{"meta":{"query_hash":"0b96b08e201c","filters":{"venue":"Journal of Bioinformatics and Computational Biology"},"cohort_total":95,"direct_labels_cover":0,"predictions_cover":95,"exported":95,"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/0b96b08e201c","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Bioinformatics+and+Computational+Biology"},"results":[{"id":"W1966875588","doi":"10.1142/s0219720006002168","title":"ON THE INFERENCE OF PARSIMONIOUS INDEL EVOLUTIONARY SCENARIOS","year":2006,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Genomics and Phylogenetic Studies","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":"McGill University","funders":"","keywords":"Indel; Divide and conquer algorithms; Inference; Phylogenetic tree; Set (abstract data type); Computer science; Tree (set theory); Multiple sequence alignment; Algorithm; Mathematics; Theoretical computer science; Sequence alignment; Biology; Artificial intelligence; Combinatorics; Genetics; Gene","score_opus":0.008418978132512304,"score_gpt":0.22929757187566646,"score_spread":0.22087859374315416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966875588","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9905886,0.00083894335,0.007581854,0.00039100405,0.00008198225,0.000052929638,0.000025248026,4.5240125e-7,0.00043895777],"genre_scores_gemma":[0.99525046,0.00014391053,0.0042750584,0.00024249792,0.00006141424,9.567691e-7,0.000014104924,0.0000025513189,0.00000904841],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99941653,0.000024335548,0.00035793398,0.000046473484,0.00007540024,0.00007930068],"domain_scores_gemma":[0.99928415,0.0001236687,0.00031496907,0.000060148082,0.00019719356,0.000019889198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015317193,0.00007185136,0.00011932761,0.000045431952,0.000062779494,0.000006845316,0.00010064381,0.000055617562,0.0000027383692],"category_scores_gemma":[0.000054030614,0.000045148303,0.000053775213,0.000039168408,0.00013747567,0.0000011781766,0.00005318515,0.000060393515,7.7611173e-7],"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":[0.0009032792,0.0007807867,0.117068276,0.0001581327,0.0011738382,0.000005932249,0.00090421713,0.3348611,0.0863542,0.40395203,0.019848961,0.033989236],"study_design_scores_gemma":[0.004081783,0.00800884,0.36527976,0.00014251836,0.00014016537,0.00045394976,0.000978361,0.09401352,0.0075249537,0.4990018,0.01955968,0.0008146854],"about_ca_topic_score_codex":0.000005669093,"about_ca_topic_score_gemma":0.000001449919,"teacher_disagreement_score":0.24821147,"about_ca_system_score_codex":0.00000481971,"about_ca_system_score_gemma":0.00007535839,"threshold_uncertainty_score":0.18410945},"labels":[],"label_agreement":null},{"id":"W1969299022","doi":"10.1142/s0219720010004987","title":"PROTEIN SECONDARY STRUCTURE PREDICTION USING NMR CHEMICAL SHIFT DATA","year":2010,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; k-nearest neighbors algorithm; Software; Data mining; Key (lock); Sequence (biology); Limit (mathematics); Algorithm; Pattern recognition (psychology); Artificial intelligence; Mathematics; Chemistry","score_opus":0.008312882145458547,"score_gpt":0.2507371658138717,"score_spread":0.24242428366841312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969299022","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9442757,0.00013980192,0.054771297,0.000107139305,0.00021069833,0.00009181132,0.0003344355,0.0000030731105,0.000066042936],"genre_scores_gemma":[0.8778135,0.000008900454,0.12109462,0.00015557928,0.00035756495,3.831035e-7,0.00056134426,0.000005772107,0.0000023484054],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992114,0.000017821243,0.00044866587,0.00010865257,0.000096427655,0.00011706902],"domain_scores_gemma":[0.9992583,0.000014113061,0.0003503268,0.00017145475,0.00013098528,0.000074859614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019688577,0.000108448425,0.00014826341,0.00006049262,0.00006089979,0.000029636458,0.00024446566,0.00021188568,0.000012453413],"category_scores_gemma":[0.000076657285,0.000084872474,0.000037199843,0.000044336248,0.0001238247,0.000024835626,0.00018558597,0.00029134966,3.4195037e-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":[0.00019120233,0.000039459366,0.0025336104,0.00008035478,0.00019999688,0.0000034176687,0.000118569515,0.0012203577,0.95951027,0.004034407,0.00034111235,0.031727225],"study_design_scores_gemma":[0.006407556,0.0023583905,0.016863795,0.000117953685,0.00023927525,0.0066295266,0.0002649079,0.71206176,0.062967055,0.15167776,0.03915593,0.0012560943],"about_ca_topic_score_codex":0.0000019762176,"about_ca_topic_score_gemma":0.0000036021697,"teacher_disagreement_score":0.8965432,"about_ca_system_score_codex":0.0000051563575,"about_ca_system_score_gemma":0.00019759574,"threshold_uncertainty_score":0.3460999},"labels":[],"label_agreement":null},{"id":"W1971269462","doi":"10.1142/s0219720006001722","title":"THE USE OF FUNCTIONAL DOMAINS TO IMPROVE TRANSMEMBRANE PROTEIN TOPOLOGY PREDICTION","year":2006,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Caprion (Canada); University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; University of Calgary","keywords":"Transmembrane protein; Topology (electrical circuits); Transmembrane domain; Membrane protein; Computational biology; Computer science; Biology; Mathematics; Gene; Genetics; Membrane","score_opus":0.008049881864178819,"score_gpt":0.22718057682381404,"score_spread":0.21913069495963522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971269462","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65071845,0.00013202764,0.34745637,0.00090917066,0.0002742412,0.00022014863,0.00008662074,0.0000043229284,0.00019866359],"genre_scores_gemma":[0.9407985,0.000048913495,0.058218148,0.00033769588,0.00027128553,0.0000065110967,0.0001605875,0.000008727017,0.0001495815],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988325,0.000051062678,0.00076567987,0.00006642843,0.00014127785,0.00014299837],"domain_scores_gemma":[0.998928,0.00011058253,0.0004919851,0.000097205084,0.00031834233,0.000053865537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034211416,0.00010710593,0.00016310671,0.000092657916,0.00012098009,0.000030074147,0.00011324417,0.00011368441,0.000004336053],"category_scores_gemma":[0.00012918295,0.00007173943,0.0000809306,0.00007683248,0.00017145257,0.000017677032,0.00005038372,0.00012498254,0.0000013860484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00243713,0.00035125302,0.011822238,0.00032926394,0.0007194647,0.000003229441,0.0005691905,0.495281,0.32411942,0.07425997,0.013830891,0.07627694],"study_design_scores_gemma":[0.0071701123,0.012858356,0.06499058,0.00013286789,0.00020079169,0.0013841013,0.00051942415,0.33740914,0.021191224,0.024024127,0.52921826,0.000900996],"about_ca_topic_score_codex":0.000008329919,"about_ca_topic_score_gemma":0.000007440208,"teacher_disagreement_score":0.51538736,"about_ca_system_score_codex":0.00001091272,"about_ca_system_score_gemma":0.000095084164,"threshold_uncertainty_score":0.2925449},"labels":[],"label_agreement":null},{"id":"W1974873233","doi":"10.1142/s0219720013410059","title":"ENHANCING GENOMICS INFORMATION RETRIEVAL THROUGH DIMENSIONAL ANALYSIS","year":2013,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Advanced Graph Neural Networks","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":"York University","funders":"Université de Neuchâtel; University of Melbourne","keywords":"Computer science; Linear subspace; Information retrieval; Dimension (graph theory); Rank (graph theory); Homogeneity (statistics); Graph; Data mining; Set (abstract data type); Genomics; Theoretical computer science; Machine learning; Mathematics; Genome","score_opus":0.00768950690829641,"score_gpt":0.23559019145499488,"score_spread":0.22790068454669846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974873233","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":[0.12606789,0.00011432504,0.87286973,0.00057177513,0.00019746227,0.00007035125,0.000003364668,0.000012372664,0.000092754824],"genre_scores_gemma":[0.49639407,0.00004798692,0.5023018,0.00118973,0.000042137595,6.677351e-7,0.000019113597,0.0000018567172,0.0000026476089],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869615,0.000032225682,0.0008387205,0.000067564404,0.00019724297,0.00016808193],"domain_scores_gemma":[0.9983027,0.0002681934,0.00075450516,0.000103264705,0.00048746253,0.00008386401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023699358,0.00011185291,0.000261013,0.00031196416,0.00010893729,0.00012988882,0.00027882546,0.000074947166,0.00001109042],"category_scores_gemma":[0.000046581805,0.00008552198,0.00011862623,0.0005714645,0.00006708743,0.0024193123,0.00013618269,0.00017120391,0.000016679158],"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":[0.00008432917,0.000093329916,0.0030007542,0.00006646062,0.0014603074,0.0000061570904,0.0043145292,0.70320266,0.0010617904,0.20165873,0.0014088702,0.083642066],"study_design_scores_gemma":[0.00039172138,0.00022687897,0.0056087496,0.00000964079,0.000044596516,0.00014117574,0.000077015626,0.9033213,0.00018168004,0.08898448,0.0008695611,0.00014318847],"about_ca_topic_score_codex":0.0000037467057,"about_ca_topic_score_gemma":5.616838e-7,"teacher_disagreement_score":0.37056792,"about_ca_system_score_codex":0.000032056294,"about_ca_system_score_gemma":0.00007475614,"threshold_uncertainty_score":0.34874848},"labels":[],"label_agreement":null},{"id":"W1975762434","doi":"10.1142/s0219720007002606","title":"A SYSTEMS BIOLOGY APPROACH TO THE STUDY OF CISPLATIN DRUG RESISTANCE IN OVARIAN CANCERS","year":2007,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"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":"McGill University; Indiana University-Purdue University Indianapolis","keywords":"Proteomics; Proteome; Computational biology; Cisplatin; Biology; Systems biology; Mechanism (biology); Drug resistance; Quantitative proteomics; Bioinformatics; Cell biology; Gene; Biochemistry; Genetics","score_opus":0.009068232204207032,"score_gpt":0.24920682124571908,"score_spread":0.24013858904151206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975762434","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76540893,0.0011093927,0.23083082,0.00017754534,0.00032370456,0.00043778232,0.000022315124,0.0000015218084,0.0016880017],"genre_scores_gemma":[0.98454016,0.00003857335,0.0150479805,0.00019987281,0.00011556747,0.0000039370525,0.000024733818,0.0000051067964,0.00002407],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858147,0.000060340702,0.0009769751,0.00008988349,0.000100416604,0.00019091254],"domain_scores_gemma":[0.9989545,0.00008470586,0.0005758058,0.00012905114,0.00018424231,0.00007169962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013773373,0.00011757342,0.0002675501,0.00015995115,0.000059246584,0.000017390383,0.00023550238,0.00009691808,6.7478953e-7],"category_scores_gemma":[0.0000385409,0.00007874109,0.000045733672,0.00017816726,0.00007808299,0.0000074473096,0.00008832654,0.00014369436,5.2378925e-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":[0.0055066883,0.002171526,0.07631602,0.0008860917,0.00226953,0.00001635674,0.057094324,0.61799234,0.007476036,0.15865786,0.018016847,0.053596385],"study_design_scores_gemma":[0.037839506,0.019018956,0.2152863,0.0008430769,0.0005045735,0.0014390645,0.11798898,0.40751797,0.0010198089,0.045329206,0.14933467,0.0038778775],"about_ca_topic_score_codex":0.00004195755,"about_ca_topic_score_gemma":0.00016255198,"teacher_disagreement_score":0.21913125,"about_ca_system_score_codex":0.00002596194,"about_ca_system_score_gemma":0.00011062288,"threshold_uncertainty_score":0.32109684},"labels":[],"label_agreement":null},{"id":"W1978319862","doi":"10.1142/s0219720006002478","title":"CHARACTERIZATION OF THE EXISTENCE OF GALLED-TREE NETWORKS","year":2006,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Algorithms and Data Compression","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":"Simon Fraser University","funders":"Simon Fraser University; Slovenská Akadémia Vied","keywords":"Mathematics; Tree (set theory); Simple (philosophy); Characterization (materials science); Root (linguistics); Convexity; Tree structure; Combinatorics; Discrete mathematics; Binary tree","score_opus":0.006882667899141399,"score_gpt":0.21145192726509057,"score_spread":0.20456925936594916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978319862","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":[0.13463968,0.00008187368,0.8647225,0.00017860834,0.00018368963,0.000036128287,0.000007869589,0.000002157351,0.00014749044],"genre_scores_gemma":[0.9032946,0.000039160663,0.096522,0.00007317871,0.000051163275,2.6756516e-7,0.000012504694,0.0000013107132,0.000005785118],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918467,0.000028793973,0.00055206165,0.000039710947,0.00013020005,0.00006457884],"domain_scores_gemma":[0.9986913,0.000084497544,0.00086798397,0.00009405576,0.00024292473,0.000019209205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019376268,0.000053640688,0.00015064761,0.00006330055,0.000043268028,0.000017186409,0.0003181719,0.00004008028,0.0000014965422],"category_scores_gemma":[0.000011458261,0.000031752214,0.000050291714,0.0001347227,0.00007806774,0.00023322031,0.00013835609,0.00006507678,1.921313e-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":[0.00009323607,0.0003850738,0.021107977,0.00019356541,0.00014283371,0.0000034948685,0.0009816139,0.075742446,0.017218541,0.55126464,0.0007831182,0.33208343],"study_design_scores_gemma":[0.00029990962,0.00014457093,0.083895765,0.000053814816,0.0000064563537,0.00006618031,0.000011224617,0.8969101,0.00046987407,0.017727977,0.0003631263,0.00005103229],"about_ca_topic_score_codex":0.0000040697014,"about_ca_topic_score_gemma":5.83978e-7,"teacher_disagreement_score":0.82116765,"about_ca_system_score_codex":0.000005420426,"about_ca_system_score_gemma":0.000050061506,"threshold_uncertainty_score":0.12948178},"labels":[],"label_agreement":null},{"id":"W1978894908","doi":"10.1142/s021972000700262x","title":"GASA: A GRAPH-BASED AUTOMATED NMR BACKBONE RESONANCE SEQUENTIAL ASSIGNMENT PROGRAM","year":2007,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Protein Structure and Dynamics","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 Alberta","funders":"","keywords":"Chaining; Assignment problem; Computer science; Algorithm; Graph; Theoretical computer science; Mathematics; Mathematical optimization","score_opus":0.007024527546030541,"score_gpt":0.2742543475937394,"score_spread":0.26722982004770884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978894908","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5616853,0.0010758197,0.43616074,0.00023005482,0.00022619161,0.00024168611,0.000032440155,0.000027773523,0.0003199864],"genre_scores_gemma":[0.8678967,0.00005554111,0.1313348,0.0004363827,0.00012961915,0.0000024487872,0.00013013148,0.0000068280974,0.000007587293],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989735,0.000028860995,0.00056161394,0.00009300622,0.00014214103,0.00020088181],"domain_scores_gemma":[0.99915296,0.000029195353,0.00040624038,0.00008110907,0.00023057187,0.00009993608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043702143,0.00012840681,0.00018082089,0.00011374606,0.00007190533,0.000026251144,0.00011752559,0.00015286468,0.0000039638444],"category_scores_gemma":[0.000036071604,0.0001011196,0.00009114152,0.00009881425,0.00014315436,0.000008825378,0.000045875706,0.00011340986,0.0000010902913],"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":[0.0045723557,0.0014149908,0.035294905,0.0005268035,0.0014611924,0.00015190365,0.0006423987,0.08178517,0.10275911,0.021558587,0.009519087,0.7403135],"study_design_scores_gemma":[0.0109814685,0.013020406,0.057787005,0.0002095055,0.00018762436,0.0021344416,0.0003447688,0.7992974,0.016741352,0.02417653,0.07373618,0.0013833466],"about_ca_topic_score_codex":0.0000018675939,"about_ca_topic_score_gemma":0.0000034764778,"teacher_disagreement_score":0.73893017,"about_ca_system_score_codex":0.00001676242,"about_ca_system_score_gemma":0.00013938086,"threshold_uncertainty_score":0.41235375},"labels":[],"label_agreement":null},{"id":"W1979548025","doi":"10.1142/s0219720011005355","title":"IMPROVED SEQUENCE-BASED PREDICTION OF STRAND RESIDUES","year":2010,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Artificial intelligence; Computational biology; Classifier (UML); Pattern recognition (psychology); Computer science; Biological system; Biology; Bioinformatics","score_opus":0.009067655613722058,"score_gpt":0.25938986886793786,"score_spread":0.2503222132542158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979548025","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9395926,0.00007017985,0.05931137,0.00019057479,0.0002513566,0.00008304209,0.00010463472,0.000004176909,0.00039204076],"genre_scores_gemma":[0.8978145,0.000032285694,0.10174704,0.00014428659,0.00010382081,7.6119113e-7,0.00014443418,0.0000047750623,0.0000080971395],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907184,0.00002568806,0.00063996797,0.00005468703,0.00010512172,0.00010271059],"domain_scores_gemma":[0.99882084,0.000058069578,0.00063325325,0.00009311004,0.00033035988,0.00006433677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040442616,0.000097229524,0.00017157028,0.00011133984,0.00004778046,0.000016553267,0.00012875731,0.00014759346,0.000010199888],"category_scores_gemma":[0.00016917948,0.00007591445,0.00006997102,0.000055777404,0.00017586742,0.000013477399,0.00003340583,0.0002001828,4.967691e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008259953,0.00025134726,0.08366129,0.0004676772,0.00045415666,0.0000023897762,0.00079728576,0.021921292,0.8176142,0.0076634916,0.0015379097,0.06480295],"study_design_scores_gemma":[0.0048870067,0.0057974155,0.032584984,0.0000897566,0.00010240926,0.0005940683,0.0003215971,0.8992808,0.036382377,0.004827493,0.014707242,0.00042485297],"about_ca_topic_score_codex":0.000002497677,"about_ca_topic_score_gemma":0.0000039033735,"teacher_disagreement_score":0.8773595,"about_ca_system_score_codex":0.000003921706,"about_ca_system_score_gemma":0.00016961372,"threshold_uncertainty_score":0.30957016},"labels":[],"label_agreement":null},{"id":"W1980611895","doi":"10.1142/s0219720006002302","title":"ITERATED LOCAL LEAST SQUARES MICROARRAY MISSING VALUE IMPUTATION","year":2006,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":87,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Chinese Academy of Sciences; University of Alberta","keywords":"Imputation (statistics); Missing data; Iterated function; Data mining; Microarray analysis techniques; Computer science; Mathematics; Statistics; Algorithm; Gene; Biology; Gene expression; Genetics","score_opus":0.006049518886673946,"score_gpt":0.24466432822405573,"score_spread":0.23861480933738177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980611895","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":[0.37098703,0.000817139,0.6269495,0.00062212505,0.00018071964,0.00005700483,0.000011651033,0.0000043485866,0.00037047215],"genre_scores_gemma":[0.97980666,0.00004584371,0.019388326,0.0003273437,0.00021397903,0.0000011355172,0.0001769486,0.000005987403,0.00003375803],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999179,0.000045208897,0.00048416236,0.00008640389,0.00009483375,0.000110386485],"domain_scores_gemma":[0.9992211,0.000021865077,0.00038876277,0.000057732766,0.0002572289,0.000053351294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001782181,0.00009858616,0.00012881578,0.000115486786,0.000082704835,0.00004346365,0.00008003208,0.000103889906,0.0000059716485],"category_scores_gemma":[0.000018973935,0.000079618614,0.000059302998,0.000078710764,0.00009597154,0.000013667455,0.000025847849,0.000072919865,0.0000021144615],"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":[0.00050315424,0.0002404509,0.0061611426,0.00012051104,0.00018000406,0.000004986399,0.00040413096,0.118928805,0.6316649,0.011978482,0.014191384,0.21562204],"study_design_scores_gemma":[0.009976918,0.004402152,0.09738699,0.0003310205,0.0001878333,0.0024096253,0.002505798,0.49326062,0.14004306,0.0742644,0.17361669,0.0016148868],"about_ca_topic_score_codex":0.000005287056,"about_ca_topic_score_gemma":0.0000010576672,"teacher_disagreement_score":0.60881966,"about_ca_system_score_codex":0.000015039893,"about_ca_system_score_gemma":0.00011135935,"threshold_uncertainty_score":0.3246753},"labels":[],"label_agreement":null},{"id":"W1981321222","doi":"10.1142/s0219720009004333","title":"ASYMPTOTICS OF CANONICAL AND SATURATED RNA SECONDARY STRUCTURES","year":2009,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Pseudoknot; Protein secondary structure; Nucleic acid secondary structure; Base (topology); Canonical form; Class (philosophy); Computation; RNA; Existential quantification","score_opus":0.0062512840611390185,"score_gpt":0.2390686562936064,"score_spread":0.2328173722324674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981321222","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98111516,0.0014109301,0.016615923,0.0003086491,0.0000900798,0.00005686709,0.000022060442,0.0000015714932,0.00037874718],"genre_scores_gemma":[0.9661605,0.0002694411,0.033129375,0.00034721527,0.000062248735,1.6384958e-7,0.00002200706,0.0000025666898,0.0000064962137],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99935275,0.00003103558,0.00040471097,0.00005568054,0.00007055166,0.000085262145],"domain_scores_gemma":[0.99937487,0.000036976824,0.00032617466,0.000049682716,0.00015176898,0.000060516097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017163022,0.00008303494,0.00018118444,0.000059588438,0.00003577673,0.000013050455,0.00007440344,0.00011515713,0.000006515092],"category_scores_gemma":[0.000050232877,0.000061763596,0.00004374597,0.000033513268,0.000080360755,0.0000073891842,0.000026918964,0.00007728226,1.7621066e-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":[0.0005243713,0.00008402442,0.0008979324,0.000096075135,0.00032206514,0.0000055504174,0.0003487231,0.0012941615,0.5917214,0.037351493,0.0007701222,0.3665841],"study_design_scores_gemma":[0.007911973,0.019222723,0.119476646,0.00022082133,0.00026742453,0.0038306555,0.0010263727,0.015759874,0.4445037,0.369823,0.016645458,0.0013113574],"about_ca_topic_score_codex":8.9860345e-7,"about_ca_topic_score_gemma":4.4960115e-7,"teacher_disagreement_score":0.36527273,"about_ca_system_score_codex":0.000003246099,"about_ca_system_score_gemma":0.000107191496,"threshold_uncertainty_score":0.25186464},"labels":[],"label_agreement":null},{"id":"W1984673676","doi":"10.1142/s0219720008003291","title":"COMPLEXITIES AND ALGORITHMS FOR GLYCAN SEQUENCING USING TANDEM MASS