{"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052617792,0.0003075773,0.94245654,0.004111392,0.00031486287,0.00009890966,0.0000037842108,0.000024566487,0.000064591935],"genre_scores_gemma":[0.52992606,0.000004119256,0.469257,0.00038301907,0.000374469,0.0000025467843,0.000007715396,0.0000048276265,0.000040257168],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986958,0.000059347192,0.00056934793,0.00020906134,0.00024729662,0.00021913569],"domain_scores_gemma":[0.9987886,0.000096677584,0.000492767,0.00017264998,0.0003324177,0.000116892596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004715252,0.00013090404,0.00024266733,0.00014441575,0.00010730303,0.00007175099,0.0006932892,0.00007996954,0.00003303612],"category_scores_gemma":[0.000041033967,0.00009921983,0.00011014211,0.00013259106,0.000049589304,0.00055100856,0.00025000394,0.0002644923,0.00002553691],"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":[0.00022840325,0.0007452066,0.0005255258,0.000033671695,0.00023925841,0.000064633125,0.0005966515,0.50506616,0.089752354,0.03087617,0.003204897,0.36866707],"study_design_scores_gemma":[0.00084336195,0.00050203357,0.0010370465,0.000059626083,0.0000066382036,0.00024781915,0.000014678154,0.96391135,0.002147405,0.01945518,0.01161806,0.00015681284],"about_ca_topic_score_codex":0.0000065543954,"about_ca_topic_score_gemma":5.4015646e-7,"teacher_disagreement_score":0.47730827,"about_ca_system_score_codex":0.00008908433,"about_ca_system_score_gemma":0.00016787673,"threshold_uncertainty_score":0.40460673},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014610556,0.00038483448,0.983179,0.0013349879,0.00021499481,0.00010818849,0.0000044318826,0.000038391572,0.00012462011],"genre_scores_gemma":[0.46857575,0.000008267168,0.5310678,0.00015372664,0.00015452846,0.0000019457216,0.000005752173,0.000004014826,0.000028228893],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99905705,0.00007979202,0.0003892147,0.00014516688,0.00011845405,0.00021033175],"domain_scores_gemma":[0.9981361,0.0008624181,0.00025503009,0.00009395355,0.000606908,0.000045586527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041725847,0.000092533184,0.00022732353,0.00023492628,0.000085646585,0.000032471977,0.0004198639,0.00007686068,0.00000354826],"category_scores_gemma":[0.00011097865,0.00007732155,0.00012171102,0.0001957449,0.00007652138,0.00027916743,0.000082029146,0.00014885564,0.000002928373],"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":[0.00046990413,0.00050965056,0.009162922,0.000057096175,0.00019243876,0.00011796268,0.00042546817,0.24730933,0.05814374,0.52954155,0.007920188,0.14614975],"study_design_scores_gemma":[0.0025738152,0.0021923722,0.007978787,0.0000325355,0.000016393562,0.0008862617,0.000027493645,0.15678431,0.04784093,0.7584323,0.022886202,0.00034857585],"about_ca_topic_score_codex":0.000006017357,"about_ca_topic_score_gemma":0.0000010475775,"teacher_disagreement_score":0.4539652,"about_ca_system_score_codex":0.00004469529,"about_ca_system_score_gemma":0.00012594838,"threshold_uncertainty_score":0.31530815},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96118975,0.0007335985,0.036184866,0.0004445099,0.0012640945,0.000121989295,0.000020933106,0.0000032712499,0.00003701286],"genre_scores_gemma":[0.82314163,0.000036712823,0.17526698,0.00028580197,0.0009779283,0.000005457632,0.0001573992,0.000011193872,0.00011690697],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99925405,0.000048066042,0.00031449323,0.00013810137,0.00008781256,0.0001574639],"domain_scores_gemma":[0.99911076,0.00007412865,0.00024324674,0.0000892901,0.0004243072,0.000058276597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027246986,0.00010389584,0.00016929196,0.000076447875,0.000047696816,0.000013351156,0.00018675793,0.00011569517,0.000025433743],"category_scores_gemma":[0.00017959048,0.00008331066,0.0001733592,0.000039981926,0.0000745909,0.000004330892,0.000035392404,0.00013059161,0.0000033618112],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014946795,0.000051872204,0.0012445154,0.0000062225695,0.00015968093,0.0000015315053,0.000018078847,0.00088680006,0.9897747,0.00055342005,0.0019662476,0.005187452],"study_design_scores_gemma":[0.013862549,0.005505482,0.04887604,0.000020873436,0.00032688255,0.0016835359,0.000059266236,0.009848191,0.5025183,0.2009375,0.21510072,0.0012606734],"about_ca_topic_score_codex":8.695716e-7,"about_ca_topic_score_gemma":0.0000016545648,"teacher_disagreement_score":0.4872564,"about_ca_system_score_codex":0.0000067546234,"about_ca_system_score_gemma":0.00009495326,"threshold_uncertainty_score":0.339731},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94411266,0.000305975,0.053947452,0.0007768019,0.00030324492,0.00006744991,0.000009051269,0.0000024963063,0.00047485257],"genre_scores_gemma":[0.9637342,0.000047779497,0.03555801,0.00019592336,0.0003450569,0.000001904249,0.000044397446,0.000007135037,0.000065568485],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99944156,0.000036767084,0.00023537542,0.000108666114,0.00007983674,0.000097807766],"domain_scores_gemma":[0.99949706,0.000018472178,0.00008997676,0.00007048899,0.00026100292,0.00006300339],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020451898,0.00007475666,0.00010707689,0.00007157873,0.000049827326,0.00001893436,0.000098666445,0.000081322956,0.000025052603],"category_scores_gemma":[0.000040787818,0.00006363676,0.00004695557,0.00003625185,0.00008001142,0.0000069990174,0.000046846966,0.000109538516,0.0000023348364],"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":[0.00003866485,0.000093358125,0.0009902352,0.0000042617553,0.00010632048,0.000002608952,0.00005980834,0.016450502,0.9728088,0.0030595958,0.0005934553,0.005792398],"study_design_scores_gemma":[0.017308185,0.014727398,0.048210107,0.000090852904,0.00046332512,0.005738886,0.0006818285,0.121099085,0.16186874,0.3008676,0.3263506,0.0025934083],"about_ca_topic_score_codex":0.0000021006495,"about_ca_topic_score_gemma":0.000015296937,"teacher_disagreement_score":0.8109401,"about_ca_system_score_codex":0.0000055945115,"about_ca_system_score_gemma":0.000061064755,"threshold_uncertainty_score":0.2595032},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91762775,0.00028976347,0.081239276,0.000263606,0.00015336965,0.00011115288,0.000005707703,0.000004029059,0.00030533504],"genre_scores_gemma":[0.95671624,0.000033429005,0.04211914,0.00023629768,0.00053069124,0.000002828426,0.00028871573,0.000011070763,0.00006159997],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9992488,0.000072454,0.00028885234,0.00013485625,0.00012105105,0.00013399462],"domain_scores_gemma":[0.99909675,0.000008013366,0.000208923,0.00008693299,0.00051052426,0.000088861365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015382687,0.000091824,0.000129249,0.000061434264,0.000042487107,0.000023517568,0.00019478922,0.0000901136,0.00012830555],"category_scores_gemma":[0.000021830985,0.000077366145,0.000045881923,0.00008932252,0.000057133046,0.00001139404,0.000038320017,0.000067566754,0.000021209782],"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":[0.00006506685,0.00081478123,0.058596004,0.00003115837,0.0006001487,0.000007632743,0.00030831867,0.117410526,0.809311,0.0025183882,0.0031178826,0.0072191097],"study_design_scores_gemma":[0.0057856967,0.007451061,0.8848388,0.0000167488,0.00012854674,0.0021417532,0.0008099325,0.004848119,0.014782963,0.031078788,0.046851307,0.0012662527],"about_ca_topic_score_codex":0.0000026055625,"about_ca_topic_score_gemma":1.8636506e-7,"teacher_disagreement_score":0.8262428,"about_ca_system_score_codex":0.000018118797,"about_ca_system_score_gemma":0.00009400608,"threshold_uncertainty_score":0.31548998},"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":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014908315,0.9411433,0.05640703,0.000016549433,0.00016650581,0.000118707416,0.0006420411,0.0000016588502,0.000013407226],"genre_scores_gemma":[0.010887138,0.9585935,0.025789717,0.000035527693,0.00042667388,0.0000011355388,0.004239687,0.000019702868,0.000006906569],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983902,0.00020230675,0.0008596272,0.0002976815,0.00012484734,0.0001253477],"domain_scores_gemma":[0.9977422,0.00023395712,0.0013903611,0.0002973562,0.00024633674,0.0000898259],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003513941,0.00020560874,0.00069220626,0.00014468563,0.000027139502,0.00001023309,0.0005067166,0.0003513429,0.000026041324],"category_scores_gemma":[0.00022555426,0.00016331955,0.00013882155,0.00007426477,0.00013922664,0.000009568065,0.00030842263,0.00017765455,0.0000014653351],"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":[0.00012533167,0.00011580338,0.00026252263,0.0015942021,0.0005702675,0.000020828587,0.000024483506,0.00025006878,0.059439287,0.00008415421,0.0013724499,0.9361406],"study_design_scores_gemma":[0.00052825833,0.0002843482,0.00025987826,0.0032401748,0.00035070154,0.00027086356,0.0000062898393,0.00017205409,0.0018655404,0.0032521926,0.98940945,0.0003602561],"about_ca_topic_score_codex":0.0000053880276,"about_ca_topic_score_gemma":0.0000018303404,"teacher_disagreement_score":0.988037,"about_ca_system_score_codex":0.000025650506,"about_ca_system_score_gemma":0.0004978353,"threshold_uncertainty_score":0.6659978},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92474455,0.0005542426,0.07425379,0.00021236972,0.000069018606,0.000060356062,0.0000031487432,0.0000010731824,0.000101465295],"genre_scores_gemma":[0.9802208,0.000030013358,0.019509977,0.00008198134,0.00012506625,0.0000013832406,0.000004392775,0.000003958669,0.00002243936],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994024,0.00011076903,0.00025552866,0.00008250898,0.000076215,0.000072559895],"domain_scores_gemma":[0.9994142,0.000097776596,0.00027584875,0.000044321252,0.00013127642,0.000036555906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034271434,0.000061144594,0.00013968564,0.00003977092,0.000024980374,0.0000048649154,0.00008542791,0.000067075656,0.000007705975],"category_scores_gemma":[0.00019560117,0.000047600897,0.000045434575,0.00002201289,0.00006401798,0.0000022799918,0.00002656136,0.000032491364,5.5385476e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000069828435,0.000018775114,0.00035230484,0.0000110715155,0.000045691537,0.0000014541905,0.000018141895,0.0038775755,0.972906,0.0041029276,0.000013927349,0.018582294],"study_design_scores_gemma":[0.00067676115,0.0026592233,0.00039796496,0.000058236215,0.000021276623,0.00021495475,0.000043502576,0.0012575282,0.90510124,0.0789139,0.010507064,0.00014838009],"about_ca_topic_score_codex":0.000001781259,"about_ca_topic_score_gemma":4.4766443e-7,"teacher_disagreement_score":0.07481097,"about_ca_system_score_codex":0.0000040510436,"about_ca_system_score_gemma":0.00003890578,"threshold_uncertainty_score":0.19411083},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9583756,0.002817241,0.038370095,0.00007639198,0.00021526766,0.00006835399,0.000028944267,6.5742086e-7,0.00004748914],"genre_scores_gemma":[0.9705224,0.00050049124,0.02853137,0.00012800832,0.00027736623,0.0000027427354,0.000021174228,0.000006829519,0.000009597617],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99933606,0.000027849463,0.00035670234,0.00010130977,0.00006027262,0.00011783011],"domain_scores_gemma":[0.9991789,0.000053462867,0.00029709993,0.00005242983,0.00038159324,0.000036524743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012629086,0.00008577471,0.00020690101,0.00005377026,0.000058376198,0.0000021048877,0.00011370877,0.00006953749,0.000001947448],"category_scores_gemma":[0.00004742272,0.000073625226,0.00013032464,0.000040172334,0.00012579167,9.737457e-7,0.000027316115,0.000038642826,3.2693924e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022905876,0.00005166843,0.036519542,0.000010387301,0.00026623558,0.0000019446913,0.000061514686,0.032809075,0.9273959,0.00025977058,0.0003606909,0.0020342101],"study_design_scores_gemma":[0.007984595,0.007864418,0.6242277,0.000036798643,0.00014709754,0.0010566898,0.00023514574,0.0017924494,0.26097134,0.02337565,0.07156534,0.0007427912],"about_ca_topic_score_codex":0.000003968214,"about_ca_topic_score_gemma":0.0000018127153,"teacher_disagreement_score":0.6664246,"about_ca_system_score_codex":0.0000062515965,"about_ca_system_score_gemma":0.00017753178,"threshold_uncertainty_score":0.30023497},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85506666,0.00004515661,0.14348167,0.0006724023,0.0005050653,0.00009115334,0.000040659972,0.0000035235707,0.00009369328],"genre_scores_gemma":[0.60504895,0.000012426838,0.39224657,0.00066038367,0.0015178772,0.0000068811883,0.0002474117,0.000014130438,0.00024534157],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920934,0.000075812764,0.000352121,0.0001402832,0.00007126875,0.0001511891],"domain_scores_gemma":[0.9989053,0.00016641474,0.00034091875,0.00007838467,0.0004502822,0.000058719554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044906366,0.00009733761,0.00018565675,0.00006116318,0.00008773435,0.000009363935,0.00013570958,0.00019859457,0.000026233418],"category_scores_gemma":[0.00036909082,0.00008195213,0.0001313064,0.000039292467,0.00008224831,0.0000033542792,0.000023996145,0.00013132808,0.000014237009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060488307,0.000636379,0.023650879,0.000017013705,0.0005367366,0.0000084897265,0.00014162197,0.052144665,0.41067165,0.0024589174,0.022795932,0.48633283],"study_design_scores_gemma":[0.005060863,0.009846615,0.12813383,0.000016659347,0.00012955042,0.0006003149,0.000027600327,0.64083004,0.008487645,0.04193702,0.16421919,0.0007106521],"about_ca_topic_score_codex":0.0000017759434,"about_ca_topic_score_gemma":0.0000030534845,"teacher_disagreement_score":0.5886854,"about_ca_system_score_codex":0.0000094933375,"about_ca_system_score_gemma":0.00015073,"threshold_uncertainty_score":0.33419108},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65316004,0.00018914243,0.34643874,0.00007672085,0.000017634864,0.000086713146,0.000005355294,0.00000116197,0.000024528788],"genre_scores_gemma":[0.96612364,0.000018130077,0.03361306,0.000112628295,0.000085164895,0.0000025330235,0.000032439202,0.000006405345,0.000006011462],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99935347,0.000033468856,0.000270069,0.00014640202,0.00007505384,0.00012155909],"domain_scores_gemma":[0.99947554,0.000022174183,0.00015708063,0.000104245795,0.0001595438,0.00008139753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031214269,0.0000800196,0.0001461986,0.00023624358,0.000019299663,0.000007542561,0.00012719823,0.00006756377,5.3826955e-7],"category_scores_gemma":[0.00002521559,0.00006827416,0.000025168343,0.00013457562,0.000040072962,0.0000046056684,0.000055214772,0.00007301179,5.6728055e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001510869,0.0004222785,0.3321772,0.000030007921,0.00014647997,0.000009286768,0.00016039073,0.14476936,0.4498997,0.003987265,0.000025744353,0.06686143],"study_design_scores_gemma":[0.0017331904,0.0034336064,0.936772,0.000020680722,0.000022166683,0.00015455285,0.000063924635,0.033138614,0.0035736237,0.020804813,0.00009826529,0.00018455074],"about_ca_topic_score_codex":0.000006828384,"about_ca_topic_score_gemma":0.000045280765,"teacher_disagreement_score":0.6045948,"about_ca_system_score_codex":0.000046582318,"about_ca_system_score_gemma":0.000060044913,"threshold_uncertainty_score":0.27841395},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9972715,0.0010734692,0.0003272031,0.0009911257,0.00003984415,0.00015002095,0.0000098968485,0.0000013600381,0.00013561962],"genre_scores_gemma":[0.9996558,0.00002902748,0.00008250041,0.0001014453,0.00010176759,6.285057e-7,0.0000043647838,0.0000025096479,0.000021964814],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99910176,0.00009182907,0.0004646932,0.0000713987,0.00020314408,0.00006715791],"domain_scores_gemma":[0.9989909,0.00009345458,0.0002963601,0.000090548594,0.00048544692,0.000043272827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003055209,0.00004587929,0.00021636707,0.00012474119,0.00004793886,0.0000042076426,0.00009819038,0.000029915842,0.000058605918],"category_scores_gemma":[0.00004380374,0.00002900292,0.00008059912,0.00015188158,0.00012853168,0.000024343795,0.00002191094,0.0001256984,8.5788116e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064968143,0.0012691815,0.19947052,0.000058021098,0.00027022147,0.000012372234,0.0015585867,0.00059599255,0.77637863,0.0064822487,0.0003090669,0.012945463],"study_design_scores_gemma":[0.0010463333,0.0011905658,0.98519003,0.0000072996986,0.000037497364,0.00005978884,0.00016109724,0.000023835171,0.0010406645,0.01075338,0.00046594738,0.000023558772],"about_ca_topic_score_codex":0.000006846537,"about_ca_topic_score_gemma":0.0000033201165,"teacher_disagreement_score":0.7857195,"about_ca_system_score_codex":0.000030860363,"about_ca_system_score_gemma":0.00008924047,"threshold_uncertainty_score":0.11827047},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29598698,0.0016255176,0.701723,0.00011944647,0.00030995085,0.000046596266,0.0000016328702,0.00000484462,0.00018207794],"genre_scores_gemma":[0.9833164,0.00005116143,0.013085746,0.0006548557,0.0027121033,0.0000021569385,0.00011858446,0.000022573988,0.000036416423],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985107,0.00024341994,0.00054528215,0.00023243492,0.00015868121,0.00030948984],"domain_scores_gemma":[0.9986997,0.0000963507,0.00049378996,0.00018588905,0.00037051973,0.00015372247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005841464,0.0001827304,0.00034546695,0.0000861677,0.00011375792,0.000019110665,0.00028505217,0.00020336996,0.00002435656],"category_scores_gemma":[0.00006082035,0.00016385238,0.00025156475,0.00013769337,0.000113909606,0.000006553821,0.00008712633,0.00016650664,0.000010186938],"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":[0.00009986282,0.000032736032,0.0004149068,0.0000018308656,0.00026868275,0.0000022997888,0.0000069732346,0.98927116,0.0013112135,0.002488885,0.0015776097,0.004523823],"study_design_scores_gemma":[0.0012701071,0.0016176113,0.0019279767,0.00002312063,0.00017899871,0.00066271937,0.000013185168,0.8885444,0.00037708867,0.10092034,0.004068913,0.0003955441],"about_ca_topic_score_codex":0.0000028281906,"about_ca_topic_score_gemma":0.000004348684,"teacher_disagreement_score":0.6886372,"about_ca_system_score_codex":0.000026499007,"about_ca_system_score_gemma":0.00015318992,"threshold_uncertainty_score":0.6681706},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98837477,0.0007241784,0.010231974,0.0002433068,0.00020968549,0.00006297983,0.000009302792,0.000001331664,0.00014246655],"genre_scores_gemma":[0.9584823,0.00009759676,0.0410589,0.00009244372,0.00022259953,6.014404e-7,0.000033609325,0.000003848689,0.000008092105],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.999254,0.000051239273,0.00039550356,0.00010995234,0.00006926238,0.00012003431],"domain_scores_gemma":[0.99930197,0.000009612465,0.00029311707,0.00005983398,0.00030052112,0.000034924535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019738782,0.00008146135,0.00018102731,0.00011866921,0.000012763062,0.0000038811054,0.00011500907,0.00009942498,0.000015241367],"category_scores_gemma":[0.000044106488,0.00007224155,0.00008267276,0.000120497025,0.000058498266,0.000005272628,0.000014502268,0.00007693549,6.7678735e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013613388,0.00008910321,0.0070012235,0.000003913435,0.00006129243,0.0000031091542,0.000027952046,0.004973472,0.9355038,0.00012844313,0.000038348495,0.052033205],"study_design_scores_gemma":[0.0049862945,0.005520465,0.7380364,0.000038204624,0.000047564754,0.0011298796,0.00010167154,0.002790686,0.20868069,0.03697941,0.0012738152,0.00041492272],"about_ca_topic_score_codex":0.0000042732736,"about_ca_topic_score_gemma":0.0000028696834,"teacher_disagreement_score":0.7310352,"about_ca_system_score_codex":0.00001770962,"about_ca_system_score_gemma":0.00014908494,"threshold_uncertainty_score":0.2945925},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9590855,0.0013759052,0.038921542,0.00008657482,0.00030267387,0.000096131436,0.00007609636,0.0000061595842,0.000049368595],"genre_scores_gemma":[0.97337353,0.0000134071815,0.025670793,0.00017934741,0.0005227963,0.000005660438,0.00020930072,0.000014561369,0.000010630194],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99893695,0.00013135425,0.0003990562,0.00014769123,0.00012614463,0.0002588267],"domain_scores_gemma":[0.99912316,0.00006290959,0.0004297332,0.000076816585,0.00017254626,0.00013485772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019743743,0.00014960658,0.00020933528,0.000053241114,0.00006424153,0.000020798596,0.00016727796,0.0001727905,0.000043212647],"category_scores_gemma":[0.000163793,0.00012469314,0.00008683882,0.00006118671,0.00019538455,0.000015441281,0.00004713378,0.00019141374,0.0000036016997],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011840968,0.00007361324,0.0452836,0.0000065943805,0.00017970595,0.0000021419805,0.00007738057,0.00021639219,0.93131745,0.00027387947,0.0005453528,0.021905497],"study_design_scores_gemma":[0.001900108,0.00085083226,0.007613617,0.00007186932,0.00004369608,0.0003114188,0.0001631439,0.000095545896,0.9105678,0.004984905,0.072864756,0.0005322895],"about_ca_topic_score_codex":0.0000018048396,"about_ca_topic_score_gemma":5.154899e-7,"teacher_disagreement_score":0.0723194,"about_ca_system_score_codex":0.000025608962,"about_ca_system_score_gemma":0.00010872005,"threshold_uncertainty_score":0.5084839},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94068027,0.0005841426,0.057552,0.00013675822,0.00025816253,0.000069853515,0.000021976473,0.0000021154638,0.0006947365],"genre_scores_gemma":[0.93942994,0.000024359975,0.060207106,0.0001800276,0.00009194117,9.4022096e-7,0.00004367952,0.0000060859084,0.000015912814],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99926615,0.00007505051,0.00037199704,0.000094433206,0.00008993775,0.000102427344],"domain_scores_gemma":[0.9990833,0.000026065809,0.00037341236,0.00008097569,0.00038741253,0.00004887621],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022036464,0.000077295095,0.00016282486,0.00009499729,0.000019870173,0.000002136541,0.00015828795,0.000079482525,0.00004751432],"category_scores_gemma":[0.000045487366,0.000065874156,0.000115907555,0.00005704139,0.00014929232,0.0000025411478,0.000027277458,0.00005574075,0.0000031590394],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057605223,0.00034430609,0.03332343,0.000042968753,0.0005377076,0.000025906484,0.00018939588,0.010355005,0.94495225,0.0012494572,0.0007044163,0.007699079],"study_design_scores_gemma":[0.010540867,0.013056826,0.12294905,0.00010762145,0.00031512408,0.0012472187,0.0003310099,0.0047237906,0.7873536,0.04432608,0.01400928,0.0010395534],"about_ca_topic_score_codex":0.0000041029853,"about_ca_topic_score_gemma":9.4724186e-7,"teacher_disagreement_score":0.15759869,"about_ca_system_score_codex":0.000010777875,"about_ca_system_score_gemma":0.00021632787,"threshold_uncertainty_score":0.26862702},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54923207,0.002001076,0.4424839,0.0057687885,0.00026401298,0.000070053364,0.000030419062,0.0000018049083,0.00014785286],"genre_scores_gemma":[0.9958064,0.00022684364,0.0030960834,0.00049884606,0.0002473527,0.0000021098826,0.00006936116,0.0000041679223,0.0000488435],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9990785,0.00019666125,0.00040555277,0.00009552956,0.00013266706,0.000091075504],"domain_scores_gemma":[0.9990022,0.00015334469,0.00036114833,0.000121321944,0.00032740174,0.00003453622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034595735,0.00006725915,0.00013789171,0.00007684717,0.00009073144,0.000015894548,0.00020635166,0.00006489211,0.0000347148],"category_scores_gemma":[0.00005103058,0.0000365031,0.000120945704,0.00013350855,0.00014848955,0.0000032181858,0.00003897088,0.00006888269,0.0000014486583],"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":[0.001095263,0.0001760452,0.0044474155,0.000008417168,0.0019526858,0.0000010890266,0.0001329229,0.36126375,0.45391715,0.013086539,0.0063833282,0.15753542],"study_design_scores_gemma":[0.0029264558,0.0019456777,0.47882986,0.000026854861,0.0013082683,0.00015097365,0.0007380675,0.060698573,0.043718267,0.0352324,0.37392282,0.0005017953],"about_ca_topic_score_codex":0.0000029145344,"about_ca_topic_score_gemma":0.000027055668,"teacher_disagreement_score":0.47438243,"about_ca_system_score_codex":0.0000133531385,"about_ca_system_score_gemma":0.0001224693,"threshold_uncertainty_score":0.14885533},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98113126,0.0026721451,0.01584949,0.00010211427,0.00009487909,0.00006888216,0.000007912865,0.0000010178618,0.00007227959],"genre_scores_gemma":[0.9871043,0.00022871843,0.012475056,0.000046492587,0.000114068534,5.6339695e-7,0.000020513084,0.0000055638466,0.0000047512744],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99919844,0.000058063764,0.00043757132,0.00009995618,0.000081123515,0.00012482081],"domain_scores_gemma":[0.9994005,0.0000901091,0.00025438674,0.000048167803,0.00015941469,0.000047450372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005369991,0.00007889596,0.00020120712,0.00016980535,0.000015342062,0.000003600258,0.00008569458,0.00008165829,0.000007752572],"category_scores_gemma":[0.00005128777,0.00006655728,0.00007109155,0.00006768599,0.00011079118,0.0000033723427,0.00003962956,0.000068751746,5.56735e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011448954,0.00028886448,0.20693117,0.000043243337,0.00029841563,0.00004394088,0.00032154477,0.0066826907,0.74003047,0.0006150761,0.00006268951,0.043537017],"study_design_scores_gemma":[0.012272569,0.0022098848,0.91014415,0.000052559284,0.000051918487,0.0007618088,0.00035100593,0.00067275105,0.051240165,0.019390408,0.0025079171,0.0003448386],"about_ca_topic_score_codex":0.0000048483926,"about_ca_topic_score_gemma":0.0000117755935,"teacher_disagreement_score":0.70321304,"about_ca_system_score_codex":0.000008517145,"about_ca_system_score_gemma":0.000047728812,"threshold_uncertainty_score":0.2714127},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37707964,0.00015254115,0.6222828,0.00009219218,0.00016742354,0.0001562811,0.000045598663,0.000001750208,0.000021758888],"genre_scores_gemma":[0.6818668,0.0000032576463,0.3173233,0.00025823718,0.0004021081,0.0000026152213,0.00011084335,0.000007207928,0.000025610889],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992359,0.000033977747,0.0003562666,0.00012155751,0.00008955343,0.00016272151],"domain_scores_gemma":[0.99926627,0.00003506567,0.00029914727,0.00006930362,0.0002669813,0.000063218955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002928903,0.00010118261,0.00016672313,0.000063057145,0.00004082287,0.0000088327215,0.00013472729,0.0001474631,0.000007048202],"category_scores_gemma":[0.00006639237,0.00007976041,0.00011771369,0.000042322798,0.000058557143,0.0000029870514,0.0000286944,0.000077304685,3.5816308e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048818017,0.00004043767,0.00016400634,0.000010368046,0.00019260895,0.000006362788,0.000020483862,0.0012764728,0.88721555,0.0021420969,0.00037738922,0.10806604],"study_design_scores_gemma":[0.008184443,0.0071288985,0.0037828332,0.000044198743,0.00009644309,0.0012400884,0.000080900645,0.005918882,0.4709522,0.3926088,0.1092535,0.00070879905],"about_ca_topic_score_codex":7.965432e-7,"about_ca_topic_score_gemma":0.0000015509098,"teacher_disagreement_score":0.41626334,"about_ca_system_score_codex":0.000017296648,"about_ca_system_score_gemma":0.00009782866,"threshold_uncertainty_score":0.32525352},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87359464,0.0029361031,0.12263509,0.000096629454,0.000612178,0.000034850593,0.000001646276,0.000004055781,0.00008482472],"genre_scores_gemma":[0.9920356,0.00036497953,0.006391904,0.00008707012,0.0010596189,3.8664567e-7,0.000026676891,0.000007128303,0.000026591708],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99925154,0.00007332698,0.00035649166,0.000120668185,0.00005755672,0.00014041572],"domain_scores_gemma":[0.99955076,0.000013488636,0.00018005786,0.000060924478,0.00015806667,0.000036728485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002471764,0.00009356246,0.00019818153,0.00011069229,0.000039284198,0.000007315482,0.00010979085,0.00009980823,0.0000048298093],"category_scores_gemma":[0.00005185306,0.00008022163,0.00007626345,0.00009631311,0.000066988636,0.000006260671,0.000027983711,0.00014503166,0.0000019796742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008613853,0.000073571,0.00579327,0.0000055426926,0.00007880182,0.000011029786,0.00009720788,0.7529543,0.2351161,0.0011905964,0.0007371737,0.0038562883],"study_design_scores_gemma":[0.009719159,0.0032976884,0.6168624,0.00018458901,0.00014346487,0.010949184,0.0006961875,0.041159526,0.09225098,0.009364303,0.21338607,0.0019864351],"about_ca_topic_score_codex":0.000006252876,"about_ca_topic_score_gemma":0.0000040871864,"teacher_disagreement_score":0.71179473,"about_ca_system_score_codex":0.000006956314,"about_ca_system_score_gemma":0.000109756715,"threshold_uncertainty_score":0.3271343},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.244661,0.0018828692,0.7529675,0.000095841315,0.0002243148,0.00008694361,0.000014058616,0.0000011432235,0.00006637721],"genre_scores_gemma":[0.90878403,0.0000979187,0.08998421,0.00024080597,0.000810155,0.0000052456376,0.000051171974,0.0000107374935,0.000015721813],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9993366,0.00003900694,0.0002523559,0.00009987573,0.00006106165,0.00021112536],"domain_scores_gemma":[0.9991483,0.00010761669,0.00023551387,0.00006727372,0.000362732,0.00007855577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000208982,0.000109568646,0.00018455219,0.0000381589,0.000060965445,0.000007558276,0.0001199064,0.00008693585,0.0000061827313],"category_scores_gemma":[0.000033477005,0.00008145495,0.00008108831,0.0000402387,0.00007239446,0.0000018158262,0.000044042692,0.000065000066,0.0000013141655],"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":[0.0012668556,0.000685074,0.19918898,0.000034076107,0.0025293946,0.000005564945,0.00025270466,0.21610382,0.10620765,0.0022144706,0.006000476,0.46551093],"study_design_scores_gemma":[0.011801299,0.018697504,0.5447442,0.00006247495,0.0005441116,0.0012921428,0.00021312348,0.06579692,0.015559571,0.06381321,0.27551606,0.0019593763],"about_ca_topic_score_codex":0.0000018831412,"about_ca_topic_score_gemma":0.0000048052348,"teacher_disagreement_score":0.66412306,"about_ca_system_score_codex":0.000008895757,"about_ca_system_score_gemma":0.00007080546,"threshold_uncertainty_score":0.33216363},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96100163,0.00053470244,0.037937906,0.00020681054,0.0001744232,0.000036086167,0.0000028249058,9.498089e-7,0.00010464681],