355777,0.006468597],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989981,0.00015076579,0.00010878159,0.00035066952,0.00028785673,0.00010388678],"domain_scores_gemma":[0.9984693,0.0007187425,0.000091027374,0.00037675898,0.0002549809,0.00008912511],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002328377,0.0023445943,0.0019705205,0.0026360909,0.0016524988,0.0023912203,0.0034688916,0.0015062261,0.03530667],"category_scores_gemma":[0.0051482785,0.0018807602,0.003083975,0.0019870307,0.0006628652,0.0021656374,0.0027961975,0.0026316014,0.019291488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001364784,0.00018563602,0.006193597,0.0037922258,0.0011997187,0.0009831962,0.0016760504,0.040235944,0.082042664,0.018956225,0.5108425,0.33252743],"study_design_scores_gemma":[0.00036924353,0.00017751506,0.005990668,0.0004669421,0.00023658418,0.0011774807,0.00040833856,0.26866916,0.0954674,0.05835082,0.56820136,0.00048459528],"about_ca_topic_score_codex":0.0032846218,"about_ca_topic_score_gemma":0.0056756856,"teacher_disagreement_score":0.03530667,"about_ca_system_score_codex":0.0010410829,"about_ca_system_score_gemma":0.0019100879,"threshold_uncertainty_score":0.118112564},"labels":[],"label_agreement":null},{"id":"W4308957951","doi":"10.1089/cmb.2022.0067","title":"Genome-Wide Association with Uncertainty in the Genetic Similarity Matrix","year":2022,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","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":"Simon Fraser University","funders":"","keywords":"Genome-wide association study; Generalized linear mixed model; Genetic association; Similarity (geometry); Population stratification; Population; Markov chain Monte Carlo; Bayesian probability; Computational biology; Biology; Mathematics; Genetics; Statistics; Computer science; Artificial intelligence; Genotype; Medicine","score_opus":0.00852950180874421,"score_gpt":0.24909899207260647,"score_spread":0.24056949026386226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308957951","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17534064,0.0012627981,0.81931776,0.0021947403,0.000083017,0.00008328178,0.00038895433,0.00039513034,0.0009337544],"genre_scores_gemma":[0.8858444,0.0006760445,0.110801764,0.0005173684,0.00015616,0.00021328364,0.00050963793,0.00009934808,0.0011818693],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98320156,0.012044523,0.00060573715,0.0027876867,0.00090492016,0.00045552995],"domain_scores_gemma":[0.8150078,0.17282373,0.005924706,0.004282817,0.0012781197,0.00068288256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03125287,0.00078023516,0.0020267505,0.0020858452,0.001289561,0.0033144525,0.0023563495,0.003125774,0.001911378],"category_scores_gemma":[0.122410335,0.0014326833,0.002072909,0.0032032323,0.0039322046,0.003220589,0.0030316822,0.003515216,0.0002252945],"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":[0.00037015992,0.00009796616,0.07611611,0.00025467336,0.0011211245,0.0010885453,0.0006602172,0.7374003,0.0014525118,0.1457673,0.0014148863,0.034256306],"study_design_scores_gemma":[0.00005125469,0.00004614473,0.0083105415,0.00004758102,0.00011771632,0.00022829568,0.00005143803,0.8700827,0.0002415511,0.12007615,0.00068656576,0.000060071685],"about_ca_topic_score_codex":0.009521861,"about_ca_topic_score_gemma":0.008242679,"teacher_disagreement_score":0.03125287,"about_ca_system_score_codex":0.0016268302,"about_ca_system_score_gemma":0.0016793589,"threshold_uncertainty_score":0.16528296},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0620943,0.000496605,0.93473047,0.00012656396,0.000041806474,0.00005542759,0.000245265,0.0002160239,0.0019934324],"genre_scores_gemma":[0.6773496,0.00031925575,0.31994522,0.00012773354,0.00007871807,0.00016925689,0.0006649446,0.000083367784,0.001261866],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871266,0.0003324593,0.00008462