SPECTROMETRY","year":2008,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Glycosylation and Glycoproteins Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Center for Advanced Study, University of Illinois at Urbana-Champaign; Natural Sciences and Engineering Research Council of Canada; Tsinghua University","keywords":"Glycan; Tandem mass spectrometry; Computational biology; Glycopeptide; Computer science; Mass spectrometry; Proteomics; Algorithm; Biology; Chemistry; Biochemistry; Gene; Chromatography","score_opus":0.05674675018465132,"score_gpt":0.31674568914313656,"score_spread":0.25999893895848525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984673676","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64681405,0.000465724,0.35231203,0.000119672506,0.000055418557,0.000091787544,0.000020821592,0.0000018350905,0.00011870431],"genre_scores_gemma":[0.76390946,0.00017521379,0.2355654,0.00014803864,0.00013745697,0.0000011797854,0.00003769907,0.0000049879304,0.00002058201],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993125,0.000025501835,0.00034826045,0.00007296166,0.00010168611,0.00013908742],"domain_scores_gemma":[0.99935216,0.00005582882,0.00021680925,0.00004368696,0.00025429027,0.0000772101],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002553419,0.00008575512,0.00016914518,0.00013216533,0.00015872438,0.000025899573,0.000065242675,0.00007709297,0.0000051700404],"category_scores_gemma":[0.00007001418,0.00007091786,0.00005145043,0.000058734993,0.00017184856,0.000015513364,0.000037358805,0.00007600983,3.0364544e-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":[0.0016584274,0.00024679853,0.043465056,0.00077896024,0.0017008899,0.00006187313,0.0030703058,0.02553691,0.8285954,0.038588002,0.0029586256,0.05333875],"study_design_scores_gemma":[0.0072994176,0.0059351074,0.013549526,0.00009876662,0.00006861849,0.008109706,0.0027684409,0.8803688,0.022826407,0.044805415,0.013357439,0.00081233174],"about_ca_topic_score_codex":0.00000410622,"about_ca_topic_score_gemma":9.2415735e-7,"teacher_disagreement_score":0.85483193,"about_ca_system_score_codex":0.000020434809,"about_ca_system_score_gemma":0.00016369822,"threshold_uncertainty_score":0.28919464},"labels":[],"label_agreement":null},{"id":"W1988405029","doi":"10.1142/s0219720009004102","title":"GENOME HALVING WITH DOUBLE CUT AND JOIN","year":2009,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Royal Society of Canada","keywords":"Join (topology); Reciprocal; Genome; Context (archaeology); Computer science; Block (permutation group theory); Combinatorics; Mathematics; Algorithm; Genetics; Biology; Gene","score_opus":0.007831224378292838,"score_gpt":0.231936087837947,"score_spread":0.22410486345965416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988405029","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96725655,0.0010558408,0.030440865,0.00051454763,0.000046959878,0.00007767787,0.0000046137534,0.00000253425,0.00060039695],"genre_scores_gemma":[0.9609852,0.00029511063,0.038218807,0.0003173319,0.00011620461,5.122026e-7,0.000035157813,0.0000038885455,0.000027809609],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99946976,0.000011158559,0.000267875,0.00006587486,0.00007420843,0.00011114329],"domain_scores_gemma":[0.99953395,0.000010555383,0.00020991823,0.00004810983,0.00012950774,0.000067951114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016031775,0.000087225795,0.00013674286,0.00007860254,0.000053606615,0.000029634597,0.00006365028,0.00005665355,0.0000030720234],"category_scores_gemma":[0.000006607359,0.00006304112,0.000027116486,0.000042646112,0.00006131492,0.00001051612,0.000029393774,0.000064464955,9.4964764e-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":[0.0046263337,0.0010158729,0.059205476,0.00055779784,0.0030423612,0.00010679966,0.0055340766,0.03317072,0.46945095,0.025734972,0.0025163477,0.39503828],"study_design_scores_gemma":[0.039510034,0.045886718,0.6393629,0.00033061724,0.0005519404,0.016136967,0.0030466116,0.06384016,0.013427608,0.05154737,0.123124376,0.0032347024],"about_ca_topic_score_codex":6.4105166e-7,"about_ca_topic_score_gemma":6.408018e-7,"teacher_disagreement_score":0.5801574,"about_ca_system_score_codex":0.000005728385,"about_ca_system_score_gemma":0.00004612316,"threshold_uncertainty_score":0.25707424},"labels":[],"label_agreement":null},{"id":"W1989027782","doi":"10.1142/s0219720012410016","title":"IDENTIFICATION OF SHORTENED 3′ UNTRANSLATED REGIONS FROM EXPRESSION ARRAYS","year":2012,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Cancer Research; Ligue Contre le Cancer; Institut National Du Cancer; European Commission","keywords":"RefSeq; Computational biology; Biology; DNA microarray; Genetics; Gene; Untranslated region; splice; Alternative splicing; Exon; Three prime untranslated region; Gene expression; Genome; Messenger RNA","score_opus":0.01353372281945734,"score_gpt":0.27811291777150116,"score_spread":0.2645791949520438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989027782","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82942724,0.0006863848,0.16958639,0.00011919688,0.00007756365,0.00004028379,0.00002450292,0.0000011817298,0.000037231606],"genre_scores_gemma":[0.98887956,0.00021776753,0.01062317,0.00005541678,0.000101463316,7.4424855e-7,0.000105861276,0.0000034183035,0.000012582871],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992246,0.000037520105,0.00048066577,0.00004411395,0.00009872816,0.000114351926],"domain_scores_gemma":[0.99927264,0.000043407457,0.00034698346,0.00006770129,0.00018511894,0.00008414693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027862858,0.00006154549,0.00012830686,0.00007399706,0.000043204196,0.000009355574,0.00008766889,0.00008212798,0.000005316923],"category_scores_gemma":[0.00005294962,0.00004699242,0.00005471792,0.000049931332,0.000069751346,0.000017812408,0.000027363989,0.00006620013,0.0000010708436],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010214944,0.00005315581,0.0049426653,0.000014668451,0.00007512645,2.4529905e-7,0.00022916633,0.0007046015,0.98854625,0.0007830334,0.00029511558,0.0042538457],"study_design_scores_gemma":[0.0041896147,0.0019886282,0.10835566,0.00019348584,0.00014013895,0.0003095969,0.0014131,0.074517585,0.7877064,0.01521767,0.0053597274,0.00060843397],"about_ca_topic_score_codex":0.0000038876806,"about_ca_topic_score_gemma":6.509264e-7,"teacher_disagreement_score":0.20083988,"about_ca_system_score_codex":0.000004445012,"about_ca_system_score_gemma":0.000045727742,"threshold_uncertainty_score":0.19162953},"labels":[],"label_agreement":null},{"id":"W1990343223","doi":"10.1142/s0219720006002442","title":"MULTIRESOLUTION ANALYSIS UNCOVERS HIDDEN CONSERVATION OF PROPERTIES IN STRUCTURALLY AND FUNCTIONALLY SIMILAR PROTEINS","year":2006,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McGill University","keywords":"Computational biology; Conserved sequence; Biology; Function (biology); Protein structure; Functional analysis; Biological system; Genetics; Peptide sequence; Computer science; Mathematics; Biochemistry; Gene","score_opus":0.005488743083350428,"score_gpt":0.20737772079378472,"score_spread":0.2018889777104343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990343223","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.973255,0.00043923905,0.025927374,0.00017742153,0.000032502146,0.00009518286,0.000024277804,0.0000012440817,0.000047760794],"genre_scores_gemma":[0.97299635,0.000055609227,0.026687209,0.00009802613,0.000037365982,0.0000013770479,0.000113980415,0.0000024916117,0.0000075791445],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99926615,0.000029576555,0.0004702563,0.00006710118,0.00009082743,0.00007607683],"domain_scores_gemma":[0.9993131,0.00001955552,0.00038004026,0.000042929893,0.00022155096,0.000022784952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015982258,0.00008131715,0.00018082379,0.00017590635,0.000032455264,0.000011944482,0.000049157778,0.00009195431,0.0000015131398],"category_scores_gemma":[0.000037862777,0.000062069936,0.000052576448,0.000120102355,0.000110016794,0.00001704816,0.000032879678,0.00005868516,5.4609583e-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":[0.0015884105,0.0001716704,0.6471527,0.00032990077,0.0012837013,0.000004853042,0.00045619367,0.18406415,0.12485419,0.015419843,0.00022832933,0.024446022],"study_design_scores_gemma":[0.0023069305,0.0014312392,0.7553864,0.000046762587,0.00018983865,0.00013304554,0.00026767232,0.21369168,0.0034372916,0.022233156,0.000595699,0.00028029003],"about_ca_topic_score_codex":0.0000480781,"about_ca_topic_score_gemma":0.00009395125,"teacher_disagreement_score":0.1214169,"about_ca_system_score_codex":0.000011126378,"about_ca_system_score_gemma":0.00008395641,"threshold_uncertainty_score":0.25311387},"labels":[],"label_agreement":null},{"id":"W1991265331","doi":"10.1142/s0219720012400082","title":"A FAST METHOD FOR LARGE-SCALE MULTICHROMOSOMAL BREAKPOINT MEDIAN PROBLEMS","year":2011,"lang":"en","type":"article","venue":"Journal of Bioinformatics and 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":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; Computer science; Scale (ratio); Algorithm; Mathematics; Biology; Chromosome; Genetics; Cartography; Geography","score_opus":0.015277791115516364,"score_gpt":0.2636110825953793,"score_spread":0.24833329147986294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991265331","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":[0.07101673,0.00026191032,0.92771035,0.00017633695,0.00018995961,0.00022283832,0.00008524699,0.0000037593782,0.00033285067],"genre_scores_gemma":[0.19786587,0.00007801286,0.8014511,0.00025178606,0.00017887163,0.000009488769,0.00012528992,0.000010763387,0.000028858338],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991099,0.00003243161,0.0004890543,0.00009508143,0.000083630686,0.0001898604],"domain_scores_gemma":[0.999146,0.00003600683,0.00035407333,0.00007231156,0.00029176523,0.00009988614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045828018,0.000116034695,0.0001983138,0.00009335075,0.000063523454,0.000014314798,0.00013013347,0.00011043327,0.000014839049],"category_scores_gemma":[0.000036362006,0.000091533475,0.00010393932,0.000046068526,0.000048149428,0.00001020687,0.0000669574,0.00007067479,0.0000023923674],"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":[0.0028385373,0.0034480144,0.0361126,0.0020248166,0.0056396164,0.00003012574,0.04649925,0.013233172,0.19307718,0.02264339,0.009166378,0.6652869],"study_design_scores_gemma":[0.017449856,0.014688509,0.02122617,0.00016290465,0.00040365098,0.0026265404,0.0056240275,0.79854274,0.017505247,0.05489432,0.065357305,0.0015187581],"about_ca_topic_score_codex":0.0000025657846,"about_ca_topic_score_gemma":0.0000067413803,"teacher_disagreement_score":0.78530955,"about_ca_system_score_codex":0.000008435826,"about_ca_system_score_gemma":0.000073350086,"threshold_uncertainty_score":0.37326267},"labels":[],"label_agreement":null},{"id":"W1991772956","doi":"10.1142/s0219720010004495","title":"A MULTI-STRATEGY APPROACH TO INFORMATIVE GENE IDENTIFICATION FROM GENE EXPRESSION DATA","year":2010,"lang":"en","type":"article","venue":"Journal of Bioinformatics and 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":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Biotechnology Research Institute; National Research Council Canada","funders":"","keywords":"Identification (biology); Computer science; Selection (genetic algorithm); Gene prediction; Data mining; Gene; Computational biology; Genomics; Artificial intelligence; Biology; Genome; Genetics","score_opus":0.036577473547878755,"score_gpt":0.30692836221762937,"score_spread":0.2703508886697506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991772956","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":[0.49022853,0.00014794688,0.5088108,0.00011670374,0.00025863035,0.00012123834,0.00017482211,0.0000040974446,0.00013722069],"genre_scores_gemma":[0.74014306,0.00007271158,0.25796664,0.00026868458,0.00018430747,0.00000497278,0.0013342077,0.0000059049285,0.00001951326],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99891317,0.00003918432,0.00062662835,0.00016280338,0.00013942418,0.00011876565],"domain_scores_gemma":[0.99871176,0.000025844967,0.00052956457,0.00030292582,0.0002956767,0.00013421645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037022046,0.00012173103,0.00015878452,0.00012881849,0.00008934493,0.000061055194,0.00039898994,0.00016412373,0.000006334879],"category_scores_gemma":[0.00009961386,0.00009580465,0.00003985421,0.00009194776,0.000067861176,0.000043611508,0.00020405628,0.00017350832,0.0000063405623],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008476693,0.0000874374,0.0005016988,0.00000988498,0.000046350637,1.994262e-7,0.00034818953,0.002125067,0.9834535,0.00014508025,0.0018598926,0.011337899],"study_design_scores_gemma":[0.005074531,0.0010708948,0.08696079,0.0000596254,0.000106239386,0.0004103609,0.0026582999,0.3445515,0.5135908,0.003076722,0.04143171,0.0010084779],"about_ca_topic_score_codex":0.0000037669124,"about_ca_topic_score_gemma":0.0000019886052,"teacher_disagreement_score":0.4698627,"about_ca_system_score_codex":0.00000679995,"about_ca_system_score_gemma":0.00013226073,"threshold_uncertainty_score":0.39068004},"labels":[],"label_agreement":null},{"id":"W1993568797","doi":"10.1142/s0219720015500134","title":"Identification of biomarker genes for resistance to a pathogen by a novel method for meta-analysis of single-channel microarray datasets","year":2015,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Mycotoxins in Agriculture and Food","field":"Agricultural and Biological Sciences","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":"Agriculture and Agri-Food Canada","funders":"","keywords":"Microarray analysis techniques; DNA microarray; Microarray; Gene; Biology; Computational biology; Gene chip analysis; Microarray databases; Identification (biology); Data mining; Computer science; Genetics; Gene expression; Botany","score_opus":0.0949890221889506,"score_gpt":0.3118014570270975,"score_spread":0.21681243483814688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993568797","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":[0.056816984,0.002220413,0.9163141,0.0014033339,0.00011135457,0.00050625077,0.022601642,0.0000039834754,0.00002188221],"genre_scores_gemma":[0.51085055,0.00003941477,0.4846462,0.00056079164,0.00008406549,0.000050190727,0.0037123116,0.0000018946931,0.000054611166],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99881953,0.000034797602,0.0008364225,0.0000908847,0.00012422746,0.00009414397],"domain_scores_gemma":[0.9977772,0.0005205123,0.0009434513,0.00003640465,0.000648321,0.00007406662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009455675,0.00009064919,0.0005072445,0.00007109154,0.000041068968,0.000019228548,0.00016124311,0.000069756185,0.0000040783902],"category_scores_gemma":[0.00013088254,0.00003476232,0.00031600127,0.00031932615,0.000033000564,0.00008293248,0.000027428485,0.000023240753,1.4315577e-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":[0.00026026947,0.00018622637,0.000029839972,0.000044598542,0.008379206,6.713238e-8,0.0002832161,0.0010469084,0.97654223,0.0011744553,0.006487466,0.005565522],"study_design_scores_gemma":[0.006254563,0.013092899,0.007582608,0.00008546202,0.117219664,0.00018435056,0.0061707767,0.17779408,0.21379206,0.055081215,0.4006415,0.0021008127],"about_ca_topic_score_codex":0.000005296078,"about_ca_topic_score_gemma":0.000025628924,"teacher_disagreement_score":0.76275015,"about_ca_system_score_codex":0.000008880446,"about_ca_system_score_gemma":0.000013473684,"threshold_uncertainty_score":0.14175662},"labels":[],"label_agreement":null},{"id":"W1995229312","doi":"10.1142/s0219720005001247","title":"SPIDER: SOFTWARE FOR PROTEIN IDENTIFICATION FROM SEQUENCE TAGS WITH <i>DE NOVO</i> SEQUENCING ERROR","year":2005,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":219,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Software; Identification (biology); Sequence (biology); Computational biology; Computer science; Sequence assembly; Protein sequencing; DNA sequencing; Protein methods; Biology; Peptide sequence; Genetics; Programming language; Gene; Transcriptome","score_opus":0.021062959777406715,"score_gpt":0.2886165250035087,"score_spread":0.26755356522610196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995229312","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":[0.31585246,0.000059268223,0.6832618,0.00053889817,0.0000066127077,0.000105916864,0.00011802271,0.000016362446,0.000040613253],"genre_scores_gemma":[0.38274175,0.000014092249,0.616873,0.00016520714,0.00008021114,0.000024903566,0.00007869518,0.0000055717587,0.000016545633],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992181,0.0000052518876,0.0004969251,0.0000801169,0.0000789159,0.00012069588],"domain_scores_gemma":[0.9988296,0.000099058445,0.0006289744,0.00007846984,0.00030600812,0.000057857967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015468664,0.000093422685,0.00015094907,0.00004530614,0.000103925326,0.000034620858,0.00012635518,0.00007651613,0.000013516156],"category_scores_gemma":[0.000055995115,0.000074482065,0.00003814614,0.000056520337,0.00007203313,0.0001943652,0.000020000478,0.0001277519,0.0000014141085],"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":[0.00049587357,0.0002445225,0.002711826,0.0004941821,0.0003012584,0.000005732489,0.0019753682,0.07340942,0.64759517,0.0464915,0.00046258018,0.22581258],"study_design_scores_gemma":[0.0028651727,0.0006378797,0.00024170903,0.0004396632,0.000120779114,0.0008416473,0.0008891415,0.43557617,0.22446072,0.31318498,0.020027924,0.0007142203],"about_ca_topic_score_codex":0.000004250966,"about_ca_topic_score_gemma":0.0000022144004,"teacher_disagreement_score":0.42313442,"about_ca_system_score_codex":0.00009126718,"about_ca_system_score_gemma":0.00016168822,"threshold_uncertainty_score":0.30372906},"labels":[],"label_agreement":null},{"id":"W1996146483","doi":"10.1142/s0219720005001314","title":"DYNAMIC MODEL-BASED CLUSTERING FOR TIME–COURSE GENE EXPRESSION DATA","year":2005,"lang":"en","type":"article","venue":"Journal of Bioinformatics and 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 Saskatchewan","funders":"Atomic Energy of Canada Limited; Natural Sciences and Engineering Research Council of Canada; Technische Universiteit Delft; University of Saskatchewan","keywords":"Cluster analysis; Computer science; Data mining; Bootstrapping (finance); Expression (computer science); Hierarchical clustering; Artificial intelligence; Mathematics","score_opus":0.018436637173491813,"score_gpt":0.3028210396366478,"score_spread":0.284384402463156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996146483","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":[0.057223443,0.00052137126,0.9412156,0.0007270547,0.00007855304,0.00009153145,0.00008848548,0.0000032693422,0.000050719445],"genre_scores_gemma":[0.6066876,0.00007843267,0.39200312,0.0004991284,0.00010929454,0.0000033416272,0.0005660161,0.0000070095357,0.000046064837],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993083,0.000017937467,0.00038179458,0.000109252695,0.00007852483,0.00010422535],"domain_scores_gemma":[0.99924046,0.000025754507,0.00033111847,0.00016686236,0.0001710935,0.00006468586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025867458,0.000088520006,0.00012483684,0.0000645824,0.00006913213,0.000020736223,0.00021687796,0.00009202177,0.0000046181985],"category_scores_gemma":[0.000030459545,0.00007094177,0.000046250057,0.000030866733,0.000044012944,0.000017880893,0.000089190304,0.000052148556,0.0000015576679],"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":[0.00032440948,0.0001115872,0.000108785665,0.00004766103,0.00006389058,2.1874261e-7,0.000072509836,0.5115602,0.40410393,0.00008313604,0.0077427053,0.07578098],"study_design_scores_gemma":[0.00083965797,0.00019998352,0.0001122436,0.000017232716,0.00001682629,0.000024751014,0.000023297513,0.98491096,0.005605751,0.00035822476,0.0078016245,0.00008941311],"about_ca_topic_score_codex":9.978795e-8,"about_ca_topic_score_gemma":6.3937824e-7,"teacher_disagreement_score":0.54946417,"about_ca_system_score_codex":0.000010982919,"about_ca_system_score_gemma":0.00016206488,"threshold_uncertainty_score":0.28929216},"labels":[],"label_agreement":null},{"id":"W1996806342","doi":"10.1142/s0219720007003107","title":"COMPUTING THE BREAKPOINT DISTANCE BETWEEN PARTIALLY ORDERED GENOMES","year":2007,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Genome Rearrangement Algorithms","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":"Tsinghua University; McMaster University; University of Minnesota; National Science Foundation","keywords":"Breakpoint; Genome; Nondeterministic algorithm; Chromosome; Computational biology; Heuristic; Biology; Algorithm; Genetics; Computer science; Gene; Artificial intelligence","score_opus":0.010050303129952113,"score_gpt":0.2603520993494437,"score_spread":0.2503017962194916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996806342","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":[0.4436067,0.0010987412,0.55416095,0.0005129727,0.00013647812,0.00009179366,0.000013844215,0.000003055338,0.0003754519],"genre_scores_gemma":[0.97116613,0.00011214763,0.028049847,0.00026158954,0.00034036723,2.9984653e-7,0.000049971895,0.0000057693546,0.000013902986],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990364,0.000030122785,0.0005630335,0.000071818555,0.0001184034,0.00018026201],"domain_scores_gemma":[0.99912876,0.000097826276,0.00041757108,0.00008006692,0.00020640617,0.00006934345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000810258,0.00010115198,0.00016136987,0.000059051978,0.000112873124,0.00003006158,0.00016897256,0.00007061998,0.000003971152],"category_scores_gemma":[0.000036945916,0.00006687733,0.000068964364,0.000073996925,0.00012720683,0.0000066817665,0.00008734412,0.000103038125,0.0000023925707],"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":[0.00033176123,0.00014811782,0.14824367,0.00013190646,0.0012510635,0.000014248899,0.0021004127,0.011516963,0.0075349812,0.008211573,0.0017710892,0.81874424],"study_design_scores_gemma":[0.007308446,0.0051662973,0.5691591,0.00013008171,0.00031279086,0.001273952,0.0036044416,0.053451993,0.004616927,0.029184794,0.32435706,0.0014341528],"about_ca_topic_score_codex":0.0000014353766,"about_ca_topic_score_gemma":0.00000414703,"teacher_disagreement_score":0.8173101,"about_ca_system_score_codex":0.00001109731,"about_ca_system_score_gemma":0.00006541013,"threshold_uncertainty_score":0.27271783},"labels":[],"label_agreement":null},{"id":"W2007567771","doi":"10.1142/s0219720009004199","title":"GENE LOSS UNDER NEIGHBORHOOD SELECTION