"genre_scores_gemma":[0.99526125,0.0000121775975,0.0039876048,0.00015623811,0.00054432824,3.2352355e-7,0.0000073089627,0.000006642533,0.000024127345],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99914587,0.00008197987,0.0003904019,0.000107133164,0.00013367065,0.00014095604],"domain_scores_gemma":[0.9990015,0.00006683908,0.0004211648,0.00013348214,0.00032683794,0.00005014333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029781167,0.00008385516,0.00020346403,0.000071998395,0.00003649668,0.0000027596707,0.00024623537,0.000085117375,0.000009229176],"category_scores_gemma":[0.000055558747,0.000056884608,0.00025686764,0.00016755813,0.00014419995,0.0000015951542,0.000068386835,0.000089434005,0.0000015064611],"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":[0.00023604435,0.00024414234,0.09952688,0.000011743749,0.00063664425,0.0000070205338,0.00009079949,0.1373328,0.7458142,0.00156199,0.0015225582,0.013015201],"study_design_scores_gemma":[0.001727808,0.0016673162,0.787955,0.000023994491,0.0002623691,0.00069853885,0.000100849065,0.0038667878,0.16157252,0.028429639,0.013368852,0.0003263378],"about_ca_topic_score_codex":0.0000024061615,"about_ca_topic_score_gemma":0.000010518271,"teacher_disagreement_score":0.6884281,"about_ca_system_score_codex":0.000012429999,"about_ca_system_score_gemma":0.0001286601,"threshold_uncertainty_score":0.2319687},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60682386,0.00065907347,0.39232773,0.000095471085,0.000044806573,0.000027419424,0.000001929486,6.856851e-7,0.000019039368],"genre_scores_gemma":[0.9800603,0.00008421453,0.019650582,0.000109566005,0.000062673345,0.0000013293958,0.000018413355,0.000003534499,0.000009394572],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99943423,0.000063289015,0.00027851926,0.00009650904,0.00006556166,0.00006187643],"domain_scores_gemma":[0.9994272,0.000017473261,0.00031052314,0.00005684547,0.0001481033,0.00003987852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015893487,0.000057771646,0.0001458949,0.00016337102,0.000024724648,0.000005069223,0.00008121879,0.00006566204,0.000008378267],"category_scores_gemma":[0.000025003523,0.000048847793,0.000068790716,0.000112074085,0.00005386208,0.000003086714,0.000025677095,0.000040760035,4.309135e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000118638774,0.000038058875,0.003909488,0.000002237032,0.00033186047,5.5100764e-7,0.000055474346,0.10486997,0.88917416,0.00029512218,0.000035682613,0.0011687574],"study_design_scores_gemma":[0.0043177656,0.0017089676,0.19934157,0.00003100364,0.00041342454,0.00010951202,0.00025763028,0.0015725933,0.77044916,0.019918522,0.0015832747,0.00029656797],"about_ca_topic_score_codex":0.0000025988936,"about_ca_topic_score_gemma":4.2724415e-7,"teacher_disagreement_score":0.37323645,"about_ca_system_score_codex":0.0000144206715,"about_ca_system_score_gemma":0.0001177628,"threshold_uncertainty_score":0.19919552},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9310924,0.0008320587,0.06668175,0.00042679854,0.00039607854,0.0000680805,0.000020511177,0.0000042204874,0.00047811156],"genre_scores_gemma":[0.9881085,0.00013192926,0.010771006,0.00010362162,0.000719953,0.0000014235325,0.00007391807,0.000008596531,0.00008105474],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991693,0.00014488593,0.0003217807,0.00013552712,0.00010810913,0.00012041473],"domain_scores_gemma":[0.999411,0.000054044078,0.00020798453,0.000056728953,0.0002224538,0.000047787125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003250316,0.000091148664,0.00014027883,0.000097884185,0.00006667505,0.000019439514,0.00007276082,0.000121953766,0.000026573949],"category_scores_gemma":[0.00004340995,0.0000782165,0.00007054514,0.00004547011,0.000059366695,0.000010292399,0.000031474636,0.000104049366,0.0000038917265],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019865498,0.00004742823,0.0012250596,0.0000065823865,0.000054613607,0.0000070049036,0.000013535168,0.0046208957,0.9822676,0.00077028613,0.0014470944,0.0093412055],"study_design_scores_gemma":[0.0012220303,0.0015907476,0.015715757,0.00003726967,0.000032114516,0.00085287244,0.000058869853,0.0020414488,0.9317905,0.024448052,0.022004629,0.00020576039],"about_ca_topic_score_codex":0.000009796647,"about_ca_topic_score_gemma":0.0000010664317,"teacher_disagreement_score":0.05701611,"about_ca_system_score_codex":0.000014017539,"about_ca_system_score_gemma":0.00006314056,"threshold_uncertainty_score":0.31895763},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7962727,0.00024569768,0.20306063,0.000117799274,0.00021281249,0.000027924076,0.00002189491,0.000001369269,0.000039184404],"genre_scores_gemma":[0.9877459,0.0000952403,0.011685111,0.00009959921,0.0002464429,0.0000015582945,0.000056097488,0.0000069665775,0.00006310479],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992782,0.00006565673,0.00034486898,0.00011219062,0.000114918985,0.000084169136],"domain_scores_gemma":[0.99917173,0.000021854099,0.00037501278,0.00009205018,0.0002950733,0.000044255612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000095435425,0.0000753895,0.0001457645,0.0000762304,0.00004159871,0.0000028188051,0.00013469432,0.00008235397,0.000033140925],"category_scores_gemma":[0.000041557094,0.000059707563,0.00007223423,0.00005526114,0.000049257975,0.000006028861,0.00003474343,0.00006432397,0.0000012117827],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007030526,0.00005126873,0.010605368,0.000005704963,0.000028852755,0.0000020066589,0.000048013182,0.011331969,0.976606,0.00014802768,0.00044000315,0.0006624877],"study_design_scores_gemma":[0.000868946,0.00037042395,0.1355465,0.000025759562,0.000007788231,0.00015100648,0.00004699054,0.0000662997,0.85784256,0.0008244583,0.0041477783,0.00010147296],"about_ca_topic_score_codex":0.0000030307224,"about_ca_topic_score_gemma":4.8055983e-7,"teacher_disagreement_score":0.19147319,"about_ca_system_score_codex":0.000009274104,"about_ca_system_score_gemma":0.00013257339,"threshold_uncertainty_score":0.24348038},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86401093,0.0010976593,0.13452677,0.000089873494,0.00014369417,0.000042200074,0.000028513428,0.0000024968258,0.00005786122],"genre_scores_gemma":[0.9832388,0.00010322769,0.016117018,0.00012983292,0.0003297249,6.161103e-7,0.000052038624,0.000010840158,0.000017858996],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992625,0.00008346023,0.00033378557,0.00012119997,0.00006208325,0.00013694647],"domain_scores_gemma":[0.9990959,0.000050646962,0.00047301123,0.00006968582,0.0002505154,0.000060232014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031691775,0.00010539926,0.00019414272,0.00007898531,0.00007665558,0.000010528279,0.000114474366,0.00015400317,0.0000058430005],"category_scores_gemma":[0.000038852497,0.000089688096,0.00009166188,0.000047467915,0.00005702287,0.000006269819,0.000059008813,0.000088696615,7.6098263e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000080131394,0.000097513905,0.8620904,0.0000338655,0.0009800979,0.0000069196653,0.00057357113,0.0033078417,0.12773399,0.00080079795,0.00040361544,0.00389123],"study_design_scores_gemma":[0.0019251427,0.0010073661,0.9127742,0.000077894074,0.0001301393,0.0006349607,0.000489228,0.008036703,0.010466449,0.058036808,0.0057680523,0.0006530522],"about_ca_topic_score_codex":0.0000045177107,"about_ca_topic_score_gemma":0.0000024586182,"teacher_disagreement_score":0.119227916,"about_ca_system_score_codex":0.000036660163,"about_ca_system_score_gemma":0.00009276751,"threshold_uncertainty_score":0.36573744},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18037383,0.00012212497,0.81766576,0.0004561911,0.0005722846,0.000018026685,7.9070475e-7,0.000019632727,0.0007713768],"genre_scores_gemma":[0.66092795,0.00000399012,0.33871895,0.00015979397,0.00015985906,2.658006e-7,0.0000010224288,0.000002602656,0.000025602223],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920744,0.00010609537,0.00030082025,0.0001107483,0.00013248771,0.0001424281],"domain_scores_gemma":[0.9991887,0.00017869506,0.00029968235,0.000075404714,0.00018690352,0.00007058771],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037652743,0.00007528596,0.00015304725,0.00017364549,0.00007502363,0.000037107475,0.0005052147,0.000044365966,0.000050529594],"category_scores_gemma":[0.000071682945,0.000058150115,0.000082482235,0.00014233479,0.0000506641,0.0002132991,0.00008217172,0.00022010758,0.000030744493],"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":[0.00011753001,0.00034333422,0.06019208,0.000017291231,0.00027486638,0.00027216732,0.0049775396,0.104357876,0.00072756596,0.5841779,0.0025757097,0.2419661],"study_design_scores_gemma":[0.0017110156,0.0026314857,0.24842663,0.00006659819,0.000022354729,0.0022710992,0.000052397456,0.42903867,0.0005952684,0.3091609,0.0055747125,0.00044888692],"about_ca_topic_score_codex":0.000009413973,"about_ca_topic_score_gemma":1.9998822e-7,"teacher_disagreement_score":0.48055407,"about_ca_system_score_codex":0.000014001615,"about_ca_system_score_gemma":0.000102783175,"threshold_uncertainty_score":0.23712929},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82091516,0.0000630933,0.17830993,0.00010503961,0.0003471062,0.00012528781,0.0000030258173,0.0000016412164,0.00012968882],"genre_scores_gemma":[0.9966589,0.000007173088,0.0028604388,0.00006485695,0.000334682,0.000003906227,0.00003228053,0.000006950271,0.00003076935],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990752,0.0000592271,0.0005647589,0.00009904119,0.00007765073,0.00012417098],"domain_scores_gemma":[0.9991083,0.000027335278,0.0005349015,0.000095071,0.00019017285,0.000044176853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032679187,0.00009279021,0.0001718962,0.00011210129,0.000023175193,0.000009792966,0.00013731064,0.00020517454,0.000014417238],"category_scores_gemma":[0.0000666419,0.00007978671,0.00009268056,0.00008551799,0.000077384655,0.000009990964,0.000050394814,0.00032685965,0.0000012811375],"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":[0.00043863966,0.00007839333,0.0014244711,0.000011290225,0.000059337977,0.0000021480644,0.000018773044,0.042885337,0.93361646,0.0004916507,0.00009462267,0.02087887],"study_design_scores_gemma":[0.009486188,0.0064406698,0.07619398,0.0003635619,0.0000671431,0.0009635679,0.000150695,0.40589553,0.3927934,0.082133606,0.024470383,0.0010412745],"about_ca_topic_score_codex":0.000011895615,"about_ca_topic_score_gemma":0.00007423488,"teacher_disagreement_score":0.5408231,"about_ca_system_score_codex":0.00001283128,"about_ca_system_score_gemma":0.00006225999,"threshold_uncertainty_score":0.32536077},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99526864,0.0013349677,0.0011595191,0.0019225065,0.00008918,0.000051169874,0.000040249975,0.000003474149,0.00013027288],"genre_scores_gemma":[0.99838716,0.000023623132,0.0013393698,0.000058798494,0.00013334586,0.0000013201463,0.00005013028,4.3251595e-7,0.000005809749],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9989131,0.00009675864,0.0005534338,0.000101609214,0.0002010979,0.00013400825],"domain_scores_gemma":[0.9985318,0.00064877566,0.00038009902,0.000023439863,0.0003695577,0.000046307945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030455342,0.00007646674,0.00020583226,0.000055748875,0.00012583037,0.000022893833,0.00019076657,0.00006192658,0.000055961485],"category_scores_gemma":[0.0000611123,0.000029238905,0.0001863162,0.00070019683,0.00012225957,0.00006108565,0.000030654213,0.000098626006,0.00000535149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016457113,0.0002701883,0.09689698,0.0000016681065,0.0003491712,0.0000041283506,0.00022415392,0.7571435,0.01256235,0.11342175,0.0000073105634,0.018954223],"study_design_scores_gemma":[0.00034835096,0.0002123094,0.6231824,0.000005497179,0.00003477785,0.000017688923,0.000101714526,0.002162362,0.00013894659,0.37229198,0.0014504496,0.000053510706],"about_ca_topic_score_codex":0.000074166375,"about_ca_topic_score_gemma":0.0003534751,"teacher_disagreement_score":0.75498116,"about_ca_system_score_codex":0.000056350986,"about_ca_system_score_gemma":0.000082384475,"threshold_uncertainty_score":0.119232796},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8918534,0.001001917,0.10212451,0.004678157,0.00016613195,0.000055890938,0.000004343385,0.00000442644,0.00011122147],"genre_scores_gemma":[0.9840327,0.000044911627,0.013616773,0.0013533533,0.000823672,7.559965e-7,0.000037465303,0.0000050833223,0.000085293104],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991299,0.000110110836,0.00029361137,0.00017638429,0.000106996755,0.00018301049],"domain_scores_gemma":[0.9991841,0.00003262989,0.00021676,0.000111809,0.00032208537,0.00013262648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024126479,0.00011890902,0.00023517097,0.000110655674,0.00004647966,0.000021535672,0.00022770427,0.00014678286,0.000014598947],"category_scores_gemma":[0.00013032554,0.00009176267,0.00018785917,0.00014081804,0.0000518706,0.0000033088138,0.00003912904,0.00009179422,0.000006104042],"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":[0.0005608269,0.00033361808,0.018903876,0.000005373292,0.00066400476,0.000041688952,0.000054152613,0.16927595,0.6862335,0.0043897526,0.031703413,0.0878338],"study_design_scores_gemma":[0.0043333326,0.020530479,0.27102512,0.00005763143,0.0002305407,0.0022558453,0.00017616541,0.0027011,0.057538144,0.08058719,0.5590666,0.0014978367],"about_ca_topic_score_codex":2.3603994e-7,"about_ca_topic_score_gemma":6.608795e-7,"teacher_disagreement_score":0.62869537,"about_ca_system_score_codex":0.0000213203,"about_ca_system_score_gemma":0.0000935352,"threshold_uncertainty_score":0.37419727},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97016186,0.0017872896,0.024794633,0.0012949251,0.00036672014,0.00065663096,0.00009001017,0.0000027291373,0.0008451794],"genre_scores_gemma":[0.9741579,0.0000720619,0.025563307,0.000046048954,0.00007409299,0.0000063507896,0.00001400921,0.000006851996,0.00005931843],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990732,0.00013183674,0.00046538375,0.00009362062,0.00010984267,0.00012613798],"domain_scores_gemma":[0.9983586,0.000083873696,0.00074039557,0.00011012764,0.0006811565,0.000025850424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043706974,0.00008768325,0.00019301152,0.000036354882,0.000091512054,0.0000053855665,0.00034704714,0.00006954317,0.000008154703],"category_scores_gemma":[0.000080520265,0.000040745595,0.00016318834,0.00006860609,0.0006741008,0.0000034662057,0.00008177712,0.00006399817,4.64571e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0068299253,0.0015157195,0.08547484,0.00054434617,0.0041231667,0.0000039232564,0.0018403059,0.001361011,0.7953573,0.060868513,0.007350083,0.034730863],"study_design_scores_gemma":[0.0052052215,0.005128248,0.16253214,0.000097920616,0.00026058403,0.00032956965,0.00066931575,0.0008322144,0.14786376,0.64388114,0.032791793,0.00040811594],"about_ca_topic_score_codex":0.000013634044,"about_ca_topic_score_gemma":0.000015301974,"teacher_disagreement_score":0.64749354,"about_ca_system_score_codex":0.000008836675,"about_ca_system_score_gemma":0.00019768019,"threshold_uncertainty_score":0.24837525},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82178,0.0005028569,0.17731835,0.00008818314,0.00021388743,0.00003999237,0.000029279221,0.0000018516547,0.000025587882],"genre_scores_gemma":[0.9605942,0.00003224027,0.03884812,0.00012412306,0.00036846325,3.6329686e-7,0.00002054299,0.0000066925713,0.0000052484456],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99937594,0.000059388352,0.00025351928,0.00011950181,0.000090661546,0.000100999794],"domain_scores_gemma":[0.9995508,0.000040418687,0.0001811564,0.000045794473,0.0001215778,0.000060236933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014588589,0.00008135477,0.00013310912,0.00007277091,0.00010493969,0.0000070154624,0.000071189716,0.00012103028,0.000015127183],"category_scores_gemma":[0.00005622974,0.00006717277,0.000057147758,0.000037556343,0.000089790374,0.0000038740036,0.000037836886,0.00012537066,2.390159e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009153617,0.000022839973,0.0005871601,0.0000045275247,0.000050912648,0.0000042591973,0.00003762605,0.020131756,0.9760352,0.0003876633,0.00003805048,0.002608481],"study_design_scores_gemma":[0.0058710133,0.0036540607,0.06262321,0.00011671173,0.00012578486,0.024432985,0.000115352144,0.037806243,0.82656693,0.030290717,0.007650875,0.0007461011],"about_ca_topic_score_codex":0.0000014177625,"about_ca_topic_score_gemma":2.3365052e-7,"teacher_disagreement_score":0.14946824,"about_ca_system_score_codex":0.000011003365,"about_ca_system_score_gemma":0.00014093758,"threshold_uncertainty_score":0.2739226},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5804891,0.0007389241,0.41842705,0.000035220288,0.0000981481,0.000057791407,0.0000032875303,0.000002057379,0.00014840765],"genre_scores_gemma":[0.94517714,0.000051109113,0.054009467,0.00013375386,0.0004682367,0.0000023917612,0.00010642947,0.000012065473,0.000039379178],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9987767,0.00014308431,0.000577858,0.00017802524,0.00016955467,0.00015477864],"domain_scores_gemma":[0.99872816,0.00003475576,0.00048977666,0.0001657923,0.0004754418,0.0001060497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034066263,0.00012353134,0.00030632238,0.00015955091,0.000055909382,0.0000034216341,0.00020494607,0.00013898428,0.000005634755],"category_scores_gemma":[0.000065248765,0.00011163518,0.00018472249,0.00019956472,0.00012674156,0.000004207802,0.000044883698,0.00008819644,0.0000020442387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001371209,0.00012711539,0.003829286,0.0000069280177,0.00020084852,0.0000026357766,0.000039894254,0.95031214,0.041586895,0.00045175053,0.0021487495,0.0011566551],"study_design_scores_gemma":[0.0064451904,0.0052756015,0.5110301,0.00010389972,0.0006628055,0.006029307,0.00020142614,0.33164713,0.11418789,0.011203293,0.011402236,0.0018111485],"about_ca_topic_score_codex":0.0000011832219,"about_ca_topic_score_gemma":3.3252775e-7,"teacher_disagreement_score":0.618665,"about_ca_system_score_codex":0.000019687854,"about_ca_system_score_gemma":0.0001290954,"threshold_uncertainty_score":0.45523506},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9988659,0.0004384179,0.000047036683,0.00025195294,0.000032297008,0.000022111042,0.000041596384,0.0000030362528,0.00029764645],"genre_scores_gemma":[0.9992109,0.00003579007,0.00052326143,0.000058777125,0.00014827156,1.4943366e-7,0.000014982601,2.4572827e-7,0.00000762997],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99942386,0.00005417564,0.00028523273,0.000057599587,0.0000931507,0.00008600344],"domain_scores_gemma":[0.99933976,0.00027618068,0.00021565711,0.000004363699,0.00013656696,0.000027496575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000090911206,0.00005717645,0.00022665401,0.000013683775,0.00006833998,0.000005068215,0.000091925605,0.000038962782,0.0004584504],"category_scores_gemma":[0.000019861818,0.000021605487,0.00008586514,0.00010384192,0.00007977785,0.000040283543,0.000009919712,0.000064150816,0.0000045090105],"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":[0.00053164136,0.0005561619,0.30693805,0.0000087581975,0.00040313642,0.000019302535,0.0004150396,0.025106141,0.35788235,0.0015910601,0.0021062226,0.30444214],"study_design_scores_gemma":[0.00032806117,0.0011603638,0.96436846,0.00003690718,0.00003535113,0.00009421889,0.00037332647,0.0028437902,0.0012634449,0.00751634,0.02183872,0.00014103815],"about_ca_topic_score_codex":0.00002369105,"about_ca_topic_score_gemma":0.000030990985,"teacher_disagreement_score":0.6574304,"about_ca_system_score_codex":0.000009045575,"about_ca_system_score_gemma":0.0000104497085,"threshold_uncertainty_score":0.50197107},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9782844,0.0019336062,0.0194543,0.00009722614,0.00011651016,0.00006917409,0.0000049073437,5.5897283e-7,0.000039301744],"genre_scores_gemma":[0.9529151,0.0000252474,0.046707194,0.00008832355,0.00024690005,0.0000010360853,0.000007877168,0.000004853154,0.0000034953591],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99898833,0.000019756131,0.0006897958,0.000117639,0.000045208228,0.00013927255],"domain_scores_gemma":[0.9987478,0.00015479495,0.00084609917,0.00002962204,0.00019380315,0.000027838732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001367236,0.000068881476,0.00016381397,0.00006873024,0.00005913317,0.000008796893,0.00005393017,0.0000543924,5.240744e-7],"category_scores_gemma":[0.00036414026,0.000058860314,0.00004965627,0.000038827457,0.000060322975,4.6911768e-7,0.000038041624,0.000051403524,9.3548486e-8],"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":[0.00007775716,0.000025306428,0.20632888,0.000016643815,0.00007003436,0.000006789284,0.0001926376,0.06990448,0.7134128,0.00029147416,0.000016645514,0.009656533],"study_design_scores_gemma":[0.0026812467,0.0016196299,0.9070429,0.00006886837,0.0000472859,0.0010304879,0.0012307119,0.03830402,0.027243283,0.017455032,0.002797305,0.00047923508],"about_ca_topic_score_codex":0.000004855506,"about_ca_topic_score_gemma":0.000011618877,"teacher_disagreement_score":0.700714,"about_ca_system_score_codex":0.00001347521,"about_ca_system_score_gemma":0.000060925777,"threshold_uncertainty_score":0.24002539},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91510546,0.000027459388,0.08421952,0.00025053116,0.00009186034,0.000043864675,0.000007333258,0.0000013077171,0.00025268493],"genre_scores_gemma":[0.9994128,0.000006422152,0.0003477061,0.00013708965,0.000076713026,3.667422e-7,0.000017126948,6.942103e-7,0.000001087219],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9996175,0.000019892641,0.00021522578,0.00003077363,0.000050414008,0.00006619124],"domain_scores_gemma":[0.9997688,0.000039104856,0.000068435016,0.000014501598,0.0000803007,0.000028877193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012743188,0.00004305563,0.000116194366,0.00005823351,0.000058296686,0.000014931522,0.000051782557,0.00003107866,0.000014874135],"category_scores_gemma":[0.0000015609027,0.00003766694,0.000042191357,0.000046800484,0.000028971566,0.00019095687,0.000013530939,0.00011624406,5.6152345e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002131643,0.00014733044,0.65025485,0.0000019256054,0.000030866613,0.0000026115677,0.0006707687,0.10818499,0.000021516496,0.19417378,0.00005076258,0.046247415],"study_design_scores_gemma":[0.002186357,0.00016829235,0.90336424,0.000008689911,0.00001433709,0.0000056119097,0.00007225006,0.01748964,0.0000020121952,0.07648879,0.00012606745,0.00007372207],"about_ca_topic_score_codex":0.000012807647,"about_ca_topic_score_gemma":6.3465126e-7,"teacher_disagreement_score":0.25310937,"about_ca_system_score_codex":0.000009454051,"about_ca_system_score_gemma":0.00002662247,"threshold_uncertainty_score":0.15360133},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9934247,0.0007278742,0.0054750764,0.00013776778,0.00013526759,0.00007352772,0.000004454645,4.8160615e-7,0.000020839629],"genre_scores_gemma":[0.96747416,0.00004257876,0.032214094,0.00018911125,0.00007033986,0.0000011287285,0.0000049672194,0.0000026090129,0.0000010141572],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9995239,0.000032647044,0.0002454635,0.00006643315,0.000040935618,0.00009062982],"domain_scores_gemma":[0.9996287,0.00003247792,0.00012784303,0.000025292087,0.0001421873,0.00004346806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009598171,0.000065377986,0.00010986949,0.00010325694,0.00004893227,0.000013681661,0.000041437346,0.000048710255,0.0000022300374],"category_scores_gemma":[0.00006773282,0.00005637419,0.000019901692,0.0000440989,0.000044954155,0.000006389542,0.00005814434,0.000052326788,5.31394e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010965827,0.0000048796733,0.11134493,0.000018037714,0.00008288798,0.0000019142115,0.00054834445,0.12546103,0.73113114,0.00022254462,0.00016257072,0.030912083],"study_design_scores_gemma":[0.0010708807,0.0008182259,0.95760113,0.00003429361,0.000015832971,0.0007287311,0.00040882148,0.01228339,0.0047033457,0.020999134,0.0010911744,0.00024505614],"about_ca_topic_score_codex":0.00003935541,"about_ca_topic_score_gemma":0.000007651497,"teacher_disagreement_score":0.8462562,"about_ca_system_score_codex":0.000020779507,"about_ca_system_score_gemma":0.000052825548,"threshold_uncertainty_score":0.22988726},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9930198,0.0009922354,0.0034499005,0.0019442912,0.00018181711,0.00010083068,0.000018145303,0.000003314719,0.0002896459],"genre_scores_gemma":[0.9742996,0.00015837631,0.024364775,0.0003665425,0.0006155935,0.0000034313025,0.000091328395,0.000010776615,0.0000895772],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99894595,0.00009314562,0.00046591976,0.00016623811,0.00013523114,0.00019353104],"domain_scores_gemma":[0.9993089,0.00002272528,0.00024569005,0.00015636017,0.00019724845,0.000069115944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038817685,0.000113145354,0.00018280413,0.00014849055,0.000025902506,0.000010610169,0.00031901934,0.00009488298,0.00006107488],"category_scores_gemma":[0.000073714444,0.000102257814,0.00008930333,0.00009542904,0.000070243375,0.00000801391,0.000106593194,0.00012337111,0.00002262037],"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":[0.00016108491,0.00019742423,0.0052825785,0.000010547663,0.00012457222,0.000029988718,0.0001456166,0.04762824,0.9365019,0.00029723922,0.0007970422,0.008823771],"study_design_scores_gemma":[0.011641572,0.006157984,0.25754458,0.00011298682,0.000094961906,0.0030051486,0.00022207054,0.0045732222,0.035795476,0.01986405,0.65963703,0.0013509062],"about_ca_topic_score_codex":0.0000040754503,"about_ca_topic_score_gemma":0.000010066817,"teacher_disagreement_score":0.9007064,"about_ca_system_score_codex":0.000070238035,"about_ca_system_score_gemma":0.00013538556,"threshold_uncertainty_score":0.4169953},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99284345,0.00007124783,0.0060713324,0.00023813227,0.00036208567,0.00012486853,0.00004451984,6.4728187e-7,0.00024372774],"genre_scores_gemma":[0.9937514,0.000014314271,0.0057971436,0.0001751036,0.00022191653,0.0000040390555,0.000023081566,0.0000064543547,0.000006544325],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9990594,0.00008806021,0.00044010434,0.00015791765,0.00012425221,0.00013030681],"domain_scores_gemma":[0.99917114,0.00005785772,0.00028777032,0.000100546706,0.00034073123,0.000041983443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057727104,0.000106822336,0.00023890349,0.0001080913,0.000038529033,0.000005187138,0.0001338934,0.00010993812,0.000013341623],"category_scores_gemma":[0.00007391497,0.000088205365,0.00009639912,0.00006429317,0.000065159,0.0000012279754,0.00008100388,0.00024655068,3.5264875e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038407464,0.0015886436,0.439153,0.0000072090584,0.000303802,0.00000303884,0.00015916451,0.010791237,0.54466856,0.001003244,0.00015756578,0.001780492],"study_design_scores_gemma":[0.0019430919,0.0022233943,0.98940635,0.0000037333866,0.000016300406,0.000018230885,0.0002326433,0.0014313426,0.0016294791,0.002297501,0.00070524175,0.00009272111],"about_ca_topic_score_codex":0.000008277783,"about_ca_topic_score_gemma":0.000097560194,"teacher_disagreement_score":0.55025333,"about_ca_system_score_codex":0.000011873572,"about_ca_system_score_gemma":0.00024432864,"threshold_uncertainty_score":0.35969102},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9916482,0.00025064376,0.0063230656,0.0008987277,0.00056878396,0.00019351658,0.0000211106,0.0000016459562,0.00009431723],"genre_scores_gemma":[0.9847987,0.00003152331,0.014575065,0.00011243807,0.00040267096,0.000008431167,0.000030887204,0.0000060885545,0.000034182405],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9993476,0.000048131078,0.00030269727,0.000113613954,0.000056277615,0.00013166704],"domain_scores_gemma":[0.99926645,0.00011947758,0.00025599753,0.000053612992,0.00027419618,0.000030283514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003978034,0.000077579985,0.00012615834,0.000059653274,0.000059095022,0.000012169105,0.00013192993,0.00009256741,0.000012795489],"category_scores_gemma":[0.0001304602,0.000046479614,0.00007300945,0.000045744615,0.00014966275,0.0000054672273,0.00002280916,0.00015520392,0.0000011086178],"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":[0.00058180536,0.00009390599,0.03231532,0.000017260729,0.0002603697,0.000004723041,0.00026506104,0.0068404297,0.9248375,0.0004903697,0.00019556191,0.034097686],"study_design_scores_gemma":[0.013356735,0.0065711197,0.7065223,0.00007595866,0.00019106884,0.0066527384,0.0021043036,0.018638609,0.041592713,0.022685703,0.18045695,0.0011518255],"about_ca_topic_score_codex":0.000005918607,"about_ca_topic_score_gemma":0.000024957779,"teacher_disagreement_score":0.8832448,"about_ca_system_score_codex":0.000009748779,"about_ca_system_score_gemma":0.00014746588,"threshold_uncertainty_score":0.18953836},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9741224,0.0016506447,0.022639047,0.0009857918,0.00037546956,0.00007727392,0.00001921995,0.0000013548856,0.00012879584],"genre_scores_gemma":[0.9625935,0.000056346515,0.035333674,0.00085142965,0.0011107874,0.0000023901425,0.0000308858,0.000010538016,0.000010428341],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9991722,0.000051097453,0.00035084217,0.00016687399,0.00008307948,0.0001759014],"domain_scores_gemma":[0.99933654,0.000036654095,0.00018325097,0.000101116995,0.00024517646,0.00009727849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013178676,0.00011701879,0.00020602792,0.00004915597,0.000051091483,0.00000937019,0.00017686933,0.00009380401,0.000008560215],"category_scores_gemma":[0.00006127752,0.000100066194,0.00011028483,0.00009621347,0.000056140434,4.8722404e-7,0.000078617035,0.000068032656,0.000010319758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002682744,0.000072691735,0.0064781196,0.0000020848922,0.00036673588,0.000010593145,0.00015692996,0.5446119,0.44208634,0.000684763,0.0014790664,0.003782553],"study_design_scores_gemma":[0.0065429383,0.00692771,0.47269687,0.00009023278,0.00019066813,0.00042332322,0.00014360776,0.00027125987,0.039313495,0.39767352,0.07483838,0.0008880064],"about_ca_topic_score_codex":0.000013401858,"about_ca_topic_score_gemma":0.000014020179,"teacher_disagreement_score":0.5443406,"about_ca_system_score_codex":0.00001809487,"about_ca_system_score_gemma":0.000130918,"threshold_uncertainty_score":0.4080581},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83610237,0.002113985,0.15950523,0.0008158942,0.00056252116,0.00006907503,0.00003530249,0.0000044704716,0.00079116365],"genre_scores_gemma":[0.9813065,0.00007082272,0.016241176,0.000254947,0.0019190939,0.0000013015868,0.000028284649,0.000008733124,0.00016916159],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