572,0.00030094347,0.0005079964,0.000061236366],"domain_scores_gemma":[0.996207,0.0022136187,0.0005260524,0.00041015405,0.00051478634,0.00012830252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014457213,0.00058594777,0.00084674073,0.00204631,0.00042162917,0.0009748492,0.0012007572,0.0008676829,0.00077399943],"category_scores_gemma":[0.0072367643,0.0002090415,0.00067660044,0.0014864546,0.0010635195,0.0015546416,0.00095291005,0.00088026817,0.00027529013],"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":[0.00022308646,0.0002248381,0.017997598,0.00030864778,0.0002878003,0.00027344233,0.00021708568,0.69166875,0.02460229,0.061861537,0.0015500549,0.20078479],"study_design_scores_gemma":[0.000008584015,0.000118023854,0.0035318614,0.000014415319,0.000021261574,0.0001834227,0.000020543708,0.9752263,0.0026447729,0.017242886,0.00095672515,0.000031289856],"about_ca_topic_score_codex":0.002198187,"about_ca_topic_score_gemma":0.0018780294,"teacher_disagreement_score":0.002198187,"about_ca_system_score_codex":0.0010583057,"about_ca_system_score_gemma":0.000847886,"threshold_uncertainty_score":0.007678628},"labels":[],"label_agreement":null},{"id":"W4380871651","doi":"10.1089/cmb.2022.0319","title":"Speeding Up the Structural Analysis of Metabolic Network Models Using the Fredman–Khachiyan Algorithm B","year":2023,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Microbial Metabolic Engineering and Bioproduction","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":"Medical Research Council","keywords":"Oracle; Computer science; Dual (grammatical number); Algorithm; Key (lock); Monotone polygon; Boolean function; Computation; Theoretical computer science; Mathematics","score_opus":0.02260259599996458,"score_gpt":0.290434149190834,"score_spread":0.26783155319086943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380871651","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022280484,0.00013721509,0.97295076,0.00038797213,0.000024738565,0.00009696567,0.00019924677,0.0021675741,0.0017550128],"genre_scores_gemma":[0.19070692,0.00014190696,0.80621016,0.0001859077,0.00003503027,0.00018679023,0.00072186056,0.0002458498,0.0015654827],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909556,0.0002793169,0.00006300608,0.00024004452,0.00019725235,0.00012484679],"domain_scores_gemma":[0.996516,0.0025289897,0.00023128137,0.00038862825,0.000251027,0.00008410909],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018211666,0.0013128858,0.0012645448,0.0016657297,0.0008225964,0.001833237,0.0019361352,0.0016765775,0.0054440335],"category_scores_gemma":[0.008753527,0.0007925598,0.0020271267,0.0010762762,0.0011967449,0.003183381,0.0023332292,0.002531475,0.0011532767],"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":[0.00045133813,0.00021483534,0.0028023168,0.0002846654,0.00011484698,0.00020243616,0.00026398548,0.68123424,0.006827043,0.08941632,0.0049041607,0.2132839],"study_design_scores_gemma":[0.000024520128,0.000016436636,0.00008803701,0.000008120314,0.000009259957,0.00002330852,0.000014669898,0.9600652,0.00093545753,0.038129896,0.0006766074,0.000008476629],"about_ca_topic_score_codex":0.010021543,"about_ca_topic_score_gemma":0.012375693,"teacher_disagreement_score":0.010021543,"about_ca_system_score_codex":0.0019862687,"about_ca_system_score_gemma":0.0027751457,"threshold_uncertainty_score":0.019926429},"labels":[],"label_agreement":null},{"id":"W4389992281","doi":"10.1089/cmb.2023.0317","title":"A Fixed-Parameter Tractable Algorithm for Finding Agreement Cherry-Reduced Subnetworks in Level-1 Orchard Networks","year":2023,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Plant and animal studies","field":"Agricultural and Biological Sciences","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 Sherbrooke; University of Manitoba","funders":"","keywords":"Reticulate; Subnetwork; Phylogenetic tree; Enhanced