FOLLOWING WHOLE GENOME DUPLICATION AND THE RECONSTRUCTION OF THE ANCESTRAL POPULUS GENOME","year":2009,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","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":"University of Ottawa","funders":"","keywords":"Genome; Gene duplication; Biology; Populus trichocarpa; Genetics; Gene; Chromosome; Genome evolution; Segmental duplication; Phylogenomics; Gene family; Computational biology; Phylogenetic tree","score_opus":0.006985693473040731,"score_gpt":0.22958404739665136,"score_spread":0.22259835392361063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007567771","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95567006,0.0008711602,0.04170215,0.0014083429,0.00012363073,0.00014231491,0.000011164255,0.000001750622,0.00006939858],"genre_scores_gemma":[0.99319506,0.00022952394,0.0062056426,0.00021606273,0.000109387074,0.0000011359343,0.00002956909,0.0000030022045,0.000010590588],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99929976,0.000047258087,0.00039790897,0.000069596426,0.00009005405,0.00009541136],"domain_scores_gemma":[0.99931765,0.000018708786,0.00043708633,0.00006668035,0.00012936421,0.000030509345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029934593,0.0000821992,0.00014535848,0.000049633316,0.000107969965,0.000021098263,0.00010260088,0.00007149722,0.0000013082686],"category_scores_gemma":[0.000019043713,0.000045559096,0.000083621344,0.000089243185,0.00012692048,0.000015834483,0.0000315611,0.00008258767,3.1688126e-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":[0.0008065637,0.00021836406,0.033394605,0.000098568125,0.0012458244,0.0000014702845,0.0014869757,0.06332263,0.71822125,0.0101132495,0.00005762447,0.17103289],"study_design_scores_gemma":[0.010927258,0.0030055095,0.79907,0.00006699454,0.0003931373,0.003360506,0.001045845,0.0635705,0.007932851,0.10804192,0.0019421619,0.0006433253],"about_ca_topic_score_codex":0.0000017169575,"about_ca_topic_score_gemma":8.3229475e-7,"teacher_disagreement_score":0.76567537,"about_ca_system_score_codex":0.000013338863,"about_ca_system_score_gemma":0.00005526756,"threshold_uncertainty_score":0.18578461},"labels":[],"label_agreement":null},{"id":"W2014066195","doi":"10.1142/s021972000800345x","title":"SEMIPARAMETRIC CLUSTERING METHOD FOR MICROARRAY DATA ANALYSIS","year":2008,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Gene expression and cancer classification","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":"Western University","funders":"National Center for Research Resources","keywords":"Cluster analysis; Nonparametric statistics; Parametric statistics; Robustness (evolution); Mixture model; Computer science; Data mining; Bayesian probability; Bayesian information criterion; Mathematics; Artificial intelligence; Statistics","score_opus":0.04351846861240303,"score_gpt":0.3385774862596929,"score_spread":0.29505901764728987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014066195","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":[0.043880135,0.00060364365,0.95504516,0.00018883709,0.00009911112,0.00006137339,0.000054129305,0.0000017485345,0.00006583735],"genre_scores_gemma":[0.4868887,0.00038728002,0.5117181,0.0003732083,0.00012891731,0.000002407083,0.00045122197,0.000004711286,0.00004546378],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999279,0.00003253944,0.00041258836,0.00011204076,0.00007164142,0.000092175476],"domain_scores_gemma":[0.99912757,0.00006746465,0.00037517282,0.00016154375,0.00020999966,0.00005823081],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037548045,0.00007514789,0.00018052364,0.00024948185,0.000083424835,0.0000133519725,0.00020713887,0.000079849946,0.0000037762863],"category_scores_gemma":[0.000092534814,0.000059758404,0.000084473635,0.00022191508,0.000045786728,0.000010348794,0.00009054702,0.00005033998,4.6344076e-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":[0.0016991579,0.00053610385,0.04124226,0.00035167387,0.0076194634,0.000006605576,0.001707905,0.2286154,0.2695661,0.0023006818,0.069808,0.37654665],"study_design_scores_gemma":[0.0018145437,0.00079395185,0.01198415,0.000012708691,0.00033860307,0.00048596776,0.00028015568,0.8979197,0.003711687,0.0012030316,0.08116552,0.00028993533],"about_ca_topic_score_codex":0.0000017733388,"about_ca_topic_score_gemma":0.0000016283075,"teacher_disagreement_score":0.6693043,"about_ca_system_score_codex":0.000006729373,"about_ca_system_score_gemma":0.000092959235,"threshold_uncertainty_score":0.24368769},"labels":[],"label_agreement":null},{"id":"W2015820505","doi":"10.1142/s0219720006001898","title":"SELECTIVE TARGETING OF INDEL-INFERRED DIFFERENCES IN SPATIAL STRUCTURES OF HOMOLOGOUS PROTEINS","year":2006,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Research on Leishmaniasis Studies","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Michael Smith Health Research BC; University of British Columbia","funders":"Michael Smith Health Research BC","keywords":"Biology; Virulence; In silico; Peptide sequence; Genetics; Human pathogen; Computational biology; Sequence alignment; Protein sequencing; Protein superfamily; Gene","score_opus":0.01524377962744824,"score_gpt":0.2806208448044124,"score_spread":0.2653770651769642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015820505","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9902232,0.00033372483,0.008803621,0.00022069037,0.000032600234,0.00014534389,0.000012497437,0.0000016191856,0.00022668502],"genre_scores_gemma":[0.9780533,0.00003883865,0.021829132,0.000018111296,0.00004505186,0.0000012845757,0.000009766101,0.0000022011109,0.0000023632224],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99888355,0.00004287148,0.00074031024,0.00004249525,0.00018275272,0.000108024775],"domain_scores_gemma":[0.99868625,0.00020002015,0.0005908106,0.000027883374,0.00046754457,0.000027466263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025274386,0.000072189076,0.0003960458,0.00028149143,0.00002525919,0.000004654193,0.000055087225,0.000060592523,0.000005795432],"category_scores_gemma":[0.00019530475,0.000048210728,0.000048091413,0.00012096728,0.00019390979,0.000053405838,0.00003692627,0.0001583107,1.2919097e-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":[0.00066209637,0.00027610772,0.9697236,0.00049221766,0.00024849683,0.000012952339,0.0017126622,0.0018398119,0.004218185,0.0060583637,0.00021054431,0.014545006],"study_design_scores_gemma":[0.0013461916,0.0015495726,0.95850474,0.000074907,0.00001652619,0.00009339452,0.00040792642,0.009447475,0.0017211627,0.026778074,0.0000071389777,0.0000529074],"about_ca_topic_score_codex":0.00012828452,"about_ca_topic_score_gemma":0.00001991315,"teacher_disagreement_score":0.020719709,"about_ca_system_score_codex":0.000023278548,"about_ca_system_score_gemma":0.00015876943,"threshold_uncertainty_score":0.19659765},"labels":[],"label_agreement":null},{"id":"W2019662118","doi":"10.1142/s0219720010005294","title":"ADVANCES IN GENOME INFORMATICS","year":2010,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Global Institute for Water Security, University of Saskatchewan","keywords":"Chinese academy of sciences; Library science; China; Informatics; Computer science; Geography; Engineering","score_opus":0.0044127069985803865,"score_gpt":0.23686196601772613,"score_spread":0.23244925901914576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019662118","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9917911,0.001248924,0.00543537,0.000091618305,0.00021626196,0.00005086409,0.000011942894,6.117349e-7,0.001153252],"genre_scores_gemma":[0.9661968,0.0015290437,0.031933732,0.0002108087,0.00010538069,0.0000010464688,0.000015375992,0.0000034380455,0.0000043981067],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992927,0.000010037688,0.00049181416,0.000039257786,0.00005723422,0.00010899051],"domain_scores_gemma":[0.9994607,0.000028746075,0.00027787205,0.000056682242,0.00012870716,0.00004729122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023443525,0.00008087637,0.00014468102,0.00009630379,0.000035814897,0.000013928182,0.00010554183,0.00007698065,0.0000031357029],"category_scores_gemma":[0.00004467915,0.00006412135,0.000040359082,0.000049610586,0.00009174225,0.0000050092704,0.000062756815,0.00011879532,0.0000012883446],"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":[0.0005917206,0.00042548997,0.16849816,0.0003851303,0.0004232758,0.000010450124,0.005381789,0.056636646,0.33044305,0.040390093,0.00050203345,0.39631215],"study_design_scores_gemma":[0.008160115,0.0051249056,0.26863536,0.00006941673,0.00008091866,0.0021080067,0.0036437444,0.04787324,0.0034455545,0.08320611,0.5762167,0.0014358889],"about_ca_topic_score_codex":6.868886e-7,"about_ca_topic_score_gemma":0.000009550453,"teacher_disagreement_score":0.5757147,"about_ca_system_score_codex":0.000003147737,"about_ca_system_score_gemma":0.000060174018,"threshold_uncertainty_score":0.2614793},"labels":[],"label_agreement":null},{"id":"W2021405914","doi":"10.1142/s0219720012500011","title":"A METHOD FOR DISCOVERING COMMON PATTERNS FROM TWO RNA SECONDARY STRUCTURES AND ITS APPLICATION TO STRUCTURAL REPEAT DETECTION","year":2011,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"RNA and protein synthesis mechanisms","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":"Western University","funders":"National Institutes of Health; Cancer Research Institute","keywords":"Computer science; Nucleic acid secondary structure; Computational biology; RNA; Protein secondary structure; Java; Source code; Tree (set theory); Theoretical computer science; Artificial intelligence; Data mining; Biology; Gene; Genetics; Mathematics; Programming language; Combinatorics","score_opus":0.012618896130908556,"score_gpt":0.27712885254702485,"score_spread":0.2645099564161163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021405914","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5377752,0.00015257635,0.4618126,0.000025795014,0.000057153393,0.000104087914,0.000058109286,0.000001424399,0.000013057718],"genre_scores_gemma":[0.8669751,0.000029786917,0.13263203,0.00018182305,0.00011763575,0.000005909915,0.00005041433,0.0000055160112,0.0000017629277],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99940073,0.00003429973,0.00032680805,0.000097927375,0.00005065523,0.00008956525],"domain_scores_gemma":[0.99946696,0.000047453395,0.00026898438,0.000056633973,0.000094373194,0.0000655853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016919024,0.00009555274,0.00015488599,0.000058607573,0.00007475137,0.000019080255,0.00007912805,0.00007466894,0.0000048958464],"category_scores_gemma":[0.000022100865,0.000075456956,0.000045980923,0.000019989113,0.000014422221,0.000015649635,0.000053267813,0.00005529118,2.5415048e-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":[0.000409209,0.000007285302,0.0006287955,0.000045227946,0.00013546472,4.923915e-7,0.000645094,0.000668585,0.48639867,0.002385472,0.0000069297143,0.5086688],"study_design_scores_gemma":[0.0019220551,0.0022134534,0.022494063,0.000041260344,0.00009087947,0.00029956564,0.00049735507,0.06825936,0.7821533,0.12051238,0.001106953,0.0004093535],"about_ca_topic_score_codex":0.000026164184,"about_ca_topic_score_gemma":0.0000170969,"teacher_disagreement_score":0.5082594,"about_ca_system_score_codex":0.000006438199,"about_ca_system_score_gemma":0.000021432186,"threshold_uncertainty_score":0.30770454},"labels":[],"label_agreement":null},{"id":"W2023250395","doi":"10.1142/s0219720010005099","title":"ADEPTS: ADVANCED PEPTIDE <i>DE NOVO</i> SEQUENCING WITH A PAIR OF TANDEM MASS SPECTRA","year":2010,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":31,"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; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computational biology; DNA sequencing; Tandem mass spectrometry; Peptide; Proteomics; Biology; Genetics; Chemistry; Mass spectrometry; Biochemistry; Gene; Chromatography","score_opus":0.007141073480087647,"score_gpt":0.24843712025055886,"score_spread":0.24129604677047123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023250395","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5961586,0.000038561328,0.40137056,0.00020217987,0.000016117106,0.000047834863,0.000025361149,0.000012820489,0.0021279366],"genre_scores_gemma":[0.5034578,0.000031416414,0.49638352,0.00006651954,0.00003342568,0.00000256438,0.000008361105,0.000004113648,0.000012292667],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992891,0.000004251359,0.0004509207,0.00005468652,0.00008491664,0.00011610876],"domain_scores_gemma":[0.99897814,0.00011017921,0.0005815456,0.000074847376,0.00019200346,0.00006331201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014600874,0.00008851405,0.00018724673,0.000053749765,0.00005163063,0.000011132155,0.00011653312,0.00007872984,0.000024199548],"category_scores_gemma":[0.000025544286,0.0000665144,0.00004474243,0.00006601251,0.00011540539,0.00010176735,0.000018897359,0.000279007,4.5373554e-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":[0.0002084565,0.000103572005,0.014215099,0.00026515068,0.00016984237,0.000011537794,0.0007297324,0.013793712,0.8761899,0.07239486,0.000108091415,0.021810068],"study_design_scores_gemma":[0.005091833,0.0015621274,0.0014632766,0.0004927006,0.00014616261,0.0048669274,0.0021023704,0.13845466,0.37077487,0.45703602,0.017075727,0.00093333377],"about_ca_topic_score_codex":0.0000013740317,"about_ca_topic_score_gemma":0.0000016010697,"teacher_disagreement_score":0.505415,"about_ca_system_score_codex":0.0000276214,"about_ca_system_score_gemma":0.00014310381,"threshold_uncertainty_score":0.27123788},"labels":[],"label_agreement":null},{"id":"W2030659385","doi":"10.1142/s0219720006001746","title":"PRIMA: PEPTIDE ROBUST IDENTIFICATION FROM MS/MS SPECTRA","year":2006,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Western University; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Tandem mass spectrometry; Mascot; Computer science; Identification (biology); Software; Construct (python library); Ion trap; Proteomics; Peptide; Tandem; Artificial intelligence; Mass spectrometry; Data mining; Chemistry; Chromatography; Biology; Engineering","score_opus":0.009623334375525457,"score_gpt":0.2478373714365536,"score_spread":0.23821403706102814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030659385","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":[0.2750617,0.00017961446,0.7209714,0.00039499436,0.000036598492,0.000050449195,0.00008414945,0.000020634607,0.003200443],"genre_scores_gemma":[0.57396984,0.00009009969,0.42532632,0.00007925801,0.00022951413,0.000004556749,0.00023031417,0.0000065940912,0.00006349784],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990837,0.0000056585827,0.00064529554,0.000072525196,0.00009412131,0.00009872105],"domain_scores_gemma":[0.99898607,0.00009738582,0.0006359479,0.00008254916,0.00015813854,0.00003991816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000105449966,0.0000901074,0.00015623514,0.00006233994,0.000085127795,0.000040381983,0.00012616572,0.00008086247,0.00006742074],"category_scores_gemma":[0.00001360917,0.00007720282,0.00005804296,0.00005805889,0.000072054114,0.00013500235,0.00003028844,0.00014830439,0.000006306123],"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":[0.00029419406,0.00089482655,0.0220272,0.00034166014,0.00046731465,0.000016556589,0.0008595681,0.14159836,0.2664633,0.4711695,0.012983835,0.08288368],"study_design_scores_gemma":[0.0011829245,0.00011678861,0.01117999,0.00007498171,0.000068294634,0.0002387518,0.00017370177,0.14749567,0.028581273,0.7950354,0.015466623,0.00038559388],"about_ca_topic_score_codex":0.000024775114,"about_ca_topic_score_gemma":0.0000026370951,"teacher_disagreement_score":0.32386592,"about_ca_system_score_codex":0.000036917656,"about_ca_system_score_gemma":0.00004220955,"threshold_uncertainty_score":0.314824},"labels":[],"label_agreement":null},{"id":"W2032713750","doi":"10.1142/s0219720007002941","title":"EVALUATION OF NORMALIZATION AND PRE-CLUSTERING ISSUES IN A NOVEL CLUSTERING APPROACH: GLOBAL OPTIMUM SEARCH WITH ENHANCED POSITIONING","year":2007,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"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":"McGill University; Foundation for the National Institutes of Health; National Science Foundation","keywords":"Cluster analysis; Normalization (sociology); Data mining; Computer science; Correlation clustering; CURE data clustering algorithm; Outlier; Fuzzy clustering; Clustering high-dimensional data; Consensus clustering; Artificial intelligence","score_opus":0.022538950893690676,"score_gpt":0.3214746440522242,"score_spread":0.2989356931585335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032713750","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":[0.47185948,0.0002730677,0.5275559,0.000025758689,0.000019718498,0.000066200635,0.0000026546409,7.314964e-7,0.00019649652],"genre_scores_gemma":[0.93315387,0.000081994505,0.06665275,0.00003469178,0.000035135294,0.0000017390884,0.000034387165,0.0000027665678,0.0000026351947],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999212,0.000037290032,0.00038643254,0.00007628779,0.00019749306,0.00009046883],"domain_scores_gemma":[0.9992111,0.000011895035,0.00026999114,0.0000444854,0.00042425355,0.00003830095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010161888,0.0000692998,0.00011537887,0.00010116749,0.00003534539,0.000016521843,0.000050191426,0.00006944427,0.0000012712634],"category_scores_gemma":[0.000027291164,0.000056597466,0.00001671735,0.00010410414,0.000056916153,0.000020294672,0.000042303167,0.000048610218,4.6238743e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008972292,0.00016103989,0.010131921,0.0001789305,0.0001350054,4.2728027e-7,0.0024424198,0.69001704,0.18620594,0.0005040435,0.00001136388,0.10931465],"study_design_scores_gemma":[0.0026484353,0.00085187383,0.07989139,0.00013806799,0.000040968745,0.0001924602,0.0013584483,0.90627205,0.008138754,0.0002791774,0.000042785767,0.0001455881],"about_ca_topic_score_codex":0.0000066413586,"about_ca_topic_score_gemma":0.000014602874,"teacher_disagreement_score":0.4612944,"about_ca_system_score_codex":0.00003258478,"about_ca_system_score_gemma":0.000120471166,"threshold_uncertainty_score":0.23079777},"labels":[],"label_agreement":null},{"id":"W2036814280","doi":"10.1142/s0219720008003813","title":"UBIQUITOUS REASSORTMENTS IN INFLUENZA A VIRUSES","year":2008,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Influenza Virus Research Studies","field":"Medicine","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 Alberta","funders":"","keywords":"Reassortment; Virology; Biology; Neuraminidase; Nucleoprotein; Hemagglutinin (influenza); Influenza A virus subtype H5N1; RNA; H5N1 genetic structure; Virus; Gene; Genetics; Coronavirus disease 2019 (COVID-19)","score_opus":0.106559983716119,"score_gpt":0.3925495000729928,"score_spread":0.28598951635687375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036814280","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9973395,0.0009124962,0.0005563121,0.00022399225,0.000054717617,0.00010082053,0.000007846469,0.000004374152,0.00079993706],"genre_scores_gemma":[0.9777198,0.0006358406,0.018503837,0.0030446143,0.00007273313,0.0000023758594,0.0000042825764,0.000004690473,0.000011834946],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990003,0.00002467441,0.0005921339,0.000044179596,0.00019200212,0.0001466863],"domain_scores_gemma":[0.99920946,0.00015171769,0.0002347122,0.00004327321,0.00027972326,0.00008112463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024422663,0.00007865937,0.00027803323,0.0003072011,0.00006145388,0.0000065012778,0.00005088727,0.00005528613,0.000009534405],"category_scores_gemma":[0.00021152246,0.00005540979,0.000049246755,0.00012512963,0.0001556025,0.000113153554,0.000047399357,0.0001765133,0.000008649957],"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":[0.001711855,0.00046944723,0.95452166,0.00022434167,0.000582794,0.000340068,0.004661204,0.0023534778,0.000599559,0.0031575914,0.0023824112,0.028995588],"study_design_scores_gemma":[0.0090929605,0.002995149,0.93866634,0.00021826134,0.00004811142,0.004572566,0.00057465537,0.014856246,0.00020446989,0.006987896,0.021547372,0.000235998],"about_ca_topic_score_codex":0.0000084767435,"about_ca_topic_score_gemma":0.0000012372396,"teacher_disagreement_score":0.02875959,"about_ca_system_score_codex":0.00004937253,"about_ca_system_score_gemma":0.00019068878,"threshold_uncertainty_score":0.22595456},"labels":[],"label_agreement":null},{"id":"W2037625634","doi":"10.1142/s0219720006002399","title":"PROTEOMIC BIOMARKER IDENTIFICATION FOR DIAGNOSIS OF EARLY RELAPSE IN OVARIAN CANCER","year":2006,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","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":"Women's Health Research Institute","funders":"National Science Foundation","keywords":"Markov blanket; Feature selection; Support vector machine; Artificial intelligence; Computer science; Feature (linguistics); Pattern recognition (psychology); Feature vector; Biomarker discovery; Biomarker; Curse of dimensionality; Machine learning; Identification (biology); Markov chain; Proteomics; Markov model; Biology","score_opus":0.013561879053840334,"score_gpt":0.29218493878624746,"score_spread":0.27862305973240714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037625634","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.817774,0.00011890648,0.18137582,0.0003441703,0.00002255215,0.00015358176,0.00010149402,0.000004040208,0.000105463914],"genre_scores_gemma":[0.88050073,0.00010261077,0.11920183,0.000018752711,0.00003339351,0.00008659015,0.000037879272,0.0000044881626,0.0000137239995],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991208,0.000005427759,0.00068758504,0.000053756015,0.000054257252,0.000078208504],"domain_scores_gemma":[0.99896854,0.00009395341,0.00068542175,0.000051875824,0.00018012416,0.000020071411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016431444,0.000063424515,0.00015243722,0.000107495456,0.000033727414,0.000011488925,0.0000846939,0.00007574931,0.000011143927],"category_scores_gemma":[0.00002055669,0.000054880315,0.000049269474,0.00007905176,0.000055783414,0.00009499652,0.000016688768,0.000070742666,2.6499075e-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":[0.0007435241,0.0007155718,0.4504823,0.0010396296,0.00022829045,0.0000020281495,0.000758633,0.016995165,0.22302832,0.19683014,0.0013016979,0.107874714],"study_design_scores_gemma":[0.003622414,0.0003178154,0.12681569,0.0003394679,0.00007887297,0.00006419711,0.00012205195,0.08739066,0.1306704,0.64748627,0.0026691246,0.00042305602],"about_ca_topic_score_codex":0.000040332237,"about_ca_topic_score_gemma":0.0000030184046,"teacher_disagreement_score":0.45065612,"about_ca_system_score_codex":0.000030470776,"about_ca_system_score_gemma":0.0000505149,"threshold_uncertainty_score":0.22379543},"labels":[],"label_agreement":null},{"id":"W2041368329","doi":"10.1142/s0219720005001570","title":"HEURISTIC