992253,0.00009710846,0.0003095612,0.00012098211,0.00011271132,0.00013433806],"domain_scores_gemma":[0.9993859,0.00004715538,0.00026468385,0.00008008495,0.00015392319,0.000068241665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015230874,0.00009841676,0.0001755095,0.000052926185,0.000051680534,0.000012478738,0.0001910323,0.00011890345,0.00012352475],"category_scores_gemma":[0.0000725253,0.00007860011,0.00010993789,0.000044839482,0.000060976527,0.000004222469,0.000030127458,0.000085490814,0.00000794231],"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":[0.00025273758,0.00012553489,0.011469517,0.000025754189,0.0006531682,0.000031349693,0.00011934654,0.00878844,0.7735405,0.020450056,0.02715587,0.1573877],"study_design_scores_gemma":[0.0027423243,0.0032410813,0.022875195,0.000042129668,0.00011094161,0.00047601046,0.000036758294,0.00085659255,0.25014296,0.28200373,0.4366868,0.00078543724],"about_ca_topic_score_codex":9.62396e-7,"about_ca_topic_score_gemma":4.3180634e-7,"teacher_disagreement_score":0.52339756,"about_ca_system_score_codex":0.000009495643,"about_ca_system_score_gemma":0.000028619874,"threshold_uncertainty_score":0.32052195},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86774635,0.0046701385,0.12682697,0.00034283125,0.0001465019,0.00007659439,0.00007315845,0.0000014890677,0.00011597577],"genre_scores_gemma":[0.99768716,0.00016779875,0.0012414918,0.0000128458,0.00050146243,0.0000013576109,0.00032675892,0.000005531381,0.000055606113],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991758,0.000088036446,0.00043325571,0.00008445436,0.0000980353,0.00012042928],"domain_scores_gemma":[0.99911,0.000111164445,0.0004174515,0.000077529476,0.00025874758,0.00002511576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035648214,0.00007571579,0.00016362022,0.000026393065,0.00006996909,0.000009379866,0.00018376195,0.00006042807,0.0000039271945],"category_scores_gemma":[0.000031083517,0.000052246276,0.00011653505,0.000047368147,0.00014094073,0.0000025835363,0.000035745215,0.00006189864,0.0000023574728],"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":[0.0017586043,0.0003255471,0.41370866,0.00006345807,0.0015344999,0.00000976578,0.000076411845,0.09347664,0.38131174,0.018693713,0.0105353985,0.07850557],"study_design_scores_gemma":[0.004574656,0.0010516222,0.631012,0.0000149630205,0.000106368585,0.000068928464,0.000045113935,0.0004832498,0.01038843,0.055113707,0.2968645,0.0002764446],"about_ca_topic_score_codex":0.0000033608128,"about_ca_topic_score_gemma":0.00000233025,"teacher_disagreement_score":0.3709233,"about_ca_system_score_codex":0.000021454132,"about_ca_system_score_gemma":0.00007752287,"threshold_uncertainty_score":0.21305414},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6928257,0.0011490451,0.30403912,0.0008335292,0.0003069224,0.00030459216,0.00001659996,0.0000012796281,0.0005232357],"genre_scores_gemma":[0.9664226,0.00009182894,0.032878153,0.00015862801,0.0003764049,0.00001527927,0.000025592253,0.0000052487976,0.000026233389],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9995121,0.000028747678,0.00025751354,0.0000814493,0.00004559445,0.00007459417],"domain_scores_gemma":[0.99918383,0.000068082634,0.0003071233,0.000061527084,0.0003613994,0.000018028175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026807463,0.000058274818,0.00008238185,0.000031731524,0.00006942333,0.0000057646275,0.00011628016,0.000051284354,0.000004777777],"category_scores_gemma":[0.000055691315,0.0000394282,0.00007631996,0.000034566357,0.000045057463,0.000001112458,0.000021524895,0.000032188702,0.0000013421106],"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":[0.0015819576,0.00046713004,0.023163585,0.00005588429,0.0012975544,7.7941814e-7,0.0021240474,0.016630068,0.7985746,0.06619786,0.010407268,0.079499245],"study_design_scores_gemma":[0.0043233545,0.005148725,0.39831743,0.000025266325,0.0002749,0.00023822948,0.00063248805,0.008597585,0.068907425,0.37909463,0.13387994,0.00056003866],"about_ca_topic_score_codex":0.0000016917818,"about_ca_topic_score_gemma":0.000002110034,"teacher_disagreement_score":0.7296672,"about_ca_system_score_codex":0.000008010045,"about_ca_system_score_gemma":0.00005581223,"threshold_uncertainty_score":0.16078353},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78759515,0.00030383043,0.21027228,0.00026719575,0.00013019012,0.00020857353,0.000011830977,0.000008705785,0.0012022606],"genre_scores_gemma":[0.93496794,0.00006493723,0.06442847,0.00013505683,0.0001790881,0.000006717827,0.00011912486,0.000014942544,0.00008371506],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990897,0.000069554386,0.0003693491,0.00016395614,0.0001589525,0.00014847892],"domain_scores_gemma":[0.99889445,0.000009666542,0.00043281517,0.000113891234,0.0004785287,0.000070622686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000195904,0.00012085498,0.00016387206,0.00012281258,0.000043793563,0.000009090348,0.00016696697,0.000096284166,0.000027595142],"category_scores_gemma":[0.00002167673,0.000092583934,0.00006198584,0.00011586106,0.000077531,0.000009587382,0.000038374164,0.00009733771,0.0000056549015],"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":[0.0014757535,0.00070270366,0.014574486,0.00005951185,0.0009992823,0.000048757833,0.00062816386,0.27256826,0.6956388,0.0032771092,0.0034208368,0.0066063884],"study_design_scores_gemma":[0.035335507,0.07081159,0.21746661,0.0005224731,0.0010764252,0.004672078,0.00057752,0.117597744,0.15820551,0.32833067,0.06087426,0.004529622],"about_ca_topic_score_codex":0.0000031640739,"about_ca_topic_score_gemma":0.0000043907844,"teacher_disagreement_score":0.53743327,"about_ca_system_score_codex":0.000024525845,"about_ca_system_score_gemma":0.00017773731,"threshold_uncertainty_score":0.37754634},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45429483,0.000033138887,0.5419776,0.0025320833,0.0007958674,0.000031608986,0.0000060357415,0.0000056507756,0.00032319906],"genre_scores_gemma":[0.94346535,0.0000024124672,0.05608209,0.00032725846,0.00011260953,4.86652e-7,0.0000022496174,0.0000020398884,0.0000055235996],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999255,0.000080750004,0.00031913217,0.000087122186,0.00016980404,0.000088191104],"domain_scores_gemma":[0.99853134,0.00069249055,0.00034924317,0.00014903868,0.00023789144,0.000039975355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042051185,0.000064555046,0.00014487527,0.000121272846,0.00004793978,0.000021751928,0.0007548782,0.000046082372,0.000038279744],"category_scores_gemma":[0.00010224299,0.000035160378,0.000100517,0.00012757744,0.00010073184,0.00012775711,0.000121703546,0.00027496374,0.0000064520286],"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":[0.00007736803,0.00016174956,0.00087453856,0.0000030609842,0.000051536714,0.000011432342,0.00016305025,0.0011195494,0.0065458226,0.9233398,0.0038458193,0.063806295],"study_design_scores_gemma":[0.00082034944,0.0013491561,0.04775512,0.00003758421,0.000008942099,0.00044368848,0.000019221567,0.08447762,0.0018716147,0.85757816,0.0055059143,0.00013262381],"about_ca_topic_score_codex":0.0000032190837,"about_ca_topic_score_gemma":0.0000018860757,"teacher_disagreement_score":0.4891705,"about_ca_system_score_codex":0.000004884574,"about_ca_system_score_gemma":0.00007771493,"threshold_uncertainty_score":0.14337985},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09686499,0.0004770801,0.90150535,0.0005128332,0.00024012342,0.000026601894,0.00001096087,0.000016739521,0.00034530458],"genre_scores_gemma":[0.7190417,0.0000027820863,0.2804661,0.000044418073,0.0004151789,4.8205766e-7,0.00001739437,0.0000023667837,0.000009576146],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989878,0.00007713501,0.0004891494,0.00012425851,0.00018442245,0.00013722277],"domain_scores_gemma":[0.99880254,0.0003660349,0.0004889303,0.0000952545,0.00020793577,0.00003929764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003070595,0.00008452703,0.00020908986,0.00011195391,0.000098145785,0.000060598602,0.00052714493,0.00004437326,0.000005209485],"category_scores_gemma":[0.000029419713,0.000061948354,0.00007326629,0.00015100342,0.00006128626,0.00032022296,0.00011410722,0.000116642834,0.0000054917123],"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":[0.000041210842,0.000257684,0.11206536,0.0000373988,0.00016235675,0.00006063074,0.00029319743,0.04945323,0.002745362,0.53444785,0.007321823,0.2931139],"study_design_scores_gemma":[0.0006756993,0.00029099826,0.12532501,0.000036195917,0.000012106794,0.00014796497,0.000018734672,0.05142065,0.00052644056,0.8105293,0.010809687,0.00020718551],"about_ca_topic_score_codex":0.000009597935,"about_ca_topic_score_gemma":0.0000010976332,"teacher_disagreement_score":0.6221767,"about_ca_system_score_codex":0.00002033079,"about_ca_system_score_gemma":0.00006673235,"threshold_uncertainty_score":0.25261807},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5062876,0.0009252855,0.4918031,0.00018206787,0.00041055816,0.00010543664,0.000011431663,0.0000021805256,0.00027235915],"genre_scores_gemma":[0.88281363,0.000031014013,0.11657154,0.0001769031,0.00028180188,0.0000032356772,0.000039227594,0.000008774494,0.00007388606],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994662,0.000044728513,0.00023120624,0.000090187765,0.000053284915,0.000114409966],"domain_scores_gemma":[0.9994487,0.00004142995,0.00016580381,0.00005233834,0.00024920565,0.000042534935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025624502,0.00006663587,0.000110202556,0.000055441007,0.000032944452,0.0000069675475,0.00008896737,0.000063148786,0.000011453372],"category_scores_gemma":[0.00013034165,0.00005855094,0.00008763651,0.000034853034,0.00002891638,0.0000020658304,0.000016347718,0.00003931405,0.0000024851472],"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":[0.00019208499,0.00015279771,0.0071372837,0.00002682711,0.00037928368,0.0000059359286,0.000050632545,0.05767652,0.91962117,0.0022383293,0.003101883,0.0094172275],"study_design_scores_gemma":[0.011213051,0.007830634,0.025468849,0.000039161958,0.00015305517,0.002642298,0.00014064983,0.004604133,0.19027221,0.0902853,0.6663705,0.0009801615],"about_ca_topic_score_codex":2.2801423e-7,"about_ca_topic_score_gemma":7.05149e-7,"teacher_disagreement_score":0.729349,"about_ca_system_score_codex":0.000010877663,"about_ca_system_score_gemma":0.00008585517,"threshold_uncertainty_score":0.2387638},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99418646,0.00014749075,0.0043837666,0.0006204763,0.00043753325,0.00006472749,0.000023978408,0.000012402143,0.0001231932],"genre_scores_gemma":[0.9083548,0.000030325786,0.0902236,0.00043485206,0.00073624455,0.0000019197753,0.00009965933,0.000009556492,0.00010900378],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99930435,0.000034121,0.00029169838,0.00015187194,0.00008017718,0.00013777154],"domain_scores_gemma":[0.99894744,0.00006490486,0.0002720042,0.000101620855,0.0005574588,0.00005655797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002497289,0.000114156086,0.00018397054,0.00008242589,0.00010280151,0.000018134975,0.00013887003,0.00017467512,0.0000035926732],"category_scores_gemma":[0.000098173005,0.000084869396,0.00019150286,0.000063908614,0.00008557999,0.0000047483654,0.000045301593,0.0001486218,0.0000010222759],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018353005,0.00006768544,0.0010479343,0.0000038351222,0.00012191805,0.0000021259887,0.000006619555,0.00011461995,0.9929253,0.0007807474,0.003968901,0.00077677023],"study_design_scores_gemma":[0.0016390167,0.0018977476,0.0021185568,0.000012578437,0.00009965954,0.0007738978,0.000021221558,0.00027742865,0.76197815,0.017562123,0.21326815,0.00035149755],"about_ca_topic_score_codex":5.349843e-7,"about_ca_topic_score_gemma":0.000013689352,"teacher_disagreement_score":0.23094718,"about_ca_system_score_codex":0.0000144670175,"about_ca_system_score_gemma":0.000100250436,"threshold_uncertainty_score":0.34608734},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4606334,0.00065806793,0.5385266,0.00004286422,0.00006118115,0.00005508926,0.000007981071,0.0000024042204,0.000012413883],"genre_scores_gemma":[0.96784693,0.000008720351,0.030330008,0.00007156722,0.0012238389,0.0000051694624,0.00042708457,0.000022045295,0.00006464494],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989405,0.00006251858,0.0004534223,0.00020098485,0.00011847878,0.00022406178],"domain_scores_gemma":[0.9988934,0.000034025798,0.00035174767,0.0001183286,0.00053793925,0.00006456411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002489635,0.00015521752,0.0002600973,0.00010063966,0.00007916208,0.000016747836,0.0001550168,0.00015336802,0.0000031277903],"category_scores_gemma":[0.000010633976,0.00012829245,0.0001757738,0.000096899734,0.00007801631,0.000005016901,0.000025705514,0.00009110387,3.2309094e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023430816,0.00003869008,0.00037717517,0.0000028019715,0.00018325353,0.0000020235666,0.0000016476355,0.99204516,0.004240029,0.0015606333,0.00024289258,0.0010713737],"study_design_scores_gemma":[0.0008796507,0.00061382784,0.00094812905,0.00000774219,0.00009213832,0.00019891644,0.000009432859,0.9898643,0.0002724205,0.0068944935,0.00006126077,0.00015768613],"about_ca_topic_score_codex":0.000005753833,"about_ca_topic_score_gemma":0.000028734297,"teacher_disagreement_score":0.5081966,"about_ca_system_score_codex":0.00004223203,"about_ca_system_score_gemma":0.00018780076,"threshold_uncertainty_score":0.5231615},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91745853,0.0014403651,0.07778249,0.00010460891,0.00021280386,0.00005789523,0.000005000365,0.0000016841842,0.0029366293],"genre_scores_gemma":[0.98237604,0.00016068816,0.01722883,0.00009848319,0.000103167375,5.154519e-7,0.000008366125,0.000004117128,0.000019772078],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994104,0.00020534008,0.00020721182,0.000067306086,0.000052359355,0.000057379533],"domain_scores_gemma":[0.9992483,0.00013152944,0.00027074307,0.00004125441,0.00027988138,0.000028285749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006704491,0.000049440114,0.00009405781,0.000056934383,0.000016634865,0.0000020989794,0.000058294427,0.000057799334,0.000020205662],"category_scores_gemma":[0.00030237582,0.000040822837,0.00004008328,0.000033585093,0.00008467683,0.0000052596,0.000015019392,0.000049463353,0.0000012167162],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001890991,0.00030067808,0.008735682,0.000027748758,0.00058301905,0.0000071786976,0.00062146975,0.0006009514,0.9521139,0.015068756,0.00033532808,0.019714275],"study_design_scores_gemma":[0.007835779,0.01903177,0.20137607,0.000081931874,0.00056417973,0.008512326,0.0024247188,0.00018779915,0.4344862,0.26126212,0.06336018,0.00087691634],"about_ca_topic_score_codex":0.0000018498514,"about_ca_topic_score_gemma":2.1718294e-7,"teacher_disagreement_score":0.5176277,"about_ca_system_score_codex":0.0000040555315,"about_ca_system_score_gemma":0.00003832463,"threshold_uncertainty_score":0.1664707},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9565944,0.0008045723,0.04076642,0.00106482,0.00037713372,0.00007762527,0.000007033588,0.0000015005819,0.00030645618],"genre_scores_gemma":[0.95568705,0.00004391104,0.042943157,0.0007738246,0.00051035127,0.000002687687,0.000011900189,0.000010307295,0.00001681629],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9990681,0.00006272736,0.00040167445,0.00016131792,0.00012442243,0.00018179236],"domain_scores_gemma":[0.9991119,0.000052379677,0.00025985047,0.00008542854,0.0004048071,0.0000856264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042710057,0.00011665749,0.00019830225,0.00010278851,0.000084161395,0.00001468798,0.00018473192,0.00008184243,0.0000036889946],"category_scores_gemma":[0.00017126759,0.000101462036,0.000116611096,0.00009316944,0.00003745804,0.0000011728479,0.000094616546,0.00008504438,0.000009870321],"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":[0.000072339804,0.000053564818,0.0026016096,0.0000054652846,0.00018425997,0.0000041195854,0.0001402971,0.12397794,0.8659134,0.0012330627,0.00028803624,0.0055259024],"study_design_scores_gemma":[0.012686251,0.01725974,0.4836189,0.0002558529,0.00023438084,0.0021699779,0.0011974592,0.0014160688,0.20315273,0.1924929,0.08353528,0.0019804745],"about_ca_topic_score_codex":0.0000043854175,"about_ca_topic_score_gemma":0.0000033965239,"teacher_disagreement_score":0.6627607,"about_ca_system_score_codex":0.00002766552,"about_ca_system_score_gemma":0.00023553894,"threshold_uncertainty_score":0.41375017},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99183315,0.0010752392,0.00631946,0.00024551342,0.00034935068,0.000048009995,0.00007604733,0.0000021138471,0.00005110422],"genre_scores_gemma":[0.95534456,0.0001424407,0.04428633,0.00003965756,0.00014966802,8.7255785e-7,0.000023629636,0.0000074707095,0.000005352012],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991298,0.00004041417,0.0004897154,0.00013669115,0.00009042978,0.00011295574],"domain_scores_gemma":[0.99851865,0.0002442722,0.00058205845,0.00013384152,0.00049776555,0.000023393408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017182749,0.00010645837,0.00031111538,0.00007540192,0.000028484923,0.0000034693894,0.00022870071,0.0001885844,0.000004700186],"category_scores_gemma":[0.00036830993,0.00008737017,0.00010746288,0.0000617427,0.00023142167,0.0000011726619,0.00010051992,0.00014097182,6.720039e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009400059,0.00004704391,0.0027299162,0.0000072413677,0.00020728618,0.0000040629675,0.000053225212,0.015249472,0.97712755,0.0010712645,0.00007606234,0.0033328738],"study_design_scores_gemma":[0.0014462401,0.0023948562,0.012924076,0.000032822616,0.0000911162,0.00014973673,0.0003693033,0.0010324335,0.9044364,0.07334224,0.003513053,0.00026769342],"about_ca_topic_score_codex":0.000049633374,"about_ca_topic_score_gemma":0.000019046178,"teacher_disagreement_score":0.07269112,"about_ca_system_score_codex":0.0000084152,"about_ca_system_score_gemma":0.00017368616,"threshold_uncertainty_score":0.3562852},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9407016,0.003948513,0.05410647,0.00045962844,0.00039608864,0.000096789445,0.000012435244,0.0000010733487,0.00027738197],"genre_scores_gemma":[0.96141934,0.000161959,0.037491545,0.00022531605,0.0006240207,0.0000040803207,0.000006460826,0.000009098382,0.00005819136],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993652,0.000031031974,0.0002963191,0.00011797938,0.000052467796,0.00013698745],"domain_scores_gemma":[0.9993213,0.00006633293,0.00021739087,0.00006177063,0.00029137987,0.00004183208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001618128,0.00008550773,0.0001500908,0.000050546278,0.00006133225,0.000007817403,0.00013233205,0.000067120454,0.000008721637],"category_scores_gemma":[0.00008445146,0.00007425394,0.00012872524,0.000035263813,0.000057300815,4.2271273e-7,0.00004047875,0.000044602013,0.0000018770526],"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":[0.00016172107,0.0002528752,0.03189886,0.00003296084,0.0008084011,0.000004188999,0.00019377933,0.03789654,0.7890774,0.002890664,0.005940073,0.1308425],"study_design_scores_gemma":[0.010417322,0.01195009,0.15081072,0.00005401689,0.0002738739,0.0012868452,0.0002803145,0.019640682,0.08110693,0.12586282,0.59687686,0.0014395454],"about_ca_topic_score_codex":4.7855417e-7,"about_ca_topic_score_gemma":4.201131e-7,"teacher_disagreement_score":0.7079705,"about_ca_system_score_codex":0.0000061707956,"about_ca_system_score_gemma":0.000022986036,"threshold_uncertainty_score":0.3027988},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9694392,0.005786136,0.0240845,0.000416248,0.0001250096,0.00004079409,0.000023143799,8.506643e-7,0.00008412822],"genre_scores_gemma":[0.9940524,0.0010542602,0.004240787,0.00024460134,0.00031183512,0.000001438617,0.00004488598,0.0000052493,0.00004454551],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9994416,0.00003768758,0.00026013033,0.00011236766,0.00006410165,0.000084074454],"domain_scores_gemma":[0.9993314,0.000026731788,0.00021017577,0.000054162636,0.00033469617,0.000042806165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011397842,0.0000720547,0.00011652139,0.00004107844,0.00008952752,0.0000040013792,0.00007469138,0.000065805434,0.0000022398797],"category_scores_gemma":[0.00003847468,0.00006450281,0.000041982054,0.00004281421,0.00011734358,0.0000012315531,0.000032404092,0.000043253352,0.0000020413474],"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":[0.00008734458,0.00007026512,0.127522,0.0000035907856,0.00016034293,0.000002413806,0.00006829528,0.002560701,0.85688066,0.0012606222,0.010344186,0.0010395807],"study_design_scores_gemma":[0.0012535485,0.0007601983,0.9156926,0.000003869118,0.000025139187,0.00075771497,0.00003532663,0.0001634787,0.01499586,0.019431435,0.046669867,0.00021095965],"about_ca_topic_score_codex":0.0000036768502,"about_ca_topic_score_gemma":6.296301e-7,"teacher_disagreement_score":0.8418848,"about_ca_system_score_codex":0.000014087269,"about_ca_system_score_gemma":0.000083022176,"threshold_uncertainty_score":0.26303482},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93883437,0.0015226823,0.058812164,0.00007946442,0.000062762294,0.000048796675,0.000004333534,0.0000020415932,0.0006334008],"genre_scores_gemma":[0.9773744,0.00008935715,0.022279225,0.00005814066,0.0001236894,0.0000011264975,0.000016744123,0.0000068034005,0.00005054797],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99954605,0.00002261561,0.00017011765,0.0001017972,0.000059950413,0.00009945189],"domain_scores_gemma":[0.9995472,0.0000114074655,0.00016703088,0.00005255518,0.00017323985,0.00004858911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000117179196,0.00007234343,0.000110424124,0.000047390393,0.000033761396,0.000007912195,0.00009006288,0.00004309385,0.00002044235],"category_scores_gemma":[0.000007857102,0.00005397489,0.000028851278,0.00003876776,0.00009886693,0.00000487695,0.00003217465,0.000052911266,0.0000017781763],"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":[0.004472649,0.0006249044,0.32755497,0.00012627768,0.0018335034,0.00015364941,0.0014708574,0.0073730536,0.6301847,0.012609658,0.0003913425,0.013204419],"study_design_scores_gemma":[0.010344826,0.008770831,0.8533735,0.00007692255,0.0001781738,0.0032760433,0.00046176804,0.00031796363,0.03477134,0.029848535,0.057602577,0.0009775036],"about_ca_topic_score_codex":0.0000023495609,"about_ca_topic_score_gemma":0.0000025049053,"teacher_disagreement_score":0.5954134,"about_ca_system_score_codex":0.0000066986595,"about_ca_system_score_gemma":0.00005277492,"threshold_uncertainty_score":0.22010322},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9781105,0.00045036667,0.02059312,0.00024231689,0.00005922657,0.000016356262,0.000023658613,0.0000012352504,0.0005032073],"genre_scores_gemma":[0.9961001,0.000027219285,0.0032278923,0.0001458085,0.00017317002,3.9594372e-7,0.00025123561,0.0000035261035,0.00007060149],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991881,0.000056601086,0.00044992217,0.000101639336,0.0001082491,0.00009546117],"domain_scores_gemma":[0.999058,0.000044314573,0.00042147696,0.00007755663,0.0003669478,0.00003168391],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018303846,0.000074251446,0.000273972,0.00027083317,0.000022678061,0.0000048824754,0.00013161499,0.000086274944,0.000050032628],"category_scores_gemma":[0.00004311852,0.000058462156,0.0003292309,0.00032723372,0.00009359392,0.000003974363,0.000025073514,0.00005377824,0.00000200967],"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":[0.0001995227,0.00024541633,0.05222008,0.000008778123,0.003110368,0.000012857909,0.000020057325,0.14656381,0.7870789,0.0040445947,0.002110842,0.0043847514],"study_design_scores_gemma":[0.002536882,0.002896501,0.67777866,0.0000267684,0.0037340592,0.00024341322,0.00012921989,0.015694816,0.18834485,0.07317596,0.03469624,0.0007426604],"about_ca_topic_score_codex":0.000032322685,"about_ca_topic_score_gemma":0.00001948289,"teacher_disagreement_score":0.62555856,"about_ca_system_score_codex":0.000008917892,"about_ca_system_score_gemma":0.00007189573,"threshold_uncertainty_score":0.23840176},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9815794,0.002618534,0.013689542,0.0010557228,0.00023359906,0.000044003715,0.000010641218,0.000001211579,0.0007673352],"genre_scores_gemma":[0.98934186,0.00018278095,0.008959622,0.0009442774,0.00052547106,4.9101027e-7,0.000021512302,0.0000052508076,0.000018754881],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9993186,0.000043971715,0.00030009155,0.000114421004,0.000071905975,0.00015103573],"domain_scores_gemma":[0.9993723,0.000022008877,0.00021021355,0.00007259597,0.00026040545,0.0000624519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018289725,0.00009468847,0.00016467721,0.00006049518,0.00004728962,0.000009622924,0.00015902123,0.00008021868,0.0000071281625],"category_scores_gemma":[0.000036811467,0.0000794455,0.00011276746,0.00004634809,0.00003831219,7.936814e-7,0.000031219013,0.00007081771,0.0000055716373],"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":[0.00013440929,0.00011292268,0.0018938999,0.000002733304,0.0001778802,0.00000855561,0.00004730904,0.0048806933,0.97191805,0.001037099,0.0010468139,0.018739654],"study_design_scores_gemma":[0.0031894017,0.008753324,0.49118444,0.000016220674,0.000094060386,0.001175157,0.00010623433,0.0002095863,0.024093445,0.30133036,0.16920497,0.00064277864],"about_ca_topic_score_codex":6.001427e-7,"about_ca_topic_score_gemma":6.6366874e-7,"teacher_disagreement_score":0.9478246,"about_ca_system_score_codex":0.000009566435,"about_ca_system_score_gemma":0.000098600955,"threshold_uncertainty_score":0.32396933},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99572843,0.00016569642,0.0023991955,0.00013003698,0.0012895126,0.00008324183,0.000041879888,0.0000018473781,0.0001601836],"genre_scores_gemma":[0.99078935,0.000016373378,0.008289908,0.00006437865,0.00070441567,4.5410266e-7,0.000109610846,0.000009899856,0.00001559077],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99915105,0.000055300443,0.00039021077,0.000119355755,0.00015432044,0.00012974179],"domain_scores_gemma":[0.99892336,0.000023740422,0.0004081697,0.00011329624,0.00046806465,0.00006335323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018667517,0.00010079436,0.00019868922,0.00010491076,0.000031503416,0.0000070783644,0.00024317933,0.00015244332,0.00010119884],"category_scores_gemma":[0.00008216137,0.00008621683,0.00010283368,0.00007080061,0.000107339096,0.0000042869624,0.00006172978,0.00018310249,0.000002740754],"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":[0.00010815644,0.00006587237,0.0048055514,0.0000087,0.00015146675,0.0000020115351,0.0000306351,0.0016587824,0.99100506,0.0011720924,0.00017266528,0.00081900647],"study_design_scores_gemma":[0.020279443,0.009599684,0.30745673,0.00005330704,0.0003292765,0.0012942313,0.00018929158,0.0008717382,0.26318833,0.21086247,0.18447788,0.001397618],"about_ca_topic_score_codex":0.000002259535,"about_ca_topic_score_gemma":0.0000029058715,"teacher_disagreement_score":0.7278167,"about_ca_system_score_codex":0.000007799424,"about_ca_system_score_gemma":0.0001272855,"threshold_uncertainty_score":0.35158202},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88541377,0.000500563,0.113205254,0.00016369925,0.00011573127,0.00023882055,0.00019265247,0.000023428018,0.00014608174],"genre_scores_gemma":[0.8533098,0.000007667969,0.1459346,0.0003378251,0.00016055268,0.00000525262,0.00021921111,0.000016465643,0.00000860261],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99818665,0.00022436214,0.00082644884,0.0002546249,0.00026996035,0.00023793406],"domain_scores_gemma":[0.99833167,0.000061689956,0.000726251,0.00021657268,0.00056251587,0.000101308426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023084432,0.0002269733,0.00043326788,0.00011304089,0.000053862237,0.000011375621,0.0003916286,0.00030808302,0.00010994598],"category_scores_gemma":[0.00020093052,0.00018139124,0.00016746816,0.000114032766,0.00021964451,0.000009251613,0.000080807644,0.00020226599,0.0000021458322],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004089587,0.0007996761,0.013176498,0.00012881706,0.0013180424,0.00008301698,0.00070970505,0.08911024,0.8578153,0.005170864,0.0014813759,0.026116831],"study_design_scores_gemma":[0.012569605,0.010425307,0.24241884,0.00029322188,0.0003374973,0.0003556909,0.00012263637,0.28041804,0.30815932,0.13895881,0.0045989743,0.0013420293],"about_ca_topic_score_codex":0.000027188898,"about_ca_topic_score_gemma":0.000008822864,"teacher_disagreement_score":0.54965603,"about_ca_system_score_codex":0.00003878068,"about_ca_system_score_gemma":0.0006221418,"threshold_uncertainty_score":0.739692},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76021045,0.00077806134,0.23837559,0.0003362252,0.000098071854,0.0001160303,0.0000103493785,0.000001631319,0.00007361541],"genre_scores_gemma":[0.9872566,0.000037860067,0.012202964,0.00024363704,0.00016504184,0.0000038110286,0.00005499662,0.0000073859337,0.000027699976],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992049,0.00008480371,0.00038809105,0.0000986269,0.00010644552,0.00011717916],"domain_scores_gemma":[0.99910885,0.000032997305,0.00030279474,0.00009534381,0.00041952397,0.000040505583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018800679,0.000090304544,0.00016093273,0.000039246268,0.000049412407,0.000010750291,0.00021349122,0.00011815488,0.000018836798],"category_scores_gemma":[0.00005343142,0.000057869584,0.000096467884,0.000059636746,0.0000921899,0.000006210757,0.000048113303,0.00012413539,0.0000023966204],"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":[0.00019692344,0.00007598874,0.0008334584,0.000018718032,0.00026698003,0.0000013039554,0.000064283566,0.08027666,0.9011485,0.0018798662,0.0014706211,0.013766712],"study_design_scores_gemma":[0.0044608326,0.0026301495,0.0023666492,0.00010111237,0.00013071972,0.00068530266,0.00026422407,0.53988117,0.23676953,0.20606524,0.0059138564,0.0007312084],"about_ca_topic_score_codex":0.000017828355,"about_ca_topic_score_gemma":8.9562224e-7,"teacher_disagreement_score":0.66437894,"about_ca_system_score_codex":0.0000083229515,"about_ca_system_score_gemma":0.000101753176,"threshold_uncertainty_score":0.23598531},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60465103,0.0005326293,0.39387488,0.0007022464,0.00006451922,0.00006399637,0.000095697906,0.0000011386823,0.000013831392],"genre_scores_gemma":[0.9745052,0.000056510264,0.024647668,0.00048932474,0.00009840049,4.5013326e-7,0.00018623182,0.0000020679836,0.000014169542],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9994834,0.000033480956,0.00025746183,0.00009100321,0.00006234802,0.00007232298],"domain_scores_gemma":[0.9988614,0.00008335387,0.0002725979,0.000028078637,0.0006976386,0.00005697399],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