Data Rates for GSM Evolution; Class (philosophy); Algorithm; Orchard; Mathematics; Time complexity; Binary number; Simple (philosophy); Combinatorics; Computer science; Artificial intelligence; Biology; Botany; Horticulture","score_opus":0.11596762481018577,"score_gpt":0.29337211840974364,"score_spread":0.17740449359955787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389992281","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058361664,0.0002735119,0.9314192,0.00050207635,0.00004208047,0.0003989635,0.00056695845,0.0029365562,0.005499011],"genre_scores_gemma":[0.24252808,0.00012238,0.7524028,0.00013655379,0.000029904997,0.00038281613,0.0014762388,0.00033626397,0.0025849997],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991347,0.00018916154,0.00005591471,0.00029963162,0.00016444751,0.00015619579],"domain_scores_gemma":[0.9973028,0.0017792868,0.00023327605,0.00035612573,0.00019776897,0.0001308646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001240191,0.0011270801,0.0014332851,0.0011534074,0.00095725467,0.0016445552,0.0024921882,0.0016820568,0.0076463185],"category_scores_gemma":[0.006952794,0.00062744034,0.0013138802,0.0011332207,0.0009196694,0.0032822324,0.0025133432,0.0018069898,0.0013661041],"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":[0.0004598538,0.00030795656,0.0032527174,0.00065197295,0.00015181111,0.0002754121,0.00057455857,0.6268842,0.010741387,0.046664063,0.011415972,0.29862005],"study_design_scores_gemma":[0.00012037364,0.00008452955,0.0003826366,0.00002866455,0.000035021538,0.00008908011,0.00013289807,0.9487813,0.0016977898,0.04634376,0.0022856067,0.000018409914],"about_ca_topic_score_codex":0.0039916867,"about_ca_topic_score_gemma":0.009064853,"teacher_disagreement_score":0.0076463185,"about_ca_system_score_codex":0.0020601067,"about_ca_system_score_gemma":0.002671048,"threshold_uncertainty_score":0.025579512},"labels":[],"label_agreement":null},{"id":"W4394810076","doi":"10.1089/cmb.2023.0400","title":"Orthology and Paralogy Relationships at Transcript Level","year":2024,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Bioinformatics and Genomic Networks","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 Sherbrooke","funders":"","keywords":"Gene; Biology; Ensembl; Genetics; Homology (biology); Orthologous Gene; Transcriptome; Homologous chromosome; Gene family; Computational biology; Genome; Gene expression; Genomics","score_opus":0.03314015103441619,"score_gpt":0.27350984674369394,"score_spread":0.24036969570927774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394810076","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62701607,0.0009525489,0.36198556,0.00018879698,0.00006336041,0.00017409022,0.002510434,0.0010650217,0.0060440153],"genre_scores_gemma":[0.8552987,0.00031826965,0.13770717,0.000047019603,0.00003238653,0.00014378203,0.00509204,0.00019337675,0.0011671969],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907136,0.0002100222,0.00007121718,0.00033858308,0.00023252261,0.000076256605],"domain_scores_gemma":[0.9985474,0.00073666987,0.00019876576,0.00020885235,0.00023111807,0.000077136945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083873427,0.00023785992,0.00037215737,0.0017976306,0.0006608114,0.0010423865,0.00055773335,0.00046537473,0.0035174352],"category_scores_gemma":[0.0035709215,0.00021723351,0.0006380453,0.0014207318,0.0006458434,0.0010053057,0.00075686077,0.0007365177,0.0007359367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016717723,0.00038304713,0.2190012,0.0011246104,0.0003747123,0.0023033996,0.00272595,0.048274,0.3731357,0.059883125,0.0030513937,0.28807116],"study_design_scores_gemma":[0.00014576048,0.0010249142,0.25629446,0.00017740497,0.0003923392,0.005569071,0.0022612405,0.4130098,0.112975016,0.16808915,0.039940596,0.00012027885],"about_ca_topic_score_codex":0.0007247532,"about_ca_topic_score_gemma":0.00084062776