SEARCH IN CONSTRAINED BIPARTITE MATCHING WITH APPLICATIONS TO PROTEIN NMR BACKBONE RESONANCE ASSIGNMENT","year":2005,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bipartite graph; Combinatorics; Matching (statistics); Heuristics; Assignment problem; Complete bipartite graph; Mathematics; Heuristic; Combinatorial optimization; Local search (optimization); Algorithm; Computer science; Graph; Mathematical optimization","score_opus":0.010647841950632267,"score_gpt":0.2710084611486648,"score_spread":0.2603606191980325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041368329","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":[0.0583776,0.00010563488,0.93754333,0.0035926993,0.000014942762,0.0001633692,0.0000039630872,0.000009141371,0.0001893376],"genre_scores_gemma":[0.5211521,0.000005511054,0.47849786,0.00027571645,0.000041145362,0.0000065937484,0.0000022302618,0.0000019694044,0.000016879165],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990999,0.000046804358,0.0004369268,0.00008945282,0.00017121279,0.00015569835],"domain_scores_gemma":[0.9994017,0.00011813689,0.00018592145,0.000077186036,0.00011917142,0.000097890574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047700593,0.00008293661,0.00016272283,0.00019848673,0.000072988216,0.00006859367,0.00021234968,0.000030092757,0.0000038600597],"category_scores_gemma":[0.000014474655,0.000060605562,0.000020211472,0.00023743446,0.00004980965,0.00017015474,0.000068305184,0.00019028687,0.000010109186],"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":[0.000044555036,0.00013004914,0.0013848752,0.000045877357,0.00002835062,0.000009189358,0.0018664035,0.34070894,0.00021563734,0.11010732,0.00005877638,0.5454],"study_design_scores_gemma":[0.00092952244,0.00063874427,0.0054078368,0.00011470697,0.000003421614,0.00027229474,0.00011890779,0.9774953,0.00005139598,0.008719418,0.0060849283,0.00016352179],"about_ca_topic_score_codex":0.0000053740127,"about_ca_topic_score_gemma":0.000003023572,"teacher_disagreement_score":0.63678634,"about_ca_system_score_codex":0.000031670483,"about_ca_system_score_gemma":0.00011459158,"threshold_uncertainty_score":0.24714231},"labels":[],"label_agreement":null},{"id":"W2041576045","doi":"10.1142/s0219720014500243","title":"A new efficient algorithm for inferring explicit hybridization networks following the Neighbor-Joining principle","year":2014,"lang":"en","type":"article","venue":"Journal of Bioinformatics and 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":"Université du Québec à Montréal","funders":"","keywords":"Phylogenetic network; Phylogenetic tree; Tree (set theory); Algorithm; Heuristic; Metric (unit); Computer science; Tree rearrangement; Distance matrix; Mathematics; Artificial intelligence; Biology; Combinatorics","score_opus":0.008442928588421848,"score_gpt":0.24694638730283322,"score_spread":0.23850345871441136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041576045","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":[0.14714274,0.00012573542,0.85219145,0.00014717966,0.0002492144,0.00007864589,0.000004757384,0.0000020570037,0.000058252463],"genre_scores_gemma":[0.86454934,0.000018212944,0.13456216,0.0004682334,0.0003039516,9.843989e-7,0.00007610981,0.0000045064567,0.000016482443],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994045,0.000026896334,0.0003153643,0.000065286695,0.00007975573,0.000108234526],"domain_scores_gemma":[0.999405,0.00006847534,0.00028683027,0.00005911286,0.0001232968,0.000057282046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029860478,0.00008072728,0.00012017864,0.000045325276,0.00014706052,0.000037398302,0.000103283906,0.00006154419,0.0000023139442],"category_scores_gemma":[0.000060817372,0.00005765223,0.00008824673,0.00005059274,0.000018139468,0.0000064866567,0.00005856063,0.00006314479,3.7003775e-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":[0.00005110651,0.000014522294,0.00477912,0.00001553043,0.00017096983,2.9811423e-7,0.00035233801,0.73794293,0.0004498778,0.00743459,0.0007785542,0.24801013],"study_design_scores_gemma":[0.0009741693,0.00028757466,0.00385598,0.0000145082595,0.000034822206,0.000049021615,0.00010183395,0.97299016,0.00017915826,0.001678187,0.019732846,0.00010174121],"about_ca_topic_score_codex":0.000002141863,"about_ca_topic_score_gemma":7.645592e-7,"teacher_disagreement_score":0.71762925,"about_ca_system_score_codex":0.00000576159,"about_ca_system_score_gemma":0.000058016605,"threshold_uncertainty_score":0.23509896},"labels":[],"label_agreement":null},{"id":"W2048065755","doi":"10.1142/s0219720009004242","title":"A TUTORIAL OF TECHNIQUES FOR IMPROVING STANDARD HIDDEN MARKOV MODEL ALGORITHMS","year":2009,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Algorithms and Data Compression","field":"Computer Science","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 Waterloo","funders":"","keywords":"Viterbi algorithm; Computer science; Hidden Markov model; Logarithm; Forward algorithm; Heuristics; Algorithm; Factor (programming language); Heuristic; Markov model; Sequence (biology); Markov chain; Space (punctuation); Parallel computing; Artificial intelligence; Mathematics; Variable-order Markov model; Machine learning; Programming language","score_opus":0.011313900673213523,"score_gpt":0.27365696638997694,"score_spread":0.2623430657167634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048065755","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":[0.0023683328,0.00012059126,0.99671745,0.00034762526,0.00019617016,0.00010305675,0.00005474806,0.000012362657,0.00007963022],"genre_scores_gemma":[0.08047592,0.000026739679,0.9191872,0.00016057013,0.00013185616,0.000001051361,0.000011408234,0.000001994482,0.0000032816008],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990099,0.000014994441,0.00061009754,0.00007572453,0.00016763707,0.00012161252],"domain_scores_gemma":[0.9987065,0.00012412686,0.0005903861,0.00009208439,0.00042636783,0.000060530758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004484473,0.00009092274,0.00025056629,0.00015300118,0.00006899266,0.000053210875,0.0003119219,0.0000723488,7.5264666e-7],"category_scores_gemma":[0.00004326434,0.000066372944,0.00007360879,0.00007847211,0.000040114443,0.00044581058,0.00008825625,0.000087156426,1.1451492e-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":[0.00007508008,0.000030484565,0.000010399724,0.000026577107,0.000016489596,7.345265e-7,0.00021929626,0.0005900439,0.00039484332,0.027230976,0.0005484744,0.9708566],"study_design_scores_gemma":[0.0005368925,0.0011166139,0.00007056718,0.000024081932,0.000008089396,0.00005401771,0.00001748524,0.9022201,0.00042526316,0.09496266,0.0004862898,0.00007799616],"about_ca_topic_score_codex":0.0000012937254,"about_ca_topic_score_gemma":7.422689e-8,"teacher_disagreement_score":0.9707786,"about_ca_system_score_codex":0.000019758576,"about_ca_system_score_gemma":0.00017266034,"threshold_uncertainty_score":0.27066103},"labels":[],"label_agreement":null},{"id":"W2051186751","doi":"10.1142/s0219720003000083","title":"Computational Assignment of Protein Backbone NMR Peaks by Efficient Bounding and Filtering","year":2003,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Bounding overwatch; Computer science; Algorithm; Assignment problem; Bipartite graph; Computation; Greedy algorithm; Weapon target assignment problem; Process (computing); Matching (statistics); Computational complexity theory; Approximation algorithm; Generalized assignment problem; Mathematical optimization; Theoretical computer science; Mathematics; Optimization problem; Artificial intelligence; Graph","score_opus":0.004713577335423098,"score_gpt":0.2258257784558294,"score_spread":0.2211122011204063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051186751","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6801549,0.00077460904,0.318654,0.0000602465,0.000046500536,0.00008858989,0.00002837471,0.0000012027691,0.0001915397],"genre_scores_gemma":[0.9277035,0.000038897477,0.07208425,0.00008384838,0.00002356465,0.0000014460461,0.00005088907,0.0000044227218,0.000009209781],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919504,0.000039569466,0.00046157878,0.000077683326,0.000115426104,0.00011071506],"domain_scores_gemma":[0.99932665,0.000033162025,0.0003889961,0.000046396624,0.00014037175,0.00006442768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027610039,0.00010063337,0.00017656179,0.000065718,0.00006261484,0.000019925723,0.00005999011,0.0000820506,0.0000045142956],"category_scores_gemma":[0.00005220617,0.000082588056,0.000042856278,0.00004260682,0.000119609875,0.000006951013,0.00004494493,0.00007635961,2.414864e-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":[0.0006751852,0.0005034182,0.00853028,0.0007873408,0.0010956147,0.000010540317,0.0013782947,0.36205006,0.46084666,0.12029045,0.0011741074,0.04265806],"study_design_scores_gemma":[0.013644274,0.009953774,0.009360766,0.000552776,0.0002261372,0.0036861908,0.0024535211,0.7365492,0.07407166,0.11780199,0.02974949,0.0019502527],"about_ca_topic_score_codex":0.0000012547216,"about_ca_topic_score_gemma":2.5857884e-7,"teacher_disagreement_score":0.386775,"about_ca_system_score_codex":0.000014016118,"about_ca_system_score_gemma":0.00007586616,"threshold_uncertainty_score":0.3367843},"labels":[],"label_agreement":null},{"id":"W2053279888","doi":"10.1142/s0219720004000843","title":"HISTOGRAM-BASED SCORING SCHEMES FOR PROTEIN NMR RESONANCE ASSIGNMENT","year":2004,"lang":"en","type":"article","venue":"Journal of Bioinformatics and 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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"University of Alberta","keywords":"Histogram; Chemical shift; Spin (aerodynamics); Adjacency list; Biological system; Computer science; Key (lock); Signature (topology); Pattern recognition (psychology); Algorithm; Data mining; Chemistry; Artificial intelligence; Mathematics; Physics; Nuclear magnetic resonance; Biology; Image (mathematics)","score_opus":0.00786710609598433,"score_gpt":0.2470661261058875,"score_spread":0.23919902000990317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053279888","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":[0.24520051,0.00094656256,0.75316805,0.000338169,0.00007726662,0.00018376466,0.000023018581,0.0000029860744,0.00005965091],"genre_scores_gemma":[0.7450342,0.000022548978,0.25443807,0.0003266402,0.00010256134,0.0000083765235,0.00005222497,0.000005358241,0.000010022749],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999329,0.000010926359,0.0003687405,0.00007781045,0.000084193474,0.00012936014],"domain_scores_gemma":[0.99937433,0.000014938858,0.0003045478,0.00006454847,0.00018403055,0.00005759919],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018017147,0.00009877421,0.00014486721,0.000061705665,0.00007401246,0.000019161742,0.00010026571,0.00009561419,0.0000011416014],"category_scores_gemma":[0.000058589827,0.000079258854,0.00007856661,0.000039680188,0.00008202123,0.000008110153,0.000029754157,0.00006911252,4.940247e-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":[0.0023969223,0.00048102412,0.004279522,0.0007347714,0.00058408047,0.00001305167,0.0004165458,0.16646223,0.22212712,0.14751709,0.0008401904,0.45414743],"study_design_scores_gemma":[0.024533896,0.013296044,0.0045942534,0.0006797469,0.00017915294,0.0007598543,0.00038114353,0.121048704,0.11886164,0.34906578,0.3647464,0.0018533887],"about_ca_topic_score_codex":0.000001241606,"about_ca_topic_score_gemma":0.0000013633966,"teacher_disagreement_score":0.49983367,"about_ca_system_score_codex":0.000025126088,"about_ca_system_score_gemma":0.00019783758,"threshold_uncertainty_score":0.32320824},"labels":[],"label_agreement":null},{"id":"W2057771742","doi":"10.1142/s0219720006002314","title":"OPTIMALLY-CONNECTED HIDDEN MARKOV MODELS FOR PREDICTING MHC-BINDING PEPTIDES","year":2006,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Max-Planck-Gesellschaft; Genome Canada","keywords":"Hidden Markov model; Computation; Computer science; Human leukocyte antigen; Pattern recognition (psychology); Artificial intelligence; Merge (version control); Heuristic; Markov chain; Computational biology; Algorithm; Machine learning; Biology; Genetics; Antigen","score_opus":0.011809212372534465,"score_gpt":0.23368368039645088,"score_spread":0.22187446802391642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057771742","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7965097,0.0005509042,0.2015086,0.00018873574,0.00013181048,0.00017461897,0.000060552018,0.0000062557488,0.00086886575],"genre_scores_gemma":[0.81451166,0.00008093124,0.18470383,0.000108420245,0.0002228517,0.000005097611,0.00031329403,0.000010239884,0.00004369978],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988431,0.000017362267,0.00076724804,0.00008354676,0.000092014925,0.00019677724],"domain_scores_gemma":[0.99889374,0.00008287901,0.0005807391,0.000076244214,0.00031424774,0.000052143638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003646743,0.0001447007,0.00023107631,0.0001173286,0.00012919112,0.00005968059,0.00014845128,0.00012696703,0.0000024456708],"category_scores_gemma":[0.000060333346,0.000116090574,0.000121176796,0.000060022434,0.000052198953,0.000036895897,0.000075820186,0.00008757666,7.2560545e-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":[0.003613962,0.001052989,0.03521939,0.002032983,0.0033419358,0.000009859443,0.0028027056,0.46605265,0.11513759,0.11802728,0.031226339,0.22148232],"study_design_scores_gemma":[0.0029996163,0.0016344714,0.0025192678,0.000069868445,0.00008356909,0.00047879573,0.0008474761,0.96200913,0.0020871605,0.024163483,0.0027143215,0.00039285945],"about_ca_topic_score_codex":0.0000038354465,"about_ca_topic_score_gemma":0.0000014340717,"teacher_disagreement_score":0.49595648,"about_ca_system_score_codex":0.000012638973,"about_ca_system_score_gemma":0.00008611564,"threshold_uncertainty_score":0.47340363},"labels":[],"label_agreement":null},{"id":"W2060355037","doi":"10.1142/s0219720006002363","title":"RNALL: AN EFFICIENT ALGORITHM FOR PREDICTING RNA LOCAL SECONDARY STRUCTURAL LANDSCAPE IN GENOMES","year":2006,"lang":"en","type":"article","venue":"Journal of Bioinformatics and 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":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; U.S. Department of Energy","keywords":"RNA; Computational biology; Nucleic acid secondary structure; Energy landscape; Computer science; Genome; Algorithm; Sliding window protocol; Bioinformatics; Data mining; Gene; Window (computing); Biology; Genetics","score_opus":0.005349491978337566,"score_gpt":0.23176467682351212,"score_spread":0.22641518484517456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060355037","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6357769,0.00081394945,0.36301273,0.0000497272,0.000117928015,0.000095153584,0.00004406685,0.0000020635407,0.000087513894],"genre_scores_gemma":[0.8860983,0.00002700379,0.113402925,0.0000994575,0.0002267155,0.0000030629694,0.00012921703,0.000006247567,0.0000070624696],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917215,0.0000329874,0.0004842705,0.00008522058,0.000078047815,0.00014730768],"domain_scores_gemma":[0.9994378,0.00004607969,0.00028765554,0.000049299742,0.00012846066,0.000050690433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032987536,0.000100339756,0.00017117512,0.00010098128,0.000064780106,0.000024837498,0.00009949714,0.00010522855,0.000006331051],"category_scores_gemma":[0.000012720273,0.00007916201,0.00006148995,0.000038679802,0.000053593445,0.000010423079,0.000030867523,0.00007255462,3.069861e-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":[0.0002819542,0.00010653739,0.0042814724,0.00008036461,0.00012520926,0.000006450987,0.00027432476,0.10088172,0.02101852,0.0029759535,0.00017702725,0.86979043],"study_design_scores_gemma":[0.0022408674,0.00176352,0.008022478,0.000029029405,0.000022682536,0.0003725376,0.00049569056,0.96507,0.0073856926,0.012885219,0.0014597306,0.00025252032],"about_ca_topic_score_codex":0.000004821608,"about_ca_topic_score_gemma":0.0000050284143,"teacher_disagreement_score":0.86953795,"about_ca_system_score_codex":0.000009300976,"about_ca_system_score_gemma":0.00008863234,"threshold_uncertainty_score":0.3228133},"labels":[],"label_agreement":null},{"id":"W2066123704","doi":"10.1142/s0219720006002119","title":"IMPROVING THE SENSITIVITY AND SPECIFICITY OF PROTEIN HOMOLOGY SEARCH BY INCORPORATING PREDICTED SECONDARY STRUCTURES","year":2006,"lang":"en","type":"article","venue":"Journal of Bioinformatics and 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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Homology (biology); Protein secondary structure; Protein structure prediction; Homology modeling; Computer science; Computational biology; Sensitivity (control systems); Protein structure; Machine learning; Artificial intelligence; Biology; Genetics; Amino acid; Engineering; Biochemistry","score_opus":0.005744006339003689,"score_gpt":0.21144460315384553,"score_spread":0.20570059681484185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066123704","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92760265,0.000674582,0.07126242,0.00015522416,0.000039568054,0.0001208543,0.00007297264,0.0000016302381,0.000070124115],"genre_scores_gemma":[0.97763395,0.00002453297,0.022121347,0.000063300264,0.00009278032,0.0000011547854,0.000051398787,0.000004246751,0.0000072766406],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991651,0.00013196829,0.00043160154,0.00007652513,0.0000920661,0.0001027058],"domain_scores_gemma":[0.9991774,0.000085476175,0.00045840573,0.000062981686,0.00018321024,0.000032511703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005745534,0.00009145817,0.00017284855,0.000049083632,0.00009372473,0.0000199078,0.000070829636,0.00011072145,0.0000030865967],"category_scores_gemma":[0.000052078292,0.0000607455,0.0000385916,0.0000417285,0.00022895758,0.00001009177,0.000079871614,0.000120472934,9.17463e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000114594855,0.000026720982,0.0014434058,0.00006591075,0.000061014664,0.0000020606283,0.000064351756,0.00050727045,0.9562183,0.004977413,0.00012655377,0.03639242],"study_design_scores_gemma":[0.0023091983,0.003337968,0.025374088,0.000070639304,0.000067602974,0.001626214,0.0008534168,0.03691721,0.87241423,0.055220686,0.001326465,0.00048225166],"about_ca_topic_score_codex":0.00003081908,"about_ca_topic_score_gemma":0.000005497487,"teacher_disagreement_score":0.08380402,"about_ca_system_score_codex":0.000004650181,"about_ca_system_score_gemma":0.00009037698,"threshold_uncertainty_score":0.24771295},"labels":[],"label_agreement":null},{"id":"W2066349684","doi":"10.1142/s0219720005001296","title":"MULTIPLE RNA STRUCTURE ALIGNMENT","year":2005,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"RNA and protein synthesis mechanisms","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":"Western University; University Health Network","funders":"","keywords":"RNA; String (physics); Algorithm; Structural alignment; Nucleic acid structure; Computer science; Sequence (biology); Multiple sequence alignment; Mathematics; Sequence alignment; Gene; Genetics; Biology; Peptide sequence","score_opus":0.007012230245182748,"score_gpt":0.23166254141168083,"score_spread":0.22465031116649808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066349684","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89970624,0.00088486634,0.09811699,0.0006960076,0.00017343854,0.000086781554,0.00003660905,0.0000028605837,0.00029618142],"genre_scores_gemma":[0.9154523,0.00011750992,0.08357076,0.00055756874,0.00024363546,7.1240635e-7,0.000030807005,0.000004341517,0.000022345019],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993669,0.000026365173,0.00035701972,0.000059324084,0.00008706484,0.00010332398],"domain_scores_gemma":[0.99946994,0.000030562373,0.00026698876,0.000059589725,0.00010826201,0.00006465734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001586879,0.000087110064,0.00012916756,0.000053042422,0.000051388644,0.000017282768,0.00009947176,0.000094128285,0.000020595871],"category_scores_gemma":[0.000042330787,0.000065276196,0.000055999346,0.000026049654,0.000043069213,0.000008507473,0.00004226799,0.000055003176,0.000002818409],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029039438,0.00010264272,0.002152797,0.000047242662,0.0003399782,0.0000027992153,0.00040556988,0.013724758,0.6010029,0.0065046665,0.0028769516,0.37254936],"study_design_scores_gemma":[0.0060546785,0.0045614336,0.005578168,0.00009710723,0.000119211334,0.0017689104,0.0006891547,0.055089533,0.54961514,0.03901859,0.33637413,0.0010339194],"about_ca_topic_score_codex":6.169782e-7,"about_ca_topic_score_gemma":0.0000013909613,"teacher_disagreement_score":0.37151542,"about_ca_system_score_codex":0.000007828752,"about_ca_system_score_gemma":0.000046964775,"threshold_uncertainty_score":0.26618862},"labels":[],"label_agreement":null},{"id":"W2067201268","doi":"10.1142/s0219720004000788","title":"IDENTIFYING UNIFORMLY MUTATED SEGMENTS WITHIN REPEATS","year":2004,"lang":"en","type":"article","venue":"Journal of Bioinformatics and 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":"Pacific Institute for the Mathematical Sciences; Simon Fraser University","funders":"","keywords":"Mathematics; String (physics); Coin flipping; Combinatorics; Set (abstract data type); Mutation; Prior probability; Algorithm; Mutation rate; Shuffling; Discrete mathematics; Statistics; Computer science; Genetics; Biology; Bayesian probability","score_opus":0.017156221096612675,"score_gpt":0.2722669738252626,"score_spread":0.2551107527286499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067201268","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":[0.07470743,0.00013176475,0.9242855,0.0003146,0.0003672526,0.000043485627,0.0000062267736,0.000014677486,0.00012910698],"genre_scores_gemma":[0.42272633,0.0000415401,0.5768368,0.000330517,0.000039449314,4.2120809e-7,0.000017087732,0.0000025457132,0.000005269431],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895936,0.00002083784,0.00062114303,0.0000813616,0.00018876613,0.00012850674],"domain_scores_gemma":[0.9989744,0.000055123994,0.0005628501,0.00010214218,0.00021100145,0.00009452293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034968893,0.00009417631,0.00017099708,0.00017652381,0.00012298813,0.00012239677,0.00033048095,0.000054192355,0.000002360529],"category_scores_gemma":[0.00002624333,0.00006804676,0.00004520488,0.00015974394,0.000049819613,0.0007840561,0.00018411358,0.00013702612,0.0000073175925],"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":[0.00011738755,0.0003911192,0.0017909714,0.0001742941,0.00043494574,0.00017151928,0.010942057,0.16771734,0.0013890883,0.53797513,0.00081560056,0.27808058],"study_design_scores_gemma":[0.0027716907,0.0008101757,0.005106668,0.00019262572,0.000019249941,0.0020036872,0.0003521054,0.59037966,0.00068159256,0.39675802,0.0006301318,0.00029440565],"about_ca_topic_score_codex":0.000005545502,"about_ca_topic_score_gemma":4.9428877e-7,"teacher_disagreement_score":0.42266232,"about_ca_system_score_codex":0.00003210561,"about_ca_system_score_gemma":0.00013651104,"threshold_uncertainty_score":0.27748662},"labels":[],"label_agreement":null},{"id":"W2070718329","doi":"10.1142/s0219720004000892","title":"IMPROVING