012381819,0.00006478541,0.00013609524,0.00006748295,0.000044448374,0.00000841087,0.000055707722,0.000038254257,0.000002285555],"category_scores_gemma":[0.00014906097,0.0000562562,0.00005607942,0.000028866174,0.00005104056,0.0000036661997,0.000015287671,0.000026942795,2.2844131e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033141496,0.00040193222,0.041488294,0.00026124527,0.00081835355,0.000025811027,0.001226067,0.5239716,0.28253,0.02981686,0.011290172,0.10485548],"study_design_scores_gemma":[0.0046666404,0.00409252,0.7886365,0.00016215294,0.00017397702,0.00024074329,0.0007822793,0.06600373,0.0020512717,0.1226233,0.010073082,0.0004937619],"about_ca_topic_score_codex":6.9803855e-7,"about_ca_topic_score_gemma":2.440741e-7,"teacher_disagreement_score":0.7471482,"about_ca_system_score_codex":0.0000035337791,"about_ca_system_score_gemma":0.00008205959,"threshold_uncertainty_score":0.22940613},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99859047,0.000026852485,0.00026902684,0.00023209938,0.00020241554,0.000030512878,0.000010338699,0.0000018939844,0.0006363702],"genre_scores_gemma":[0.9946226,0.000017508526,0.0051281396,0.00018466219,0.000017327991,5.140916e-7,0.000009092297,0.0000016792965,0.000018482488],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.999621,0.000047293786,0.00019538346,0.000038358474,0.000031474556,0.00006648822],"domain_scores_gemma":[0.999655,0.00013789331,0.00012734738,0.000030394294,0.00001880426,0.00003057516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012669498,0.00004842127,0.000113874295,0.000055208402,0.000047588273,0.000012393681,0.000086144806,0.000038568098,0.00041203038],"category_scores_gemma":[0.000004826288,0.000040698662,0.000026251499,0.000050150502,0.00020513203,0.00010974055,0.00004701464,0.00027782936,0.00001396721],"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":[0.00011495187,0.0002654067,0.0628891,0.0000041044714,0.0000558361,0.000013532712,0.004607255,0.011480174,0.9057089,0.006499947,0.0015691468,0.0067916075],"study_design_scores_gemma":[0.000895838,0.00028053927,0.93139756,0.000010229444,0.000011356536,0.00073610374,0.00077102904,0.0024982658,0.0014779143,0.03559064,0.02618267,0.00014787677],"about_ca_topic_score_codex":0.00013545749,"about_ca_topic_score_gemma":0.00060568046,"teacher_disagreement_score":0.904231,"about_ca_system_score_codex":0.000021543416,"about_ca_system_score_gemma":0.000011468946,"threshold_uncertainty_score":0.45114437},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81029195,0.00023253595,0.18803042,0.0010129542,0.000069231246,0.000086337306,0.0000037596596,0.00000264499,0.00027019644],"genre_scores_gemma":[0.92012125,0.000014756863,0.07817592,0.0014484386,0.00015387025,0.000001337339,0.00003351309,0.0000058780465,0.000045055083],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991561,0.00007030389,0.00035983208,0.00014136414,0.0001058712,0.00016651911],"domain_scores_gemma":[0.99949384,0.000020668813,0.00022852891,0.00007309141,0.00012329005,0.000060565424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024828064,0.0001093763,0.00017246141,0.00011058725,0.000033629138,0.000010151044,0.00015447162,0.00016652812,0.0000047916715],"category_scores_gemma":[0.00006276187,0.000095303956,0.00007942724,0.00007706895,0.00005060973,0.000009026171,0.000032040192,0.00018397444,0.0000015737311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045706338,0.00014270295,0.0011061463,0.000008420243,0.000082216924,0.000021837935,0.00007127406,0.5658964,0.40102023,0.0194052,0.0004220333,0.011366507],"study_design_scores_gemma":[0.0031833956,0.0018684377,0.011336342,0.00006050586,0.000029833309,0.0004596891,0.000041014646,0.23035876,0.008832604,0.74123925,0.0021402652,0.0004498932],"about_ca_topic_score_codex":0.0000016645953,"about_ca_topic_score_gemma":0.000004426054,"teacher_disagreement_score":0.72183406,"about_ca_system_score_codex":0.000030212817,"about_ca_system_score_gemma":0.0002222064,"threshold_uncertainty_score":0.38863826},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8701046,0.0015877967,0.1275567,0.00019054626,0.00014802534,0.000101613434,0.0000068182967,0.0000025090844,0.00030134758],"genre_scores_gemma":[0.84936386,0.000024430075,0.14988835,0.00025186714,0.00039352223,8.197501e-7,0.000044218446,0.00000531272,0.000027591723],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9990947,0.00009222329,0.0003868078,0.0001544695,0.000111720525,0.00016006999],"domain_scores_gemma":[0.99929684,0.000012641614,0.0003096723,0.00008775535,0.00022840696,0.00006465095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017459554,0.00011988564,0.00021466713,0.00010320001,0.000048787366,0.00001266664,0.00017506082,0.000077538614,0.00001671307],"category_scores_gemma":[0.000008850939,0.00010421991,0.00010540024,0.00006056742,0.000054681455,0.0000030161023,0.000034170276,0.00008929833,0.000006084193],"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":[0.00027122346,0.00040813044,0.0039272546,0.000014727485,0.00042199265,0.000011651385,0.00021369489,0.31072792,0.6762032,0.00071311684,0.0020322471,0.0050548785],"study_design_scores_gemma":[0.017774891,0.019795751,0.61421657,0.0001104664,0.00060350087,0.0046933866,0.0009976204,0.115649715,0.021462116,0.06758577,0.13443547,0.0026747552],"about_ca_topic_score_codex":0.0000012830694,"about_ca_topic_score_gemma":2.741775e-7,"teacher_disagreement_score":0.65474105,"about_ca_system_score_codex":0.00003664717,"about_ca_system_score_gemma":0.000121393976,"threshold_uncertainty_score":0.42499644},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91471076,0.0016219416,0.082180984,0.00064408424,0.00031676245,0.000033948218,0.000017027636,0.0000016014618,0.00047289726],"genre_scores_gemma":[0.9933891,0.00022057244,0.0058102114,0.00015796973,0.00023356781,3.4221145e-7,0.00012577209,0.000004093209,0.00005831176],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994117,0.000052940337,0.0002953897,0.000104232495,0.000070349786,0.000065369604],"domain_scores_gemma":[0.9992564,0.00002311511,0.0003279042,0.00015700948,0.00020183438,0.000033789212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021880871,0.000049886225,0.00010582587,0.000055551543,0.000019722313,0.000003879766,0.00028388636,0.00006187482,0.000028115375],"category_scores_gemma":[0.00007050267,0.000041018302,0.00004280184,0.00007145948,0.000049916947,0.000004543125,0.00006493431,0.000048193408,0.0000015959241],"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":[0.00012753971,0.0000480123,0.007320471,0.0000041280573,0.000051979667,0.0000012080362,0.000015859945,0.002059545,0.9752134,0.00041433162,0.006544082,0.008199427],"study_design_scores_gemma":[0.0026657393,0.001205268,0.03399995,0.00006478459,0.000059497615,0.0007945787,0.00025838806,0.0013943632,0.23206037,0.010222751,0.71695924,0.00031508962],"about_ca_topic_score_codex":0.0000010047373,"about_ca_topic_score_gemma":6.920631e-7,"teacher_disagreement_score":0.74315304,"about_ca_system_score_codex":0.0000055226783,"about_ca_system_score_gemma":0.000118034455,"threshold_uncertainty_score":0.16726778},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91251546,0.00022343185,0.08587614,0.0008853572,0.00003834383,0.00018148689,0.000010823912,0.0000023755626,0.0002665572],"genre_scores_gemma":[0.8276713,0.0000053127583,0.1713913,0.0006174774,0.00026190543,0.000003802499,0.000030784522,0.0000063371413,0.000011827899],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990606,0.000110208966,0.00042506272,0.00012376833,0.00012080424,0.00015959264],"domain_scores_gemma":[0.99940145,0.000027333184,0.0003209559,0.000086619584,0.00013134503,0.000032270364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040240298,0.00010717096,0.00014981219,0.000077809105,0.000055054155,0.000017361033,0.00025364588,0.00012358342,0.0000047416493],"category_scores_gemma":[0.000078917874,0.00007203807,0.00007406322,0.00008228364,0.000060485567,0.000010372643,0.000047165784,0.00020836668,7.082521e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011055319,0.00004243976,0.000803288,0.00001616916,0.000048097576,0.000004153159,0.0002860946,0.7216851,0.2573496,0.009608074,0.00026651347,0.009779903],"study_design_scores_gemma":[0.0031395305,0.0011735254,0.0015520187,0.00008219647,0.0000422233,0.0009571028,0.00026207435,0.48629227,0.024473386,0.47698268,0.0045186216,0.0005243717],"about_ca_topic_score_codex":0.0000020854156,"about_ca_topic_score_gemma":0.000019690691,"teacher_disagreement_score":0.46737462,"about_ca_system_score_codex":0.00002267984,"about_ca_system_score_gemma":0.00014542301,"threshold_uncertainty_score":0.29376274},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5568334,0.00035716902,0.43921447,0.0032255219,0.00006555689,0.00024333816,0.000025226125,0.000003893919,0.000031473355],"genre_scores_gemma":[0.84691703,0.000031423537,0.15148915,0.00058821304,0.0007745247,0.000014127817,0.00013755566,0.000013255387,0.000034748682],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991834,0.00006970903,0.00032849913,0.00019502184,0.00007864437,0.00014469771],"domain_scores_gemma":[0.9992511,0.00008413804,0.0002871726,0.000072891344,0.0001798775,0.00012480302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002908894,0.00011813702,0.00018721352,0.00008496803,0.000067542955,0.000019983529,0.000106608495,0.00011080389,0.000010472662],"category_scores_gemma":[0.00004620832,0.00009177519,0.00007122002,0.000056469642,0.000028876628,0.000011280705,0.000019267085,0.000061642444,0.0000044211233],"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":[0.0008616981,0.00002751137,0.00076171965,0.000013380209,0.0001730014,6.2560093e-7,0.00008200125,0.0034481057,0.3153625,0.0011589836,0.00046094283,0.6776495],"study_design_scores_gemma":[0.007215057,0.0097124865,0.016198272,0.00017218383,0.0003348667,0.0014943252,0.00014706804,0.003260881,0.69837964,0.15939252,0.10250135,0.0011913748],"about_ca_topic_score_codex":0.000004048687,"about_ca_topic_score_gemma":0.000011001547,"teacher_disagreement_score":0.6764581,"about_ca_system_score_codex":0.00001578712,"about_ca_system_score_gemma":0.00010199487,"threshold_uncertainty_score":0.3742484},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94183415,0.0003913576,0.05726223,0.00010069824,0.000097649165,0.00015208656,0.000029030345,0.00000436056,0.00012845446],"genre_scores_gemma":[0.91964984,0.000020989139,0.0797864,0.00020256352,0.00019354752,0.0000030946396,0.00008177708,0.000014627448,0.000047138343],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987063,0.00009898378,0.00060121005,0.00019774899,0.00015134126,0.0002444551],"domain_scores_gemma":[0.9991224,0.000024145082,0.00044449803,0.00011611363,0.00021464011,0.00007824155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025209348,0.00016316888,0.0002932397,0.00015930974,0.000087934684,0.000009833903,0.00021352925,0.00019570309,0.000008278042],"category_scores_gemma":[0.00012226075,0.0001416509,0.00009968082,0.00013224178,0.000103627004,0.000015627384,0.00008440515,0.00024857116,0.0000010515732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015751245,0.000033009368,0.0029482378,0.000017876728,0.00004844664,0.00002350174,0.00009949189,0.31936148,0.67604053,0.000825968,0.00010663537,0.00033729908],"study_design_scores_gemma":[0.0076513872,0.003099192,0.0030466341,0.00017978388,0.000055406614,0.0033990196,0.0001631494,0.62325674,0.15564959,0.2003676,0.001983932,0.0011475375],"about_ca_topic_score_codex":0.000014172465,"about_ca_topic_score_gemma":0.0000212844,"teacher_disagreement_score":0.520391,"about_ca_system_score_codex":0.000045693625,"about_ca_system_score_gemma":0.00030908495,"threshold_uncertainty_score":0.57763565},"labels":[],"label_agreement":null},{"id":"W2047429137","doi":"10.1089/cmb.2008.0031","title":"Learned Random-Walk Kernels and Empirical-Map Kernels for Protein Sequence Classification","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"String kernel; Kernel (algebra); Support vector machine; Random walk; Computer science; Kernel method; Pairwise comparison; Sequence (biology); Artificial intelligence; Pattern recognition (psychology); Random forest; Similarity (geometry); Protein sequencing; Mathematics; Machine learning; Radial basis function kernel; Biology; Peptide sequence; Combinatorics; Statistics; Genetics","score_opus":0.04333806705082064,"score_gpt":0.36681261528494014,"score_spread":0.3234745482341195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047429137","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6826909,0.00042437483,0.30807826,0.007978795,0.00014600436,0.0003849687,0.000022228842,0.000010023565,0.00026442474],"genre_scores_gemma":[0.9530387,0.000030250143,0.045446515,0.0009504565,0.00027379332,0.000005633322,0.00012515657,0.0000070155584,0.0001225046],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990201,0.000115141374,0.00047458807,0.00013860197,0.00010559744,0.00014597317],"domain_scores_gemma":[0.9988899,0.00009855233,0.0004867671,0.000087313245,0.0003496679,0.000087763474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057612587,0.00011574496,0.00020710318,0.00007747008,0.000070805414,0.000024971043,0.00014806486,0.00014779497,0.000009772348],"category_scores_gemma":[0.0006472078,0.00009434915,0.00009141605,0.000051967276,0.00009687227,0.000010476553,0.000022917648,0.00014410859,0.0000024960045],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025612307,0.000251271,0.0074987942,0.00011683349,0.00027437444,0.0000050910057,0.00034219757,0.022590853,0.8481206,0.010546174,0.0059767463,0.101715796],"study_design_scores_gemma":[0.023677787,0.016713832,0.07243971,0.00024215704,0.00019666979,0.001355905,0.00026288204,0.18445115,0.03481072,0.2841774,0.3801603,0.0015114886],"about_ca_topic_score_codex":5.73835e-7,"about_ca_topic_score_gemma":3.3429222e-7,"teacher_disagreement_score":0.8133099,"about_ca_system_score_codex":0.000016160238,"about_ca_system_score_gemma":0.00015108909,"threshold_uncertainty_score":0.38474467},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9835552,0.0037988897,0.0112757655,0.0008184742,0.00008368522,0.0000355334,0.000024079824,5.7003234e-7,0.00040781294],"genre_scores_gemma":[0.9867758,0.00070099975,0.012208469,0.00013595319,0.00012721063,3.9268042e-7,0.000010576506,0.0000027777185,0.000037777892],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99949825,0.0000337718,0.00025700295,0.0000840521,0.000050931158,0.00007601111],"domain_scores_gemma":[0.9994118,0.000033139597,0.00022107149,0.000051213305,0.0002494424,0.000033289463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011253074,0.000067762325,0.00015995288,0.000049946997,0.00003540498,0.000004518425,0.00007347205,0.000056349058,0.0000020868088],"category_scores_gemma":[0.000035681674,0.000057183308,0.00006165726,0.00003324757,0.00007707111,0.0000012148059,0.000017237699,0.00003802034,1.9248687e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011454442,0.00010163344,0.0073349127,0.0000048329434,0.00022803542,0.0000019035884,0.00024976305,0.09397534,0.8801405,0.010985138,0.0009903669,0.0058730626],"study_design_scores_gemma":[0.0032223277,0.006082016,0.53799284,0.000030373589,0.0001349135,0.00040162378,0.00049526163,0.0039768503,0.090214595,0.3414917,0.0154478075,0.0005097098],"about_ca_topic_score_codex":0.0000016294252,"about_ca_topic_score_gemma":0.0000030649178,"teacher_disagreement_score":0.7899259,"about_ca_system_score_codex":0.000005291444,"about_ca_system_score_gemma":0.00006380822,"threshold_uncertainty_score":0.23318677},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9580363,0.0005953928,0.03994491,0.0009441396,0.000028292861,0.00016740062,0.00006217216,9.897753e-7,0.00022038285],"genre_scores_gemma":[0.9966179,0.000016265467,0.0031087925,0.000103530976,0.000066803346,0.0000054246166,0.00006263322,0.0000042705815,0.000014383404],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99934316,0.00006141484,0.00034931957,0.00008395379,0.00009241202,0.000069735026],"domain_scores_gemma":[0.99913317,0.00012986863,0.00028986746,0.00006715939,0.00035084898,0.000029072735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000195618,0.00006233054,0.00014660782,0.00007686241,0.000038997132,0.0000035550106,0.00012110911,0.00004947882,0.000011297364],"category_scores_gemma":[0.00005114616,0.000046353693,0.000052745083,0.00008545511,0.000060878185,0.000001925239,0.000035329012,0.000058204714,0.0000017361962],"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":[0.00016141363,0.000505545,0.009614994,0.000043970307,0.00025970532,8.18556e-7,0.00017851313,0.1897452,0.74452084,0.05178453,0.0014189645,0.0017654827],"study_design_scores_gemma":[0.0031309556,0.005330883,0.6939421,0.000050928316,0.00021639076,0.00016965278,0.00042419872,0.007104199,0.096697785,0.15250145,0.03983404,0.00059739006],"about_ca_topic_score_codex":0.0000025275813,"about_ca_topic_score_gemma":0.000002635558,"teacher_disagreement_score":0.6843271,"about_ca_system_score_codex":0.0000062339177,"about_ca_system_score_gemma":0.000051293748,"threshold_uncertainty_score":0.18902487},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98297966,0.00023714582,0.015997108,0.00040023855,0.000066922024,0.00026113173,0.0000023748114,0.000001192318,0.000054237804],"genre_scores_gemma":[0.999305,0.000017738483,0.00046531289,0.00008466423,0.00009674165,0.000006406576,0.0000106214975,0.0000030537765,0.000010431902],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99925137,0.00013650989,0.0003738111,0.00007402906,0.000058541893,0.00010575439],"domain_scores_gemma":[0.99948144,0.000071158676,0.00026632453,0.00006784896,0.00008397373,0.00002926481],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052956626,0.000076251694,0.00013974452,0.0000623984,0.00007502076,0.000012332843,0.00008818369,0.0000671964,0.000001196559],"category_scores_gemma":[0.000048713286,0.00005017402,0.000051645427,0.00006918281,0.000041205818,0.000005344877,0.000024987308,0.00015931527,4.2108218e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010529892,0.0022772858,0.05269208,0.000064556174,0.0008206229,0.00001852035,0.001476507,0.60918695,0.12988801,0.010744708,0.0017167905,0.1805841],"study_design_scores_gemma":[0.02827862,0.14499341,0.51044035,0.00087979896,0.0002353692,0.00062824134,0.002331245,0.20252512,0.020087436,0.07053077,0.017683592,0.0013860292],"about_ca_topic_score_codex":0.0000019870324,"about_ca_topic_score_gemma":0.00002101194,"teacher_disagreement_score":0.45774826,"about_ca_system_score_codex":0.000011806786,"about_ca_system_score_gemma":0.00002483318,"threshold_uncertainty_score":0.20460373},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12463253,0.000050207494,0.8744353,0.0005328707,0.00022119026,0.00006571798,0.000053787888,0.0000026870973,0.0000056887643],"genre_scores_gemma":[0.35897267,0.000014350056,0.6407573,0.00019976996,0.000042122396,0.0000010328039,0.000009468201,0.0000020998393,0.0000011426514],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999165,0.00009958378,0.00045514264,0.000098058765,0.00007851277,0.000103725084],"domain_scores_gemma":[0.9986929,0.0005257292,0.0003916086,0.000051832805,0.0003026277,0.000035279314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040219506,0.00006317301,0.00019347471,0.0001732471,0.00002021394,0.000018674817,0.00019709245,0.00005228438,0.000003352113],"category_scores_gemma":[0.00008474629,0.000052796102,0.00005361653,0.00009258162,0.000046262245,0.00018485138,0.000023669068,0.00008424229,0.000001039073],"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":[0.00008199548,0.00020773897,0.0018192127,0.00004650905,0.00008086998,0.000031196047,0.0008182788,0.053599786,0.009063936,0.1604799,0.00021663486,0.7735539],"study_design_scores_gemma":[0.0006643858,0.000428508,0.007787975,0.000036003494,0.0000068491086,0.000098751414,0.0000037535085,0.017131751,0.00075194135,0.9728899,0.00012645764,0.0000737412],"about_ca_topic_score_codex":0.00001686576,"about_ca_topic_score_gemma":0.0000104261935,"teacher_disagreement_score":0.81241,"about_ca_system_score_codex":0.000043268006,"about_ca_system_score_gemma":0.00022120714,"threshold_uncertainty_score":0.21529625},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35444027,0.0016961984,0.64329946,0.00017138866,0.0001474644,0.00008872624,0.000025154226,0.0000035544808,0.00012775545],"genre_scores_gemma":[0.90581954,0.000046791276,0.09316606,0.00037631424,0.00051984476,0.0000012103416,0.000049557602,0.000009005613,0.000011673643],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993104,0.000052590167,0.00030519563,0.0001271148,0.00007495689,0.00012974626],"domain_scores_gemma":[0.99939835,0.000053755924,0.00023396459,0.00006778499,0.00017000375,0.000076158976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031312896,0.0000888608,0.00013659027,0.00008023525,0.00007711927,0.000012471383,0.000106249405,0.00012997506,0.00002963917],"category_scores_gemma":[0.000027623879,0.00007712255,0.00005377458,0.0000586287,0.00007813482,0.000005103054,0.000033165008,0.00010311449,0.0000016748711],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054953078,0.000019767192,0.00024948095,0.0000050200333,0.00006450257,0.0000033309614,0.000015817035,0.00010023477,0.71249783,0.0010678738,0.00011402235,0.28580716],"study_design_scores_gemma":[0.0019488429,0.001326143,0.018698359,0.00002833622,0.00007105102,0.0024971918,0.00013423376,0.00035347327,0.7403225,0.1485099,0.08564648,0.0004635343],"about_ca_topic_score_codex":7.43876e-7,"about_ca_topic_score_gemma":9.36452e-7,"teacher_disagreement_score":0.55137926,"about_ca_system_score_codex":0.0000092478085,"about_ca_system_score_gemma":0.00007824065,"threshold_uncertainty_score":0.31449664},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3732008,0.00039750573,0.6234792,0.0022961013,0.0003766767,0.00008766654,0.000028619515,0.0000024569315,0.00013097722],"genre_scores_gemma":[0.9856273,0.00002373471,0.012871878,0.0009569609,0.0004178014,0.0000062877857,0.00006233045,0.0000059528697,0.00002774923],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99931914,0.000059330894,0.00033832534,0.000113856506,0.000071593495,0.00009773355],"domain_scores_gemma":[0.9991425,0.000031382067,0.0003077725,0.00007027504,0.0003940234,0.000054021635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030765936,0.00007054083,0.00014137484,0.000052463354,0.000043395306,0.000008328504,0.00012781114,0.00009579467,0.000008127991],"category_scores_gemma":[0.00013309663,0.000057496796,0.00013289905,0.000038479764,0.00005314174,0.0000030022945,0.0000116671845,0.000050785315,0.0000018782041],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046007131,0.00008187038,0.0005452844,0.0000086241525,0.000082070386,3.8027736e-7,0.000028411476,0.010610122,0.97230023,0.008794423,0.002017187,0.005071335],"study_design_scores_gemma":[0.016623715,0.0031037205,0.05944269,0.00004211464,0.00006970871,0.0002100039,0.00017750532,0.0001441105,0.45738673,0.22753528,0.23478375,0.0004806672],"about_ca_topic_score_codex":0.0000015512496,"about_ca_topic_score_gemma":0.0000013375846,"teacher_disagreement_score":0.6124265,"about_ca_system_score_codex":0.000023397823,"about_ca_system_score_gemma":0.00029326597,"threshold_uncertainty_score":0.23446514},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25565332,0.00029398268,0.7431688,0.00065291976,0.00009447204,0.00011143515,0.0000114773375,0.0000017371245,0.000011902944],"genre_scores_gemma":[0.6745288,0.00010277161,0.3249025,0.00021662997,0.0001900767,0.0000021984276,0.000016948408,0.0000066735292,0.000033417517],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993621,0.00006443002,0.00027082744,0.00012612589,0.00006061528,0.000115879564],"domain_scores_gemma":[0.9992116,0.00010836609,0.00023879722,0.000055721433,0.0003030441,0.00008249081],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028397344,0.00008607565,0.00014313856,0.000032000207,0.00007424465,0.000010019791,0.00007219416,0.00011584701,0.0000016844261],"category_scores_gemma":[0.00012702662,0.00007259184,0.00006372322,0.000023475413,0.000077992445,0.0000051965153,0.00003309511,0.00008384629,3.6752274e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014418337,0.00018936179,0.005844004,0.000044222877,0.00044272284,0.000031545995,0.00018360445,0.018322885,0.9434464,0.006432971,0.008050302,0.015570141],"study_design_scores_gemma":[0.019831063,0.026461838,0.03762312,0.000103785576,0.00042491345,0.04381247,0.00032893603,0.22536464,0.1383889,0.40199676,0.10327581,0.0023877649],"about_ca_topic_score_codex":0.0000018731896,"about_ca_topic_score_gemma":0.0000015516925,"teacher_disagreement_score":0.8050575,"about_ca_system_score_codex":0.000013833672,"about_ca_system_score_gemma":0.0004970952,"threshold_uncertainty_score":0.29602095},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8393068,0.0008592559,0.1589122,0.00030176586,0.00017928574,0.00006899359,0.000001357799,0.000002855345,0.0003675018],"genre_scores_gemma":[0.9909842,0.00020687887,0.008125323,0.00015530421,0.00037260726,0.0000020572363,0.00006039335,0.000010424636,0.00008278765],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9993395,0.0000848976,0.00022941909,0.000118860786,0.000093816336,0.00013348575],"domain_scores_gemma":[0.9993204,0.00002888897,0.00022266063,0.00006948215,0.0003076611,0.000050918734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002184243,0.00009129107,0.000130274,0.00008235119,0.000040340397,0.000010664198,0.0001237713,0.00008013881,0.000031220065],"category_scores_gemma":[0.0000235292,0.00007083594,0.00006181233,0.00009773399,0.000056009976,0.0000032977887,0.000023305998,0.00008441081,0.0000042035613],"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":[0.0009656858,0.0003835708,0.1649445,0.000013597299,0.0007019946,0.00005367761,0.000066414475,0.6868437,0.07161407,0.0006916008,0.0020511986,0.07167],"study_design_scores_gemma":[0.016442463,0.028968412,0.70174927,0.00011958741,0.00034403522,0.009834047,0.00021947027,0.041392572,0.008591129,0.023434257,0.16723296,0.0016718305],"about_ca_topic_score_codex":9.5031083e-7,"about_ca_topic_score_gemma":0.0000020294863,"teacher_disagreement_score":0.6454511,"about_ca_system_score_codex":0.000015855201,"about_ca_system_score_gemma":0.00006741132,"threshold_uncertainty_score":0.28886056},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9421309,0.0009876231,0.056020036,0.0004339006,0.0002130999,0.000086859036,0.00006674301,0.0000010143068,0.00005977207],"genre_scores_gemma":[0.98331225,0.00019065746,0.01569591,0.00046268434,0.00028496026,0.000004645793,0.000030841795,0.0000068429426,0.000011180846],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993164,0.000056034056,0.00027314827,0.00014598275,0.000057926245,0.00015048776],"domain_scores_gemma":[0.9993561,0.00012191697,0.00021550537,0.00005676884,0.00019321135,0.000056483666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030361325,0.000097606906,0.00017044372,0.00003378486,0.000082776845,0.000011282282,0.00010291415,0.000060857736,0.0000022058903],"category_scores_gemma":[0.00014129825,0.00007959605,0.000070488844,0.000021234579,0.00010355094,0.0000013379779,0.000031779473,0.00004110746,6.619759e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010444282,0.000039406306,0.020877292,0.000014720921,0.00013476676,8.0192467e-7,0.000072636714,0.002291101,0.96984535,0.0023006324,0.00045910984,0.0038597523],"study_design_scores_gemma":[0.00955601,0.010548881,0.14191811,0.000074728916,0.00018743893,0.0007173788,0.00064274017,0.007781061,0.34979594,0.125366,0.3522577,0.001154015],"about_ca_topic_score_codex":0.0000025150675,"about_ca_topic_score_gemma":0.000005863698,"teacher_disagreement_score":0.6200494,"about_ca_system_score_codex":0.00000910698,"about_ca_system_score_gemma":0.0000498546,"threshold_uncertainty_score":0.32458326},"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":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000044842167,0.9960496,0.0031292182,0.000073491814,0.00018346723,0.00014227189,0.00020083004,0.000004149115,0.00017216898],"genre_scores_gemma":[0.0003748711,0.9931255,0.0015746694,0.0007153692,0.0006650759,0.000009089942,0.0034543544,0.000016925056,0.000064142456],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979939,0.00035941068,0.0009758726,0.00032514293,0.00016788997,0.0001777798],"domain_scores_gemma":[0.9979848,0.00006292302,0.0011989799,0.00023723392,0.00040827293,0.00010776965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004322315,0.00031613643,0.0013736708,0.0005592524,0.000044110704,0.000019003892,0.00032995275,0.00038973967,0.000075398915],"category_scores_gemma":[0.00011383963,0.00021545951,0.0018185868,0.00075265474,0.000069433496,0.0000063308376,0.000031427528,0.00035912255,0.000014345524],"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":[0.00038923122,0.00094731175,0.00024219953,0.01677076,0.022648597,0.00028956484,0.00003065804,0.008947495,0.00030943312,0.0005838961,0.012946035,0.93589485],"study_design_scores_gemma":[0.00026873816,0.0013578924,0.0000703086,0.0102366675,0.0082642445,0.0004214344,0.000001037256,0.00019327969,0.000036296056,0.00056894077,0.9782403,0.00034084605],"about_ca_topic_score_codex":0.000001232616,"about_ca_topic_score_gemma":0.0000012513356,"teacher_disagreement_score":0.9652943,"about_ca_system_score_codex":0.0000409858,"about_ca_system_score_gemma":0.000381143,"threshold_uncertainty_score":0.87861836},"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":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007392652,0.99762034,0.000450597,0.0005019075,0.0004780787,0.00012859357,0.000036321537,0.0000021435083,0.000042733096],"genre_scores_gemma":[0.00036977025,0.9937277,0.0034119545,0.0010237258,0.0008699475,0.000009702161,0.00055161136,0.00001525993,0.000020356392],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973201,0.0012583463,0.00079101406,0.00022791202,0.00018250974,0.00022012589],"domain_scores_gemma":[0.99856883,0.00042949757,0.0006029246,0.0002134189,0.00012049195,0.00006480545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014260017,0.0002442596,0.0007120127,0.00014702235,0.000076916906,0.00004626896,0.0007986201,0.0005671188,0.000011751832],"category_scores_gemma":[0.0002687662,0.00010970533,0.0003623672,0.00028342826,0.00032374408,0.0000033347844,0.00006942468,0.0006703572,0.0000037214122],"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":[0.00001974639,0.00011505429,0.00001981734,0.00041065083,0.00020124676,0.000049123264,0.00018145583,0.00002490669,0.000012333826,0.000647363,0.0056606107,0.99265766],"study_design_scores_gemma":[0.00023347195,0.00056053774,0.000105920444,0.00074498396,0.00009163529,0.0019324363,0.000059541064,0.000008368917,2.514211e-7,0.0011884258,0.9949473,0.00012710485],"about_ca_topic_score_codex":9.840843e-7,"about_ca_topic_score_gemma":0.0000024832293,"teacher_disagreement_score":0.9925306,"about_ca_system_score_codex":0.000023715571,"about_ca_system_score_gemma":0.0005418135,"threshold