,"teacher_disagreement_score":0.0035174352,"about_ca_system_score_codex":0.00038693057,"about_ca_system_score_gemma":0.00057565654,"threshold_uncertainty_score":0.01176703},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016782196,0.0011808738,0.976232,0.0012458356,0.000047070458,0.000013271111,0.000060285904,0.00015362045,0.0042849155],"genre_scores_gemma":[0.53942466,0.0048221014,0.44160834,0.0009758351,0.0004901678,0.00022873511,0.00029694283,0.00034974667,0.011803389],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995701,0.00015847266,0.000025737165,0.00011334941,0.000087326,0.000045036184],"domain_scores_gemma":[0.9978022,0.001576593,0.00017015387,0.00019582162,0.00019872618,0.00005651971],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015721087,0.0008051482,0.00049710216,0.001288421,0.00048793197,0.0010256129,0.0010184693,0.0013484604,0.002143192],"category_scores_gemma":[0.007219484,0.0005728075,0.00083143666,0.0010920177,0.0026347898,0.003087582,0.0014000295,0.0022891283,0.00037850149],"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":[0.000031980308,0.000023059212,0.0010428253,0.000097402575,0.00003305203,0.00008451732,0.000112307105,0.13814025,0.0019000489,0.81659764,0.0014143198,0.040522605],"study_design_scores_gemma":[0.0000045519732,0.000017851244,0.00036258704,0.000023299692,0.000006552317,0.00004309445,0.00001356948,0.48971367,0.00065698125,0.507648,0.0014958385,0.00001406121],"about_ca_topic_score_codex":0.004387116,"about_ca_topic_score_gemma":0.0033103153,"teacher_disagreement_score":0.004387116,"about_ca_system_score_codex":0.0018537068,"about_ca_system_score_gemma":0.00063039875,"threshold_uncertainty_score":0.013449609},"labels":[],"label_agreement":null},{"id":"W4401212766","doi":"10.1089/cmb.2023.0331","title":"A Rigorous Framework to Classify the Postduplication Fate of Paralogous Genes","year":2024,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"CRISPR and Genetic Engineering","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":"Université de Sherbrooke","funders":"Agence Nationale de la Recherche","keywords":"Biology; Gene; Computational biology; Genetics; Computer science; Evolutionary biology","score_opus":0.009343085250732642,"score_gpt":0.3580712821803014,"score_spread":0.34872819692956875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401212766","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018523922,0.0003335351,0.97513235,0.00044116637,0.00008031322,0.000039191065,0.00015536122,0.00014532142,0.005148833],"genre_scores_gemma":[0.57123727,0.0014649717,0.41829923,0.00055082387,0.00036335833,0.00049449067,0.00071054394,0.00045710368,0.006422286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988201,0.00037076522,0.00011412148,0.00017108691,0.00038040892,0.00014350207],"domain_scores_gemma":[0.9946654,0.0027388416,0.0006775983,0.00087468285,0.00073163555,0.00031183273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005118423,0.0007788367,0.0009565153,0.0019405512,0.00090078777,0.0022953323,0.0022933446,0.0017495371,0.0028497363],"category_scores_gemma":[0.009322384,0.00032678546,0.0016090722,0.00069581013,0.0035456272,0.002618676,0.002064908,0.0026355241,0.0005915488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012371805,0.00003277128,0.0012015421,0.000065592365,0.000030801508,0.00008577445,0.00007253783,0.12138925,0.0051984596,0.8658773,0.00058654003,0.005447066],"study_design_scores_gemma":[0.000017204995,0.00005864906,0.0006545574,0.000035212615,0.000018098905,0.000120184086,0.0000429161,0.42788723,0.0015800492,0.5659041,0.0036443304,0.000037451297],"about_ca_topic_score_codex":0.001649542,"about_ca_topic_score_gemma":0.0014199041,"teacher_disagreement_score":0.005118423,"about_ca_system_score_codex":0.0014205789,"about_ca_system_score_gemma":0.0021279885,"threshold_uncertainty_score":0.027069151},"labels":[],"label_agreement":null},{"id":"W4401272365","doi":"10.1089/cmb.2023.0377","title":"From