GENE NETWORK INFERENCE BY COMPARING EXPRESSION TIME-SERIES ACROSS SPECIES, DEVELOPMENTAL STAGES OR TISSUES","year":2004,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Gene Regulatory Network Analysis","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; Université de Montréal","funders":"","keywords":"Inference; Gene regulatory network; Computer science; Graph; Time series; Series (stratigraphy); Gene; Data mining; Computational biology; Gene expression; Biology; Artificial intelligence; Machine learning; Theoretical computer science; Genetics","score_opus":0.01041361670249012,"score_gpt":0.2526595291995905,"score_spread":0.2422459124971004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070718329","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90458393,0.0011742269,0.09396716,0.00006151083,0.0000839847,0.0000541952,0.000023950852,0.0000049618175,0.000046086418],"genre_scores_gemma":[0.86338276,0.0003013563,0.13564968,0.0001100525,0.00020394243,0.0000013124021,0.00022431325,0.000008130109,0.00011844076],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989986,0.000027697983,0.00052982447,0.00010624468,0.00012234152,0.00021530228],"domain_scores_gemma":[0.99922556,0.000028284605,0.00044097612,0.000064471635,0.00015273939,0.000087959525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023575746,0.00014373861,0.00025640932,0.000037539285,0.00017240808,0.000057448106,0.00014961678,0.00010428835,0.000013216221],"category_scores_gemma":[0.000038863927,0.000107899425,0.00005812121,0.00008502609,0.00012828544,0.000024974068,0.00016979492,0.00008679581,0.0000030960905],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009851005,0.00020890313,0.069329955,0.00014726413,0.00088051986,0.000020259398,0.0014282523,0.40176544,0.48555252,0.00041838826,0.0067675365,0.032495856],"study_design_scores_gemma":[0.016889518,0.009069947,0.072355516,0.0008000563,0.0004181207,0.0045259143,0.0055930456,0.06842452,0.6939567,0.012591272,0.11116198,0.004213407],"about_ca_topic_score_codex":0.0000031340553,"about_ca_topic_score_gemma":0.0000066030557,"teacher_disagreement_score":0.3333409,"about_ca_system_score_codex":0.000028845467,"about_ca_system_score_gemma":0.00015766374,"threshold_uncertainty_score":0.4400011},"labels":[],"label_agreement":null},{"id":"W2071777796","doi":"10.1142/s021972000300023x","title":"BIOINFORMATICS MEETS PROTEOMICS — BRIDGING THE GAP BETWEEN MASS SPECTROMETRY DATA ANALYSIS AND CELL BIOLOGY","year":2003,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","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":"Caprion (Canada)","funders":"","keywords":"Proteomics; Proteome; Computational biology; Context (archaeology); Bridging (networking); Mass spectrometry; Identification (biology); Systems biology; Biomarker discovery; Biology; Bioinformatics; Computer science; Data science; Chemistry; Biochemistry; Chromatography","score_opus":0.02296125878695445,"score_gpt":0.2901927437328728,"score_spread":0.26723148494591836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071777796","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":[0.092683144,0.00029713984,0.904947,0.00049614283,0.00002140242,0.00011248429,0.00027955015,0.000014087176,0.0011490387],"genre_scores_gemma":[0.37382793,0.00035282265,0.6254478,0.00010863103,0.000059539343,0.0000032669088,0.0001858608,0.0000061337464,0.0000079691235],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986916,0.000028745806,0.0008482718,0.00012459721,0.000104956845,0.00020181674],"domain_scores_gemma":[0.9982275,0.00033269695,0.00091991376,0.00028875825,0.00013782304,0.00009333059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060485944,0.00016045732,0.00036365067,0.0002235233,0.00019844472,0.000066928675,0.0003798081,0.00013283604,0.000021657974],"category_scores_gemma":[0.00008440673,0.00011068488,0.00007552905,0.00031811485,0.00020136037,0.00019743672,0.00014997215,0.00031149658,0.000001526413],"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":[0.00026876776,0.0006028108,0.26696545,0.0020205374,0.009716545,0.000015610758,0.0037774693,0.020815564,0.12669566,0.37528917,0.002056909,0.19177552],"study_design_scores_gemma":[0.0020727792,0.00041417265,0.0017386149,0.000069677386,0.0013873633,0.00037707924,0.0011878798,0.695576,0.026037168,0.25428495,0.015949694,0.00090460345],"about_ca_topic_score_codex":0.0000034785771,"about_ca_topic_score_gemma":5.9892074e-7,"teacher_disagreement_score":0.67476046,"about_ca_system_score_codex":0.00002741861,"about_ca_system_score_gemma":0.00007993413,"threshold_uncertainty_score":0.45135984},"labels":[],"label_agreement":null},{"id":"W2075341611","doi":"10.1142/s0219720005001065","title":"APPROXIMATE MATCHING OF STRUCTURED MOTIFS IN DNA SEQUENCES","year":2005,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"RNA and protein synthesis mechanisms","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":"Computer Research Institute of Montréal; Université de Montréal","funders":"","keywords":"Regular expression; Pattern matching; Automaton; Theoretical computer science; Algorithm; Genome; Mathematics; Computer science; Time complexity; Pushdown automaton; Computational biology; Combinatorics; Biology; Genetics; Artificial intelligence; Gene","score_opus":0.008234771360779138,"score_gpt":0.2438183279726577,"score_spread":0.23558355661187858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075341611","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9543345,0.00054166873,0.044645946,0.00020196567,0.00006230549,0.000056696637,0.0000121181965,0.0000011181907,0.00014368774],"genre_scores_gemma":[0.92034507,0.0001109057,0.07934282,0.00011323458,0.00006567805,7.279718e-7,0.00001351948,0.0000031145369,0.000004952132],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99924445,0.000035221634,0.0004949694,0.00005409473,0.00007796964,0.00009330122],"domain_scores_gemma":[0.9994198,0.000030044022,0.00037993595,0.00004838873,0.000086978966,0.00003483103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003056972,0.000076241246,0.00017292149,0.00009589695,0.000022993388,0.000009945912,0.00010572046,0.00008572739,0.000007389854],"category_scores_gemma":[0.000029741495,0.000058203765,0.000047725393,0.000044790395,0.00005774759,0.000011885469,0.00003517054,0.000057067096,4.9580603e-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":[0.00031855077,0.000114759634,0.003979149,0.00017837243,0.00020176683,0.0000037626212,0.0014748112,0.046728026,0.7326286,0.01322039,0.00010639942,0.20104545],"study_design_scores_gemma":[0.0060857255,0.004125123,0.019208776,0.00039245753,0.000092023205,0.0016809464,0.0027611891,0.107450165,0.6078,0.24265425,0.0066525606,0.0010967887],"about_ca_topic_score_codex":0.0000024717422,"about_ca_topic_score_gemma":0.000003711416,"teacher_disagreement_score":0.22943386,"about_ca_system_score_codex":0.0000063877324,"about_ca_system_score_gemma":0.000058159676,"threshold_uncertainty_score":0.23734806},"labels":[],"label_agreement":null},{"id":"W2076795608","doi":"10.1142/s0219720008003527","title":"MANGO: MULTIPLE ALIGNMENT WITH N GAPPED OLIGOS","year":2008,"lang":"en","type":"article","venue":"Journal of Bioinformatics and 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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Canada Research Chairs","keywords":"Multiple sequence alignment; Heuristics; Scalability; Computer science; Dynamic programming; Sequence (biology); Sequence alignment; Task (project management); State (computer science); Algorithm; Biology","score_opus":0.0105151779553291,"score_gpt":0.2176171667524678,"score_spread":0.2071019887971387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076795608","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9785954,0.00071587844,0.020079246,0.00016378298,0.00007065485,0.00006409249,0.000015136534,9.2670774e-7,0.00029493254],"genre_scores_gemma":[0.9675662,0.0005667713,0.031411905,0.00031291254,0.000094528994,0.0000016870251,0.000018800902,0.000004920772,0.000022302745],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994296,0.000015564417,0.0003002473,0.00006503459,0.00007792189,0.000111620335],"domain_scores_gemma":[0.9994743,0.000028891478,0.00022741492,0.000058580732,0.00015138501,0.00005946985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009554651,0.000093958755,0.00015055017,0.000047921196,0.000089800444,0.0000072224952,0.000076685974,0.0000519709,0.0000021782998],"category_scores_gemma":[0.000015978936,0.000065634675,0.000045020362,0.000032911605,0.00012070627,0.0000016581221,0.00005097301,0.00004580157,0.0000014358812],"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":[0.0027738789,0.0009087276,0.6428013,0.00027414694,0.0041370788,0.000100537625,0.0054940293,0.05281775,0.20297883,0.010217335,0.014086987,0.0634094],"study_design_scores_gemma":[0.022294493,0.022993073,0.59750533,0.0001584114,0.00031832646,0.016893692,0.002795562,0.053552136,0.034149442,0.011840614,0.23506162,0.002437299],"about_ca_topic_score_codex":0.0000022469526,"about_ca_topic_score_gemma":0.0000019055199,"teacher_disagreement_score":0.22097462,"about_ca_system_score_codex":0.0000056435615,"about_ca_system_score_gemma":0.0000669422,"threshold_uncertainty_score":0.26765043},"labels":[],"label_agreement":null},{"id":"W2082232137","doi":"10.1142/s0219720004000776","title":"DISCOVERY OF FUNCTIONAL GENES FOR SYSTEMIC ACQUIRED RESISTANCE IN<i>ARABIDOPSIS THALIANA</i>THROUGH INTEGRATED DATA MINING","year":2004,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; Plant Biotechnology Institute","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Gene; Cluster analysis; Arabidopsis thaliana; Computational biology; Arabidopsis; Biology; Genetics; Candidate gene; Promoter; Data mining; Computer science; Artificial intelligence; Mutant; Gene expression","score_opus":0.034269504117523004,"score_gpt":0.2854363661434654,"score_spread":0.2511668620259424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082232137","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5612636,0.0031553654,0.43465054,0.00045367738,0.00019138242,0.00011456389,0.000115913426,0.0000017002793,0.000053249416],"genre_scores_gemma":[0.94680893,0.0004543496,0.05196489,0.00015950359,0.00008573271,0.0000044740045,0.00048828032,0.0000051179163,0.000028731873],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990954,0.0000256865,0.00058687123,0.00011082248,0.00008955173,0.000091710834],"domain_scores_gemma":[0.9990503,0.000042713225,0.0005124284,0.0001319287,0.00023878402,0.000023821538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025721866,0.0000864692,0.0001830705,0.000085658015,0.00003641103,0.000016700611,0.00017236946,0.00008931012,0.0000010373429],"category_scores_gemma":[0.0000673428,0.00006844987,0.000048324062,0.00009787626,0.00007931882,0.000037666592,0.000049587536,0.000034373967,1.7994975e-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":[0.004699189,0.0006146945,0.013132444,0.001297929,0.00091217656,0.000006977176,0.0023903444,0.067308754,0.8386256,0.031411353,0.014624141,0.02497637],"study_design_scores_gemma":[0.07441112,0.011552786,0.11005438,0.006765604,0.0009340654,0.003960544,0.041492235,0.10020536,0.2585609,0.17516284,0.21205233,0.0048478288],"about_ca_topic_score_codex":0.0000030744343,"about_ca_topic_score_gemma":0.0000117542995,"teacher_disagreement_score":0.5800647,"about_ca_system_score_codex":0.00001908671,"about_ca_system_score_gemma":0.00026499055,"threshold_uncertainty_score":0.27913046},"labels":[],"label_agreement":null},{"id":"W2084252156","doi":"10.1142/s0219720004000983","title":"A TUTORIAL OF RECENT DEVELOPMENTS IN THE SEEDING OF LOCAL ALIGNMENT","year":2004,"lang":"en","type":"review","venue":"Journal of Bioinformatics and Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"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 Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Seeding; Heuristic; Focus (optics); Sensitivity (control systems); Computer science; Artificial intelligence; Machine learning; Algorithm; Biology; Engineering; Physics","score_opus":0.03088546029394813,"score_gpt":0.30646730880305817,"score_spread":0.27558184850911005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084252156","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":[0.0036194928,0.99226743,0.0032431597,0.0000307162,0.00038642998,0.00021928393,0.000055847333,2.2515903e-7,0.00017740192],"genre_scores_gemma":[0.018809538,0.97472554,0.0062792767,0.000031374537,0.000097902375,0.0000030160495,0.00004728621,0.0000050395065,0.000001009303],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986061,0.000053540072,0.0010527864,0.00006685424,0.00012115919,0.00009955883],"domain_scores_gemma":[0.9986829,0.00007352425,0.0009955841,0.000062067586,0.0001619702,0.000023917855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045766775,0.00013907398,0.00058288174,0.00010793937,0.00002253012,0.00000570119,0.00018823612,0.00014138252,0.0000012151814],"category_scores_gemma":[0.000028887865,0.0000854844,0.00013401502,0.0000856852,0.00011779285,0.0000010550087,0.00009085358,0.00009683608,2.0222429e-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":[0.00006188507,0.00013537247,0.000111994916,0.0033840297,0.0007247809,0.0000022715494,0.00075244444,0.0013423132,0.000096538,0.002665603,0.00009360957,0.99062914],"study_design_scores_gemma":[0.0016128026,0.0016852024,0.00042185542,0.0023801818,0.00030263717,0.00040031064,0.0008169393,0.00008413057,0.00011352298,0.002757497,0.9890941,0.00033086818],"about_ca_topic_score_codex":0.000002645979,"about_ca_topic_score_gemma":0.0000010520746,"teacher_disagreement_score":0.9902983,"about_ca_system_score_codex":0.000024342062,"about_ca_system_score_gemma":0.0004224159,"threshold_uncertainty_score":0.34859526},"labels":[],"label_agreement":null},{"id":"W2084332942","doi":"10.1142/s0219720008003308","title":"FITTING PROTEIN CHAINS TO CUBIC LATTICE IS NP-COMPLETE","year":2008,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Protein Structure and Dynamics","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 Lethbridge; Simon Fraser University","funders":"","keywords":"Lattice (music); Combinatorics; Protein folding; Square lattice; Crystal structure; Mathematics; Chain (unit); Crystallography; Physics; Statistical physics; Chemistry; Quantum mechanics","score_opus":0.012204151468651761,"score_gpt":0.2475589559974527,"score_spread":0.23535480452880095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084332942","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89553636,0.0003125997,0.102712125,0.00084666384,0.000090665206,0.00013660373,0.000035842426,0.0000036174076,0.00032553048],"genre_scores_gemma":[0.8911097,0.00007344106,0.105943285,0.0025528888,0.00020126927,0.000002658297,0.00003792365,0.0000073085034,0.00007152573],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99916893,0.000025495236,0.0004474293,0.00009060775,0.00011008206,0.00015743177],"domain_scores_gemma":[0.9992653,0.000024159177,0.0002883696,0.00008470676,0.00022953743,0.000107895234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017718384,0.00011508467,0.00018293424,0.00009645111,0.00011922938,0.0000149492325,0.00013816149,0.000100941674,0.0000062866957],"category_scores_gemma":[0.00007276281,0.00009315135,0.00007144585,0.00008046375,0.000079720936,0.000009837197,0.000087381995,0.000107479194,0.0000052807122],"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":[0.0020665694,0.0005073745,0.027042098,0.00059214566,0.0020148957,0.00013249867,0.010373564,0.022070605,0.70327693,0.06060263,0.02134095,0.14997971],"study_design_scores_gemma":[0.014380374,0.020398736,0.051220678,0.00046733936,0.00021322667,0.022264866,0.0016021344,0.28538242,0.05421188,0.082132556,0.46372202,0.004003782],"about_ca_topic_score_codex":0.0000026058526,"about_ca_topic_score_gemma":9.3871137e-7,"teacher_disagreement_score":0.6490651,"about_ca_system_score_codex":0.0000091289985,"about_ca_system_score_gemma":0.00009839479,"threshold_uncertainty_score":0.3798602},"labels":[],"label_agreement":null},{"id":"W2087799175","doi":"10.1142/s0219720008003801","title":"MODELING OF GLYCEROL-3-PHOSPHATE TRANSPORTER SUGGESTS A POTENTIAL 'TILT' MECHANISM INVOLVED IN ITS FUNCTION","year":2008,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Drug Transport and Resistance Mechanisms","field":"Medicine","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":"National Institute of Allergy and Infectious Diseases; National Institutes of Health; McGill University","keywords":"Major facilitator superfamily; Transporter; Permease; Transmembrane domain; Periplasmic space; Lactose permease; Membrane transport protein; Transport protein; Protein structure; Biology; Transmembrane protein; ATP-binding cassette transporter; Ligand (biochemistry); Biophysics; Chemistry; Biochemistry; Amino acid; Gene; Receptor","score_opus":0.015852783756237724,"score_gpt":0.23200887046751428,"score_spread":0.21615608671127656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087799175","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78683966,0.0003542844,0.21231563,0.00017452252,0.00016722608,0.00008964637,0.000008246582,0.000004091096,0.00004665528],"genre_scores_gemma":[0.9872498,0.00042660988,0.012042517,0.00018211569,0.00004289148,9.585087e-7,0.000038077957,0.0000057122757,0.000011299962],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880123,0.000012158178,0.00081075635,0.000062828185,0.0001852727,0.00012776122],"domain_scores_gemma":[0.99931204,0.000017235407,0.000267595,0.00004115369,0.00028437958,0.00007758026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021702815,0.00010231628,0.0003588092,0.00024314581,0.00003985063,0.0000037163813,0.000048687372,0.00010773564,0.000016451519],"category_scores_gemma":[0.000006196585,0.000076622506,0.00010385342,0.000108611464,0.00004540695,0.00013414575,0.000006265445,0.00015666403,0.000001099319],"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":[0.02533421,0.0028975883,0.046661243,0.0035345876,0.002382495,0.0013323185,0.017493334,0.7303729,0.052036066,0.0894313,0.0001713629,0.028352601],"study_design_scores_gemma":[0.005482654,0.0014665299,0.01758908,0.00023000788,0.00013652093,0.000629781,0.0004491383,0.9569428,0.0009450373,0.015925314,0.000046471032,0.00015666807],"about_ca_topic_score_codex":0.0000046455493,"about_ca_topic_score_gemma":0.00000508516,"teacher_disagreement_score":0.2265699,"about_ca_system_score_codex":0.000016707792,"about_ca_system_score_gemma":0.00013489275,"threshold_uncertainty_score":0.31245753},"labels":[],"label_agreement":null},{"id":"W2096487774","doi":"10.1142/s0219720010004872","title":"THE IMPORTANCE OF INHIBITORS FOR THE SIMULATION OF METABOLIC PROCESSES: <i>IN SILICO</i><font>Zn<sup>2+</sup></font> INHIBITION OF m-ACONITASE FROM ANALYSIS OF GLYCOLYSIS AND KREBS CYCLE KINETIC MODELS","year":2010,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Enzyme Structure and Function","field":"Materials Science","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":"National Research Council Canada; Mount Allison University; University of New Brunswick","funders":"","keywords":"Aconitase; Glycolysis; Citric acid cycle; Enzyme; Chemistry; Metabolite; Non-competitive inhibition; Metabolism; Biochemistry; Mixed inhibition; Biophysics; Biology","score_opus":0.008604154339040906,"score_gpt":0.24694955928707146,"score_spread":0.23834540494803055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096487774","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96922874,0.000690917,0.029602379,0.00007101575,0.000063820786,0.00013548355,0.00019533488,0.0000011706571,0.000011135755],"genre_scores_gemma":[0.9946226,0.00011328076,0.005164311,0.000028947146,0.0000332318,0.0000029165165,0.000031578005,0.0000026650007,4.9915866e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862045,0.000034673714,0.0010349203,0.0000670529,0.00016155958,0.00008133475],"domain_scores_gemma":[0.99696124,0.0010614909,0.0013237426,0.000087159155,0.00054104783,0.00002534743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005567518,0.0000842952,0.00037756897,0.00019069003,0.000056491925,0.000013798123,0.00008870254,0.00007248876,0.0000075909425],"category_scores_gemma":[0.00017283137,0.00004880065,0.00009018441,0.00032677903,0.00022367027,0.00020415301,0.000026998896,0.00007571288,4.7204267e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024626584,0.000040283525,0.0049608303,0.00009694498,0.00021315704,9.0885315e-8,0.0016417613,0.95787513,0.029771322,0.0025394147,0.0000059941217,0.0026087842],"study_design_scores_gemma":[0.00066407974,0.00021359047,0.009176607,0.000026620184,0.00040323177,0.000003022723,0.0007115013,0.95740706,0.013214872,0.01809922,0.000023146842,0.000057021596],"about_ca_topic_score_codex":0.000045880966,"about_ca_topic_score_gemma":0.00008350815,"teacher_disagreement_score":0.025393827,"about_ca_system_score_codex":0.0000041804597,"about_ca_system_score_gemma":0.00007470795,"threshold_uncertainty_score":0.19900328},"labels":[],"label_agreement":null},{"id":"W2097950066","doi":"10.1142/s0219720014410091","title":"<i>In silico</i>evolution of the<i>hunchback</i>gene indicates redundancy in cis-regulatory organization and spatial gene expression","year":2014,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Plant Molecular Biology Research","field":"Agricultural and Biological Sciences","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":"British Columbia Institute of Technology","funders":"National Institute of General Medical Sciences; National Institutes of Health; Russian Foundation for Basic Research","keywords":"Modularity (biology); Computational biology; Biology; In silico; Modular design; Redundancy (engineering); Gene regulatory network; Cis-regulatory module; Robustness (evolution); Gene; Genetics; Regulatory sequence; Expression (computer science); Regulation of gene expression; Gene expression; Function (biology); Computer