_uncertainty_score":0.44736534},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96869934,0.000045984918,0.030646835,0.00033049483,0.00011368548,0.000091736445,0.00003936545,0.000010824374,0.000021747734],"genre_scores_gemma":[0.96325743,7.401962e-7,0.03652351,0.00010894338,0.000045081186,0.0000012417408,0.0000485925,0.000011668535,0.0000028145575],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998312,0.00027601846,0.00082729914,0.00018737739,0.00022790118,0.00016938146],"domain_scores_gemma":[0.99766904,0.00066814385,0.00092906674,0.00012568494,0.0005049873,0.00010304983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000765557,0.00014657942,0.00067610753,0.0006111407,0.00007769266,0.00002132504,0.00017342073,0.0000943958,0.000008510202],"category_scores_gemma":[0.000106301166,0.0001085621,0.00026276236,0.00038282853,0.00019761089,0.000059545244,0.000035859044,0.000099771,2.926748e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006329793,0.00043317332,0.00065093674,0.000011340935,0.0004016362,0.0000026694795,0.00047952647,0.028636785,0.9623087,0.00032538272,0.000019159726,0.000400911],"study_design_scores_gemma":[0.0008815468,0.006103943,0.0033702191,0.000067040455,0.0005855327,0.000048941463,0.0002316812,0.038090672,0.94926137,0.0010597331,0.00013112115,0.00016821423],"about_ca_topic_score_codex":0.000019412806,"about_ca_topic_score_gemma":0.000005647252,"teacher_disagreement_score":0.013047331,"about_ca_system_score_codex":0.00009808568,"about_ca_system_score_gemma":0.00003974339,"threshold_uncertainty_score":0.44270337},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9200696,0.0067302384,0.0706812,0.00073423114,0.00038722417,0.00012924308,0.000013487157,0.0000089819905,0.0012458323],"genre_scores_gemma":[0.90409917,0.00029091453,0.09489477,0.00015344385,0.00043845057,6.826693e-7,0.000018524868,0.000008991486,0.0000950457],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99928683,0.000066329245,0.00025755484,0.00015991571,0.00008593273,0.00014346068],"domain_scores_gemma":[0.9993468,0.000031333613,0.00025050214,0.000060209368,0.00021057301,0.000100613295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002222769,0.000101940874,0.00015201504,0.000073027404,0.000037666403,0.0000108982385,0.00013615451,0.000087577806,0.000031576863],"category_scores_gemma":[0.000087103756,0.000087525026,0.00006588558,0.000047112073,0.00011524953,0.000007189139,0.000055666707,0.000097218894,0.0000030032602],"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":[0.0022284966,0.0013972746,0.14600131,0.00015615043,0.0065740934,0.0005699886,0.030934097,0.008449995,0.4805055,0.018939244,0.019603396,0.28464043],"study_design_scores_gemma":[0.021366963,0.028086003,0.34019214,0.00030926339,0.0009822119,0.016385254,0.015664266,0.0070210686,0.039964307,0.39535177,0.13068266,0.0039940886],"about_ca_topic_score_codex":0.000025334857,"about_ca_topic_score_gemma":0.0000025008953,"teacher_disagreement_score":0.4405412,"about_ca_system_score_codex":0.000016630675,"about_ca_system_score_gemma":0.0001441644,"threshold_uncertainty_score":0.3569167},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.991118,0.001893924,0.006270658,0.00027146444,0.000063074964,0.00009771679,0.000015684807,6.011874e-7,0.00026883473],"genre_scores_gemma":[0.99646384,0.0000296023,0.0033357786,0.000024646113,0.0000984481,0.0000016122837,0.00004058669,0.0000029975806,0.0000024880824],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99881417,0.00021501996,0.0005992687,0.000087804285,0.00019002371,0.00009371173],"domain_scores_gemma":[0.9990484,0.000068553825,0.00047171736,0.000089891415,0.00030785787,0.000013582034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000817855,0.00006965898,0.00021827631,0.00007622092,0.00001617541,0.0000034388943,0.00022616689,0.00005753408,0.000013305694],"category_scores_gemma":[0.000045953107,0.000047648406,0.00008814359,0.0000965348,0.00015000555,0.000002944466,0.000026116302,0.00007225223,4.1777184e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013231521,0.0003465162,0.15429041,0.000027449552,0.00008321943,0.0000013820327,0.00023099929,0.028994048,0.8138351,0.0006371843,0.00014423043,0.0012771847],"study_design_scores_gemma":[0.0019241027,0.0026688064,0.87595695,0.000028006298,0.000058374513,0.000055110682,0.0010675635,0.0005184408,0.092170276,0.0187437,0.006597318,0.00021136749],"about_ca_topic_score_codex":0.000033439785,"about_ca_topic_score_gemma":0.000033267195,"teacher_disagreement_score":0.7216665,"about_ca_system_score_codex":0.000014197359,"about_ca_system_score_gemma":0.00008786871,"threshold_uncertainty_score":0.19430457},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7075256,0.000094957955,0.29075646,0.0014462924,0.000036902642,0.000052639698,0.000005457299,0.0000035870596,0.00007812055],"genre_scores_gemma":[0.9337746,0.00002586679,0.06528548,0.0008185606,0.000075579344,2.2008153e-7,0.00001213653,0.0000025928375,0.000004945541],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992619,0.00017283205,0.00031325236,0.00008382627,0.000086531334,0.00008165719],"domain_scores_gemma":[0.99912,0.00015310729,0.00037273634,0.00008740012,0.00024285007,0.000023931838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003874357,0.00007555739,0.00017483815,0.000056527966,0.000041233387,0.000005077861,0.0001395157,0.0000661278,0.0000022837646],"category_scores_gemma":[0.00021117147,0.000044688448,0.00012693273,0.00007052763,0.00016663551,0.0000017690905,0.000013286716,0.00008626157,4.0648928e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006361459,0.00012729775,0.000066073684,0.0000017560191,0.0001249857,0.0000025993318,0.000012560092,0.007311403,0.97324055,0.011622257,0.00088684045,0.0059675453],"study_design_scores_gemma":[0.0005474031,0.003552783,0.0024672374,0.00002921004,0.000038537164,0.00011877393,0.000018977475,0.00174826,0.62255317,0.36820945,0.00058150705,0.0001346836],"about_ca_topic_score_codex":4.6106467e-7,"about_ca_topic_score_gemma":1.3587781e-7,"teacher_disagreement_score":0.3565872,"about_ca_system_score_codex":0.0000067952433,"about_ca_system_score_gemma":0.00004484722,"threshold_uncertainty_score":0.1822342},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6030943,0.0068467855,0.38839206,0.0010135772,0.0003342694,0.00017760559,0.000026151498,9.579558e-7,0.00011433026],"genre_scores_gemma":[0.9714349,0.0002697338,0.027450928,0.00033246825,0.0004784903,0.0000027494088,0.000010516689,0.000006966793,0.000013232642],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999418,0.000020906442,0.0002675275,0.00009934858,0.000051778614,0.00014239],"domain_scores_gemma":[0.99925387,0.00022244714,0.0001846403,0.00004995495,0.00024552873,0.000043573484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051575614,0.00007857393,0.000118396354,0.00003578605,0.000089189125,0.000009642632,0.00010255307,0.00006525596,0.0000015031161],"category_scores_gemma":[0.000058529033,0.000051378076,0.000066182896,0.000029275894,0.000090795635,5.936626e-7,0.000046721405,0.000061623985,3.9367018e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017862725,0.00037962614,0.045999758,0.00009495461,0.002362551,0.00001602352,0.00063088804,0.0120163495,0.3309372,0.007023279,0.008136205,0.5906169],"study_design_scores_gemma":[0.005543706,0.0061872383,0.3044051,0.000030838346,0.00024939503,0.0012350169,0.0004947062,0.0024730342,0.010176894,0.4286989,0.23989084,0.00061433035],"about_ca_topic_score_codex":0.000002172637,"about_ca_topic_score_gemma":0.0000042533698,"teacher_disagreement_score":0.59000254,"about_ca_system_score_codex":0.0000059661666,"about_ca_system_score_gemma":0.00006415708,"threshold_uncertainty_score":0.20951371},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9558168,0.0006147121,0.04296158,0.00024058936,0.00021596033,0.000032169417,0.0000024073688,0.0000010926411,0.00011467822],"genre_scores_gemma":[0.99645966,0.0001456565,0.0027660185,0.0001969794,0.0003830805,6.879559e-7,0.000017376147,0.000005395034,0.000025133657],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9992495,0.00013983775,0.00034201992,0.000089428024,0.000090720765,0.00008848013],"domain_scores_gemma":[0.99907947,0.00009096022,0.00041650294,0.000103098464,0.0002765334,0.000033438853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024826243,0.000073245275,0.00015866506,0.00006273096,0.00006169415,0.0000020412988,0.0001351144,0.00008836296,0.000028281735],"category_scores_gemma":[0.000061281375,0.00004921509,0.00015776703,0.00009671031,0.00017232882,0.0000018844233,0.000017841536,0.00008969994,0.0000017985308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020533167,0.000061473955,0.010694164,0.000001712896,0.00037571424,0.000004671488,0.000018749633,0.9446543,0.035092637,0.0016508913,0.003669068,0.0035713047],"study_design_scores_gemma":[0.008609679,0.012678757,0.37129936,0.00018687075,0.0007543483,0.021597173,0.0003280703,0.16086806,0.28568375,0.11088553,0.025310295,0.0017981002],"about_ca_topic_score_codex":9.076721e-7,"about_ca_topic_score_gemma":8.282496e-7,"teacher_disagreement_score":0.78378624,"about_ca_system_score_codex":0.000009234626,"about_ca_system_score_gemma":0.00008705133,"threshold_uncertainty_score":0.20069332},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86175144,0.0007365888,0.13505606,0.00091114326,0.00017292309,0.000056613142,0.000018005729,0.0000034599582,0.00129374],"genre_scores_gemma":[0.99415714,0.000012487188,0.0050654025,0.00020218689,0.0002673261,0.0000013201092,0.0001586531,0.0000066963585,0.00012876278],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994162,0.000042931835,0.00027596907,0.00008649193,0.00008115253,0.0000973027],"domain_scores_gemma":[0.9995526,0.000035988392,0.00018620529,0.00004733671,0.00015063024,0.000027207985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014262491,0.000065291766,0.000091506336,0.00005722681,0.00003967055,0.0000072673274,0.000095746116,0.000058927584,0.000020197083],"category_scores_gemma":[0.00002663336,0.000056961984,0.00007155283,0.000048649545,0.000039148523,0.0000019913668,0.000008529249,0.00006280567,0.000007396128],"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":[0.0001459891,0.0004265773,0.0049916417,0.000010278387,0.0001986626,0.0000050717726,0.000029740246,0.10675262,0.81718624,0.014003871,0.045339026,0.010910304],"study_design_scores_gemma":[0.01007514,0.0084992815,0.05249779,0.00007361763,0.00017508084,0.00072016445,0.00013746913,0.0045510773,0.1546614,0.49553394,0.27174905,0.0013260014],"about_ca_topic_score_codex":0.0000026988175,"about_ca_topic_score_gemma":0.0000012841041,"teacher_disagreement_score":0.6625248,"about_ca_system_score_codex":0.0000103882885,"about_ca_system_score_gemma":0.000051344374,"threshold_uncertainty_score":0.23228423},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31204635,0.0014321975,0.6838478,0.0015538232,0.00006543077,0.000031461062,0.0007107402,0.000018688957,0.0002935294],"genre_scores_gemma":[0.49224004,0.00023389625,0.50669426,0.00013146672,0.0003529577,0.0000025129614,0.0003127533,0.0000081287635,0.000023944398],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991639,0.000012035449,0.00040298793,0.00017787647,0.00012198784,0.00012118821],"domain_scores_gemma":[0.9988322,0.0004049324,0.00041426008,0.0001832171,0.00010204457,0.000063349355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001347639,0.000091701404,0.00016945277,0.00007288467,0.00006147509,0.000017681024,0.00048450817,0.000096878786,0.00066895137],"category_scores_gemma":[0.000061231825,0.00008080486,0.000049034865,0.000100402875,0.000048756265,0.00013540621,0.000085871536,0.00019975398,0.000007961919],"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":[0.00019365727,0.00013094833,0.0076294914,0.00000801212,0.0002705735,0.0000052774662,0.00002894444,0.0058538076,0.8236658,0.0012496646,0.029607762,0.13135605],"study_design_scores_gemma":[0.0024985957,0.00012046771,0.0022099025,0.00021866486,0.00011530823,0.00014055472,0.000068293855,0.040652707,0.20629503,0.43886736,0.30815366,0.0006594603],"about_ca_topic_score_codex":0.000016882494,"about_ca_topic_score_gemma":0.0000027791677,"teacher_disagreement_score":0.6173708,"about_ca_system_score_codex":0.000116371186,"about_ca_system_score_gemma":0.00007293646,"threshold_uncertainty_score":0.73245484},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9132901,0.0002921635,0.083247535,0.00077691075,0.0008216811,0.000044041037,0.000018920455,0.000005586221,0.0015031014],"genre_scores_gemma":[0.9912008,0.000049778566,0.007025228,0.0009633313,0.0006346348,3.3896734e-7,0.000044094468,0.000005552578,0.000076228054],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99934834,0.000035126774,0.00025841707,0.00012465019,0.000085451626,0.00014802777],"domain_scores_gemma":[0.99935246,0.00004041079,0.000209146,0.000080214035,0.00023618949,0.00008161401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019895565,0.00009697325,0.00015740797,0.000062106614,0.00007906679,0.000017515702,0.00019038815,0.00013853409,0.00009339441],"category_scores_gemma":[0.000044329507,0.00008188507,0.000109798624,0.00004087061,0.0000719574,0.000003244255,0.00009244784,0.00018317046,0.0000120444],"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":[0.00043802842,0.00022264582,0.07632659,0.000019752755,0.0005540359,0.000030397461,0.00012864808,0.03343458,0.8214098,0.002631542,0.036173273,0.028630683],"study_design_scores_gemma":[0.004957522,0.0038176496,0.19939442,0.000054186155,0.00017578181,0.0028763376,0.00008939798,0.024389211,0.0107411705,0.050999045,0.7013399,0.0011653593],"about_ca_topic_score_codex":0.0000049465534,"about_ca_topic_score_gemma":0.0000066648495,"teacher_disagreement_score":0.81066865,"about_ca_system_score_codex":0.0000029287246,"about_ca_system_score_gemma":0.0000557992,"threshold_uncertainty_score":0.33391762},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95950824,0.0015230919,0.03824703,0.00047239903,0.000059767834,0.00010726889,0.0000056341987,0.000002645985,0.00007391326],"genre_scores_gemma":[0.98301435,0.00012260319,0.016494554,0.00013523715,0.00016728081,7.5847197e-7,0.00004999593,0.000006755937,0.000008462247],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99922216,0.00007396891,0.00031305687,0.00013585275,0.0001423979,0.00011254059],"domain_scores_gemma":[0.9991968,0.000021891228,0.00031377716,0.00006256929,0.00035058483,0.00005435682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023129654,0.00010584195,0.00021279416,0.00010772106,0.000034743505,0.00000714548,0.00008586742,0.00007116406,0.0000067115507],"category_scores_gemma":[0.00002619178,0.0000830135,0.0000616211,0.000077840465,0.000088367284,0.0000060429384,0.000020111285,0.000074364325,9.496379e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007141981,0.00044002073,0.023066455,0.00009055869,0.0007372381,0.000029914783,0.0003364206,0.11351725,0.80791014,0.00038950113,0.0004844184,0.05228387],"study_design_scores_gemma":[0.02263088,0.049352948,0.747265,0.0005103792,0.000670305,0.003979736,0.00072104845,0.031032935,0.10246027,0.02279153,0.016788106,0.0017968667],"about_ca_topic_score_codex":0.0000015717912,"about_ca_topic_score_gemma":5.792617e-7,"teacher_disagreement_score":0.7241985,"about_ca_system_score_codex":0.000012799292,"about_ca_system_score_gemma":0.00008686195,"threshold_uncertainty_score":0.33851925},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9583275,0.0012350433,0.039739203,0.00005019694,0.00016943915,0.000028460023,0.000045017303,5.8248594e-7,0.0004045906],"genre_scores_gemma":[0.9878535,0.00002941657,0.011811624,0.00014889939,0.00008437966,0.0000010806477,0.000051126754,0.0000044389785,0.000015485077],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9993106,0.00005927251,0.00036625707,0.00010091319,0.0000790942,0.00008387348],"domain_scores_gemma":[0.99907553,0.00004750609,0.00036125083,0.00007622896,0.0004022402,0.00003722007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021387597,0.00007861876,0.0002497481,0.00021361494,0.00002747246,0.0000020386342,0.0001111026,0.000060670594,0.00006780113],"category_scores_gemma":[0.00003733929,0.000063651154,0.00027057974,0.00016008972,0.00009479916,6.136119e-7,0.000029385728,0.0000408572,9.832411e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007784399,0.00041787617,0.17586157,0.00001548236,0.010666181,0.0000057885777,0.00021616934,0.14196709,0.658451,0.0065804864,0.00041907822,0.0046208133],"study_design_scores_gemma":[0.0009519025,0.0013671961,0.9338204,0.000003624482,0.00076719985,0.000020094698,0.00006550579,0.0009994728,0.049084317,0.0078173,0.004921881,0.00018107361],"about_ca_topic_score_codex":0.0000041059957,"about_ca_topic_score_gemma":0.0000042449883,"teacher_disagreement_score":0.7579589,"about_ca_system_score_codex":0.0000054717834,"about_ca_system_score_gemma":0.00015332203,"threshold_uncertainty_score":0.25956187},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00095888274,0.00039017055,0.99456906,0.0028603154,0.0006986338,0.00023197998,0.000025436068,0.000040844196,0.00022464883],"genre_scores_gemma":[0.10818917,0.00003826324,0.8892823,0.0011151446,0.001246332,0.00002131105,0.00004061819,0.00001297304,0.000053892854],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998428,0.0001625644,0.0006200317,0.0002307913,0.00030129906,0.00025734992],"domain_scores_gemma":[0.9977674,0.00094609667,0.00053993124,0.00020924336,0.00046579435,0.000071571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008893378,0.00015221229,0.00024097385,0.00016721622,0.00031064052,0.00013429612,0.0009437801,0.00008482047,0.000007555665],"category_scores_gemma":[0.00001309127,0.000104732404,0.00019411488,0.00034353792,0.00012543102,0.00039889847,0.00007432458,0.000174171,0.0000075402536],"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":[0.00005621641,0.0007510064,0.00027402316,0.000010493229,0.00016471649,0.000016008495,0.00008177553,0.17122568,0.0037783217,0.33271456,0.027437922,0.46348926],"study_design_scores_gemma":[0.00079347345,0.00088039186,0.00089542277,0.000011798418,0.000023080665,0.00022156848,0.0000074799514,0.45161206,0.00043376235,0.51829624,0.026672376,0.0001523697],"about_ca_topic_score_codex":0.000017148028,"about_ca_topic_score_gemma":0.0000015973214,"teacher_disagreement_score":0.46333688,"about_ca_system_score_codex":0.00005621268,"about_ca_system_score_gemma":0.00016777983,"threshold_uncertainty_score":0.42708632},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7144454,0.0014806689,0.28338236,0.00016419131,0.00020678485,0.0000371293,0.00009365834,0.0000013962795,0.000188388],"genre_scores_gemma":[0.98424464,0.00012428798,0.014529696,0.00017155948,0.00016771072,2.0750511e-7,0.0007279404,0.0000042787806,0.000029694982],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991441,0.000054601194,0.0005079728,0.00010772439,0.00008959846,0.00009603297],"domain_scores_gemma":[0.9988765,0.000042938387,0.000566626,0.00021967132,0.00024575432,0.00004848598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029308116,0.00007987939,0.00026062943,0.00015082382,0.000042468404,0.000002863423,0.00033589767,0.00011256923,0.000020494688],"category_scores_gemma":[0.000035076817,0.000059151047,0.00013607737,0.00016648439,0.00011231212,0.0000054741445,0.00012089253,0.00008368966,0.000001456051],"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":[0.0010331006,0.0005449418,0.06769045,0.000046387395,0.008510036,0.00003662478,0.0005038205,0.15932468,0.67192525,0.0014417043,0.028720785,0.06022221],"study_design_scores_gemma":[0.010225158,0.0070019527,0.38283965,0.00017932171,0.0029227852,0.004216876,0.00033317256,0.24996959,0.07494659,0.037559718,0.22770919,0.002096009],"about_ca_topic_score_codex":0.0000025934478,"about_ca_topic_score_gemma":0.0000030317094,"teacher_disagreement_score":0.59697866,"about_ca_system_score_codex":0.0000059916765,"about_ca_system_score_gemma":0.00014573675,"threshold_uncertainty_score":0.24121097},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7744188,0.000143756,0.22398752,0.0005699231,0.00043139505,0.000062380524,0.000004167201,0.0000110798055,0.00037097576],"genre_scores_gemma":[0.9802206,0.000077088866,0.018688824,0.00046862417,0.00046489527,6.2068966e-7,0.000027528245,0.000007344492,0.00004446921],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992204,0.00012963188,0.0002928343,0.00012783687,0.00010843516,0.0001208966],"domain_scores_gemma":[0.9992324,0.000095815594,0.00025974374,0.00008381371,0.00027528495,0.000052933734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002860624,0.00010054303,0.00017088494,0.000101193364,0.00004985054,0.000009489306,0.00013117453,0.00012051888,0.000004806879],"category_scores_gemma":[0.00015270905,0.000076998156,0.000120239165,0.00009753362,0.00008012629,0.0000029345822,0.000023540772,0.00010431632,0.0000032759756],"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":[0.0049793846,0.00088540785,0.0023592697,0.0000075201738,0.00075047335,0.0001186535,0.000033561035,0.023828145,0.8624532,0.021173637,0.025638461,0.057772294],"study_design_scores_gemma":[0.004117083,0.009924923,0.0034291863,0.00006862491,0.00011837215,0.0014535827,0.0000392758,0.0010616175,0.3746721,0.519545,0.08485576,0.0007144515],"about_ca_topic_score_codex":4.6797476e-7,"about_ca_topic_score_gemma":3.0474848e-7,"teacher_disagreement_score":0.49837136,"about_ca_system_score_codex":0.00001662436,"about_ca_system_score_gemma":0.00007101839,"threshold_uncertainty_score":0.31398934},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6019368,0.0015265815,0.39560482,0.0005200074,0.00013021908,0.000068996276,0.00007298062,0.0000020231132,0.00013756851],"genre_scores_gemma":[0.96981716,0.00009391717,0.028636709,0.00041820062,0.00030201336,0.0000030372805,0.0006048842,0.000010215248,0.00011386655],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989846,0.00007915946,0.0004362656,0.0002477342,0.00010742875,0.00014483194],"domain_scores_gemma":[0.9992872,0.000018702196,0.0002997248,0.0001807328,0.00017125101,0.000042391406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034003443,0.000112653,0.00018142768,0.00012760659,0.00004142774,0.000016441867,0.00033245672,0.0001253138,0.0000070163264],"category_scores_gemma":[0.000022794946,0.00009727722,0.00006054383,0.00009004065,0.00005681744,0.000012288386,0.000050031995,0.00011665415,0.0000011902084],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008928966,0.00007729323,0.0011502445,0.00000394199,0.000020876361,0.0000012198411,0.00003579474,0.15159158,0.84536123,0.0003261251,0.0010321038,0.0003102691],"study_design_scores_gemma":[0.014354482,0.0014115904,0.13470279,0.00016587584,0.0001514114,0.00079833705,0.0006600454,0.25583917,0.45307392,0.05594345,0.08115067,0.0017482523],"about_ca_topic_score_codex":0.000005585691,"about_ca_topic_score_gemma":0.000014939541,"teacher_disagreement_score":0.3922873,"about_ca_system_score_codex":0.000026240248,"about_ca_system_score_gemma":0.00023507336,"threshold_uncertainty_score":0.39668497},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60397553,0.0006059501,0.39494044,0.00016718303,0.00010531185,0.000074168114,0.000088663015,6.050546e-7,0.00004212989],"genre_scores_gemma":[0.94354326,0.000037963502,0.05600346,0.0001902372,0.00013185528,0.000007751966,0.00007046649,0.0000045613388,0.000010479828],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99940056,0.000047218626,0.00027487145,0.00012825316,0.00004615558,0.00010295371],"domain_scores_gemma":[0.9993997,0.00004390366,0.00014015929,0.00006388612,0.00031162534,0.000040705163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017494019,0.000080953505,0.00014237285,0.000029880039,0.00007285815,0.000005910734,0.000074476106,0.00008526872,0.0000050541084],"category_scores_gemma":[0.00008820872,0.000070369744,0.0001265625,0.000027156802,0.00008085074,9.66229e-7,0.000009157527,0.000047877376,4.821324e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023301563,0.00018102756,0.0020411422,0.000008077792,0.00028432565,6.466112e-7,0.00022056181,0.46178377,0.5257729,0.008078989,0.000544884,0.0008506212],"study_design_scores_gemma":[0.004102901,0.0016574758,0.010883438,0.000016949745,0.00018995456,0.00012819935,0.00010154948,0.052531507,0.07271124,0.84224725,0.014972225,0.00045731745],"about_ca_topic_score_codex":0.0000016331062,"about_ca_topic_score_gemma":0.000006434841,"teacher_disagreement_score":0.83416826,"about_ca_system_score_codex":0.000012776179,"about_ca_system_score_gemma":0.00016865568,"threshold_uncertainty_score":0.28695947},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61099416,0.0013086091,0.3853019,0.0011799656,0.0007351749,0.0003183347,0.000042245225,0.00000753368,0.000112077934],"genre_scores_gemma":[0.91320705,0.00013266494,0.08460007,0.00035218292,0.0011957787,0.000021233876,0.00022741483,0.000016131116,0.00024749324],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992954,0.000064495754,0.0003114202,0.0001444731,0.00009185495,0.000092322836],"domain_scores_gemma":[0.9990798,0.00009171203,0.00031319834,0.000093113034,0.0003828992,0.00003924604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016027586,0.00008100803,0.00012047249,0.000040362065,0.00012570077,0.0000070328397,0.00014084081,0.00009800568,0.000028480572],"category_scores_gemma":[0.000097641016,0.000055421006,0.00009328294,0.00005256787,0.00010883841,0.0000050733706,0.0000171701,0.0000757337,0.000006468111],"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":[0.0012425273,0.00033023424,0.0053002466,0.000021917816,0.0006887057,0.0000041949047,0.00022454675,0.06907159,0.80383736,0.0006045661,0.020101938,0.09857217],"study_design_scores_gemma":[0.011643501,0.0064429333,0.06311524,0.00020725906,0.0004096817,0.0022109088,0.00027435547,0.16222316,0.111983545,0.13897252,0.5012627,0.0012541504],"about_ca_topic_score_codex":0.0000035759026,"about_ca_topic_score_gemma":6.6535756e-7,"teacher_disagreement_score":0.6918538,"about_ca_system_score_codex":0.000019547375,"about_ca_system_score_gemma":0.00018133155,"threshold_uncertainty_score":0.22600031},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64957905,0.00048469694,0.34938458,0.00029069788,0.00006905234,0.000110208646,0.000051386764,0.0000026635596,0.000027697979],"genre_scores_gemma":[0.9186904,0.0000806869,0.080610365,0.00030043503,0.00024475693,0.0000021174778,0.00005757326,0.0000070472574,0.000006656718],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991556,0.000096982105,0.00040222943,0.00014238192,0.000077414756,0.00012543554],"domain_scores_gemma":[0.99939793,0.000047637135,0.00024756943,0.00007022824,0.00017557663,0.000061025512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003999315,0.00009583426,0.0002082879,0.00010913961,0.000042687818,0.000010191418,0.0001058534,0.00014737564,0.000002747371],"category_scores_gemma":[0.000049514652,0.00008586106,0.00007421069,0.00005458838,0.000055303182,0.000012548097,0.000012011972,0.00006680974,1.5290361e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026223744,0.00020372507,0.0016079099,0.000012831351,0.00005467112,0.0000029583148,0.00015178682,0.012732631,0.7589083,0.0012425234,0.0001332596,0.22468717],"study_design_scores_gemma":[0.010852889,0.029517084,0.050472856,0.00030132735,0.0001499588,0.0011340397,0.00063166354,0.24369442,0.50830954,0.13733539,0.016752584,0.0008482396],"about_ca_topic_score_codex":0.0000017152352,"about_ca_topic_score_gemma":6.512685e-7,"teacher_disagreement_score":0.26911134,"about_ca_system_score_codex":0.000010138339,"about_ca_system_score_gemma":0.00008136927,"threshold_uncertainty_score":0.3501312},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.966183,0.000048054815,0.033092886,0.00020994259,0.00010919564,0.00009493825,0.000012739348,0.0000025644424,0.0002466499],"genre_scores_gemma":[0.92897373,0.000014547883,0.070600286,0.00009222824,0.00023429177,0.0000018782747,0.000029483632,0.000012117715,0.00004142207],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925905,0.0000382887,0.00034232673,0.00010532632,0.00011553814,0.00013949042],"domain_scores_gemma":[0.9987901,0.00002819015,0.00064322253,0.00008382444,0.00040820852,0.00004646807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002863341,0.000094667004,0.00019253494,0.000040816474,0.00004991321,0.000010755813,0.00014813068,0.0001617079,0.0000070799765],"category_scores_gemma":[0.00006713633,0.00007540794,0.00007596681,0.000038518905,0.00006535558,0.00000464374,0.000038668513,0.00018128887,8.748058e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002664542,0.00006413582,0.010833109,0.000025096526,0.00027560838,0.0000018061936,0.00010282182,0.6618961,0.32147422,0.0035139944,0.00062031957,0.0009263013],"study_design_scores_gemma":[0.004142506,0.0043850983,0.018894311,0.00008818208,0.00018215986,0.00040871184,0.000100120626,0.87232965,0.011956432,0.08174115,0.0051110475,0.000660624],"about_ca_topic_score_codex":0.0000027452336,"about_ca_topic_score_gemma":0.000017825476,"teacher_disagreement_score":0.3095178,"about_ca_system_score_codex":0.00004372246,"about_ca_system_score_gemma":0.00039248122,"threshold_uncertainty_score":0.30750465},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5366787,0.000060694485,0.4629547,0.00009781501,0.000029710873,0.00011818213,0.0000043812897,0.0000038945686,0.000051955718],"genre_scores_gemma":[0.9349956,0.00000889836,0.06419841,0.000378746,0.00010177154,0.000014764933,0.0002883086,0.00000808745,0.00000542256],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9989495,0.0001141664,0.00051414495,0.00021195957,0.00007651926,0.00013368372],"domain_scores_gemma":[0.99917,0.000013424822,0.0003694631,0.00014077059,0.0002373361,0.0000689899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032333672,0.00011107354,0.00021656127,0.00040606406,0.00004575397,0.000006692898,0.00016907658,0.00018578366,0.0000129422015],"category_scores_gemma":[0.00005168491,0.00010480095,0.00012809185,0.0004920436,0.000026237834,0.000007199493,0.00004245699,0.00009966975,0.0000020420762],"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":[0.00017800594,0.00021600918,0.13861321,0.0000071221616,0.00049251894,0.0000034387454,0.0001905991,0.037270844,0.8105598,0.0060639274,0.00013442626,0.0062701046],"study_design_scores_gemma":[0.0010546184,0.0007848473,0.9044993,0.00003157865,0.00033281522,0.00013500683,0.000107066575,0.016045226,0.03591731,0.03809078,0.0024916676,0.00050977996],"about_ca_topic_score_codex":0.0000449291,"about_ca_topic_score_gemma":0.000048060658,"teacher_disagreement_score":0.77464247,"about_ca_system_score_codex":0.00003472065,"about_ca_system_score_gemma":0.00006452852,"threshold_uncertainty_score":0.42736587},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30427572,0.000083422834,0.6910428,0.001414626,0.002695687,0.00041216268,0.000003855438,0.0000197067,0.000052072402],"genre_scores_gemma":[0.5959928,4.989276e-7,0.40301573,0.0000970233,0.0008252895,0.000025333875,0.000021854934,0.0000074667664,0.000013998202],