Policy to Prediction: Assessing Forecasting Accuracy in an Integrated Framework with Machine Learning and Disease Models","year":2024,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Brock University; University of Alberta","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Predictive modelling","score_opus":0.12741096904976712,"score_gpt":0.4464266282206925,"score_spread":0.3190156591709254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401272365","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.854579,0.0017781979,0.13651426,0.0021598742,0.00013676658,0.00012652665,0.00086924975,0.0006285001,0.003207574],"genre_scores_gemma":[0.9726415,0.00022971023,0.026000528,0.000093778806,0.00006012751,0.00004900459,0.00058480323,0.000021082844,0.0003194754],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99649686,0.0021774634,0.00018232981,0.00049495377,0.00041772323,0.00023073982],"domain_scores_gemma":[0.983383,0.0127088,0.0010343962,0.001120524,0.0012904282,0.00046278982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015391486,0.001129719,0.0014594627,0.0017219023,0.0005557776,0.0020435776,0.001392882,0.0015566152,0.0010278182],"category_scores_gemma":[0.032788213,0.0005855262,0.0012061778,0.0017367913,0.0006563475,0.0027397885,0.0016383445,0.0022154187,0.00021532233],"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":[0.0006806918,0.00023285941,0.057348225,0.000083104154,0.00058018597,0.000067296976,0.00014834794,0.90030646,0.00030659392,0.0028086319,0.00069077115,0.036746845],"study_design_scores_gemma":[0.000014137067,0.000103164246,0.0048991335,0.000012554813,0.000044590295,0.000011272365,0.000032920172,0.99269086,0.00011532833,0.0019095977,0.00015584305,0.000010615047],"about_ca_topic_score_codex":0.04691325,"about_ca_topic_score_gemma":0.023571024,"teacher_disagreement_score":0.04691325,"about_ca_system_score_codex":0.0016405688,"about_ca_system_score_gemma":0.0023718702,"threshold_uncertainty_score":0.093280375},"labels":[],"label_agreement":null},{"id":"W4402501334","doi":"10.1089/cmb.2024.0485","title":"Bifurcations and Homoclinic Orbits of a Model Consisting of Vegetation–Prey–Predator Populations","year":2024,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Mathematical and Theoretical Epidemiology and Ecology Models","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Homoclinic orbit; Mathematics; Center manifold; Hopf bifurcation; Limit cycle; Population; Saddle; Bifurcation; Pitchfork bifurcation; Bogdanov–Takens bifurcation; Statistical physics; Mathematical analysis; Applied mathematics; Limit (mathematics); Physics; Mathematical optimization; Nonlinear system","score_opus":0.0882146600878417,"score_gpt":0.3912425892642358,"score_spread":0.3030279291763941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402501334","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8775904,0.00058954116,0.10253924,0.00040834764,0.000041499363,0.00004375897,0.00027826955,0.00014927772,0.018359575],"genre_scores_gemma":[0.9938543,0.00013332484,0.0033522863,0.000016137037,0.0000091398515,0.00002530272,0.00006411929,0.000011814116,0.0025336344],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999169,0.000020284959,0.000003930728,0.00001639624,0.000017858254,0.000024625175],"domain_scores_gemma":[0.99986446,0.00004493523,0.00003289937,0.0000108294935,0.00002234783,0.00002457572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002470639,0.0003825845,0.00043368712,0.0007126701,0.00076511217,0.0008102788,0.0006780906,0.00083647436,0.0015627437],"category_scores_gemma":[0.00062238117,0.0002339301,0.0007155989,0.0002797289,0.00084838626,0.000531363,0.0007049536,0.00040897934,0.00015824508],"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":[0.000058715363,0.000032715478,0.0053090714,0.000040389787,0.00006495034,0.