science; Promoter","score_opus":0.005311822434021521,"score_gpt":0.2025287940153882,"score_spread":0.1972169715813667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097950066","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9977987,0.00020356635,0.0013646864,0.00047418394,0.00005827686,0.000069161026,0.000014442068,0.0000015195494,0.00001545508],"genre_scores_gemma":[0.9987001,0.00006644379,0.0010708832,0.00008587081,0.000044359793,5.347524e-7,0.000029493942,5.145356e-7,0.0000017903614],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991889,0.00012171337,0.00040872037,0.00006698955,0.00011049991,0.000103194485],"domain_scores_gemma":[0.9993377,0.0001860136,0.00031160316,0.000022182534,0.0001065732,0.000035958914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041082685,0.000065108674,0.0001600702,0.000056971636,0.000052398573,0.0000098532755,0.00012006938,0.00010085753,0.0000065410277],"category_scores_gemma":[0.00012308898,0.000026122729,0.000022734754,0.000205787,0.00012677406,0.00007427328,0.00008295261,0.00011032361,5.755673e-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":[0.000057614816,0.00005865755,0.2248223,0.000016586439,0.000009743599,0.0000010707175,0.00014720326,0.00051263196,0.7618897,0.00080398313,0.00004006485,0.011640452],"study_design_scores_gemma":[0.0005525891,0.00041685437,0.9470651,0.00005069329,0.000005228779,0.00018165763,0.00006830976,0.008313182,0.034761593,0.008366222,0.00012473442,0.00009384792],"about_ca_topic_score_codex":0.000027340993,"about_ca_topic_score_gemma":0.000033386237,"teacher_disagreement_score":0.7271281,"about_ca_system_score_codex":0.000018637937,"about_ca_system_score_gemma":0.000029739796,"threshold_uncertainty_score":0.1065254},"labels":[],"label_agreement":null},{"id":"W2107187602","doi":"10.1142/s0219720005001053","title":"CLUSTERING AND RE-CLUSTERING FOR PATTERN DISCOVERY IN GENE EXPRESSION DATA","year":2005,"lang":"en","type":"article","venue":"Journal of Bioinformatics and 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":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Cluster analysis; Data mining; Single-linkage clustering; Computational biology; Computer science; Correlation clustering; Expression (computer science); Gene; Pairwise comparison; CURE data clustering algorithm; Pattern recognition (psychology); Biology; Artificial intelligence; Genetics","score_opus":0.02993371998511228,"score_gpt":0.30038400889389766,"score_spread":0.27045028890878536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107187602","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":[0.32486263,0.0006999281,0.6737098,0.0004872506,0.00009200687,0.00007870701,0.000036191483,0.0000012862607,0.000032192456],"genre_scores_gemma":[0.9398024,0.00040643607,0.059094675,0.0003336391,0.00017956237,0.0000027752687,0.00016081952,0.0000047409812,0.0000149624075],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993717,0.000018621138,0.00036587476,0.000102237354,0.000052345942,0.00008919711],"domain_scores_gemma":[0.99954677,0.000028579385,0.00022877778,0.00010278784,0.00005307997,0.00004003728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023583599,0.000071854774,0.00011399159,0.00007808816,0.00003941718,0.000032876,0.00012285922,0.000067971,0.0000015309839],"category_scores_gemma":[0.000029840288,0.000057599762,0.000020717416,0.000026140746,0.0000320825,0.000035295427,0.00017141309,0.000051077983,1.8182972e-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":[0.0006603385,0.00014185783,0.012666609,0.00025314157,0.000100685815,0.0000016746496,0.0009113804,0.039630797,0.41064283,0.00009639492,0.003721135,0.53117317],"study_design_scores_gemma":[0.0038625782,0.0007641216,0.012901995,0.0001725977,0.000024412653,0.00022064689,0.00072904193,0.93761885,0.017610285,0.00069717347,0.025043888,0.00035438914],"about_ca_topic_score_codex":0.0000011011763,"about_ca_topic_score_gemma":0.000010333441,"teacher_disagreement_score":0.8979881,"about_ca_system_score_codex":0.000008175761,"about_ca_system_score_gemma":0.00003818204,"threshold_uncertainty_score":0.234885},"labels":[],"label_agreement":null},{"id":"W2109628189","doi":"10.1142/s0219720013500078","title":"<i>DE NOVO</i> SEQUENCING WITH LIMITED NUMBER OF POST-TRANSLATIONAL MODIFICATIONS PER PEPTIDE","year":2013,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","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 Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computational biology; Posttranslational modification; Computer science; Proteomics; Peptide; Sequence (biology); DNA sequencing; Tandem mass spectrometry; Biology; Identification (biology); Chemistry; Genetics; Mass spectrometry; Biochemistry; Gene; Chromatography","score_opus":0.011816309144595085,"score_gpt":0.2614766387186723,"score_spread":0.24966032957407724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109628189","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63714135,0.000030242521,0.35939693,0.0007214065,0.00000604819,0.00006688395,0.00005400249,0.000009990978,0.0025731295],"genre_scores_gemma":[0.6003989,0.000023141942,0.3993539,0.00012972738,0.000020862391,0.000007516803,0.00004051808,0.0000041879575,0.000021263859],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992676,0.0000064113838,0.00047985904,0.000052209645,0.00009434982,0.00009960569],"domain_scores_gemma":[0.9987141,0.00013704627,0.00044660407,0.00006772902,0.0005745994,0.000059948088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008112586,0.00008189337,0.00014809864,0.000055373283,0.00006595979,0.000020670654,0.00009937409,0.00006626244,0.00015565644],"category_scores_gemma":[0.000015432432,0.00006253685,0.00004537732,0.00006534089,0.00010970056,0.0001677413,0.000015405863,0.00013987503,0.0000046995847],"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":[0.0003058424,0.0005087451,0.054210532,0.000674761,0.00069326855,0.000004147891,0.0052685672,0.094666064,0.36976135,0.42772642,0.000722934,0.045457378],"study_design_scores_gemma":[0.0040179,0.0006957842,0.014439488,0.00043373366,0.00022125525,0.0054535237,0.0039654514,0.48803395,0.027574161,0.44750312,0.006580418,0.0010812061],"about_ca_topic_score_codex":0.000010078001,"about_ca_topic_score_gemma":5.247089e-7,"teacher_disagreement_score":0.3933679,"about_ca_system_score_codex":0.000025630921,"about_ca_system_score_gemma":0.00014425034,"threshold_uncertainty_score":0.25501785},"labels":[],"label_agreement":null},{"id":"W2110186020","doi":"10.1142/s0219720009004345","title":"PREDICTING LOCAL QUALITY OF A SEQUENCE–STRUCTURE ALIGNMENT","year":2009,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Science and Technology of the People's Republic of China","keywords":"Protein structure prediction; Threading (protein sequence); Computer science; Support vector machine; CASP; Sequence (biology); Artificial intelligence; Quality (philosophy); Data mining; Homology modeling; Local structure; Similarity (geometry); Loop modeling; Smith–Waterman algorithm; Protein structure; Sequence alignment; Biology; Peptide sequence","score_opus":0.010224034197594269,"score_gpt":0.28141123862534545,"score_spread":0.2711872044277512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110186020","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85305923,0.00030372493,0.14617318,0.00016322297,0.0000739511,0.00005098355,0.000048912767,0.0000015569235,0.00012520271],"genre_scores_gemma":[0.96853834,0.000049913157,0.030899236,0.0003732056,0.00007734058,1.7979896e-7,0.00005707212,0.0000020161135,0.0000027080719],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99913985,0.000031943026,0.0005651721,0.00005902009,0.0001096228,0.00009438669],"domain_scores_gemma":[0.9991617,0.000023559283,0.0005153064,0.00006358352,0.00018390914,0.000051946663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021092006,0.00008418598,0.00018786335,0.000049464583,0.000034052995,0.000007977384,0.00009726535,0.00011014942,0.0000027088847],"category_scores_gemma":[0.000047499554,0.00006321438,0.0000641731,0.00004302326,0.00010496331,0.000007753501,0.000030406305,0.00008100721,1.1267113e-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":[0.0011602114,0.00019383311,0.039528605,0.00028318944,0.0006576446,0.000007877579,0.0012174643,0.06088278,0.47250667,0.056231752,0.0004809347,0.36684904],"study_design_scores_gemma":[0.009403285,0.016346302,0.17834102,0.00026685325,0.0002090806,0.003078966,0.0020412637,0.22308372,0.07254907,0.48827899,0.0049709575,0.0014305129],"about_ca_topic_score_codex":0.0000026182217,"about_ca_topic_score_gemma":0.0000014660217,"teacher_disagreement_score":0.43204722,"about_ca_system_score_codex":0.000009230802,"about_ca_system_score_gemma":0.00008689974,"threshold_uncertainty_score":0.25778076},"labels":[],"label_agreement":null},{"id":"W2111107841","doi":"10.1142/s0219720004000545","title":"DERIVING HAPLOTYPES THROUGH RECOMBINATION AND GENE CONVERSION PATHWAYS","year":2004,"lang":"en","type":"article","venue":"Journal of Bioinformatics and 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":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Haplotype; Biology; Genetics; Genome; Haplotype estimation; Gene; Evolutionary biology; Computational biology; Allele","score_opus":0.01155091853823511,"score_gpt":0.2252479685338379,"score_spread":0.2136970499956028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111107841","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96815526,0.0015712635,0.029688122,0.00029632574,0.00012773133,0.00004400117,0.000008908974,9.927852e-7,0.00010738194],"genre_scores_gemma":[0.9538807,0.0014820547,0.044274814,0.0002775973,0.000059755144,5.84101e-7,0.000018184404,0.0000037975349,0.0000024885626],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999527,0.00001321555,0.00026458423,0.00006439566,0.000049419035,0.00008141984],"domain_scores_gemma":[0.99956524,0.000021900942,0.00020689233,0.00003659942,0.00013398961,0.000035390574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012949205,0.000075932156,0.000119457814,0.000037802154,0.00008324762,0.00001624328,0.000049111557,0.00006444172,9.739514e-7],"category_scores_gemma":[0.000028873643,0.00006208628,0.00003278541,0.000026796595,0.000079933205,0.0000043319633,0.00006459973,0.00004501007,6.8197596e-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":[0.00060899893,0.00044356124,0.043297242,0.00037146913,0.0014425683,0.000016683576,0.0077467156,0.03245199,0.7388826,0.07415364,0.0008501074,0.09973444],"study_design_scores_gemma":[0.018201798,0.013682516,0.22838965,0.00024370413,0.00030408255,0.0038350292,0.004124218,0.014908608,0.13117602,0.5491109,0.03423332,0.001790158],"about_ca_topic_score_codex":0.0000030682756,"about_ca_topic_score_gemma":9.951294e-7,"teacher_disagreement_score":0.60770655,"about_ca_system_score_codex":0.000007975051,"about_ca_system_score_gemma":0.00005167297,"threshold_uncertainty_score":0.2531805},"labels":[],"label_agreement":null},{"id":"W2112332161","doi":"10.1142/s0219720004000764","title":"MODELING AND SIMULATION OF MOLECULAR BIOLOGY SYSTEMS USING PETRI NETS: MODELING GOALS OF VARIOUS APPROACHES","year":2004,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":138,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Petri net; Computer science; Concurrency; Process architecture; Stochastic Petri net; Representation (politics); Synchronization (alternating current); Systems biology; Theoretical computer science; Modeling and simulation; Distributed computing; Event (particle physics); Programming language; Computational biology; Simulation; Biology","score_opus":0.026486863741333418,"score_gpt":0.2677644995817309,"score_spread":0.24127763584039746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112332161","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50984734,0.0020712689,0.4879862,0.000012328948,0.000027954964,0.000041179406,0.00000661849,7.877351e-7,0.000006339826],"genre_scores_gemma":[0.95655334,0.00014757446,0.04318351,0.000021901391,0.000044092154,4.913934e-7,0.000041610023,0.0000070588503,3.9956558e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875927,0.000054661847,0.0008579495,0.00010434713,0.00009877158,0.00012502131],"domain_scores_gemma":[0.99890786,0.000029387144,0.0005755126,0.00008897077,0.00034049014,0.000057764726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037008128,0.00012502671,0.00036413447,0.00019406724,0.000044410845,0.000011731555,0.00009145174,0.0001622042,4.0650798e-7],"category_scores_gemma":[0.00004158734,0.000107186286,0.000095742434,0.00010549138,0.00009727175,0.000013059106,0.000068986024,0.00007064725,5.9830015e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003846788,0.000024316902,0.0004462575,0.000059990787,0.0002050932,3.737689e-7,0.00009547715,0.9820989,0.015003216,0.0013066633,2.535651e-7,0.0007210162],"study_design_scores_gemma":[0.00060604705,0.00031426852,0.000019495119,0.000039570015,0.00008137962,0.00007938366,0.00019367528,0.99268085,0.00072882534,0.005153422,0.0000054997918,0.00009760578],"about_ca_topic_score_codex":0.00001880653,"about_ca_topic_score_gemma":9.1477375e-7,"teacher_disagreement_score":0.44670606,"about_ca_system_score_codex":0.000014927218,"about_ca_system_score_gemma":0.00012111885,"threshold_uncertainty_score":0.437093},"labels":[],"label_agreement":null},{"id":"W2115024530","doi":"10.1142/s021972000400082x","title":"PAIRWISE PROTEIN STRUCTURE ALIGNMENT BASED ON AN ORIENTATION-INDEPENDENT BACKBONE REPRESENTATION","year":2004,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Protein Structure and Dynamics","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 Alberta","funders":"Fudan University; Purdue University","keywords":"Pairwise comparison; Representation (politics); Structural alignment; Algorithm; Computer science; Orientation (vector space); Multiple sequence alignment; Dynamic programming; Protein structure; Artificial intelligence; Mathematics; Sequence alignment; Geometry","score_opus":0.005996132849436699,"score_gpt":0.2523833834124025,"score_spread":0.24638725056296581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115024530","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81103957,0.00004354105,0.18815912,0.0003109502,0.00012332847,0.00018344738,0.000044647448,0.0000037556977,0.00009165038],"genre_scores_gemma":[0.93669415,0.000010341691,0.06224418,0.00058754405,0.00012490021,0.000003037799,0.00032299143,0.0000068428885,0.0000060254524],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990776,0.00004514775,0.0004385445,0.0001227912,0.00019435213,0.00012152703],"domain_scores_gemma":[0.9991759,0.000014813553,0.00038655527,0.000119931596,0.00020546927,0.00009734467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016557668,0.00012748165,0.00015047548,0.000103035854,0.00007805106,0.00003284016,0.00010885562,0.00012598735,0.0000083379355],"category_scores_gemma":[0.00004240623,0.000100147365,0.000058708163,0.000068161484,0.00006691066,0.000019994104,0.000028476952,0.00010617798,0.0000010090291],"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":[0.0013286535,0.00036494946,0.0038464244,0.000098434975,0.00024409952,0.000018656356,0.00068542897,0.80733865,0.12607151,0.02569526,0.00019184171,0.034116082],"study_design_scores_gemma":[0.029507896,0.030881856,0.046474103,0.00036565046,0.0002445365,0.001466154,0.0023050578,0.2979598,0.17675288,0.40678746,0.0050522545,0.0022023458],"about_ca_topic_score_codex":0.0000044830044,"about_ca_topic_score_gemma":0.000005199305,"teacher_disagreement_score":0.50937885,"about_ca_system_score_codex":0.00002990936,"about_ca_system_score_gemma":0.00016355915,"threshold_uncertainty_score":0.4083891},"labels":[],"label_agreement":null},{"id":"W2119868771","doi":"10.1142/s021972001000504x","title":"ON COMPARING TWO STRUCTURED RNA MULTIPLE ALIGNMENTS","year":2010,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Genomics and Phylogenetic Studies","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":"Western University","funders":"","keywords":"Multiple sequence alignment; Computer science; Pairwise comparison; Phylogenetic tree; Alignment-free sequence analysis; Structural alignment; Sequence alignment; Set (abstract data type); Dynamic programming; Block (permutation group theory); Tree (set theory); Web server; Data mining; Theoretical computer science; Algorithm; Computational biology; Biology; Artificial intelligence; Mathematics; Combinatorics; Genetics; The Internet; Peptide sequence","score_opus":0.009100982297949489,"score_gpt":0.25120980141436283,"score_spread":0.24210881911641335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119868771","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99491894,0.00011270154,0.003959958,0.000080916405,0.00038918626,0.000050871844,0.000016092612,8.543314e-7,0.0004704777],"genre_scores_gemma":[0.9816956,0.000042070456,0.017779632,0.000298018,0.00015078987,7.9605996e-7,0.00002204878,0.000004771416,0.000006263168],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99939734,0.000014587453,0.00033149947,0.00007056294,0.00007519547,0.000110801746],"domain_scores_gemma":[0.9994369,0.000050528466,0.00025672076,0.000070606,0.000121739984,0.000063481166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014201736,0.00009828048,0.00015798007,0.00005769486,0.00007605124,0.00001889494,0.00010812547,0.000063205756,0.0000039152837],"category_scores_gemma":[0.00005663707,0.00007579182,0.00005492837,0.000025803303,0.00007967755,0.0000015950764,0.000066342494,0.00011450889,0.0000015606512],"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":[0.0005016817,0.00017266099,0.08241006,0.000043247845,0.00072564377,0.000004196469,0.0005710163,0.026340306,0.82175094,0.022155382,0.0016908272,0.043634027],"study_design_scores_gemma":[0.024556918,0.009450598,0.41953257,0.00010799825,0.00025132956,0.0017146533,0.0010942029,0.20128763,0.09745084,0.18921562,0.053200357,0.0021373073],"about_ca_topic_score_codex":0.0000021790095,"about_ca_topic_score_gemma":0.000008413141,"teacher_disagreement_score":0.72430015,"about_ca_system_score_codex":0.0000037020104,"about_ca_system_score_gemma":0.00003664903,"threshold_uncertainty_score":0.30907005},"labels":[],"label_agreement":null},{"id":"W2120649366","doi":"10.1142/s0219720008003321","title":"DESIGN AND ANALYSIS OF QUANTITATIVE DIFFERENTIAL PROTEOMICS INVESTIGATIONS USING LC-MS TECHNOLOGY","year":2008,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","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 Toronto; University Health Network","funders":"","keywords":"Pipeline (software); Pooling; Computer science; Biomarker discovery; Proteomics; Quantitative proteomics; Data mining; Computational biology; Identification (biology); Deconvolution; Artificial intelligence; Biology; Algorithm","score_opus":0.037417142446872394,"score_gpt":0.30122854702450924,"score_spread":0.26381140457763685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120649366","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":[0.4726763,0.000054992255,0.5271153,0.00006610152,0.0000045034612,0.000042915653,0.000019940364,0.0000047557564,0.0000152305465],"genre_scores_gemma":[0.41892806,0.00010395347,0.5809249,0.000013663095,0.00000594492,0.0000029274802,0.000016504755,0.0000025430963,0.0000014509343],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920756,0.000011846079,0.0005654378,0.000063896674,0.000069631096,0.0000816239],"domain_scores_gemma":[0.9987873,0.00014854582,0.0007063362,0.00006181352,0.0002506723,0.000045337965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000089732304,0.00008549756,0.00029076153,0.00037495533,0.000115203286,0.0000074331792,0.00008520013,0.00010254412,0.000009972848],"category_scores_gemma":[0.000045327593,0.00007188873,0.000052658903,0.00031366257,0.00036335218,0.000084206105,0.000046124656,0.00013284707,1.238621e-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":[0.00028732006,0.00035884572,0.049452286,0.00026984586,0.0035078335,0.0000071922564,0.0033816707,0.24697182,0.4235281,0.2641622,0.000051180068,0.00802167],"study_design_scores_gemma":[0.0003744816,0.00016152284,0.0007651672,0.00002807754,0.00024674126,0.00017636207,0.00016059469,0.9187155,0.016051585,0.06316711,0.00003568597,0.00011719798],"about_ca_topic_score_codex":0.0000028645006,"about_ca_topic_score_gemma":2.348182e-7,"teacher_disagreement_score":0.67174363,"about_ca_system_score_codex":0.000017560682,"about_ca_system_score_gemma":0.00008107179,"threshold_uncertainty_score":0.29315376},"labels":[],"label_agreement":null},{"id":"W2120691528","doi":"10.1142/s0219720006002284","title":"COMPARATIVE GENOMICS OF TRANSCRIPTIONAL REGULATION IN YEASTS AND ITS APPLICATION TO IDENTIFICATION OF A CANDIDATE ALPHA-ISOPROPYLMALATE TRANSPORTER","year":2006,"lang":"en","type":"article","venue":"Journal of Bioinformatics and 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":"University of Toronto","funders":"Russian Academy of Sciences; Ludwig Institute for Cancer Research; Pew Charitable Trusts; Burroughs Wellcome Fund; Howard Hughes Medical Institute","keywords":"Biology; Start codon; Genetics; Genome; Conserved sequence; Regulator; Computational biology; Saccharomyces cerevisiae; Genomics; Gene; Peptide sequence; Messenger RNA","score_opus":0.007871627652280947,"score_gpt":0.24039515579791132,"score_spread":0.23252352814563038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120691528","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8539762,0.0002887834,0.14540498,0.000089469126,0.000024176345,0.00014466028,0.000044878343,6.0810174e-7,0.000026243866],"genre_scores_gemma":[0.9930228,0.000059145612,0.0067633903,0.000024560704,0.000027009797,0.00000395712,0.0000898276,0.0000029026241,0.0000063776656],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99911636,0.000026898777,0.0006520111,0.000068536916,0.00007548744,0.000060685965],"domain_scores_gemma":[0.999291,0.000016062302,0.0004411042,0.00004013496,0.00018460468,0.000027115044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026207423,0.00006747199,0.00017917076,0.00012337888,0.000018195795,0.000004812183,0.00005325641,0.00006726084,0.0000019293416],"category_scores_gemma":[0.0000058412506,0.000060098228,0.000033172004,0.00006235004,0.000038125236,0.000013640345,0.000008731882,0.000030839685,3.429792e-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":[0.00018383644,0.00004073951,0.0009484497,0.000043576867,0.000026833844,1.15395345e-7,0.00029088772,0.008415645,0.98255026,0.0043261372,0.000006198368,0.0031673156],"study_design_scores_gemma":[0.0018014868,0.0010211688,0.2826375,0.00007512489,0.00005401122,0.000087542365,0.00022601093,0.061415453,0.6314104,0.020287422,0.0007352091,0.0002486307],"about_ca_topic_score_codex":0.000007873443,"about_ca_topic_score_gemma":0.000010579722,"teacher_disagreement_score":0.3511398,"about_ca_system_score_codex":0.0000073780325,"about_ca_system_score_gemma":0.000042975214,"threshold_uncertainty_score":0.24507347},"labels":[],"label_agreement":null},{"id":"W2124808836","doi":"10.1142/s0219720008003485","title":"PP<i>i</i>Clust: EFFICIENT CLUSTERING OF 3D PROTEIN–PROTEIN INTERACTION INTERFACES","year":2008,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Protein Structure and Dynamics","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":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"","keywords":"Interface (matter); Cluster analysis; Cluster (spacecraft); Protein–protein interaction; Computer science; Computational biology; Scalability; Biological system; Data mining; Chemistry; Biology; Artificial intelligence; Database; Biochemistry; Parallel computing; Programming language","score_opus":0.00792344490157071,"score_gpt":0.24124251798026833,"score_spread":0.23331907307869762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124808836","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8377453,0.00039414022,0.16135311,0.000064174325,0.00011099456,0.00011477008,0.000012774107,0.0000023038572,0.00020239907],"genre_scores_gemma":[0.9482773,0.000070499686,0.051451515,0.000073626594,0.00007983313,0.000002064127,0.000024505849,0.0000051930006,0.000015477008],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991196,0.000031317402,0.000556393,0.00007547241,0.00010768391,0.000109543114],"domain_scores_gemma":[0.9990576,0.000017640792,0.000563218,0.000073874035,0.00023926403,0.00004840047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016723623,0.000108579035,0.00019630388,0.0000830822,0.0000640136,0.000009424323,0.00011470113,0.00010399287,0.000004314609],"category_scores_gemma":[0.000053111562,0.000085035346,0.000060947776,0.000055907192,0.00013439481,0.0000110231695,0.000101613725,0.00011221084,9.1285824e-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":[0.0017255767,0.00032112203,0.0019337287,0.00051963114,0.00065321475,0.000018710809,0.0017301929,0.26027763,0.6687782,0.0032237754,0.00043288627,0.060385387],"study_design_scores_gemma":[0.0050459104,0.0073376843,0.004015047,0.00048147183,0.00008146034,0.004381702,0.0010051139,0.812494,0.15216345,0.0048776832,0.007230107,0.0008864194],"about_ca_topic_score_codex":0.000004603805,"about_ca_topic_score_gemma":0.0000017817825,"teacher_disagreement_score":0.55221635,"about_ca_system_score_codex":0.000011897833,"about_ca_system_score_gemma":0.00008209158,"threshold_uncertainty_score":0.34676406},"labels":[],"label_agreement":null},{"id":"W2127251093","doi":"10.1142/s0219720012500217","title":"A FLEXIBLE NONPARAMETRIC APPROACH TO FIND CANDIDATE GENES ASSOCIATED WITH DISEASE IN MICROARRAY EXPERIMENTS","year":2012,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Gene expression and cancer classification","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":"Hospital for Sick Children; McMaster University; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Candidate gene; Gene; Function (biology); Computational biology; Nonparametric statistics; Biology; Microarray; Genetics; Microarray analysis techniques; DNA microarray; Gene prediction; Gene expression; Mathematics; Statistics; Genome","score_opus":0.017192287097399873,"score_gpt":0.27662449809982526,"score_spread":0.25943221100242536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127251093","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94835544,0.00126482,0.049782667,0.00008206097,0.00008447435,0.00010680033,0.00001520177,0.0000018998822,0.0003066313],"genre_scores_gemma":[0.98735774,0.00006759025,0.012049321,0.00031735215,0.000056526973,0.0000075327,0.00009405145,0.000004967394,0.00004494802],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.999353,0.0000364199,0.00029439278,0.00007270822,0.000093168666,0.00015030663],"domain_scores_gemma":[0.9994356,0.000016594813,0.00021935928,0.00006416091,0.00010421529,0.00016008544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020760112,0.0000872834,0.00012791816,0.00019494846,0.000036736903,0.000017204926,0.00008327604,0.0000583778,0.0000027426813],"category_scores_gemma":[0.000044100798,0.00006367988,0.000028970187,0.0001838392,0.000035503333,0.000013424597,0.00003439099,0.00005526937,0.0000012155133],"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":[0.0027113224,0.0025207698,0.64036274,0.0001552566,0.000648649,0.0000034036143,0.0036496306,0.06676977,0.22637127,0.0027788794,0.0064956136,0.04753271],"study_design_scores_gemma":[0.005165639,0.0016429655,0.9349807,0.00013549878,0.00007134454,0.00010487737,0.0011331515,0.014738834,0.023762157,0.00051922794,0.017018555,0.00072708714],"about_ca_topic_score_codex":0.0000021620501,"about_ca_topic_score_gemma":3.6025185e-7,"teacher_disagreement_score":0.29461795,"about_ca_system_score_codex":0.000021190643,"about_ca_system_score_gemma":0.0000961821,"threshold_uncertainty_score":0.25967902},"labels":[],"label_agreement":null},{"id":"W2131989567","doi":"10.1142/s0219720004000661","title":"PATTERNHUNTER II: HIGHLY SENSITIVE AND FAST HOMOLOGY SEARCH","year":2004,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":231,"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; Bioinformatics Solutions (Canada); University of Waterloo","funders":"","keywords":"Homology (biology); Sensitivity (control systems); Smith–Waterman algorithm; Computer science; Mathematics; Computational biology; Biology; Genetics; Sequence alignment; Engineering; Gene","score_opus":0.011082962675431672,"score_gpt":0.24645442387469926,"score_spread":0.23537146119926758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131989567","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":[0.36208743,0.0001053494,0.63395005,0.003635868,0.00007696646,0.000022876271,0.000013866842,0.0000054752613,0.00010211803],"genre_scores_gemma":[0.91376245,0.00009322923,0.08505571,0.0010309567,0.000037963848,2.533086e-7,0.00000936139,0.0000011898803,0.00000887199],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99921894,0.000034933655,0.00038806885,0.00009178992,0.00012091003,0.00014537077],"domain_scores_gemma":[0.9992833,0.000156495,0.0001962849,0.0000670593,0.00019955238,0.000097308075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027826405,0.00008451053,0.0002218243,0.00031138049,0.00012036823,0.000058093734,0.00019810065,0.00006405447,0.0000037778545],"category_scores_gemma":[0.000031319007,0.00005609251,0.000048449183,0.00024911406,0.00015911937,0.00027836824,0.0002884979,0.00013965483,0.0000056909903],"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":[0.000064158136,0.00029158016,0.0051358654,0.00004761014,0.0005157046,0.0001480656,0.0046765544,0.014518203,0.00022366024,0.54323924,0.00035957288,0.43077978],"study_design_scores_gemma":[0.006760806,0.009252112,0.20476954,0.00010239216,0.0001340886,0.010873042,0.0016095167,0.30995104,0.00066650554,0.45058814,0.004314837,0.0009779815],"about_ca_topic_score_codex":0.000016234026,"about_ca_topic_score_gemma":0.0000013893041,"teacher_disagreement_score":0.551675,"about_ca_system_score_codex":0.000015665353,"about_ca_system_score_gemma":0.00005110879,"threshold_uncertainty_score":0.22873862},"labels":[],"label_agreement":null},{"id":"W2133854884","doi":"10.1142/s0219720014500073","title":"Prediction of gene-based drug indications using compendia of public gene expression data and PubMed abstracts","year":2014,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Microarray databases; Computer science; Drug discovery; Relevance (law); Data mining; Computational biology; Microarray analysis techniques; Disease; Raw data; Biological data; Drug development; Drug; Bioinformatics; Gene; Biology; Medicine; Gene expression; Genetics","score_opus":0.030645397612834073,"score_gpt":0.24865058207971955,"score_spread":0.21800518446688547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133854884","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6284646,0.00037956078,0.37061834,0.00008239488,0.00009474049,0.00008645503,0.00021153572,0.0000014055887,0.000060982995],"genre_scores_gemma":[0.89701295,0.00009273885,0.10219175,0.0000784249,0.00007417941,8.832449e-7,0.000543386,0.000004518353,0.0000011773968],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878925,0.000050062714,0.00083734916,0.00008374903,0.00011491285,0.0001246702],"domain_scores_gemma":[0.99831074,0.0000748405,0.0011199114,0.00017618846,0.0002214933,0.00009680018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084659376,0.00009625352,0.00021727168,0.00014135677,0.000062016734,0.000018947918,0.00020493072,0.00011108426,0.0000018263856],"category_scores_gemma":[0.0000795292,0.00007930803,0.00003911097,0.00006127813,0.00017274992,0.000028517316,0.00011979859,0.00008528868,1.3635625e-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":[0.00068304886,0.001044219,0.11456621,0.0014200485,0.0014608878,0.0000020476077,0.0019075178,0.13656196,0.4181449,0.007073498,0.0031662325,0.31396943],"study_design_scores_gemma":[0.0028506133,0.0006785865,0.051971037,0.00009388342,0.00011584745,0.00022630983,0.00028680093,0.9123908,0.024364484,0.004535624,0.0022142534,0.00027170384],"about_ca_topic_score_codex":0.0000026380078,"about_ca_topic_score_gemma":0.0000011035977,"teacher_disagreement_score":0.7758289,"about_ca_system_score_codex":0.0000065765157,"about_ca_system_score_gemma":0.00013149514,"threshold_uncertainty_score":0.32340878},"labels":[],"label_agreement":null},{"id":"W2133903964","doi":"10.1142/s0219720004000326","title":"OPTIMAL SPACED SEEDS FOR HOMOLOGOUS CODING REGIONS","year":2004,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Coding (social sciences); Coding region; Homology (biology); Computational biology; Homologous chromosome; Computer science; Homologous recombination; Smith–Waterman algorithm; Gene; Biology; Genetics; Algorithm; Mathematics; Sequence alignment; Statistics","score_opus":0.013003031956219038,"score_gpt":0.25438642812638906,"score_spread":0.24138339617017002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133903964","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72051007,0.0007757199,0.27737746,0.0008897817,0.00018077335,0.00010102668,0.000034550394,0.0000012400824,0.00012942689],"genre_scores_gemma":[0.87990344,0.00032340872,0.11919459,0.00037711204,0.00015026247,0.0000028785182,0.0000285483,0.0000054229426,0.000014347567],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994162,0.000009810251,0.00032920373,0.00006850761,0.000046107485,0.0001301923],"domain_scores_gemma":[0.99931955,0.000039754323,0.00025218315,0.000052769617,0.00027960943,0.00005613794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016775505,0.00009203564,0.00016230004,0.0000652588,0.000104028135,0.000015846303,0.00008685487,0.00008122175,7.64809e-7],"category_scores_gemma":[0.000062425854,0.00007502225,0.00008701363,0.000035313395,0.00009927523,0.0000019209142,0.00005210492,0.000051630857,5.753518e-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":[0.0014896933,0.0005181515,0.0053425822,0.0003329444,0.0026414816,0.000016445712,0.0038253542,0.5137068,0.24332774,0.19088753,0.0073254285,0.030585872],"study_design_scores_gemma":[0.049634293,0.047567554,0.0539315,0.00042688113,0.0010520595,0.0121508995,0.011399336,0.068803996,0.067639224,0.46380758,0.21930663,0.0042800284],"about_ca_topic_score_codex":0.0000014896541,"about_ca_topic_score_gemma":0.0000014753821,"teacher_disagreement_score":0.44490278,"about_ca_system_score_codex":0.000010200596,"about_ca_system_score_gemma":0.000104060506,"threshold_uncertainty_score":0.30593187},"labels":[],"label_agreement":null},{"id":"W2134922741","doi":"10.1142/s0219720012710023","title":"DETECTION AND DECOMPOSITION: TREATMENT-INDUCED CYCLIC GENE EXPRESSION DISRUPTION IN HIGH-THROUGHPUT TIME-SERIES DATASETS","year":2012,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Evolutionary Algorithms and Applications","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":"Lakehead University","funders":"","keywords":"Gene; Gene expression; Organism; Decomposition; Computational biology; Biology; Expression (computer science); Series (stratigraphy); Computer science; Genetics; Ecology","score_opus":0.012441089639826432,"score_gpt":0.27673103492857876,"score_spread":0.2642899452887523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134922741","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.543129,0.00026727232,0.4559117,0.00044182572,0.000118247604,0.000077565324,0.00002759621,0.000009070811,0.000017697901],"genre_scores_gemma":[0.78008157,0.00014966905,0.21953887,0.000053602147,0.00008846976,0.0000045179004,0.000079022466,0.0000020197306,0.0000022417116],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931085,0.000040410596,0.00037240345,0.000073559306,0.00007919082,0.00012355881],"domain_scores_gemma":[0.99945134,0.00009045573,0.00025292396,0.00007611411,0.0000510557,0.00007811328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017460078,0.000088000386,0.00014329806,0.00013563054,0.00012769426,0.000041437088,0.00008730485,0.000057346293,0.0000027240694],"category_scores_gemma":[0.000007203024,0.00006796688,0.000023377354,0.00011753537,0.000038955175,0.0010343718,0.000063301326,0.00006522669,0.00000525773],"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":[0.00024003354,0.0015575427,0.016070532,0.00009288177,0.00020343588,0.000013851624,0.0054769577,0.006365132,0.13818067,0.081533246,0.00038733563,0.7498784],"study_design_scores_gemma":[0.0047355006,0.0030265355,0.30808988,0.000109843706,0.000060314123,0.004022891,0.00032392077,0.58740896,0.017165145,0.069657855,0.0046849726,0.0007141551],"about_ca_topic_score_codex":0.0000065014906,"about_ca_topic_score_gemma":0.0000012930543,"teacher_disagreement_score":0.7491642,"about_ca_system_score_codex":0.000044463843,"about_ca_system_score_gemma":0.000026866312,"threshold_uncertainty_score":0.27716088},"labels":[],"label_agreement":null},{"id":"W2135899964","doi":"10.1142/s0219720014500255","title":"Evaluating predictive performance of network biomarkers with network structures","year":2014,"lang":"en","type":"article","venue":"Journal of Bioinformatics and 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":"University of Calgary","funders":"","keywords":"Social connectedness; Computer science; Data mining; Graph; Weighted network; Network performance; Network analysis; Support vector machine; Network structure; Gene regulatory network; Artificial intelligence; Machine learning; Complex network; Theoretical computer science; Biology; Gene; Gene expression","score_opus":0.008379428439424798,"score_gpt":0.25114489197362383,"score_spread":0.24276546353419903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135899964","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7851605,0.00052322075,0.21314973,0.00006599961,0.00021588006,0.0001228888,0.000010840317,0.0000032506496,0.00074769533],"genre_scores_gemma":[0.872451,0.0000949492,0.12678388,0.00021688137,0.00038780994,0.0000012751964,0.0000518517,0.000007361443,0.000004977303],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988058,0.000055331144,0.00069291,0.000083126055,0.00015046314,0.00021234331],"domain_scores_gemma":[0.99850875,0.00008993074,0.0008949994,0.000105744126,0.00032219966,0.00007836559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007940552,0.00014438704,0.000277661,0.00005521968,0.0001006844,0.000018215678,0.00015204921,0.00012478836,0.000004557173],"category_scores_gemma":[0.0000357512,0.000101542944,0.00006500019,0.00010477292,0.00018880703,0.000015170098,0.00007863705,0.000121580786,4.2776085e-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":[0.0009883912,0.000023514536,0.015939556,0.00011743121,0.0005683114,3.0181982e-7,0.00015923868,0.904366,0.00044986102,0.0062543433,0.0013342403,0.06979881],"study_design_scores_gemma":[0.0020710367,0.008914792,0.02262192,0.00014826893,0.00010826247,0.000309737,0.00012891219,0.94383657,0.00022050858,0.018843833,0.0024921237,0.0003040437],"about_ca_topic_score_codex":0.0000010273453,"about_ca_topic_score_gemma":0.0000012561314,"teacher_disagreement_score":0.08729052,"about_ca_system_score_codex":0.0000074631353,"about_ca_system_score_gemma":0.00010815931,"threshold_uncertainty_score":0.4140801},"labels":[],"label_agreement":null},{"id":"W2137504100","doi":"10.1142/s0219720011005276","title":"ERROR TOLERANT NMR BACKBONE RESONANCE ASSIGNMENT AND AUTOMATED STRUCTURE GENERATION","year":2010,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Protein Structure and Dynamics","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":"York University; University of Waterloo","funders":"","keywords":"Probabilistic logic; Computer science; Precision and recall; Protein secondary structure; Algorithm; Artificial intelligence; Biology","score_opus":0.006003271850188033,"score_gpt":0.2457398115828957,"score_spread":0.23973653973270767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137504100","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97831357,0.00052990793,0.020498488,0.000247202,0.00022561122,0.0000767876,0.000055180237,0.000005517648,0.000047741432],"genre_scores_gemma":[0.941301,0.000066615576,0.057898965,0.00036786083,0.0002103013,8.2251063e-7,0.00014035296,0.0000047663743,0.000009300718],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934894,0.000021874626,0.0003569401,0.00008336999,0.00008525279,0.00010363667],"domain_scores_gemma":[0.99943787,0.000016286707,0.00026754107,0.000067638844,0.00014193522,0.00006873249],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014541393,0.00010364456,0.0001463854,0.00005217872,0.00007505788,0.000030736468,0.00007017442,0.00016813852,0.0000067254523],"category_scores_gemma":[0.000034839417,0.0000775356,0.00002829966,0.000034321358,0.00009833793,0.000011943008,0.0000481568,0.00015583687,3.6192478e-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":[0.00027159913,0.00007043112,0.0057347356,0.00008212331,0.00023692091,0.000008445468,0.00045732516,0.014651496,0.85760796,0.01157365,0.0031043717,0.10620092],"study_design_scores_gemma":[0.001995186,0.001226095,0.022652198,0.000020312971,0.00004235834,0.001568808,0.000088641355,0.9382048,0.006701337,0.0071835876,0.019949159,0.00036751744],"about_ca_topic_score_codex":0.0000015350378,"about_ca_topic_score_gemma":0.000008895192,"teacher_disagreement_score":0.9235533,"about_ca_system_score_codex":0.000004667441,"about_ca_system_score_gemma":0.000069347036,"threshold_uncertainty_score":0.316181},"labels":[],"label_agreement":null},{"id":"W2140934347","doi":"10.1142/s0219720013500029","title":"WHOLE GENOME IDENTITY-BY-DESCENT DETERMINATION","year":2012,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Alberta Agricultural Research Institute","keywords":"Haplotype; Identity by descent; Haplotype estimation; Genetics; Genotyping; Genome; Biology; Linkage (software); Mendelian inheritance; Allele; Genotype; Computational biology; Single-nucleotide polymorphism; Gene","score_opus":0.010675163598570198,"score_gpt":0.2744912583305859,"score_spread":0.2638160947320157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140934347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7531664,0.0015742441,0.24434587,0.00038680527,0.00023047258,0.00005743627,0.000040762592,0.0000021185122,0.00019592998],"genre_scores_gemma":[0.96904325,0.00024927314,0.029735679,0.00052278826,0.00020765649,0.0000014425812,0.00020279126,0.000004797467,0.000032344517],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991848,0.000057108027,0.00045321093,0.00005317633,0.000079354584,0.00017236706],"domain_scores_gemma":[0.99922824,0.00003944725,0.0004142273,0.00005428648,0.00016964762,0.00009417954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005581848,0.00008358482,0.00015397966,0.00006738797,0.00007007292,0.000015931602,0.000094548195,0.0001141439,0.000007685958],"category_scores_gemma":[0.000100515,0.00006997578,0.000061185,0.000047899583,0.000061138984,0.000024696963,0.000058046295,0.000071273396,0.0000075558964],"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":[0.00027622413,0.0010998367,0.45075154,0.00022757892,0.0010898376,0.0000028685822,0.0028196564,0.006076093,0.36004245,0.011936379,0.029067533,0.13660999],"study_design_scores_gemma":[0.0041546277,0.0033018203,0.6595273,0.000042265572,0.00021185075,0.0012128789,0.0016108956,0.0221082,0.001675199,0.020614455,0.28448844,0.001052064],"about_ca_topic_score_codex":0.0000012978694,"about_ca_topic_score_gemma":7.023807e-7,"teacher_disagreement_score":0.35836726,"about_ca_system_score_codex":0.000016237147,"about_ca_system_score_gemma":0.000039042458,"threshold_uncertainty_score":0.28535295},"labels":[],"label_agreement":null},{"id":"W2141375003","doi":"10.1142/s0219720004000557","title":"ANCESTRAL MAXIMUM LIKELIHOOD OF EVOLUTIONARY TREES IS HARD","year":2004,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Evolution and Genetic Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; McGill University","funders":"Israel Science Foundation; McGill University","keywords":"Maximum likelihood; Evolutionary biology; Biology; Phylogenetics; Tree rearrangement; Phylogenetic tree; Tree (set theory); Mathematics; Statistics; Combinatorics; Genetics; Gene","score_opus":0.007763901412861236,"score_gpt":0.24548396799682093,"score_spread":0.2377200665839597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141375003","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87776566,0.0014346989,0.11940966,0.0007596384,0.00017863263,0.000062221676,0.00007676719,0.0000026686077,0.0003100315],"genre_scores_gemma":[0.9145641,0.00041499911,0.08444341,0.00040346652,0.00008757252,5.729445e-7,0.00006787278,0.0000041859926,0.000013842006],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99920684,0.000015347267,0.00048527625,0.00006860646,0.000104717124,0.000119206736],"domain_scores_gemma":[0.9992401,0.000012973431,0.00035814338,0.00006749828,0.00025088835,0.00007036709],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012015901,0.00008983754,0.0001611715,0.00008290923,0.00004118459,0.0000076231377,0.00010716914,0.000101290876,0.000008266835],"category_scores_gemma":[0.000024598785,0.00007495009,0.000091217145,0.00006139471,0.00014884306,0.0000092490955,0.000043958364,0.00006991577,0.0000020222087],"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":[0.0024027491,0.00239397,0.14154151,0.00079235405,0.0030013495,0.000026527601,0.0044763153,0.39479,0.15273535,0.075368494,0.02782298,0.1946484],"study_design_scores_gemma":[0.012322733,0.011499735,0.40082407,0.00023346944,0.00020769912,0.0027600005,0.0016510638,0.06797293,0.008773517,0.46159565,0.031013036,0.0011460858],"about_ca_topic_score_codex":0.0000032551047,"about_ca_topic_score_gemma":0.0000027998597,"teacher_disagreement_score":0.38622716,"about_ca_system_score_codex":0.000011882313,"about_ca_system_score_gemma":0.00020309833,"threshold_uncertainty_score":0.3056376},"labels":[],"label_agreement":null},{"id":"W2148088562","doi":"10.1142/s0219720010005002","title":"A