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976354,0.00051331456,0.0007838424,0.00028726374,0.0005178252,0.0002623163],"domain_scores_gemma":[0.996458,0.0006490205,0.00096396025,0.00016075824,0.0016701376,0.00009810482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003501347,0.0001635358,0.00027499974,0.00028122636,0.00020506984,0.00016476783,0.0006356119,0.00009469173,0.000039482293],"category_scores_gemma":[0.00058385445,0.00015042472,0.0002290105,0.00028027003,0.00006148026,0.0008833381,0.00013629768,0.00042425972,0.000010993319],"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":[0.00012524502,0.0001019836,0.00006005059,0.000018943721,0.00008793604,0.00000526857,0.00014506905,0.7958173,0.028429516,0.120504424,0.00077797886,0.053926293],"study_design_scores_gemma":[0.0006606831,0.00011737959,0.0017854582,0.000027002468,0.000016228101,0.0001175003,0.000009412383,0.50201166,0.0012723597,0.4926839,0.0011830918,0.0001153354],"about_ca_topic_score_codex":0.0000046807427,"about_ca_topic_score_gemma":0.0000056225363,"teacher_disagreement_score":0.37217948,"about_ca_system_score_codex":0.000087527165,"about_ca_system_score_gemma":0.00051253685,"threshold_uncertainty_score":0.61341417},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9484831,0.00089414447,0.0501471,0.00014934897,0.00014573967,0.000077556455,0.000031160063,0.0000022032684,0.00006963125],"genre_scores_gemma":[0.96127623,0.00012391935,0.03798792,0.000106214335,0.0002527341,0.0000018081507,0.00017276018,0.000010473803,0.00006792694],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.999078,0.000069623966,0.000464849,0.00013496076,0.0001305282,0.000122038575],"domain_scores_gemma":[0.9986845,0.000020174873,0.0004980531,0.00010850711,0.00063217035,0.000056549874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002234267,0.00009813076,0.00019400603,0.00010627046,0.00004727732,0.0000029204039,0.00018627291,0.00009828921,0.00001791982],"category_scores_gemma":[0.00006167545,0.00008651284,0.00008753191,0.00011931791,0.00012899282,0.0000044648796,0.000045163633,0.00007768886,0.000009225059],"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":[0.00007296766,0.000094692456,0.006123426,0.0000066182,0.00013137185,0.0000045505667,0.00007510553,0.016619632,0.97606266,0.000076633645,0.0001589016,0.0005734541],"study_design_scores_gemma":[0.006551888,0.0046667997,0.57764375,0.000034223787,0.00013602214,0.0036389064,0.00014108449,0.00252273,0.3595146,0.009118296,0.035207395,0.0008242955],"about_ca_topic_score_codex":0.0000019863664,"about_ca_topic_score_gemma":7.9961154e-7,"teacher_disagreement_score":0.61654806,"about_ca_system_score_codex":0.000015906406,"about_ca_system_score_gemma":0.00019705862,"threshold_uncertainty_score":0.35278913},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98239154,0.008276839,0.008791814,0.00007060437,0.00018538651,0.000033501346,0.0000035409093,5.4046933e-7,0.00024621835],"genre_scores_gemma":[0.99442273,0.0005952457,0.0046563833,0.00016206934,0.00010661212,2.8838616e-7,0.00001229496,0.0000036888189,0.000040708648],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99948907,0.000027063805,0.0002835191,0.00008351985,0.000050636158,0.000066162334],"domain_scores_gemma":[0.9993188,0.000040924468,0.0002829295,0.000046816633,0.00027672132,0.000033835262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002860979,0.00005535317,0.00011822798,0.00006535868,0.00001694557,0.0000011657354,0.000058057103,0.000067903275,0.000002307983],"category_scores_gemma":[0.00003563904,0.000047829104,0.000044708173,0.000026771984,0.00010197524,7.1804556e-7,0.000033987482,0.000035426685,3.7139455e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014671576,0.000025424406,0.019293575,0.0000062372164,0.000074959695,0.0000010138428,0.0000695008,0.00048732763,0.9703006,0.00033015365,0.0008762926,0.008388182],"study_design_scores_gemma":[0.0023907784,0.002549906,0.7036268,0.000025511523,0.00008209974,0.00023966539,0.000259843,0.0005286967,0.05295944,0.009052107,0.22798844,0.00029668806],"about_ca_topic_score_codex":0.000005034768,"about_ca_topic_score_gemma":0.0000019964723,"teacher_disagreement_score":0.9173412,"about_ca_system_score_codex":0.000023094752,"about_ca_system_score_gemma":0.0000953296,"threshold_uncertainty_score":0.19504142},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97917974,0.00036353726,0.020071613,0.00015379285,0.00008205921,0.00005090206,0.000085409825,0.0000016192114,0.000011340641],"genre_scores_gemma":[0.9958865,0.000016971606,0.0037620729,0.000022498722,0.00012432908,7.2418806e-7,0.00017307281,0.000004786032,0.000009021875],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99941725,0.000050553772,0.0003469778,0.00006702533,0.000058673675,0.000059500202],"domain_scores_gemma":[0.99942523,0.00002652995,0.00034641742,0.00003340896,0.00015417759,0.000014220864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011560633,0.00006076934,0.00009451647,0.00003549476,0.000087370354,0.000014723044,0.000059974427,0.000053834425,0.0000023662585],"category_scores_gemma":[0.000029281016,0.00004177937,0.000039412844,0.000035556466,0.00007529757,0.0000076237993,0.000015223238,0.00005917664,1.1824702e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018981633,0.00001120387,0.007505193,0.000008361173,0.00003554618,9.1078036e-8,0.00005866653,0.006824442,0.9847309,0.00056338473,0.000053283296,0.00018997585],"study_design_scores_gemma":[0.002756782,0.001847829,0.21945323,0.00007569616,0.00013621125,0.00034658497,0.00072265725,0.06302607,0.6805229,0.029927107,0.000801924,0.00038296537],"about_ca_topic_score_codex":0.000011071751,"about_ca_topic_score_gemma":0.0000128157,"teacher_disagreement_score":0.30420792,"about_ca_system_score_codex":0.000011075287,"about_ca_system_score_gemma":0.00004713086,"threshold_uncertainty_score":0.17037134},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9949365,0.0004844232,0.0032679893,0.0007625095,0.00014001502,0.000033156164,0.00000563727,2.936088e-7,0.00036942257],"genre_scores_gemma":[0.9978682,0.00004200962,0.0016505676,0.00031926445,0.00009827398,9.2680807e-7,0.000005942554,0.000003046392,0.000011779307],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995324,0.00009198418,0.00019424093,0.000055263496,0.000065479544,0.000060644492],"domain_scores_gemma":[0.99928826,0.00010798982,0.00020707055,0.00005928662,0.0003070006,0.000030392352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025363275,0.000044709413,0.00009256535,0.000034243472,0.000021102212,0.0000031797251,0.000104911625,0.0000385058,0.0000028993813],"category_scores_gemma":[0.00019213748,0.000028996781,0.00006745093,0.000046207653,0.000075341064,3.888929e-7,0.000026222428,0.000042551655,9.2229595e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00100626,0.00022983347,0.1037343,0.000008965401,0.00064166926,0.0000048992815,0.00063215755,0.14574745,0.62919194,0.08881437,0.025005417,0.0049827276],"study_design_scores_gemma":[0.0019787778,0.004099,0.12795027,0.000018035613,0.000055453565,0.0001923441,0.00048601732,0.00066172134,0.08241938,0.77386683,0.00807913,0.00019303709],"about_ca_topic_score_codex":0.0000027534068,"about_ca_topic_score_gemma":0.0000011937319,"teacher_disagreement_score":0.68505245,"about_ca_system_score_codex":0.0000061246324,"about_ca_system_score_gemma":0.000099944475,"threshold_uncertainty_score":0.118245445},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8169527,0.00023645547,0.18245529,0.0001604537,0.00004978474,0.00008657155,0.000005425023,0.0000035015883,0.000049807488],"genre_scores_gemma":[0.9508583,0.00017172452,0.048548866,0.0000855707,0.00010022938,0.0000034632546,0.00020532357,0.000008392553,0.000018148712],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993178,0.0000842477,0.00026773714,0.00013812714,0.00008922408,0.00010282578],"domain_scores_gemma":[0.99906415,0.000054369288,0.00032974742,0.000038084196,0.00047550784,0.000038148504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000085427746,0.000098794306,0.00012655489,0.000042458254,0.00008059132,0.000034865796,0.00007423346,0.00008917475,0.000013133855],"category_scores_gemma":[0.000047394413,0.00007914999,0.000028448772,0.00005033836,0.000060534876,0.00002193565,0.000022857308,0.00009014613,0.0000025310624],"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":[0.00015485343,0.0001006824,0.008373641,0.000037206275,0.00025064076,0.000013802885,0.0007313746,0.57695985,0.36172205,0.0005843866,0.0000732751,0.050998244],"study_design_scores_gemma":[0.004904097,0.008494753,0.064641014,0.0001845029,0.00014973657,0.0038669815,0.0014255511,0.84173346,0.032503817,0.040367816,0.0007386209,0.0009896241],"about_ca_topic_score_codex":0.000009373544,"about_ca_topic_score_gemma":0.0000028238676,"teacher_disagreement_score":0.32921824,"about_ca_system_score_codex":0.000016108106,"about_ca_system_score_gemma":0.00007439002,"threshold_uncertainty_score":0.3227643},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86376005,0.0034513073,0.13089092,0.0011567407,0.0004161662,0.00015484639,0.00014293342,0.0000028444822,0.000024212219],"genre_scores_gemma":[0.92363626,0.00022661297,0.07401019,0.000639288,0.0008508406,0.000014027121,0.0005894372,0.000015594342,0.000017737826],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989439,0.00006996791,0.0004534715,0.00026069008,0.000066097666,0.00020582741],"domain_scores_gemma":[0.99885786,0.00006395537,0.0002841387,0.00020676925,0.0005310711,0.000056222463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002643581,0.00014143654,0.00025013095,0.00009777119,0.00009061445,0.00003553256,0.00038496844,0.00018273228,0.000018729555],"category_scores_gemma":[0.00010862027,0.00012343763,0.00008242494,0.00007871722,0.000075054915,0.0000069288362,0.00008965214,0.000098753066,0.000004529545],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031584572,0.000023737146,0.0011444245,0.000003450305,0.0002945779,9.2070565e-7,0.000022721313,0.0071737105,0.9852586,0.00023486814,0.0032345005,0.0025769486],"study_design_scores_gemma":[0.006070449,0.0029354729,0.0069249687,0.00003679629,0.000442102,0.00057686935,0.00042340776,0.1311147,0.67162055,0.101100564,0.077653214,0.0011009088],"about_ca_topic_score_codex":0.000023446306,"about_ca_topic_score_gemma":0.000016473841,"teacher_disagreement_score":0.313638,"about_ca_system_score_codex":0.000030485831,"about_ca_system_score_gemma":0.00028205113,"threshold_uncertainty_score":0.503364},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8788791,0.0011922378,0.11927882,0.00019847682,0.00011928821,0.000036867197,0.0000016814864,0.000001046207,0.00029250802],"genre_scores_gemma":[0.9915712,0.000043084405,0.008007307,0.00020376695,0.0001507727,3.7951622e-7,0.000008475618,0.0000038126518,0.000011189382],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992999,0.000078307814,0.00035575827,0.00009049841,0.0000653263,0.00011022659],"domain_scores_gemma":[0.99954414,0.00007889296,0.00018665113,0.000043559754,0.00009500226,0.000051758358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080192246,0.00006293551,0.00015055701,0.000075587406,0.000020888374,0.0000055674022,0.00007853522,0.00010104459,0.000008865666],"category_scores_gemma":[0.00008541242,0.00005315944,0.000039319337,0.000045028137,0.000058241076,0.0000026339324,0.000027467964,0.00007864545,0.0000013948029],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007367046,0.0001743478,0.0954538,0.000017796121,0.00008068672,0.00002266743,0.00009522547,0.002786582,0.82723486,0.0058955825,0.0005541313,0.06694762],"study_design_scores_gemma":[0.0031568874,0.002541897,0.31123516,0.000057800444,0.000028127166,0.0006097064,0.00029100734,0.0006000392,0.5421226,0.09604113,0.042860445,0.00045517192],"about_ca_topic_score_codex":0.000003977623,"about_ca_topic_score_gemma":0.000009724827,"teacher_disagreement_score":0.28511223,"about_ca_system_score_codex":0.0000071732284,"about_ca_system_score_gemma":0.000043124597,"threshold_uncertainty_score":0.21677792},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87942487,0.0010829606,0.11545,0.0016244105,0.00009978726,0.00003538394,0.000041402636,0.000010877632,0.0022302906],"genre_scores_gemma":[0.9793962,0.000033888133,0.02012875,0.00019074907,0.00016696776,4.1357413e-7,0.000038025595,0.0000027486515,0.000042252443],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99918365,0.000021523598,0.00048206048,0.000077717166,0.0001336115,0.00010142307],"domain_scores_gemma":[0.99889517,0.00015771436,0.00055009505,0.000042304644,0.00031421662,0.000040523817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010351154,0.0000793576,0.00024695712,0.00016172315,0.000031131734,0.000008005964,0.00011829969,0.00005783846,0.0008164624],"category_scores_gemma":[0.00003041857,0.00006460363,0.000111456204,0.0001790085,0.00004333176,0.000076847165,0.000008686764,0.00011509654,0.0000027737972],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011648847,0.001887127,0.1011241,0.0001332466,0.0034897123,0.00009710388,0.0038581414,0.046453863,0.53996897,0.07457342,0.011668171,0.21558125],"study_design_scores_gemma":[0.007872748,0.0033753396,0.11480156,0.000060986156,0.00058617233,0.0006392327,0.003120392,0.0036423535,0.5018932,0.35919043,0.0041613337,0.0006562129],"about_ca_topic_score_codex":0.000005244944,"about_ca_topic_score_gemma":6.2198257e-7,"teacher_disagreement_score":0.28461704,"about_ca_system_score_codex":0.000040962797,"about_ca_system_score_gemma":0.00008908499,"threshold_uncertainty_score":0.89396906},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6910418,0.0009079596,0.30748057,0.00008242387,0.00030082476,0.00005978663,0.000010809507,0.0000022363608,0.000113540074],"genre_scores_gemma":[0.9288026,0.00008243825,0.06995755,0.00013686807,0.0008101945,4.6066683e-7,0.00015739155,0.000011618093,0.000040881645],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99911124,0.0000496137,0.0004183169,0.00012996016,0.000125991,0.00016485892],"domain_scores_gemma":[0.9992072,0.00002461783,0.00033872222,0.00007389469,0.0002933195,0.00006225053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005576147,0.00009588592,0.00013966029,0.00011725115,0.000054810505,0.000012493721,0.00013727718,0.0000854849,0.000016781503],"category_scores_gemma":[0.00003513528,0.00008621228,0.0000832209,0.00008530573,0.0000601435,0.0000049168343,0.000042681288,0.00007037406,0.0000043192144],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016446212,0.000065187676,0.008895938,0.000007729877,0.00015414658,0.00000917783,0.000042493888,0.02548033,0.95832056,0.00023085084,0.00021736407,0.0064117503],"study_design_scores_gemma":[0.012003281,0.0063406434,0.25672472,0.000112864655,0.00043087505,0.0022629797,0.0006546877,0.011272424,0.40008828,0.04407986,0.26401073,0.0020186696],"about_ca_topic_score_codex":0.0000024953083,"about_ca_topic_score_gemma":0.0000030358713,"teacher_disagreement_score":0.5582323,"about_ca_system_score_codex":0.00004286344,"about_ca_system_score_gemma":0.00009254544,"threshold_uncertainty_score":0.35156348},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6971562,0.0004337225,0.3009822,0.0006091958,0.000561519,0.00010494119,0.00003483312,0.000004598435,0.00011275944],"genre_scores_gemma":[0.93222934,0.0000057771035,0.066322275,0.0005103017,0.00082824193,0.0000010604962,0.00007338848,0.000010186638,0.000019456736],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991441,0.00010265208,0.0003425196,0.0001376541,0.000110860026,0.00016225454],"domain_scores_gemma":[0.9988493,0.00008772322,0.00035775438,0.00007277752,0.0005286538,0.0001038024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057927653,0.00010988293,0.00020434149,0.000064381704,0.0000660157,0.000015700673,0.0001905313,0.00016331853,0.0000063837597],"category_scores_gemma":[0.0003047069,0.00009179092,0.000110383466,0.00005139469,0.00005741976,0.000005271608,0.00004573977,0.0000957948,9.572233e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006047857,0.0000530143,0.001973447,0.000024330888,0.00025060697,0.000008365259,0.00024497183,0.049518816,0.91305214,0.006162561,0.0023049444,0.025802001],"study_design_scores_gemma":[0.0074563567,0.0065087536,0.0018009268,0.000106604915,0.00012385525,0.0016006293,0.0005162665,0.01679766,0.48283768,0.4017911,0.07953286,0.0009272891],"about_ca_topic_score_codex":0.0000015585308,"about_ca_topic_score_gemma":9.732769e-7,"teacher_disagreement_score":0.43021446,"about_ca_system_score_codex":0.000020389954,"about_ca_system_score_gemma":0.00025185605,"threshold_uncertainty_score":0.37431252},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62092733,0.00024069645,0.3779938,0.0007273361,0.000046394776,0.000043781594,0.000002746853,0.0000010988601,0.00001678562],"genre_scores_gemma":[0.99049807,0.000096167794,0.008964057,0.0002443142,0.00013882804,0.0000024602475,0.000008105324,0.000005065933,0.000042916043],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9995993,0.00005177624,0.00013106318,0.000111500936,0.00003745073,0.00006895953],"domain_scores_gemma":[0.9996256,0.000040172767,0.000119785735,0.00003623113,0.00012459293,0.00005360281],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002150262,0.0000589705,0.00008101024,0.000043378008,0.000037801456,0.000009793502,0.0000553385,0.00007141355,0.0000034818638],"category_scores_gemma":[0.000043958342,0.000040934912,0.000023240347,0.000031045343,0.000053108135,0.0000034608795,0.00003324633,0.00003590111,0.0000011587005],"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":[0.00016645133,0.000015406591,0.003215671,0.0000072197813,0.00007439246,5.144842e-7,0.000054276563,0.0010098444,0.9421837,0.0031468398,0.0002689223,0.049856763],"study_design_scores_gemma":[0.0059542283,0.0062846327,0.46941468,0.00013353508,0.00017408191,0.0033682315,0.00034204195,0.0062296386,0.11490619,0.34304222,0.049009096,0.0011414118],"about_ca_topic_score_codex":3.612443e-7,"about_ca_topic_score_gemma":0.0000028797438,"teacher_disagreement_score":0.8272775,"about_ca_system_score_codex":0.000012943441,"about_ca_system_score_gemma":0.00003457066,"threshold_uncertainty_score":0.16692773},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94328105,0.00022113278,0.055388927,0.0004222047,0.00029423131,0.000088384666,0.00008080539,0.0000023232749,0.00022094573],"genre_scores_gemma":[0.9315124,0.000024096958,0.068162955,0.00005940111,0.00015311278,0.0000020235188,0.00007211259,0.0000059333465,0.000007945538],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99911606,0.000062921405,0.00043775645,0.00014127039,0.00012781534,0.00011417902],"domain_scores_gemma":[0.9991565,0.0000757541,0.00036806113,0.00008412281,0.00024593883,0.00006963286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024963892,0.000097711614,0.00021683075,0.00009524835,0.00004051122,0.000010365502,0.00011034676,0.00007702359,0.00003687468],"category_scores_gemma":[0.00007188073,0.00008250899,0.00006084562,0.00005046623,0.00022703892,0.000004141817,0.000021545775,0.0001464424,0.0000013542102],"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":[0.00094793027,0.00058452506,0.08747565,0.000080670354,0.00033498093,0.000008049854,0.00012266202,0.019884946,0.8357921,0.0051937,0.0005856817,0.048989087],"study_design_scores_gemma":[0.008377523,0.014638894,0.84172577,0.00011286607,0.0002101909,0.00055646774,0.000555617,0.018509591,0.025500601,0.03902843,0.04980779,0.0009762567],"about_ca_topic_score_codex":0.0000024054968,"about_ca_topic_score_gemma":0.000011470372,"teacher_disagreement_score":0.8102915,"about_ca_system_score_codex":0.00000898324,"about_ca_system_score_gemma":0.0001088822,"threshold_uncertainty_score":0.33646187},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9531656,0.0004526774,0.04483038,0.0005229912,0.0006832316,0.00008747362,0.000058389225,0.0000027377587,0.0001965377],"genre_scores_gemma":[0.77908224,0.000022956652,0.22025797,0.00007770301,0.00041805924,0.000002260345,0.0000725726,0.000006851925,0.000059365946],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989531,0.00016070205,0.0005013099,0.00013227512,0.00012231091,0.00013030179],"domain_scores_gemma":[0.9987287,0.00011122728,0.0004602667,0.00011337172,0.0005375447,0.000048910708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006667657,0.000102897735,0.00018972144,0.000095311116,0.000108327564,0.000011111474,0.00025731858,0.00010319568,0.00008317684],"category_scores_gemma":[0.00012748338,0.00007420869,0.00014764689,0.00009451482,0.00040060174,0.00000811241,0.00007139796,0.00020507321,0.0000024370638],"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":[0.00017803638,0.00020063456,0.0053014606,0.000024105742,0.00056099927,0.0000017098155,0.00035592995,0.059038647,0.897699,0.008680503,0.00047947475,0.027479518],"study_design_scores_gemma":[0.005239018,0.005342685,0.28992757,0.000047370853,0.00022901426,0.0042090635,0.0014808704,0.004848118,0.050943125,0.5505681,0.086180225,0.000984806],"about_ca_topic_score_codex":0.0000034828738,"about_ca_topic_score_gemma":0.000003123155,"teacher_disagreement_score":0.84675586,"about_ca_system_score_codex":0.000009520005,"about_ca_system_score_gemma":0.00024641285,"threshold_uncertainty_score":0.30261427},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.784289,0.00019678794,0.21503033,0.00010867391,0.000064666565,0.00014687219,0.000045701538,6.953427e-7,0.00011730105],"genre_scores_gemma":[0.96570945,0.000016560756,0.03378654,0.00035240978,0.00008111414,0.00000884281,0.000014882625,0.000007052483,0.000023128941],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994553,0.000028942442,0.00022782036,0.00012224962,0.00005272149,0.000113018716],"domain_scores_gemma":[0.99917907,0.000039718125,0.00021593524,0.00005386527,0.00046872807,0.000042662996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014590136,0.00008876015,0.00015242427,0.00003060329,0.00004085837,0.000003611854,0.000086973625,0.00005409813,0.0000014030454],"category_scores_gemma":[0.00003702736,0.000064754626,0.00006287557,0.000021080998,0.00011816083,8.626093e-7,0.000027332364,0.000038597536,4.426544e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0056479163,0.0006469939,0.008074336,0.00007178418,0.0023165555,0.000024594978,0.0038854019,0.38227898,0.5198923,0.06234419,0.0013696365,0.013447346],"study_design_scores_gemma":[0.013291297,0.027508494,0.035469487,0.0001454244,0.0005471959,0.0019476507,0.001437842,0.15510516,0.104159825,0.6516966,0.0070035015,0.0016875044],"about_ca_topic_score_codex":0.000003033661,"about_ca_topic_score_gemma":0.000007553988,"teacher_disagreement_score":0.5893524,"about_ca_system_score_codex":0.000013338872,"about_ca_system_score_gemma":0.00017138406,"threshold_uncertainty_score":0.2640617},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9485713,0.0012312426,0.047784556,0.00010723335,0.00020266863,0.00007036035,0.000008490972,0.000004372183,0.002019738],"genre_scores_gemma":[0.9680806,0.00006153277,0.031188495,0.00019102465,0.0003580011,8.120528e-7,0.000055495762,0.000009012933,0.000055044966],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9992966,0.00007311178,0.00032313698,0.000106497544,0.00007581787,0.00012483964],"domain_scores_gemma":[0.9992823,0.000015319978,0.00028239845,0.00007384205,0.00028955034,0.000056575132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002942559,0.000080201695,0.0001383471,0.000088678564,0.000031066644,0.000005331602,0.00016856677,0.00007405424,0.00009067058],"category_scores_gemma":[0.000043068198,0.000068855865,0.00009509841,0.00006529511,0.000048739937,0.0000033079807,0.00004904136,0.00007465699,0.000014832392],"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":[0.00038685935,0.00027649399,0.03600427,0.00003321638,0.0009915481,0.00004430107,0.0004538218,0.0024369746,0.9469806,0.003247686,0.0007976466,0.008346579],"study_design_scores_gemma":[0.0065134694,0.008523244,0.7010957,0.00008225476,0.0003021989,0.0027528193,0.00035823902,0.0007420756,0.050602127,0.07451977,0.1531727,0.0013353727],"about_ca_topic_score_codex":0.000001087633,"about_ca_topic_score_gemma":2.5023732e-7,"teacher_disagreement_score":0.89637846,"about_ca_system_score_codex":0.000010243046,"about_ca_system_score_gemma":0.000060399132,"threshold_uncertainty_score":0.28078607},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90240574,0.00047196654,0.09556079,0.00021636601,0.00042723818,0.0000347769,0.00083072245,0.0000013449633,0.000051079558],"genre_scores_gemma":[0.9758993,0.00010130282,0.022323573,0.0004345331,0.0007472415,3.1516169e-7,0.00048358468,0.000007239183,0.0000029098248],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99918586,0.00005154337,0.000331181,0.00020998792,0.00009465342,0.00012679494],"domain_scores_gemma":[0.99844605,0.00018084321,0.00063229294,0.00042443082,0.00024812904,0.000068241614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022485189,0.00009942661,0.00018393298,0.000027287871,0.00014600644,0.00007895477,0.0007153351,0.00007085136,0.000020489791],"category_scores_gemma":[0.0009660353,0.00009167508,0.00005859903,0.000015457133,0.00017040448,0.000016764754,0.00038812085,0.000097254604,0.000001874016],"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":[0.00035793174,0.00022830177,0.1406822,0.000016439006,0.00027590027,0.000052702173,0.00003851081,0.032930035,0.81131196,0.0012512133,0.0009089651,0.011945861],"study_design_scores_gemma":[0.0070937416,0.0022084448,0.50764114,0.00034493592,0.0003262239,0.00084480515,0.000081843056,0.04602441,0.08925454,0.2461779,0.09825259,0.0017494047],"about_ca_topic_score_codex":0.00017534813,"about_ca_topic_score_gemma":0.000045341738,"teacher_disagreement_score":0.7220574,"about_ca_system_score_codex":0.000028915656,"about_ca_system_score_gemma":0.00040950664,"threshold_uncertainty_score":0.37384012},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98748374,0.00032973365,0.009815627,0.0019475657,0.00020981445,0.0000540171,0.00010417926,0.000004255414,0.00005104217],"genre_scores_gemma":[0.99630666,0.00030743048,0.002465482,0.00047624134,0.00034516648,0.0000016547284,0.00005195504,0.000012899646,0.00003248522],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9990264,0.00008160543,0.00040967864,0.0001957293,0.00010864816,0.0001779169],"domain_scores_gemma":[0.99919116,0.00006899008,0.00035850424,0.000093323695,0.00018790254,0.00010013823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015334107,0.0001435924,0.00021360388,0.00006277392,0.00008491796,0.0000253064,0.00018231805,0.000115003524,0.000016869273],"category_scores_gemma":[0.00003994598,0.000096608324,0.000088105946,0.000031893556,0.00015030199,0.00001129246,0.00009043793,0.00008532858,0.000003151299],"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":[0.00008284952,0.00005229545,0.035305098,0.000017620192,0.00011214927,0.000014669041,0.000039058534,0.0006471292,0.95582557,0.002567407,0.000119046876,0.0052170954],"study_design_scores_gemma":[0.008807723,0.008590347,0.5934816,0.0007676473,0.00022205712,0.007459343,0.00021425713,0.0038527653,0.056994803,0.3110484,0.006625577,0.0019354767],"about_ca_topic_score_codex":0.0000028355018,"about_ca_topic_score_gemma":0.0000032013254,"teacher_disagreement_score":0.8988308,"about_ca_system_score_codex":0.000030329373,"about_ca_system_score_gemma":0.00006785259,"threshold_uncertainty_score":0.39395732},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7640704,0.0007919825,0.23452514,0.00013548498,0.00022656635,0.0000755108,0.00003631591,7.778366e-7,0.0001378055],"genre_scores_gemma":[0.8851529,0.00004642932,0.113221355,0.0000960544,0.001119181,0.000002479814,0.00034073673,0.0000074380464,0.000013426325],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934447,0.00003705652,0.00025252055,0.00020730423,0.000054391036,0.00010425919],"domain_scores_gemma":[0.9989068,0.000019081126,0.00043621095,0.00030340962,0.00029291798,0.000041614374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043772443,0.00007944232,0.00013716098,0.000027950362,0.00028702148,0.00007501696,0.00048029158,0.00007342998,8.8893e-7],"category_scores_gemma":[0.0001959856,0.00006767909,0.00004531659,0.000009673025,0.000081538186,0.00000859781,0.00013960192,0.00004597666,1.6973118e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008736584,0.000050062314,0.004672243,0.000016251603,0.00014470292,6.125277e-7,0.0000777539,0.030115793,0.9482689,0.0004769875,0.00031147595,0.015777875],"study_design_scores_gemma":[0.006679763,0.004795254,0.06429416,0.000051315088,0.00034865056,0.00085089006,0.0008331009,0.76301444,0.08147056,0.043514337,0.032816622,0.0013309288],"about_ca_topic_score_codex":0.0000034758327,"about_ca_topic_score_gemma":0.0000040052428,"teacher_disagreement_score":0.86679834,"about_ca_system_score_codex":0.000010363752,"about_ca_system_score_gemma":0.00018560962,"threshold_uncertainty_score":0.27598733},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6210186,0.0010690804,0.37717876,0.000073560055,0.00026997356,0.000096771306,0.00027642475,8.213495e-7,0.000016009231],"genre_scores_gemma":[0.93047446,0.00015954416,0.068599455,0.00006694339,0.00043915454,0.0000012114971,0.00024770305,0.000009245876,0.000002288881],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921143,0.00004584831,0.00041154528,0.00015475825,0.000043571952,0.00013287271],"domain_scores_gemma":[0.99874973,0.000033033542,0.0007540322,0.00022061385,0.00018741797,0.000055196593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043628624,0.000109044726,0.00024400999,0.000047059162,0.00013858447,0.00004828479,0.0004825419,0.0001057436,0.0000035069913],"category_scores_gemma":[0.000017071063,0.000087110544,0.00006867082,0.000015902866,0.00018883683,0.00003309125,0.00010880349,0.00008441625,5.0676494e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041532367,0.00023169517,0.04411034,0.00020598511,0.003006158,0.0000019338106,0.000751765,0.09966826,0.7792232,0.001871159,0.002075947,0.06470033],"study_design_scores_gemma":[0.004257505,0.0008856129,0.0760536,0.00020002901,0.0003616366,0.0006283805,0.0006456395,0.89539087,0.0030331633,0.016810164,0.0011680945,0.00056531077],"about_ca_topic_score_codex":0.000026570504,"about_ca_topic_score_gemma":0.000021600132,"teacher_disagreement_score":0.7957226,"about_ca_system_score_codex":0.000014493796,"about_ca_system_score_gemma":0.00014318156,"threshold_uncertainty_score":0.3552265},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93657684,0.000084226376,0.06222393,0.00055770075,0.00006852757,0.00008311502,0.000011995655,0.000001576418,0.00039207484],"genre_scores_gemma":[0.980584,0.000020354888,0.01897858,0.00024501604,0.00008793836,0.00000304085,0.000023395962,0.0000052439436,0.00005238306],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99937034,0.00004533742,0.0002509402,0.000120786804,0.00007500215,0.00013758092],"domain_scores_gemma":[0.9993581,0.000024922032,0.0003260338,0.00011873366,0.00013084685,0.000041329058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000195738,0.00008350087,0.00015568608,0.00005834953,0.00008837784,0.00002448