00030907188,0.00021219926,0.9475255,0.004713273,0.03769001,0.0005099669,0.0035342034],"study_design_scores_gemma":[0.000005576211,0.000010443031,0.0008708445,0.0000037614095,0.000010669464,0.000024487597,0.000036157966,0.993903,0.00012584495,0.0047698393,0.00023343346,0.0000057928487],"about_ca_topic_score_codex":0.057290405,"about_ca_topic_score_gemma":0.032591466,"teacher_disagreement_score":0.057290405,"about_ca_system_score_codex":0.0013571513,"about_ca_system_score_gemma":0.001249566,"threshold_uncertainty_score":0.11391389},"labels":[],"label_agreement":null},{"id":"W4405835851","doi":"10.1089/cmb.2024.0635","title":"Generative Adversarial Networks for Neuroimage Translation","year":2024,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute","funders":"","keywords":"Adversarial system; Translation (biology); Generative grammar; Computer science; Artificial intelligence; Natural language processing; Biology","score_opus":0.022621946314076054,"score_gpt":0.32234251959595933,"score_spread":0.2997205732818833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405835851","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022704111,0.000809772,0.9700336,0.00057274866,0.00007705172,0.000050574614,0.0001808987,0.00076135603,0.0048099337],"genre_scores_gemma":[0.8693393,0.00061276025,0.11920069,0.00037841572,0.00007313445,0.00018919316,0.00045527093,0.00024136635,0.009509779],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99975806,0.00009021892,0.000008364302,0.00005600031,0.0000587213,0.000028656248],"domain_scores_gemma":[0.9991611,0.00061394507,0.00006621974,0.00005573124,0.00007798992,0.000024990008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073085434,0.0007242337,0.0005223381,0.00036854765,0.0001875283,0.00047625022,0.00078650226,0.000793585,0.002678042],"category_scores_gemma":[0.0023365915,0.00040770348,0.0005751484,0.00032984032,0.00072469696,0.00056827086,0.0009529037,0.0015307057,0.0005348667],"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":[0.000031309744,0.00001087273,0.0001507392,0.000021557365,0.00001535579,0.000034477594,0.00001651833,0.9806788,0.0012753968,0.0058680475,0.000639491,0.011257404],"study_design_scores_gemma":[0.0000016688199,0.0000059300714,0.00003402307,0.0000031847144,0.0000018092027,0.000008205544,0.0000015349701,0.99678326,0.00035605513,0.0025612388,0.00024064879,0.0000023505982],"about_ca_topic_score_codex":0.003359285,"about_ca_topic_score_gemma":0.0036967623,"teacher_disagreement_score":0.003359285,"about_ca_system_score_codex":0.0008718727,"about_ca_system_score_gemma":0.0005835162,"threshold_uncertainty_score":0.008958936},"labels":[],"label_agreement":null},{"id":"W4406624837","doi":"10.1089/cmb.2024.0563","title":"A Joint Bayesian Model for Change-Points and Heteroskedasticity Applied to the Canadian Longitudinal Study on Aging","year":2025,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Simon Fraser University","funders":"","keywords":"Heteroscedasticity; Econometrics; Bayesian probability; Longitudinal data; Joint (building); Longitudinal study; Computer science; Bayesian inference; Mathematics; Statistics; Data mining; Engineering; Structural engineering","score_opus":0.14533772964344766,"score_gpt":0.4225286146185697,"score_spread":0.27719088497512206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406624837","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062436588,0.0011856867,0.92592937,0.0031703308,0.00019234576,0.0005241413,0.0032915159,0.00055704935,0.0027129913],"genre_scores_gemma":[0.67788905,0.0014443359,0.30560133,0.0008436778,0.00021920034,0.0013671414,0.0042344835,0.00016183812,0.008238888],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9912363,0.005307704,0.0003205308,0.0014487737,0.0010403616,0.0006462531],"domain_scores_gemma":[0.97769964,0.01672082,0.0012962739,0.0013372517,0.0024712547,0.00047479864