726,0.0002607802,0.000112775946,0.0000062833583],"category_scores_gemma":[0.00020190804,0.00006418128,0.00006161064,0.000015667787,0.00008909779,0.0000068141344,0.000073281975,0.00012790757,0.0000011207494],"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":[0.0006076825,0.00009853973,0.0055038864,0.000009683534,0.000069209964,0.0000254105,0.000039469785,0.7696539,0.18341854,0.037037063,0.00025012702,0.0032864888],"study_design_scores_gemma":[0.00196799,0.002178924,0.01050631,0.000055224293,0.000009507689,0.000075738746,0.000020550196,0.09237906,0.009751349,0.8821685,0.00064164633,0.00024522774],"about_ca_topic_score_codex":0.0000051423153,"about_ca_topic_score_gemma":0.0000114831155,"teacher_disagreement_score":0.8451314,"about_ca_system_score_codex":0.00001787438,"about_ca_system_score_gemma":0.00011287189,"threshold_uncertainty_score":0.26172367},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8560334,0.00020512272,0.13959453,0.0021626735,0.00051888864,0.000041493156,0.0000021249546,0.000020276444,0.0014215026],"genre_scores_gemma":[0.9954463,0.0000102284,0.0025307564,0.00058519363,0.0013558249,0.0000018818736,0.000014349936,0.0000135873315,0.000041873485],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896777,0.000009298093,0.0005012254,0.00015435394,0.00021123575,0.0001561115],"domain_scores_gemma":[0.99754834,0.000029091527,0.0013956,0.00013149393,0.0008799826,0.000015513495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040902762,0.0001355885,0.0003221644,0.00025779306,0.0003927779,0.0003729479,0.00049462,0.00006672436,0.00002864467],"category_scores_gemma":[0.00015731592,0.000102882754,0.00013152095,0.0001071473,0.00009476136,0.0017062898,0.00009508356,0.00015118129,0.000015169685],"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":[0.00007983659,0.000060120296,0.008471687,0.00006905805,0.00010734541,0.000010153149,0.00005609837,0.96019864,0.00012973999,0.026339205,0.0001379163,0.0043402025],"study_design_scores_gemma":[0.0006574954,0.000009605962,0.002117654,0.000057416746,0.00006892929,0.000016902797,0.000033986427,0.57220554,0.000020769317,0.4243619,0.0003131896,0.00013658786],"about_ca_topic_score_codex":0.00007175438,"about_ca_topic_score_gemma":0.000010859282,"teacher_disagreement_score":0.3980227,"about_ca_system_score_codex":0.000014321693,"about_ca_system_score_gemma":0.000083472834,"threshold_uncertainty_score":0.4195437},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80478096,0.00016344516,0.15259868,0.040331367,0.0007425376,0.0003286095,0.00008722641,0.0000072266903,0.00095995795],"genre_scores_gemma":[0.99276054,0.000277947,0.005564985,0.0007562689,0.0005275814,0.000003627076,0.000072635296,0.000006997107,0.000029398694],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985987,0.00006889469,0.00057298713,0.00015430112,0.0003921137,0.00021298077],"domain_scores_gemma":[0.9980805,0.00028645815,0.00059861125,0.00025385234,0.0006768308,0.00010376593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006196945,0.00015700299,0.0001854242,0.000056410547,0.0003619905,0.00023631766,0.0008191863,0.00013737462,0.000045815726],"category_scores_gemma":[0.0009221946,0.00008009592,0.00006671513,0.000063551866,0.00092250603,0.00001541035,0.0002250836,0.00034604146,0.000011067367],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036900162,0.00052753626,0.0031060409,0.000040799525,0.0015003824,0.000022313618,0.0037144206,0.013366912,0.07428444,0.04129141,0.005612482,0.8528432],"study_design_scores_gemma":[0.0019520193,0.012882505,0.14069442,0.0007076262,0.00035377912,0.00069286185,0.020330057,0.29019618,0.17368743,0.32645467,0.029888166,0.002160291],"about_ca_topic_score_codex":0.000008930613,"about_ca_topic_score_gemma":0.000068919566,"teacher_disagreement_score":0.850683,"about_ca_system_score_codex":0.000020408464,"about_ca_system_score_gemma":0.00031642916,"threshold_uncertainty_score":0.3399012},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032433756,0.0009698003,0.9660304,0.00013057052,0.00018650082,0.00014946898,0.00006610259,0.000002321325,0.000031042066],"genre_scores_gemma":[0.82354313,0.000027140408,0.17592846,0.00008635751,0.00028562936,0.000012183908,0.00009979989,0.000007379522,0.000009912758],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992508,0.00012006664,0.0003187254,0.000111601716,0.00010867637,0.0000901214],"domain_scores_gemma":[0.99874675,0.00019581444,0.00038444635,0.000073673655,0.00056404155,0.00003526811],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003329182,0.0000839427,0.00013227738,0.000055436998,0.000082263134,0.000005353924,0.00016557326,0.000098433935,0.000024966037],"category_scores_gemma":[0.00005172649,0.00005915361,0.0001034619,0.000042426505,0.00006232756,0.000020672145,0.00001532719,0.00005238081,5.289698e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002426289,0.0006113939,0.0003869536,0.000029189949,0.0015839766,0.000002602115,0.0008216205,0.3316571,0.48705336,0.05347465,0.00047288864,0.121479966],"study_design_scores_gemma":[0.0036414363,0.008486552,0.019272048,0.0000680601,0.00039024765,0.00023893856,0.0016580772,0.11344053,0.265723,0.58119977,0.005344794,0.00053653354],"about_ca_topic_score_codex":0.0000037115806,"about_ca_topic_score_gemma":0.0000016903624,"teacher_disagreement_score":0.7911094,"about_ca_system_score_codex":0.0000057383704,"about_ca_system_score_gemma":0.00014754338,"threshold_uncertainty_score":0.24122143},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06230628,0.0005693728,0.93255216,0.0027311638,0.00079278165,0.00006364833,0.000031115014,0.000028273622,0.0009251893],"genre_scores_gemma":[0.5996561,0.00007824077,0.3995249,0.00046080974,0.00020270114,9.767625e-7,0.000019206622,0.0000058067985,0.000051249408],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988384,0.0001227125,0.0004148594,0.00020880588,0.00024685642,0.00016833846],"domain_scores_gemma":[0.99847865,0.00025222657,0.00039487742,0.00038973647,0.0003726186,0.000111883666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032694024,0.00011652473,0.0002206824,0.00015970998,0.00014629899,0.000062771906,0.0012653718,0.00008531808,0.000037880982],"category_scores_gemma":[0.000104328115,0.00008405821,0.00004002731,0.00012386445,0.00017366445,0.0003812675,0.00090234017,0.00016269536,0.000011943349],"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":[0.00042066493,0.0005160812,0.0032840928,0.000043767166,0.00027796332,0.000114012364,0.001031879,0.0017995342,0.012472726,0.3824612,0.08583673,0.51174134],"study_design_scores_gemma":[0.0022301932,0.0014645242,0.02726615,0.000110915775,0.000014525688,0.00070744567,0.000025218445,0.17417495,0.00022677466,0.75714153,0.036394138,0.00024361096],"about_ca_topic_score_codex":0.000007801351,"about_ca_topic_score_gemma":0.0000027741694,"teacher_disagreement_score":0.5373498,"about_ca_system_score_codex":0.000030184743,"about_ca_system_score_gemma":0.00008970146,"threshold_uncertainty_score":0.3427794},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65924704,0.00021709649,0.3401613,0.0000086281525,0.00008527215,0.00006473098,0.000012118716,0.0000014038711,0.00020241042],"genre_scores_gemma":[0.9177058,0.0000042628108,0.08211748,0.000039536782,0.000106391104,9.543459e-7,0.000014210682,0.00000814178,0.0000032589378],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99916106,0.00007123136,0.00040357737,0.00011994317,0.00010779061,0.00013639434],"domain_scores_gemma":[0.99914867,0.000015401563,0.00041419413,0.00008147923,0.0002878599,0.000052390842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022606768,0.000101945516,0.0002072532,0.000086976725,0.000035958754,0.0000035743074,0.00015038566,0.00012949876,0.000008721516],"category_scores_gemma":[0.000025225449,0.000084960775,0.0001331366,0.000057594712,0.00008397227,0.0000036770746,0.000049474445,0.00008956978,3.768268e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002261976,0.00006351648,0.00022686677,0.000012988752,0.00010785767,0.0000057278226,0.00014266605,0.26106578,0.72430426,0.012613606,0.000009911171,0.0012205928],"study_design_scores_gemma":[0.0024197032,0.0031054865,0.001557591,0.00008917804,0.00011329987,0.0006285654,0.0001615167,0.21958755,0.54598,0.22579008,0.00011841761,0.00044864713],"about_ca_topic_score_codex":0.000006354445,"about_ca_topic_score_gemma":9.887027e-7,"teacher_disagreement_score":0.2584587,"about_ca_system_score_codex":0.000014785896,"about_ca_system_score_gemma":0.0001765823,"threshold_uncertainty_score":0.34645998},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9415073,0.00073270936,0.05673032,0.000618484,0.00021124349,0.000102134356,0.000054133852,5.112204e-7,0.00004318752],"genre_scores_gemma":[0.922117,0.00009484579,0.077490084,0.00008280027,0.00014101384,0.000002067208,0.000051341318,0.00000405798,0.00001681751],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99948794,0.00006560122,0.00021572947,0.00011265161,0.000050498984,0.00006757264],"domain_scores_gemma":[0.9992582,0.00007090579,0.00033628804,0.00006951607,0.00023804355,0.000027035596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026512952,0.000065058,0.00014540233,0.00003927369,0.00002413796,0.0000065907207,0.000105565094,0.000084050516,0.0000021087424],"category_scores_gemma":[0.000045714667,0.000052469273,0.000054020973,0.000020284597,0.00004000555,0.0000029436958,0.000027718997,0.000039973886,1.8670309e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001858641,0.00002646106,0.0044420147,0.0000134503625,0.00010160131,1.5100788e-7,0.000058479647,0.002774404,0.9853149,0.0023883693,0.00019931067,0.004495007],"study_design_scores_gemma":[0.0054255635,0.010339858,0.5206914,0.000033588385,0.00019125683,0.000434788,0.001001201,0.013184709,0.23372418,0.18994325,0.02449601,0.0005342096],"about_ca_topic_score_codex":0.00000274823,"about_ca_topic_score_gemma":0.0000017456517,"teacher_disagreement_score":0.7515907,"about_ca_system_score_codex":0.0000065765353,"about_ca_system_score_gemma":0.00005733893,"threshold_uncertainty_score":0.2139635},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022864155,0.00027834202,0.9728288,0.0016299286,0.0017969416,0.0002567695,0.00030226508,0.000013663185,0.00002913875],"genre_scores_gemma":[0.41478541,0.000026104828,0.58456326,0.00017293043,0.00031815824,0.000005413329,0.000119547556,0.000007717017,0.0000014318229],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998095,0.00013003324,0.0010114785,0.00031622808,0.00028620564,0.00016108411],"domain_scores_gemma":[0.9966672,0.00044308574,0.0018646532,0.00022522482,0.00070370926,0.00009609471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040994317,0.00018982365,0.0005894258,0.00021853887,0.000064151856,0.000044167155,0.00089397904,0.00018229896,0.0000060398543],"category_scores_gemma":[0.00007263859,0.00016092774,0.00025409693,0.00010528235,0.00012362999,0.000044599416,0.00081536704,0.0003308313,0.000001959521],"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":[0.0002491028,0.00019576953,0.00023969676,0.00015853437,0.0003492632,0.0000105362005,0.0003955043,0.83595705,0.0027400528,0.098973945,0.0011416678,0.05958888],"study_design_scores_gemma":[0.00087248196,0.0004621941,0.001354984,0.00010966672,0.00003080803,0.00013347808,0.000022291913,0.75421953,0.00022625139,0.237359,0.0050362716,0.00017302654],"about_ca_topic_score_codex":0.000008897316,"about_ca_topic_score_gemma":2.857675e-7,"teacher_disagreement_score":0.39192125,"about_ca_system_score_codex":0.00011098411,"about_ca_system_score_gemma":0.0005782596,"threshold_uncertainty_score":0.6562443},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85018444,0.00024979655,0.02679018,0.115538515,0.0015043314,0.00060284353,0.00020078976,0.000014001295,0.0049150917],"genre_scores_gemma":[0.9941687,0.00039248008,0.0008960599,0.0035061021,0.0004700574,0.000006716146,0.0004142805,0.000009856388,0.00013576365],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816585,0.00030484248,0.0005326509,0.00026595188,0.0005164421,0.00021427986],"domain_scores_gemma":[0.99774927,0.0008092588,0.0004834944,0.00015867673,0.0007170204,0.000082253355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087007467,0.0002040452,0.00024607865,0.000093663635,0.00017693637,0.00011958118,0.00067742786,0.00014771867,0.00025562668],"category_scores_gemma":[0.00051191304,0.00009371673,0.00010114925,0.00010036777,0.00087472075,0.000008305535,0.00017875854,0.0006652556,0.00004312948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02181743,0.0013417328,0.012873071,0.000032887227,0.004425435,0.000022107564,0.0034493946,0.2598768,0.08319228,0.44277775,0.017302295,0.15288885],"study_design_scores_gemma":[0.009857105,0.015156924,0.067983724,0.00058052456,0.00016922486,0.0003793039,0.0053125788,0.63412255,0.011021328,0.19023639,0.0637975,0.0013828451],"about_ca_topic_score_codex":0.000019633615,"about_ca_topic_score_gemma":0.000035847555,"teacher_disagreement_score":0.3742458,"about_ca_system_score_codex":0.00003915379,"about_ca_system_score_gemma":0.0002992661,"threshold_uncertainty_score":0.38216573},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7656376,0.00032132227,0.23341508,0.00004750461,0.00036007576,0.000074345255,0.00010748033,0.0000014300167,0.00003517704],"genre_scores_gemma":[0.9457225,0.000012661826,0.05256011,0.00009468402,0.0006162238,0.0000023600398,0.00096891925,0.000006789235,0.000015722688],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99920636,0.000049823928,0.00038147968,0.00017729367,0.0000759619,0.00010904905],"domain_scores_gemma":[0.9992,0.000031721953,0.00033735545,0.0001393388,0.0002525178,0.000039058705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025170657,0.00008868807,0.0001572878,0.000059734026,0.00005401804,0.000003664393,0.00027097322,0.000105670646,0.000018618262],"category_scores_gemma":[0.000024997513,0.000073976604,0.000066642926,0.000027675813,0.00012593316,0.00001251503,0.00012350074,0.000036560443,0.0000011806301],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059417175,0.000096566866,0.0018160286,0.0000049022615,0.00008529287,4.4380138e-7,0.000050465045,0.0020830387,0.9931459,0.0002521186,0.00063341955,0.0012376882],"study_design_scores_gemma":[0.0015124715,0.001164304,0.0017805579,0.000014457634,0.0000147212895,0.000083230676,0.00005178894,0.0028340367,0.9878437,0.0036853494,0.0009080005,0.000107404485],"about_ca_topic_score_codex":0.0000018016796,"about_ca_topic_score_gemma":0.000001910958,"teacher_disagreement_score":0.18085496,"about_ca_system_score_codex":0.000008703738,"about_ca_system_score_gemma":0.00009959107,"threshold_uncertainty_score":0.30166784},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9959717,0.0023520668,0.00119365,0.000286504,0.000044147,0.00011590267,0.000025236775,9.902539e-7,0.000009794171],"genre_scores_gemma":[0.99356735,0.00023721924,0.006048664,0.000084473504,0.00002634925,0.000002750487,0.000027689579,0.0000033772967,0.0000021166436],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99904925,0.00006147718,0.0005520718,0.00010131098,0.00016289091,0.00007298647],"domain_scores_gemma":[0.9990536,0.00013415041,0.00047338306,0.000040659193,0.00025722908,0.00004098015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026608174,0.00006771101,0.00044512123,0.0003981135,0.000014026111,0.000003501581,0.000031228174,0.000040146602,0.000084980915],"category_scores_gemma":[0.000009574,0.000051308733,0.000071841445,0.00022388046,0.000048164075,0.000040976378,0.000020692958,0.00006320258,6.6945816e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017276384,0.000087588065,0.7477779,0.00006026255,0.00048941944,7.8400353e-7,0.0003354545,0.023242716,0.22470726,0.00007380878,0.000009487394,0.0030425538],"study_design_scores_gemma":[0.0019068528,0.0008172259,0.865436,0.00022235507,0.00041161917,0.000008431764,0.00035560227,0.011837051,0.11849609,0.00040410736,0.000038988434,0.00006567031],"about_ca_topic_score_codex":0.00007470412,"about_ca_topic_score_gemma":0.000018742592,"teacher_disagreement_score":0.11765811,"about_ca_system_score_codex":0.000037017377,"about_ca_system_score_gemma":0.00008161236,"threshold_uncertainty_score":0.20923094},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9758316,0.00014992898,0.022268713,0.00024551578,0.0013333122,0.00009036002,0.000013486521,0.0000037787213,0.00006329386],"genre_scores_gemma":[0.99422836,0.000060682873,0.00464028,0.00033986286,0.00062903104,0.0000032657654,0.000062461666,0.000013319325,0.000022738062],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991736,0.00005812528,0.00037192518,0.00015166878,0.00010009875,0.00014460697],"domain_scores_gemma":[0.99937975,0.000025659836,0.00023362508,0.00009665987,0.00019353561,0.000070742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000161316,0.00010674569,0.00017229747,0.0000773255,0.000038561204,0.000020823923,0.00014498048,0.00007755626,0.000020497057],"category_scores_gemma":[0.000016306938,0.00010061164,0.00013066299,0.00006382132,0.000018272107,0.000015731473,0.00003658313,0.0001043337,0.000021048161],"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":[0.00018993784,0.000037953847,0.003174547,0.000011992183,0.00008645918,0.0000012521652,0.00007768707,0.3152016,0.6765334,0.00061591965,0.00035461114,0.0037146464],"study_design_scores_gemma":[0.0044325246,0.0060777836,0.82670736,0.00025215774,0.00011084846,0.000804068,0.0004323156,0.018468376,0.04140936,0.036133837,0.06388017,0.0012912013],"about_ca_topic_score_codex":0.0000015235306,"about_ca_topic_score_gemma":0.0000025281736,"teacher_disagreement_score":0.8235328,"about_ca_system_score_codex":0.000033599234,"about_ca_system_score_gemma":0.000047564507,"threshold_uncertainty_score":0.41028237},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9405582,0.0007914279,0.056179885,0.0017865383,0.00023921503,0.00018427339,0.000047524372,0.00001004478,0.00020289897],"genre_scores_gemma":[0.99317515,0.000095957876,0.00538463,0.00057826994,0.00047190214,0.0000071520735,0.00014214062,0.000017366463,0.00012740362],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99848527,0.00031289272,0.00062321726,0.00024635668,0.0001464867,0.00018580767],"domain_scores_gemma":[0.99857104,0.00017825932,0.0006126943,0.00007298941,0.00045737013,0.00010762821],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002910001,0.00016961205,0.00030365877,0.000093938026,0.00009623374,0.000062042986,0.00020675902,0.0001252065,0.000046116475],"category_scores_gemma":[0.0006917849,0.0001533027,0.00013813551,0.00016543693,0.000070565715,0.00003064273,0.000071588445,0.0002835119,0.000009817189],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072152127,0.0001054316,0.014301987,0.0000374529,0.00014942967,0.000021838652,0.00038417327,0.14038508,0.8337262,0.00020413168,0.0004874475,0.0094753],"study_design_scores_gemma":[0.0072266785,0.0028397604,0.031868223,0.00030058817,0.00014611555,0.00061878393,0.0006073123,0.016821312,0.8321683,0.008843639,0.09749732,0.0010620148],"about_ca_topic_score_codex":0.000009101836,"about_ca_topic_score_gemma":0.0000071329737,"teacher_disagreement_score":0.12356376,"about_ca_system_score_codex":0.00001732531,"about_ca_system_score_gemma":0.00017011582,"threshold_uncertainty_score":0.62515026},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1508594,0.000901501,0.84401786,0.00344599,0.0003724464,0.00013454794,0.00019217192,0.0000049595365,0.00007109682],"genre_scores_gemma":[0.8207237,0.000009336932,0.1768435,0.0010543829,0.0009227598,0.0000019817048,0.000423935,0.000008401137,0.000011990459],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991768,0.00007162401,0.00033539,0.00018014485,0.000070629256,0.00016542227],"domain_scores_gemma":[0.99919814,0.00009984915,0.00021494547,0.00013599209,0.0002456155,0.00010545122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022844493,0.00008753289,0.00015065666,0.00001924902,0.00007147711,0.00000971742,0.00042751103,0.00009411516,0.000015206865],"category_scores_gemma":[0.00040087395,0.00007683585,0.000076232514,0.00004510267,0.000075076576,0.0000049224254,0.00013979492,0.00008107964,0.000004489103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031462517,0.0005320476,0.013705224,0.00010621302,0.0011836714,0.0000030638814,0.00052528013,0.61713314,0.14949085,0.110016294,0.0720526,0.03210539],"study_design_scores_gemma":[0.0105515905,0.012962898,0.25281286,0.0000438994,0.0003879961,0.00019862269,0.00027524607,0.03454685,0.004759335,0.20753801,0.47483855,0.0010841368],"about_ca_topic_score_codex":9.4871564e-7,"about_ca_topic_score_gemma":0.0000032173089,"teacher_disagreement_score":0.6698643,"about_ca_system_score_codex":0.0000041819067,"about_ca_system_score_gemma":0.00023153452,"threshold_uncertainty_score":0.3133275},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33391368,0.00017402646,0.4968075,0.16809009,0.0005016995,0.00014545661,0.000012422225,0.000034010525,0.00032111973],"genre_scores_gemma":[0.98832303,0.000011493422,0.0011125864,0.010280049,0.00023929446,0.00000509739,0.0000062871036,0.00001269233,0.000009444306],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985877,0.0003155513,0.0003600776,0.00023857284,0.00033255277,0.00016549297],"domain_scores_gemma":[0.98657984,0.012727808,0.00046407318,0.00004732763,0.000100552046,0.000080419944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022522155,0.00013965732,0.00029609137,0.00014998704,0.00014399446,0.000012605779,0.00013258735,0.00005929528,0.00015251052],"category_scores_gemma":[0.0032325897,0.00010763613,0.00011554713,0.00035610012,0.00020471902,0.000088790934,0.000036640322,0.0003819615,0.0000081946],"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":[0.0006571053,0.00011431414,0.039947435,0.000007874775,0.000040269722,0.000014976898,0.000055619777,0.94948095,0.00034441662,0.006954124,0.00094466,0.0014382714],"study_design_scores_gemma":[0.003947283,0.008566893,0.2650424,0.00008155583,0.000051268737,0.00016411103,0.000093075774,0.69598573,0.0013823528,0.012196866,0.012108761,0.00037973362],"about_ca_topic_score_codex":0.000001932163,"about_ca_topic_score_gemma":0.0000031408986,"teacher_disagreement_score":0.65440935,"about_ca_system_score_codex":0.000038270435,"about_ca_system_score_gemma":0.00010517832,"threshold_uncertainty_score":0.43892738},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89335734,0.0015303243,0.10449461,0.00011968283,0.00039766548,0.000019212592,0.000015197996,0.0000016528555,0.00006432141],"genre_scores_gemma":[0.782907,0.000020604448,0.21643397,0.00021997208,0.00036026386,9.284272e-8,0.000038675233,0.0000036405972,0.000015787225],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.999364,0.00009184481,0.000257649,0.000109933826,0.00008179923,0.00009476039],"domain_scores_gemma":[0.99919087,0.000028572902,0.0002475501,0.00006319883,0.0004243948,0.000045387074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009436431,0.000074210184,0.00013007609,0.00004806475,0.00007758029,0.000017447635,0.000101304315,0.00009792064,0.000037481626],"category_scores_gemma":[0.00009681866,0.000070465016,0.00009333498,0.00007807499,0.00004974741,0.00000348147,0.00006205443,0.000073785886,0.0000015978507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055064007,0.000042079988,0.0657907,0.000017772725,0.00014969763,0.000024582016,0.0000689746,0.7969459,0.13027504,0.00030514863,0.00046152237,0.005863486],"study_design_scores_gemma":[0.0056501385,0.001715468,0.61606866,0.00012108786,0.0005344181,0.011031,0.000618772,0.08636752,0.07494018,0.1346157,0.06692444,0.0014126062],"about_ca_topic_score_codex":0.0000016937333,"about_ca_topic_score_gemma":0.0000012241737,"teacher_disagreement_score":0.71057844,"about_ca_system_score_codex":0.000008260183,"about_ca_system_score_gemma":0.00017313566,"threshold_uncertainty_score":0.287348},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17143317,0.00010672637,0.8242116,0.003435726,0.00046221164,0.00005954487,0.000010521659,0.000016009111,0.0002645013],"genre_scores_gemma":[0.7733492,0.000002486986,0.22584184,0.0005824572,0.00018544131,0.0000020107082,0.000014830532,0.000004699842,0.000017014585],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984979,0.000419013,0.0004226963,0.00022264438,0.00030823666,0.00012947715],"domain_scores_gemma":[0.9981917,0.0007553207,0.00028682078,0.00011697522,0.00056423334,0.000084927866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054022117,0.00010784369,0.00020114525,0.00020887986,0.00008141115,0.00008082638,0.00023440584,0.00006403271,0.000019342948],"category_scores_gemma":[0.00026120868,0.0000966353,0.00008823202,0.0002638458,0.00006802866,0.00024619992,0.00009209306,0.00019557023,0.0000054436837],"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":[0.00009337953,0.00023574196,0.0009299306,0.000018561248,0.00006110728,0.00009573602,0.000085517626,0.81817484,0.004693452,0.15244213,0.00030876786,0.022860823],"study_design_scores_gemma":[0.0010388701,0.0004196605,0.021207765,0.000052735904,0.00000984106,0.0003772093,0.0000072755165,0.80886096,0.00274042,0.16391662,0.001250714,0.0001179628],"about_ca_topic_score_codex":0.0000010441889,"about_ca_topic_score_gemma":4.6072887e-7,"teacher_disagreement_score":0.6019161,"about_ca_system_score_codex":0.000046588695,"about_ca_system_score_gemma":0.00055339054,"threshold_uncertainty_score":0.39406735},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42312106,0.000339464,0.57610875,0.00003440481,0.00025819932,0.000054844335,0.000028851553,0.0000014126362,0.000053017284],"genre_scores_gemma":[0.9533654,0.000063256564,0.04581523,0.00007814277,0.00045227323,9.989272e-7,0.00017972421,0.000009082154,0.000035882833],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99922067,0.000064194646,0.00038687777,0.00011661624,0.00009606753,0.000115558556],"domain_scores_gemma":[0.99876744,0.000042206517,0.00041288958,0.00007895495,0.00064285024,0.00005566505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017599763,0.00010231114,0.00017855341,0.000059139446,0.000063377585,0.000021323469,0.00007910219,0.00010884365,0.000010897161],"category_scores_gemma":[0.000054877142,0.000078001045,0.00007503627,0.000109498156,0.000042771648,0.0000125288225,0.000041222866,0.000110148416,0.0000010095778],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045833542,0.00011195922,0.0038870722,0.000017137167,0.00044200307,0.000006942123,0.0001885342,0.19252382,0.78995436,0.00092905416,0.00019058079,0.011290214],"study_design_scores_gemma":[0.010188455,0.005686558,0.043344546,0.00020265018,0.00035684698,0.0027976672,0.00066688226,0.343266,0.5168929,0.05361812,0.02195886,0.0010205206],"about_ca_topic_score_codex":0.0000017377881,"about_ca_topic_score_gemma":0.0000023328469,"teacher_disagreement_score":0.5302935,"about_ca_system_score_codex":0.000017640066,"about_ca_system_score_gemma":0.00034595944,"threshold_uncertainty_score":0.31807902},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9900828,0.0010958511,0.008064759,0.0004079208,0.00014809992,0.00007970161,0.000037855036,0.0000049298988,0.000078080055],"genre_scores_gemma":[0.9972265,0.0001513509,0.0020702924,0.000040448827,0.00025674558,0.0000027251347,0.00021732843,0.00000884019,0.00002579324],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991924,0.000053392912,0.0003586561,0.00014155985,0.00012407372,0.0001298946],"domain_scores_gemma":[0.999215,0.000040148694,0.00031690177,0.00006861809,0.00030557215,0.00005376548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024976936,0.0000901901,0.00019083719,0.000141694,0.000031028165,0.000006422078,0.00013657117,0.00010180187,0.000018306733],"category_scores_gemma":[0.000034920366,0.00007964748,0.00007421153,0.00015028221,0.00008232598,0.000005382241,0.000057203608,0.000073901094,0.000008649372],"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":[0.00083962403,0.0001609842,0.032899857,0.000056821176,0.0007139197,0.000013951881,0.00034522652,0.040774357,0.9195945,0.00093410286,0.0007404814,0.0029261291],"study_design_scores_gemma":[0.013151849,0.0043613366,0.7658941,0.00010425665,0.00023065488,0.00030380566,0.00096189795,0.007939657,0.042673558,0.14414081,0.019321267,0.00091677887],"about_ca_topic_score_codex":0.0000063803054,"about_ca_topic_score_gemma":0.0000027312694,"teacher_disagreement_score":0.876921,"about_ca_system_score_codex":0.000013789903,"about_ca_system_score_gemma":0.00011553174,"threshold_uncertainty_score":0.32479298},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9960225,0.001013508,0.0000983106,0.0023310413,0.00021489606,0.000048780952,0.00021426473,0.000008942466,0.000047750418],"genre_scores_gemma":[0.9938548,0.0002020664,0.005015887,0.00037369216,0.0003470422,0.0000020155824,0.00019746598,8.7348485e-7,0.000006153313],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9990606,0.000108557644,0.00031214667,0.00019302822,0.00015938231,0.0001663141],"domain_scores_gemma":[0.9991129,0.0004004946,0.00018681801,0.000023785975,0.00016744436,0.00010855974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013532634,0.0001276494,0.0002444568,0.00002804459,0.0001745025,0.000055598874,0.00009227085,0.00007445943,0.00017179444],"category_scores_gemma":[0.00006148661,0.000058364818,0.00006540236,0.00013702223,0.00012252583,0.00006704299,0.000029602445,0.000106098014,0.0000016166422],"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":[0.00026743443,0.0003764847,0.056875717,0.000024150686,0.00018624353,0.00017823624,0.00025293432,0.021618074,0.88577217,0.0029476448,0.00030894927,0.031191938],"study_design_scores_gemma":[0.0020305552,0.0022530158,0.920386,0.000086097745,0.000062562656,0.0016011968,0.00018406658,0.020677742,0.036242258,0.008311058,0.007674401,0.0004910001],"about_ca_topic_score_codex":0.000010691771,"about_ca_topic_score_gemma":0.00003364407,"teacher_disagreement_score":0.8635103,"about_ca_system_score_codex":0.000014331022,"about_ca_system_score_gemma":0.00007867812,"threshold_uncertainty_score":0.23800482},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98818964,0.0012733665,0.009517708,0.00049778284,0.00037019988,0.000042101332,0.000017268121,5.641228e-7,0.000091384056],"genre_scores_gemma":[0.9970382,0.00002642138,0.002228852,0.0003599593,0.00030427324,0.0000019145637,0.0000092177825,0.000006738261,0.000024450703],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99935997,0.000112203474,0.00023009664,0.000089123125,0.00009554899,0.00011308906],"domain_scores_gemma":[0.9995255,0.00005651665,0.00023628904,0.00006338918,0.00009500037,0.000023289962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003199754,0.000070420254,0.00011252816,0.00004505033,0.00024210749,0.00000907812,0.00019803282,0.000028487037,0.000028958546],"category_scores_gemma":[0.000025078727,0.00005133367,0.00009679975,0.000055540964,0.000065749664,5.730087e-7,0.00017295186,0.000113055736,4.914511e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029852748,0.00008428593,0.055214453,0.0000052294513,0.00043715583,0.000011013157,0.00025203882,0.5590379,0.37852716,0.0013093515,0.0015278482,0.0032950093],"study_design_scores_gemma":[0.0064521097,0.006916129,0.37079075,0.00002522583,0.00031245945,0.008692752,0.0056750122,0.029587405,0.023028325,0.13287069,0.4142202,0.0014289265],"about_ca_topic_score_codex":0.0000045263514,"about_ca_topic_score_gemma":8.566634e-7,"teacher_disagreement_score":0.52945054,"about_ca_system_score_codex":0.00002051224,"about_ca_system_score_gemma":0.000117085016,"threshold_uncertainty_score":0.20933264},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98453844,0.0015497687,0.012984138,0.00031593873,0.00036169525,0.000096317846,0.000086216576,9.1971907e-7,0.000066554734],"genre_scores_gemma":[0.9942918,0.00004203095,0.0049392525,0.00027614288,0.00032928947,0.000015263284,0.000046825604,0.000010710605,0.00004871823],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99933,0.00005769556,0.00027754306,0.00012485332,0.00006996346,0.00013993944],"domain_scores_gemma":[0.9994621,0.00007047633,0.00025821687,0.000057564677,0.00011659294,0.00003500482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027286384,0.000085837986,0.00016209637,0.00007505392,0.00015301093,0.000007970131,0.00017223174,0.000041844156,0.000021341588],"category_scores_gemma":[0.00003297276,0.00008059421,0.00011569512,0.000040270745,0.000042176736,6.578352e-7,0.00012604844,0.00008159991,7.6253843e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013639091,0.00020783037,0.090369664,0.000023546247,0.0008787185,0.000008896614,0.00028388307,0.21051641,0.6780713,0.0017642842,0.00558836,0.010923205],"study_design_scores_gemma":[0.009073903,0.013691719,0.32212892,0.000016307318,0.00021060303,0.001793607,0.0020004835,0.0047424305,0.018342659,0.13028608,0.49653557,0.0011777309],"about_ca_topic_score_codex":0.0000027783997,"about_ca_topic_score_gemma":0.0000015354731,"teacher_disagreement_score":0.65972865,"about_ca_system_score_codex":0.000027394051,"about_ca_system_score_gemma":0.0001254818,"threshold_uncertainty_score":0.32865366},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9824707,0.004062973,0.011595153,0.00069913006,0.00045071568,0.000059729384,0.00007704329,0.0000025009174,0.00058206],"genre_scores_gemma":[0.99724966,0.000097379496,0.0016335669,0.00034423897,0.00028619476,0.000004601939,0.00014939421,0.000013349745,0.00022160789],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991078,0.00007438753,0.00035893556,0.00015235519,0.00012987295,0.00017668428],"domain_scores_gemma":[0.9993485,0.000043745324,0.00030434594,0.00007466755,0.00016968868,0.000059023405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024057136,0.00011384128,0.0001784067,0.000070047674,0.00024400391,0.000014317046,0.0001821898,0.00004737079,0.00009505727],"category_scores_gemma":[0.00003258982,0.00010852117,0.00011049528,0.00007877724,0.00007698806,0.0000018118216,0.0001304035,0.00013188965,0.0000024376238],"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":[0.0006125442,0.00034538668,0.028743688,0.000011285973,0.0006505352,0.000015272937,0.00023852395,0.08546209,0.83937365,0.0010627102,0.014047109,0.029437225],"study_design_scores_gemma":[0.00953021,0.012740562,0.12679908,0.000047562255,0.00031086773,0.0033698652,0.0014928526,0.0049832524,0.0484505,0.033835705,0.75671244,0.0017271031],"about_ca_topic_score_codex":0.0000062593504,"about_ca_topic_score_gemma":0.0000075365283,"teacher_disagreement_score":0.7909231,"about_ca_system_score_codex":0.000032614862,"about_ca_system_score_gemma":0.0001283605,"threshold_uncertainty_score":0.4425365},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94151145,0.00019841274,0.05647129,0.0005600732,0.00044975776,0.000105845356,0.000024320641,0.0000051797997,0.00067367364],"genre_scores_gemma":[0.97451526,0.000019759329,0.02370906,0.00041090106,0.0009946378,0.0000024932554,0.00012512907,0.00001426373,0.00020850271],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9990246,0.00012326488,0.0003379013,0.00017291117,0.00017283505,0.00016848605],"domain_scores_gemma":[0.9992909,0.00003498361,0.00018082283,0.000110163935,0.0003077088,0.00007544098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015461557,0.00012357532,0.00016170646,0.00011478375,0.00005260652,0.0000127633975,0.00016630883,0.0001320325,0.00025583204],"category_scores_gemma":[0.00004528992,0.0001079931,0.00012033165,0.00010821726,0.00006107796,0.000004965706,0.000015336593,0.000115597126,0.000065095504],"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":[0.0036457803,0.00075699657,0.009322753,0.000014391692,0.0005100394,0.000043886685,0.00006920593,0.5111493,0.4190677,0.00047799517,0.0058760573,0.049065933],"study_design_scores_gemma":[0.031377465,0.025888775,0.63740414,0.00014704872,0.0003132022,0.0013212889,0.000038324095,0.049697068,0.040006667,0.03890184,0.17275907,0.002145129],"about_ca_topic_score_codex":0.000004714375,"about_ca_topic_score_gemma":8.7534727e-7,"teacher_disagreement_score":0.6280814,"about_ca_system_score_codex":0.000034884928,"about_ca_system_score_gemma":0.00017303332,"threshold_uncertainty_score":0.4403831},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09282789,0.00013751435,0.90476495,0.0014344344,0.0006163672,0.00012406503,0.00002960513,0.000015462294,0.00004970917],"genre_scores_gemma":[0.7099292,8.3860107e-7,0.28956082,0.00032866036,0.00014042128,0.0000044627373,0.0000176459,0.0000030827548,0.0000148711015],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896777,0.00013558764,0.00036525266,0.00014878713,0.00022959033,0.00015303798],"domain_scores_gemma":[0.9989319,0.00025634194,0.0004584695,0.00008381608,0.00021805275,0.0000514559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062427577,0.000075614,0.00017146634,0.00013610788,0.00030232398,0.00004265044,0.00070937845,0.000023659304,0.000022400282],"category_scores_gemma":[0.000046720932,0.00006359294,0.0000932617,0.00016017503,0.000041167714,0.00022457483,0.00031679135,0.00016937319,0.0000016118454],"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":[0.00020034095,0.00022648144,0.00050423347,0.000018000479,0.00011325321,0.000053071657,0.00039820946,0.57330984,0.011180765,0.3048569,0.00604945,0.103089444],"study_design_scores_gemma":[0.0015905718,0.0020735306,0.0012816072,0.00002084256,0.0000085028305,0.0007830663,0.000103233266,0.59451383,0.0005925374,0.35342777,0.04537496,0.00022953018],"about_ca_topic_score_codex":0.00000408815,"about_ca_topic_score_gemma":1.1849337e-7,"teacher_disagreement_score":0.6171013,"about_ca_system_score_codex":0.000062048166,"about_ca_system_score_gemma":0.0002603124,"threshold_uncertainty_score":0.2593245},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87356794,0.00043700964,0.12522556,0.00029624562,0.00029162623,0.00009388251,0.000036823134,0.0000025739023,0.00004833234],"genre_scores_gemma":[0.98628265,0.000016724305,0.012856394,0.00044771083,0.00019548381,0.0000060361117,0.00014046973,0.000010046853,0.00004449125],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99936134,0.00007606883,0.00027232498,0.00011633865,0.000072175535,0.0001017501],"domain_scores_gemma":[0.9995307,0.000070165544,0.00016590672,0.000042920303,0.0001577026,0.00003265868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002261189,0.00007552872,0.00012471103,0.000067249384,0.000117320844,0.000012894229,0.00009464693,0.000046536854,0.000010532357],"category_scores_gemma":[0.000032484575,0.0000740535,0.00007416165,0.000045937595,0.000038193542,0.0000045329552,0.00004389691,0.00007914662,1.9347465e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008348722,0.00019507798,0.0034995126,0.00003144748,0.00006737233,0.0000030721953,0.0001498657,0.06179987,0.92424005,0.0002810614,0.000514614,0.008383198],"study_design_scores_gemma":[0.047538616,0.05474255,0.03408511,0.00009188363,0.0004888637,0.0036326435,0.0019441219,0.17115134,0.19012547,0.05262365,0.44070786,0.002867881],"about_ca_topic_score_codex":0.0000016437564,"about_ca_topic_score_gemma":0.0000014732072,"teacher_disagreement_score":0.7341146,"about_ca_system_score_codex":0.000018078266,"about_ca_system_score_gemma":0.000076674696,"threshold_uncertainty_score":0.30198142},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9954973,0.0011118025,0.0010534175,0.0020206189,0.0001095053,0.00008478382,0.000025182446,4.9155045e-7,0.000096908596],"genre_scores_gemma":[0.9972748,0.00006486333,0.0013868939,0.0010621166,0.00014095227,0.000008021523,0.000033152453,0.000005107814,0.000024057372],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9990857,0.00026415035,0.00025939898,0.00010397817,0.0001594878,0.00012728179],"domain_scores_gemma":[0.9992808,0.00018956058,0.00029563,0.000069585665,0.00014536535,0.000019069355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059033,0.00007416439,0.00012946546,0.00005521071,0.000116684896,0.000009157915,0.00021625825,0.00003895821,0.000013560726],"category_scores_gemma":[0.000081226746,0.00005161393,0.000060811017,0.000098726276,0.000033290693,5.9210237e-7,0.00007095709,0.00015826877,5.9355324e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017661031,0.00008523973,0.3905149,0.0000028528011,0.00013369949,0.000010017788,0.00020636867,0.60035235,0.007562354,0.00013509611,0.0005999858,0.00022048909],"study_design_scores_gemma":[0.0009858712,0.0013900116,0.93733656,0.000001468687,0.000027945136,0.00014448,0.00036018612,0.0002967541,0.00007338658,0.0072266664,0.05203643,0.000120257595],"about_ca_topic_score_codex":0.000007997898,"about_ca_topic_score_gemma":0.000016211146,"teacher_disagreement_score":0.60005563,"about_ca_system_score_codex":0.00006042006,"about_ca_system_score_gemma":0.00014122536,"threshold_uncertainty_score":0.21047549},"labels":[],"label_agreement":null},{"id":"W4313544751","doi":"10.1089/cmb.2022.0395","title":"A Novel Information-Theory-Based Genetic Distance That Approximates Phenotypic Differences","year":2023,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"Centers for Disease Control and Prevention; National Institutes of Health","keywords":"Biology; Genetics; Phenotype; Entropy (arrow of time); Computational biology; Major histocompatibility complex; In silico; Distance matrix; Pairwise comparison; Mathematics; Combinatorics; Gene; Statistics","score_opus":0.011664451772865346,"score_gpt":0.2586015842894526,"score_spread":0.24693713251658728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313544751","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37006408,0.00009623402,0.62895703,0.00033026704,0.00022195729,0.00006768962,0.000043431108,0.000014236086,0.00020509343],"genre_scores_gemma":[0.9561005,0.000020381203,0.042891983,0.0004961757,0.00012799495,0.000004151698,0.0003118892,0.000007489106,0.00003943648],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99908096,0.00007206968,0.00043467848,0.00007926249,0.00016441006,0.00016864331],"domain_scores_gemma":[0.9989465,0.00017581426,0.0004898882,0.00010034406,0.00022981585,0.00005764646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035544002,0.0001222901,0.00017423091,0.00016105249,0.00007586856,0.000033203964,0.0002570565,0.00010139176,0.00002308981],"category_scores_gemma":[0.00027518178,0.00009635545,0.000093294984,0.00015074995,0.00011885489,0.000014098687,0.000052253672,0.00012792219,0.0000299297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011248519,0.00026981905,0.20117383,0.00033989985,0.000618955,0.0000075247403,0.0008951035,0.6840904,0.024450053,0.04364287,0.005871525,0.03751517],"study_design_scores_gemma":[0.0057354853,0.0024451283,0.5240243,0.0001432698,0.00010909786,0.0004218616,0.0004938451,0.30649048,0.0039289263,0.07663309,0.07854313,0.0010314063],"about_ca_topic_score_codex":0.0000010711691,"about_ca_topic_score_gemma":8.39004e-7,"teacher_disagreement_score":0.58606505,"about_ca_system_score_codex":0.000012188641,"about_ca_system_score_gemma":0.00014293529,"threshold_uncertainty_score":0.39292613},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89480907,0.002019864,0.10184904,0.00029542684,0.0009418637,0.000049602662,0.000023206363,0.00000382902,0.000008103869],"genre_scores_gemma":[0.9916884,0.00018714365,0.006617745,0.00006916827,0.0013345359,5.128883e-7,0.00006793794,0.000006631575,0.000027981396],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999161,0.000109548506,0.00036161346,0.000111940935,0.000109373505,0.00014652328],"domain_scores_gemma":[0.9992665,0.00003572229,0.0003178462,0.00011347829,0.00024090886,0.000025553456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006073427,0.00009250065,0.0002384291,0.00014309821,0.00010492197,0.000011843378,0.00021279436,0.00006826198,0.000006090962],"category_scores_gemma":[0.000046150028,0.00005149276,0.00021957434,0.00066638784,0.000093085815,0.0000057190086,0.000058154477,0.00011958295,3.952696e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016793281,0.0000034109162,0.00034853973,0.0000016585047,0.00085420255,3.244675e-7,0.00006198751,0.9130835,0.080814764,0.0011434325,0.0002928049,0.0033785729],"study_design_scores_gemma":[0.00043187672,0.00013950618,0.020143468,0.0000114657305,0.0010798873,0.00017316332,0.0001548048,0.95250887,0.009437567,0.009827667,0.005905148,0.00018657885],"about_ca_topic_score_codex":0.000015069104,"about_ca_topic_score_gemma":0.0000024070464,"teacher_disagreement_score":0.09687928,"about_ca_system_score_codex":0.000004700751,"about_ca_system_score_gemma":0.000049329232,"threshold_uncertainty_score":0.20998138},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.993642,0.00033096722,0.004103079,0.0013634034,0.0002876936,0.0001407261,0.00006921626,0.000013067805,0.000049898837],"genre_scores_gemma":[0.99533415,0.00012506997,0.003451958,0.00017906805,0.0007275984,0.000009506195,0.000074886106,9.3322245e-7,0.00009685701],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990578,0.000056255645,0.00037405992,0.0001277809,0.000102063816,0.00028201388],"domain_scores_gemma":[0.9984418,0.0011703387,0.0002144238,0.000007702684,0.0001165091,0.00004920915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005025485,0.00010172734,0.00026073956,0.000042848736,0.00011006525,0.000023008413,0.00014573857,0.00009398503,0.00003911078],"category_scores_gemma":[0.000055460503,0.000042959346,0.000121033845,0.00030334695,0.00003351188,0.00006199158,0.00003884361,0.00014984292,0.000007553348],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041690344,0.0002654896,0.028899724,0.000011497394,0.00034747212,0.00006130985,0.00025931536,0.06325159,0.036008082,0.0007516296,0.013356397,0.85637057],"study_design_scores_gemma":[0.00089424266,0.0011627492,0.8220288,0.00007278448,0.000025366267,0.000059181784,0.000238897,0.15309997,0.00011908905,0.010116626,0.011913816,0.00026846936],"about_ca_topic_score_codex":0.000013659492,"about_ca_topic_score_gemma":0.00009407437,"teacher_disagreement_score":0.8561021,"about_ca_system_score_codex":0.000031021675,"about_ca_system_score_gemma":0.000013194928,"threshold_uncertainty_score":0.17518313},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8112763,0.008053086,0.17761166,0.0017490765,0.00069467543,0.000061044586,0.00003969475,0.000005739646,0.0005086829],"genre_scores_gemma":[0.99271935,0.0002003376,0.0061602313,0.00032827607,0.00029162137,0.0000011814595,0.00009474029,0.000007874332,0.00019639733],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99927866,0.00008362729,0.00035930114,0.0001095149,0.000047796726,0.00012108836],"domain_scores_gemma":[0.9996,0.000095177485,0.000102563055,0.000054191525,0.00008782076,0.00006025595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003513023,0.000086023436,0.0001409326,0.000086440945,0.00006819526,0.0000149488005,0.00007824127,0.00016809731,0.00002113633],"category_scores_gemma":[0.000026494923,0.00006992531,0.00007772381,0.000050426825,0.0001259216,0.000005528206,0.000038902203,0.00017467594,0.000009603004],"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":[0.0016900653,0.00025691758,0.07087522,0.00035859138,0.002622462,0.0002200658,0.0027650842,0.060402457,0.23068663,0.35891587,0.114919804,0.15628682],"study_design_scores_gemma":[0.0026476043,0.0028464706,0.10363649,0.00009149823,0.00019619931,0.011897086,0.00019155689,0.017539205,0.0014079084,0.40372613,0.45510167,0.00071817875],"about_ca_topic_score_codex":9.131925e-7,"about_ca_topic_score_gemma":0.000009722104,"teacher_disagreement_score":0.34018186,"about_ca_system_score_codex":0.000013070348,"about_ca_system_score_gemma":0.00009051389,"threshold_uncertainty_score":0.28514713},"labels":[],"label_agreement":null},{"id":"W4396515244","doi":"10.1089/cmb.2024.0483","title":"On Minimizers and Convolutional Filters: Theoretical Connections and Applications to Genome Analysis","year":2024,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Convolutional neural network; Categorical variable; Computer science; Pooling; Sequence (biology); Initialization; Hash function; Pattern recognition (psychology); Artificial intelligence; Mathematics; Algorithm; Biology; Machine learning; Genetics","score_opus":0.00539845112460039,"score_gpt":0.28790181847405233,"score_spread":0.2825033673494519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396515244","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.403716,0.00061363773,0.5928514,0.0021283748,0.00009087423,0.00009807022,0.000085522515,0.000007652567,0.00040846426],"genre_scores_gemma":[0.985846,0.00004098137,0.013153667,0.00062489405,0.00016779432,0.000005527108,0.00012829782,0.000004877078,0.00002797237],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99943537,0.000050959217,0.00024157333,0.00012011642,0.00007137779,0.00008061587],"domain_scores_gemma":[0.9994412,0.00024151443,0.00006760917,0.00005392318,0.00011038861,0.00008533295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021050137,0.00007443074,0.00012844996,0.00023622357,0.000057479818,0.000030168441,0.000063606756,0.00006689366,0.000043500262],"category_scores_gemma":[0.000107844804,0.000060805465,0.000068190326,0.0001582812,0.0001748302,0.0000037560562,0.000040368755,0.00010745024,0.0000058361616],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001771893,0.000056416444,0.0021750955,0.000033552275,0.0013953629,0.0000033427207,0.0001610284,0.12989861,0.0062952247,0.8551042,0.0011157463,0.0035842455],"study_design_scores_gemma":[0.002618771,0.006929037,0.10094893,0.000093253606,0.0015585456,0.002070193,0.0004373578,0.19674219,0.00052964134,0.37171048,0.31525275,0.0011088706],"about_ca_topic_score_codex":5.804894e-7,"about_ca_topic_score_gemma":6.0975907e-7,"teacher_disagreement_score":0.58213,"about_ca_system_score_codex":0.000011609137,"about_ca_system_score_gemma":0.000056125882,"threshold_uncertainty_score":0.24795748},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5174068,0.0051525724,0.47543052,0.0015507326,0.00034489777,0.00005773609,0.000010508398,0.0000034897123,0.000042697102],"genre_scores_gemma":[0.9868655,0.0001417715,0.012335606,0.00023869403,0.00037182635,0.0000028411846,0.000016078766,0.000007450678,0.000020213502],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994377,0.000036591515,0.000268429,0.000097222604,0.000072343544,0.0000877142],"domain_scores_gemma":[0.9995454,0.00010041425,0.00007751909,0.000086150736,0.00015300873,0.000037512462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001801518,0.000068471665,0.00010686985,0.000063852065,0.000023303466,0.000011489237,0.00014787423,0.00008396443,0.000007381384],"category_scores_gemma":[0.00006749229,0.000045913945,0.00008664648,0.00009934603,0.000042709853,0.000001825751,0.000034549,0.00009601715,0.0000052811083],"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":[0.00014796709,0.00005265434,0.0015047119,0.00004528752,0.00032320077,0.000008408855,0.00028008025,0.27456155,0.6431144,0.0123821525,0.0027292722,0.0648503],"study_design_scores_gemma":[0.0012059418,0.006341253,0.09381924,0.00036828665,0.00027585472,0.00253633,0.0003386319,0.022262743,0.32612693,0.15398702,0.39183947,0.0008982983],"about_ca_topic_score_codex":0.0000020187379,"about_ca_topic_score_gemma":0.0000011621947,"teacher_disagreement_score":0.46945867,"about_ca_system_score_codex":0.00000779313,"about_ca_system_score_gemma":0.00007286251,"threshold_uncertainty_score":0.18723163},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40061954,0.0001834557,0.59602696,0.002987589,0.00004729988,0.000049196944,0.00003576932,0.000022250422,0.000027941713],"genre_scores_gemma":[0.8095729,0.000005412623,0.18997803,0.00016845121,0.00023604644,0.0000035067796,0.000023274228,0.000006641778,0.000005747776],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987348,0.00015284863,0.0005175641,0.00022222364,0.00026245374,0.000110153596],"domain_scores_gemma":[0.9964688,0.0027273411,0.00020954887,0.00006981442,0.00034333928,0.00018117776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008482263,0.00008878302,0.00017893387,0.0005327143,0.00009384012,0.00031369296,0.00019123817,0.00005295845,0.000022803802],"category_scores_gemma":[0.0025112487,0.000057041343,0.000033631626,0.0008157634,0.000059739024,0.0004709341,0.000057042816,0.0003654245,0.0000018215482],"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":[0.00016800521,0.000058036203,0.040410597,0.0000050359213,0.000025445199,0.000045874396,0.0009232874,0.6965811,0.0001062849,0.022560073,0.0003003596,0.23881587],"study_design_scores_gemma":[0.000063624226,0.00012824676,0.004328152,0.00013019622,0.000004564739,0.000039925366,0.00009008802,0.53876686,0.0000019731374,0.45537043,0.0010375297,0.000038393915],"about_ca_topic_score_codex":0.00004866224,"about_ca_topic_score_gemma":0.000009238226,"teacher_disagreement_score":0.43281037,"about_ca_system_score_codex":0.000049158825,"about_ca_system_score_gemma":0.0003372287,"threshold_uncertainty_score":0.30249485},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6466267,0.001199728,0.3492078,0.0020824543,0.000106054154,0.00006763871,0.000014042939,0.000006624349,0.0006889794],"genre_scores_gemma":[0.9580324,0.000030717427,0.04166042,0.00018986998,0.000044545923,0.0000017188404,0.00001410854,0.0000040590385,0.00002215046],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99888647,0.000081958344,0.0007971696,0.00008836582,0.00006485573,0.00008117028],"domain_scores_gemma":[0.9974052,0.0018876853,0.00025758552,0.000049899365,0.0003313702,0.0000682734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006270096,0.00006410851,0.00040412514,0.00016726191,0.000031828746,0.0000020542973,0.00004049626,0.00011359003,0.00005199003],"category_scores_gemma":[0.0011784486,0.000045685898,0.00010548371,0.000108085296,0.00037112017,0.00004385762,0.00001934991,0.00016926597,0.0000027266822],"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":[0.00006355309,0.000105943494,0.0043164473,0.00025967797,0.00016601937,0.0000033291476,0.00017838806,0.020026308,0.00049795164,0.9734307,0.00009461615,0.0008570459],"study_design_scores_gemma":[0.00024945938,0.00021071256,0.0060844384,0.00015751478,0.00012117665,0.00016831033,0.000013169254,0.39278954,0.000045516794,0.6001234,0.000009952491,0.000026781812],"about_ca_topic_score_codex":7.738746e-7,"about_ca_topic_score_gemma":6.981383e-7,"teacher_disagreement_score":0.37330732,"about_ca_system_score_codex":0.000008747675,"about_ca_system_score_gemma":0.00020180219,"threshold_uncertainty_score":0.1863017},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00044653303,0.0050271912,0.9901433,0.0031014632,0.0010986576,0.00007988836,0.000004266884,0.00007234037,0.000026360034],"genre_scores_gemma":[0.36839983,0.000010132466,0.63083446,0.00026733492,0.0004679008,0.0000018612319,0.00000823349,0.0000040029217,0.000006233333],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99932784,0.00006892529,0.00027828693,0.00013136295,0.00009230241,0.000101258454],"domain_scores_gemma":[0.99902064,0.0005350658,0.00012448282,0.00004770126,0.00024092833,0.000031184587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003318626,0.00007384529,0.00012736146,0.00015862592,0.000048417358,0.00010300634,0.00029336297,0.00006574769,0.000003349611],"category_scores_gemma":[0.000048086797,0.000056266726,0.00010247127,0.00017472092,0.000032814776,0.00037499785,0.000023696515,0.00016698216,0.000001031837],"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":[0.00008883496,0.000038087415,0.000019737778,0.00003197143,0.00009877123,0.000040517603,0.00043115212,0.054916736,0.0048488695,0.5165441,0.0042603523,0.41868085],"study_design_scores_gemma":[0.0001884907,0.00027723628,0.000023877628,0.000019666964,0.000008342418,0.00010962254,0.0000013188683,0.60677624,0.00043501233,0.38873178,0.003370791,0.00005761626],"about_ca_topic_score_codex":5.6527296e-7,"about_ca_topic_score_gemma":2.7450605e-7,"teacher_disagreement_score":0.5518595,"about_ca_system_score_codex":0.00002678392,"about_ca_system_score_gemma":0.00013454125,"threshold_uncertainty_score":0.22944905},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51926017,0.000089697176,0.25964317,0.21796341,0.00086230953,0.0012397581,0.00003852058,0.00000867572,0.00089428475],"genre_scores_gemma":[0.9864164,0.0000028772781,0.0019976282,0.011331379,0.00020770058,0.000017805913,0.0000011235863,0.000002247203,0.000022810827],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9992748,0.00008956718,0.00022931556,0.00008840476,0.00010749535,0.00021040985],"domain_scores_gemma":[0.99917585,0.00039957557,0.00008737225,0.000033034095,0.00015004992,0.00015411194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094004074,0.000055637945,0.00015972955,0.00015596629,0.00061075407,0.000044241136,0.00011025542,0.00003828625,0.000004159553],"category_scores_gemma":[0.0001846338,0.000039111655,0.00003553236,0.000091947186,0.00005978497,0.00002936704,0.000018625375,0.00010155052,8.9692145e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002104565,0.00017356325,0.22345622,0.00005332005,0.00016823926,0.00000585198,0.027533427,0.028415937,0.0000017528245,0.6989651,0.0037345248,0.017281609],"study_design_scores_gemma":[0.00067037955,0.00025300556,0.8884223,0.000043912976,0.000024367699,0.000002293761,0.0022643276,0.01662697,7.7231635e-7,0.088226624,0.003375159,0.00008985696],"about_ca_topic_score_codex":0.012542034,"about_ca_topic_score_gemma":0.2349644,"teacher_disagreement_score":0.6649661,"about_ca_system_score_codex":0.00015117566,"about_ca_system_score_gemma":0.0005505481,"threshold_uncertainty_score":0.9940335},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8089931,0.0005368054,0.18928805,0.00014663523,0.00054474483,0.00035165504,0.00006703909,0.000008246549,0.000063734245],"genre_scores_gemma":[0.98955655,0.000008621302,0.009501793,0.00013824902,0.00019596302,0.00001729912,0.00040726428,0.000007745013,0.00016648954],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998743,0.00030749277,0.0004630322,0.00021726167,0.000059201084,0.00021002749],"domain_scores_gemma":[0.9986578,0.0004856355,0.00028102536,0.000077411925,0.00042249952,0.00007558567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006376133,0.00012378066,0.0002995919,0.00016380196,0.0002033682,0.000083089006,0.00015453022,0.00015116486,0.000028531467],"category_scores_gemma":[0.00023190459,0.000104469174,0.00011199136,0.00018440692,0.00026003396,0.00015327797,0.00005214087,0.00020456822,0.000002302648],"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":[0.0029849405,0.00012007274,0.5574627,0.0003464624,0.0004325737,0.0000068922336,0.00003611936,0.057336375,0.37047428,0.005094773,0.001907002,0.0037978292],"study_design_scores_gemma":[0.0026294237,0.0004244427,0.81692046,0.000135534,0.00014595641,0.00015933807,0.000019530515,0.15767375,0.0056011085,0.015586392,0.00046450607,0.0002395527],"about_ca_topic_score_codex":0.000004464393,"about_ca_topic_score_gemma":9.562856e-7,"teacher_disagreement_score":0.36487317,"about_ca_system_score_codex":0.00006491122,"about_ca_system_score_gemma":0.00019497213,"threshold_uncertainty_score":0.42601293},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36878225,0.0026189066,0.6280565,0.00011704639,0.00030022068,0.00008341341,0.00000806294,0.0000016577858,0.000031922875],"genre_scores_gemma":[0.99519795,0.00015566415,0.004169766,0.000064302665,0.00017600156,0.0000044522762,0.00018139838,0.0000049335267,0.000045519304],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990345,0.00013801867,0.0005230218,0.00013182907,0.00005693468,0.00011568904],"domain_scores_gemma":[0.9988336,0.00011875241,0.00044007748,0.00009026089,0.00048502142,0.000032270837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004172393,0.000089344176,0.00026751345,0.00013022263,0.00003839177,0.0000072005964,0.00015839683,0.00017479455,0.0000033503302],"category_scores_gemma":[0.00008860143,0.00007258789,0.00020003722,0.00013406364,0.00008058137,0.0000023944415,0.000033274104,0.000056355428,2.1159026e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022569639,0.00006212462,0.00852736,0.000021542384,0.00049064535,4.89696e-7,0.0000045250504,0.9588752,0.025557507,0.002207401,0.0013141487,0.002713364],"study_design_scores_gemma":[0.0048514074,0.0039714347,0.04023485,0.0001794009,0.0005502044,0.00019077126,0.00016566446,0.86292773,0.01537338,0.044375192,0.026539389,0.00064058363],"about_ca_topic_score_codex":0.0000010350304,"about_ca_topic_score_gemma":6.6152563e-7,"teacher_disagreement_score":0.6264157,"about_ca_system_score_codex":0.000019334128,"about_ca_system_score_gemma":0.000117766416,"threshold_uncertainty_score":0.29600483},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46614248,0.00046576734,0.5325217,0.0005591814,0.00009600004,0.00010105643,0.000092189795,0.0000014505198,0.000020158921],"genre_scores_gemma":[0.930425,0.00007478034,0.068732105,0.00043583746,0.0002049531,0.000009992058,0.0000916167,0.000009437777,0.000016266958],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937856,0.000034432476,0.00027494546,0.00013378292,0.000065253495,0.000112995804],"domain_scores_gemma":[0.9990472,0.0000798196,0.00023994023,0.000054468073,0.00054666854,0.00003186378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018560473,0.000093199465,0.00015408506,0.00010042003,0.00007418324,0.000017173095,0.000086772845,0.000093210176,0.0000030413137],"category_scores_gemma":[0.000034263157,0.00007906094,0.00006975889,0.000080896076,0.00004418119,0.0000069252496,0.000022910455,0.00005637063,1.1931107e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007387791,0.00003446668,0.0021209924,0.000023403993,0.00015738358,4.351792e-7,0.000053276624,0.8547572,0.13466522,0.0028487097,0.00016244606,0.004437715],"study_design_scores_gemma":[0.0042896005,0.0006093707,0.011406813,0.00015194547,0.00018792033,0.00010781846,0.00022134531,0.90564406,0.016330736,0.059090868,0.001624898,0.00033460822],"about_ca_topic_score_codex":0.000009932494,"about_ca_topic_score_gemma":0.000023313232,"teacher_disagreement_score":0.4642825,"about_ca_system_score_codex":0.00005551111,"about_ca_system_score_gemma":0.00075972325,"threshold_uncertainty_score":0.32240114},"labels":[],"label_agreement":null}]}