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023265745,0.0012941931,0.0023376355,0.0025494774,0.0018893292,0.0023857665,0.005401451,0.0020003049,0.004305663],"category_scores_gemma":[0.052944753,0.0010000351,0.0023445517,0.0038335938,0.0028841854,0.0015774004,0.0021296488,0.0036856616,0.00047771857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000740813,0.00018736026,0.056978572,0.00034440885,0.0011948734,0.000613177,0.001332843,0.50945234,0.0007852843,0.29491067,0.011484292,0.12197543],"study_design_scores_gemma":[0.00017897817,0.0000935552,0.013180519,0.00009356689,0.00027626092,0.000110368346,0.00017163626,0.8716123,0.00021191701,0.10823746,0.0057311477,0.000102340426],"about_ca_topic_score_codex":0.5740658,"about_ca_topic_score_gemma":0.5414002,"teacher_disagreement_score":0.5740658,"about_ca_system_score_codex":0.0066581145,"about_ca_system_score_gemma":0.013357957,"threshold_uncertainty_score":0.8568852},"labels":[],"label_agreement":null},{"id":"W4413055840","doi":"10.1177/15578666251364292","title":"Enhanced Interpretable Neural Network Approach for Unified Batch Effect Mitigation and Disease Classification Using Cross-Cohort Microbiome Profiles","year":2025,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Oral microbiology and periodontitis research","field":"Dentistry","cited_by":0,"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; University of Manitoba","funders":"","keywords":"Microbiome; Cohort; Artificial neural network; Disease; Artificial intelligence; Computer science; Machine learning; Computational biology; Biology; Mathematics; Medicine; Bioinformatics; Statistics; Internal medicine","score_opus":0.01939396327145821,"score_gpt":0.3546994212512898,"score_spread":0.3353054579798316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413055840","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13569602,0.0032439705,0.8521247,0.0019816372,0.00037016225,0.00023326077,0.001838781,0.0026804928,0.0018309313],"genre_scores_gemma":[0.82855505,0.0010429703,0.15658003,0.0011372911,0.00043551635,0.0006105906,0.0056838347,0.0002058238,0.005748975],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898595,0.00038152104,0.000073293544,0.00030848908,0.00011713515,0.00013360438],"domain_scores_gemma":[0.9980019,0.0011639998,0.00017094756,0.00013704515,0.00039612505,0.00012991729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036512255,0.0015007656,0.0016574811,0.0011183268,0.000573413,0.0013506114,0.0019913143,0.0015674267,0.0023858664],"category_scores_gemma":[0.004853019,0.0005580175,0.0019370939,0.0007191553,0.0004188847,0.00080147124,0.0015429945,0.0026516998,0.0006994642],"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":[0.0017759006,0.00095558836,0.041186646,0.00036037806,0.0012286052,0.00081911293,0.0002694275,0.5784493,0.007141757,0.0028398207,0.008858574,0.356115],"study_design_scores_gemma":[0.000017259708,0.00006695488,0.0012056264,0.000013456829,0.000042755557,0.00003485077,0.000015601638,0.99650675,0.00041813392,0.0012835264,0.00038304421,0.000011946423],"about_ca_topic_score_codex":0.012026735,"about_ca_topic_score_gemma":0.012145413,"teacher_disagreement_score":0.012026735,"about_ca_system_score_codex":0.0008963781,"about_ca_system_score_gemma":0.0015358661,"threshold_uncertainty_score":0.023913443},"labels":[],"label_agreement":null},{"id":"W4414824146","doi":"10.1177/15578666251382251","title":"Bayesian Validation of Dynamic Systems for Biological Networks","year":2025,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Gene Regulatory Network Analysis","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":"National Research Foundation of Korea","keywords":"Ode; Bayesian probability; Set (abstract data type); Process (computing); Biological data; Ordinary differential equation; Biological network; Bayesian network; Interpretation (philosophy)","score_opus":0.008340144347964068,"score_gpt":0.2789221383341564,"score_spread":0.2705819939861923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414824146","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008152194,0.00022333571,0.99009514,0.00018377928,0.00003397254,0.000050977484,0.00008061875,0.0001630626,0.0010168895],"genre_scores_gemma":[0.5409935,0.00092828064,0.45297095,0.00042853056,0.00018324205,0.00078246713,0.00115354,0.0003133908,0.0022460804],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98779154,0.0071552508,0.0005625129,0.0016077757,0.0024813863,0.00040151403],"domain_scores_gemma":[0.917613,0.06639973,0.005456846,0.0038301512,0.005989608,0.00071062514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025098769,0.0013467176,0.0016797284,0.0034295616,0.0013999109,0.0027570887,0.0027375694,0.0025477658,0.0024850457],"category_scores_gemma":[0.13221954,0.00096889085,0.0018627589,0.0013712771,0.0030047914,0.0035687536,0.0037290142,0.0034242983,0.0005704853],"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":[0.00014865116,0.00006298009,0.006097645,0.0002491526,0.00018691891,0.00014830734,0.000246841,0.775205,0.0021997562,0.16577232,0.0011081373,0.048574284],"study_design_scores_gemma":[0.0000114374525,0.000021718157,0.00054041756,0.00006167146,0.000014427635,0.00003664574,0.000014385428,0.9421936,0.0007322668,0.055523388,0.0008314253,0.00001849281],"about_ca_topic_score_codex":0.006376349,"about_ca_topic_score_gemma":0.00460569,"teacher_disagreement_score":0.025098769,"about_ca_system_score_codex":0.003301076,"about_ca_system_score_gemma":0.003709908,"threshold_uncertainty_score":0.13273656},"labels":[],"label_agreement":null},{"id":"W4414824426","doi":"10.1177/15578666251380233","title":"BCtypeFinder: A Semi-Supervised Model with Domain Adaptation for Breast Cancer Subtyping Using DNA Methylation Profiles","year":2025,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Cancer Genomics and Diagnostics","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 Cancer Research","funders":"National Institutes of Health","keywords":"Subtyping; DNA methylation; Breast cancer; Epigenetics; Robustness (evolution); Domain adaptation; Adaptation (eye)","score_opus":0.01938780498434136,"score_gpt":0.29418571315808206,"score_spread":0.2747979081737407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414824426","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06408535,0.0010799019,0.9159,0.00086479826,0.00018521033,0.00036714654,0.0041054455,0.011585122,0.001826986],"genre_scores_gemma":[0.53352636,0.0005636732,0.4429675,0.0012231263,0.00021052167,0.0009272835,0.013827084,0.0007295622,0.0060249474],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993399,0.00020518793,0.000037702473,0.00024904122,0.000111993555,0.00005623715],"domain_scores_gemma":[0.9984842,0.00082784216,0.00011418977,0.00019725012,0.00029630578,0.0000802785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002035615,0.0010460484,0.00104004,0.0009932611,0.0004696641,0.0006391293,0.0023669098,0.0013523496,0.0016558637],"category_scores_gemma":[0.0044240244,0.00053703244,0.001448825,0.00074096303,0.00039063997,0.0010100164,0.0009964971,0.002135463,0.0010274848],"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":[0.00078300794,0.0005608715,0.0126339635,0.00024128925,0.00037984858,0.00025700324,0.00016489017,0.5202711,0.0058364305,0.0024366574,0.02899641,0.4274385],"study_design_scores_gemma":[0.00001913257,0.000028028622,0.0004291558,0.000007898351,0.000010861653,0.000025495488,0.000008009905,0.9959202,0.0006943988,0.0019474952,0.00089893595,0.000010408996],"about_ca_topic_score_codex":0.012025443,"about_ca_topic_score_gemma":0.018689059,"teacher_disagreement_score":0.012025443,"about_ca_system_score_codex":0.0009315494,"about_ca_system_score_gemma":0.0017057973,"threshold_uncertainty_score":0.02391088},"labels":[],"label_agreement":null}]}