GRAPH-BASED ALGORITHM FOR MINING MULTI-LEVEL PATTERNS IN GENOMIC DATA","year":2010,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Genome Rearrangement Algorithms","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 Waterloo; University of Guelph","funders":"","keywords":"Genome; Comparative genomics; Genomics; Computer science; Graph; Computational biology; Data mining; Gene; Theoretical computer science; Biology; Genetics","score_opus":0.039847663363638125,"score_gpt":0.2978313042449222,"score_spread":0.2579836408812841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148088562","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":[0.406325,0.0001704728,0.59274274,0.00015043338,0.00018507581,0.00011456381,0.00030532965,0.0000013744385,0.000004990564],"genre_scores_gemma":[0.24808002,0.00007630982,0.75080264,0.00022179243,0.00013509917,0.0000038123842,0.0006669362,0.000008203542,0.0000051685347],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992058,0.000017247283,0.00045209116,0.000111064655,0.0000651232,0.00014867527],"domain_scores_gemma":[0.9993192,0.000053058873,0.00029142704,0.00013414703,0.0001429578,0.000059197686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043889665,0.00010209739,0.00016329593,0.00016016801,0.000039580435,0.000022326069,0.00025893986,0.00010753639,0.000003787225],"category_scores_gemma":[0.000039011502,0.00008781124,0.000050548264,0.000047292266,0.000057306243,0.000011047,0.00010572477,0.000105821644,5.930394e-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":[0.00012987471,0.00031758155,0.032715257,0.00012556065,0.0002902465,0.0000061027736,0.00030024297,0.002820868,0.033629756,0.00015149172,0.00069532666,0.9288177],"study_design_scores_gemma":[0.004224426,0.00070356816,0.03631204,0.000023234677,0.000029939667,0.00012820619,0.00020731457,0.9511013,0.00046097243,0.00055474485,0.006005828,0.0002484438],"about_ca_topic_score_codex":0.0000041281296,"about_ca_topic_score_gemma":0.000037053727,"teacher_disagreement_score":0.9482804,"about_ca_system_score_codex":0.0000053235103,"about_ca_system_score_gemma":0.0001153123,"threshold_uncertainty_score":0.35808384},"labels":[],"label_agreement":null},{"id":"W2160672912","doi":"10.1142/s0219720003000186","title":"RAPTOR: OPTIMAL PROTEIN THREADING BY LINEAR PROGRAMMING","year":2003,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":294,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Threading (protein sequence); Linear programming; Computer science; Pairwise comparison; Integer programming; Protein structure prediction; Server; Benchmark (surveying); Algorithm; Theoretical computer science; Mathematical optimization; Protein structure; Artificial intelligence; Mathematics; Biology; Computer network","score_opus":0.0053852942881868725,"score_gpt":0.24188663847241743,"score_spread":0.23650134418423055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160672912","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6413356,0.0011804446,0.35672757,0.00012872546,0.00011214362,0.00015632815,0.000018302237,0.000004258682,0.00033660684],"genre_scores_gemma":[0.71633947,0.00005803863,0.2832508,0.00016917486,0.00007875715,0.0000027769356,0.000063555104,0.000006907958,0.000030497129],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99927914,0.000033367884,0.000383409,0.00007567245,0.000083963125,0.00014443691],"domain_scores_gemma":[0.9993857,0.000015750136,0.0002982632,0.00007852899,0.00014791133,0.000073829375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025766314,0.00010616723,0.000151256,0.00005288361,0.00007044991,0.000023379074,0.0001163795,0.000117039446,0.000004038567],"category_scores_gemma":[0.00010299498,0.00008328072,0.00006186367,0.00005031105,0.00008219203,0.00001083333,0.000042837084,0.00010709994,9.980672e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016799301,0.0007151511,0.013527333,0.00060265546,0.002141629,0.000030981675,0.001715655,0.032067087,0.49441,0.14157836,0.010571845,0.30095935],"study_design_scores_gemma":[0.011476696,0.016578201,0.00080842356,0.00026744005,0.00022178327,0.005018349,0.001922018,0.0974772,0.129699,0.07070688,0.6634021,0.0024218988],"about_ca_topic_score_codex":6.784724e-7,"about_ca_topic_score_gemma":2.845483e-7,"teacher_disagreement_score":0.65283024,"about_ca_system_score_codex":0.000007866383,"about_ca_system_score_gemma":0.0000889607,"threshold_uncertainty_score":0.33960894},"labels":[],"label_agreement":null},{"id":"W2167445572","doi":"10.1142/s0219720014500279","title":"IncMD: Incremental trie-based structural motif discovery algorithm","year":2014,"lang":"en","type":"article","venue":"Journal of Bioinformatics and 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":"University of Ottawa","funders":"","keywords":"Structural motif; Motif (music); Scalability; Computer science; Nucleic acid secondary structure; Trie; Sequence motif; Computational biology; A priori and a posteriori; Algorithm; Data structure; Theoretical computer science; RNA; Biology; Genetics","score_opus":0.006031222069649855,"score_gpt":0.23177202764777677,"score_spread":0.22574080557812692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167445572","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":[0.49428472,0.0001724037,0.5049522,0.00017067554,0.00018971566,0.00006311078,0.00002774869,0.0000024721319,0.00013698843],"genre_scores_gemma":[0.89394,0.000024242712,0.10519862,0.000537252,0.00019735217,0.0000012761368,0.00008122816,0.000005963135,0.000014096078],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917924,0.00006756356,0.000429529,0.000079434954,0.00011787363,0.00012636348],"domain_scores_gemma":[0.99933237,0.00005795704,0.00035013448,0.00007275211,0.00011765054,0.0000691206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034770044,0.000114767,0.00018168791,0.000079735946,0.000079234494,0.000044304845,0.00012796957,0.00010176342,0.000010662942],"category_scores_gemma":[0.00006277902,0.00008617994,0.00008355693,0.000039782713,0.00008109074,0.00001734165,0.000051244297,0.00007217679,0.0000017553511],"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":[0.00070115156,0.00013219765,0.007719466,0.00014219117,0.0005234242,0.0000058346395,0.00022089499,0.0073393784,0.17687528,0.012081178,0.0012692523,0.79298973],"study_design_scores_gemma":[0.009695987,0.010396946,0.018084703,0.00015248187,0.00017089272,0.0010838484,0.00045302874,0.67334485,0.18721357,0.07251724,0.025551442,0.0013350379],"about_ca_topic_score_codex":0.0000026103376,"about_ca_topic_score_gemma":6.3149264e-7,"teacher_disagreement_score":0.7916547,"about_ca_system_score_codex":0.000009017332,"about_ca_system_score_gemma":0.000077412726,"threshold_uncertainty_score":0.3514316},"labels":[],"label_agreement":null},{"id":"W2168695474","doi":"10.1142/s0219720008003254","title":"THE DISTRIBUTION OF DISTANCES BETWEEN RANDOMLY CONSTRUCTED GENOMES: GENERATING FUNCTION, EXPECTATION, VARIANCE AND LIMITS","year":2008,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Genome Rearrangement Algorithms","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 Ottawa","funders":"","keywords":"Genome; Combinatorics; Limit (mathematics); Biology; Graph; Breakpoint; Mathematics; Variance (accounting); Function (biology); Genetics; Chromosome; Gene; Evolutionary biology","score_opus":0.010180695695394211,"score_gpt":0.22572594971298096,"score_spread":0.21554525401758676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168695474","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81536293,0.0028734785,0.18140523,0.000128256,0.00008700126,0.00007367217,0.00004006177,0.0000015377541,0.000027825417],"genre_scores_gemma":[0.98923767,0.0014581134,0.008966593,0.000029579849,0.00013328873,0.0000017603891,0.00015988284,0.0000031556392,0.000009964912],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991937,0.000044605003,0.00051157636,0.00006292922,0.00009511904,0.00009206945],"domain_scores_gemma":[0.9989439,0.00010941763,0.0004940778,0.000049498885,0.00036132633,0.000041731928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024099404,0.00008013505,0.00015952025,0.000031830437,0.00020737453,0.000016552278,0.00006805199,0.000056577606,0.0000011474237],"category_scores_gemma":[0.000074777956,0.000055009383,0.000038655642,0.00006572015,0.0002539142,0.000012669188,0.000025415036,0.000055518423,2.201178e-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":[0.002312354,0.00024244993,0.5654405,0.00045494785,0.004022992,0.000009611428,0.0056498344,0.016349688,0.083984405,0.019375606,0.0050055976,0.29715207],"study_design_scores_gemma":[0.020150976,0.0072765206,0.8201932,0.000161248,0.00048377996,0.0021641992,0.0062557105,0.067020126,0.0088204015,0.02164893,0.04451932,0.0013056238],"about_ca_topic_score_codex":9.623607e-7,"about_ca_topic_score_gemma":7.20686e-7,"teacher_disagreement_score":0.29584643,"about_ca_system_score_codex":0.0000064883598,"about_ca_system_score_gemma":0.00007699049,"threshold_uncertainty_score":0.22432175},"labels":[],"label_agreement":null},{"id":"W2170694711","doi":"10.1142/s021972000900445x","title":"A PROBABILISTIC FRAMEWORK TO IMPROVE MICRORNA TARGET PREDICTION BY INCORPORATING PROTEOMICS DATA","year":2009,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Complementarity (molecular biology); microRNA; Computational biology; Messenger RNA; Biology; Probabilistic logic; Proteomics; Genetics; Computer science; Gene; Artificial intelligence","score_opus":0.008801695579537777,"score_gpt":0.255764492977427,"score_spread":0.2469627973978892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170694711","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":[0.4650797,0.0003556094,0.53287995,0.0008260678,0.00014776061,0.00029313224,0.00037500515,0.000005559005,0.000037246387],"genre_scores_gemma":[0.68201774,0.000018478902,0.31633747,0.0006508407,0.00021584867,0.000002214761,0.0007466407,0.0000058632445,0.0000049221985],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990085,0.00003487546,0.0005792698,0.00014461912,0.00010489921,0.00012783495],"domain_scores_gemma":[0.99894917,0.000029432844,0.00048344815,0.00018223526,0.00024035879,0.00011535552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003553726,0.00011797614,0.00016187433,0.0000718079,0.0000689714,0.000042417058,0.00023059588,0.00013627797,0.000002490723],"category_scores_gemma":[0.00028540514,0.000101445745,0.000036479247,0.00008326494,0.000052247426,0.000024364135,0.00011071939,0.00011421396,0.0000017066261],"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":[0.00074333395,0.00038990812,0.0029464548,0.00016293899,0.00030586988,0.0000033454655,0.00035403925,0.023649681,0.901889,0.0044652047,0.020986205,0.044104006],"study_design_scores_gemma":[0.005153855,0.013790741,0.023731448,0.0004822005,0.0002662505,0.001025781,0.0004286852,0.6168774,0.045937836,0.2594752,0.031222293,0.0016083651],"about_ca_topic_score_codex":6.752463e-7,"about_ca_topic_score_gemma":2.1868244e-7,"teacher_disagreement_score":0.8559512,"about_ca_system_score_codex":0.000020894344,"about_ca_system_score_gemma":0.0001446395,"threshold_uncertainty_score":0.41368374},"labels":[],"label_agreement":null},{"id":"W2212557680","doi":"10.1142/s0219720016500049","title":"Predicting GHS toxicity using RTCA and discrete-time Fourier transform","year":2015,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Computational Drug Discovery Methods","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":"Alberta Health; University of Calgary; University of Alberta","funders":"","keywords":"Cytotoxicity; Toxicity; In vivo; Acute toxicity; Computer science; Biological system; Pharmacology; Toxicology; Biology; Chemistry; In vitro; Biochemistry; Biotechnology","score_opus":0.02996827221963222,"score_gpt":0.3055107492716636,"score_spread":0.2755424770520314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2212557680","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":[0.2945754,0.00016970097,0.70405555,0.00068690977,0.00015951695,0.000058990943,0.000008809978,0.000010344837,0.00027475972],"genre_scores_gemma":[0.37465465,0.0000128212505,0.6249767,0.00025680597,0.00008474528,4.6738367e-7,0.0000049044,0.000004050126,0.0000048512793],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987149,0.00009709174,0.0006404445,0.00010617672,0.0002729392,0.00016843219],"domain_scores_gemma":[0.9985821,0.0004352159,0.00041327035,0.000075706885,0.00029598526,0.00019769241],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010839591,0.00012902732,0.00026868473,0.00019893165,0.000104531784,0.00013222604,0.00023557976,0.00006805334,0.0000021106778],"category_scores_gemma":[0.00012856029,0.000101987614,0.00005946938,0.00016069798,0.00011200413,0.0008657014,0.00015118076,0.00015497093,0.0000016392673],"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":[0.00019271435,0.00016722802,0.00835219,0.00013619094,0.0003927123,0.000028365486,0.00896604,0.5257353,0.00032132916,0.0896448,0.00041108252,0.36565205],"study_design_scores_gemma":[0.000579108,0.0002874654,0.0010316961,0.000024777122,0.000013591046,0.0006333732,0.000107195585,0.90268284,0.00003388239,0.094246544,0.0002519628,0.00010757517],"about_ca_topic_score_codex":0.0000046503515,"about_ca_topic_score_gemma":5.2310713e-7,"teacher_disagreement_score":0.37694752,"about_ca_system_score_codex":0.000045373166,"about_ca_system_score_gemma":0.00027554668,"threshold_uncertainty_score":0.4158934},"labels":[],"label_agreement":null},{"id":"W2294194070","doi":"10.1142/s0219720016410055","title":"Sequential construction of a model for modular gene expression control, applied to spatial patterning of the<i>Drosophila</i>gene<i>hunchback</i>","year":2016,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Gene Regulatory Network Analysis","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 Victoria; British Columbia Institute of Technology","funders":"National Institute of General Medical Sciences; National Institutes of Health; Russian Foundation for Basic Research","keywords":"Gene regulatory network; Gene; Biology; Computational biology; Cis-regulatory module; Regulation of gene expression; Genetics; Gene expression; Regulator gene; Regulatory sequence; Transcription factor; Translation (biology); Regulator; Gap gene; Transcription (linguistics); Messenger RNA; Promoter","score_opus":0.008403906487245838,"score_gpt":0.22243375229412654,"score_spread":0.2140298458068807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2294194070","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":[0.47778517,0.000051424362,0.52184516,0.000099819095,0.000062436484,0.0000842386,0.000066289824,6.299036e-7,0.0000048219154],"genre_scores_gemma":[0.9357207,0.000029281833,0.0639583,0.00013043705,0.00012595093,0.000003698333,0.000021751664,0.0000062191993,0.0000036517838],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989938,0.00003228252,0.0006385566,0.00009317231,0.00012895375,0.0001132128],"domain_scores_gemma":[0.9986972,0.00003671789,0.0007608222,0.00011335139,0.00033502257,0.00005688156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023944514,0.00010444938,0.0002652641,0.00007345748,0.000050560044,0.000005345193,0.00013920528,0.000102566875,0.000001671516],"category_scores_gemma":[0.000029608083,0.000063953004,0.00015785765,0.000049403894,0.00012467855,0.0000070434803,0.00007205642,0.000035084027,1.7737611e-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":[0.0002426344,0.000017961076,0.001430543,0.000021599444,0.0001298374,5.8281284e-8,0.000046098874,0.16617657,0.826559,0.0002970751,0.000053328167,0.0050253137],"study_design_scores_gemma":[0.0041972194,0.0007770481,0.0022768225,0.00008810108,0.0001920116,0.00009490984,0.00005150434,0.2735936,0.70895535,0.009274835,0.00024854712,0.0002500421],"about_ca_topic_score_codex":9.662184e-7,"about_ca_topic_score_gemma":0.0000010514414,"teacher_disagreement_score":0.45793554,"about_ca_system_score_codex":0.000010460954,"about_ca_system_score_gemma":0.00010487177,"threshold_uncertainty_score":0.26079276},"labels":[],"label_agreement":null},{"id":"W2301989113","doi":"10.1142/s0219720016500153","title":"Gene-set activity toolbox (GAT): A platform for microarray-based cancer diagnosis using an integrative gene-set analysis approach","year":2016,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"King Mongkut's University of Technology Thonburi; Mahidol University; Prince of Songkla University; Thailand Research Fund; University of Toronto; King Mongkut's Institute of Technology Ladkrabang; University of Notre Dame; National Center for Genetic Engineering and Biotechnology; Higher Education Research Promotion","keywords":"Toolbox; Computational biology; Microarray analysis techniques; Computer science; Gene expression profiling; Data mining; Data set; Microarray databases; Set (abstract data type); Gene; Bioinformatics; Gene expression; Biology; Artificial intelligence; Genetics","score_opus":0.042005073215708566,"score_gpt":0.32428068830936896,"score_spread":0.2822756150936604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2301989113","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5314922,0.0001988112,0.46769324,0.00012504781,0.00007000979,0.000096581694,0.00031282732,0.0000021265012,0.000009202172],"genre_scores_gemma":[0.9313293,0.0002545055,0.06762753,0.0003003752,0.00015533187,0.00004409613,0.0002695167,0.000008842723,0.0000105024965],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99904865,0.000049840848,0.00044600925,0.00017447637,0.00011280559,0.00016820258],"domain_scores_gemma":[0.9987075,0.00007119942,0.0006120833,0.00012970554,0.00036556693,0.00011398784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002759259,0.00016291511,0.00028696013,0.00022624638,0.000113030896,0.000035126912,0.00015986359,0.00015845198,0.000011500656],"category_scores_gemma":[0.000043969172,0.00010205123,0.00018933318,0.00016610436,0.00010894808,0.000033354372,0.000028518398,0.000065281594,2.8235428e-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":[0.0015625458,0.00045322263,0.026257254,0.000102601385,0.0022481587,0.0000010678133,0.0007410508,0.042624332,0.802986,0.00038903047,0.0026312328,0.120003484],"study_design_scores_gemma":[0.0062775845,0.0025813286,0.014085407,0.00010234703,0.0009467544,0.00009209957,0.0010669759,0.41337585,0.5482839,0.0015131711,0.010728011,0.0009465591],"about_ca_topic_score_codex":0.0000105722875,"about_ca_topic_score_gemma":0.000009160169,"teacher_disagreement_score":0.40006572,"about_ca_system_score_codex":0.000049199112,"about_ca_system_score_gemma":0.00027503548,"threshold_uncertainty_score":0.41615283},"labels":[],"label_agreement":null},{"id":"W2344448545","doi":"10.1142/s0219720016500190","title":"A novel Arg H52/Tyr H33 conservative motif in antibodies: A correlation between sequence of antibodies and antigen binding","year":2016,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McGill University","keywords":"Sequence motif; Antibody; Antigen; Sequence (biology); Motif (music); Molecular biology; Computational biology; Biology; Chemistry; Genetics; Physics; Gene","score_opus":0.05648765464284376,"score_gpt":0.3410180651211903,"score_spread":0.28453041047834654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2344448545","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98342174,0.0005488475,0.01382455,0.0017707415,0.00005059726,0.00012605744,0.00015497857,0.00000314639,0.000099332356],"genre_scores_gemma":[0.97690886,0.002059026,0.02080474,0.00010455743,0.000052392737,6.430974e-7,0.00003352867,0.0000046351533,0.000031594154],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99870783,0.000037709317,0.000782815,0.00008860693,0.00020723467,0.0001758008],"domain_scores_gemma":[0.9981769,0.0008105353,0.00050045893,0.00004648827,0.00036712218,0.00009853481],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047014587,0.0001221493,0.00046428136,0.000383746,0.000059108163,0.000012100641,0.000058656573,0.00009224983,0.000010173716],"category_scores_gemma":[0.00020067787,0.00007349556,0.000060030834,0.00015398664,0.0004210896,0.00019403952,0.0000675473,0.0001531908,0.0000024148694],"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":[0.00026789604,0.000059884176,0.9500204,0.00020287414,0.00018131439,0.000013487786,0.0009786487,0.000049430433,0.018412765,0.002638943,0.000054012045,0.02712035],"study_design_scores_gemma":[0.0026785072,0.0010432214,0.9736189,0.0009102981,0.00004031739,0.0007277661,0.00051595736,0.014667568,0.0008160129,0.0042601195,0.0005641122,0.00015719094],"about_ca_topic_score_codex":0.000029453504,"about_ca_topic_score_gemma":0.0000037940904,"teacher_disagreement_score":0.026963158,"about_ca_system_score_codex":0.000028032153,"about_ca_system_score_gemma":0.00016573221,"threshold_uncertainty_score":0.29970622},"labels":[],"label_agreement":null},{"id":"W2745681143","doi":"10.1142/s0219720017500196","title":"Systematic investigations of gene effects on both topologies and supports: An <i>Echinococcus</i> illustration","year":2017,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Phylogenetics; Network topology; Phylogenetic tree; Biology; Computational biology; Nuclear gene; Coalescent theory; Tree (set theory); Evolutionary biology; Genome; Echinococcus; Computer science; Gene; Mathematics; Genetics; Zoology","score_opus":0.013017846059582075,"score_gpt":0.2589808945093313,"score_spread":0.24596304844974926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2745681143","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9950829,0.0005596967,0.0037410723,0.00021449853,0.00011536475,0.00013406675,0.00002409479,8.6866226e-7,0.0001274412],"genre_scores_gemma":[0.9839306,0.00028169015,0.015464891,0.00021840996,0.00007164832,0.0000025758357,0.000021119087,0.000003642488,0.0000054089965],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9993102,0.000041352083,0.00043197378,0.00007197109,0.000064577915,0.00007994945],"domain_scores_gemma":[0.998894,0.000074020856,0.0007079636,0.00013209229,0.0001356554,0.000056303707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026340366,0.00009470125,0.0002346366,0.00005623015,0.00016552604,0.000037222188,0.00011952759,0.000075627,4.3984548e-7],"category_scores_gemma":[0.00017327182,0.00007007018,0.00004092878,0.000012845901,0.00020160354,0.0000070986525,0.00005199349,0.000049583192,1.8381992e-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":[0.0005097333,0.0004501477,0.099019244,0.009900416,0.0023155415,0.000014659119,0.004206823,0.008667838,0.779685,0.067118526,0.0009694702,0.02714259],"study_design_scores_gemma":[0.007713088,0.024775904,0.6768714,0.0021511896,0.00074001506,0.0013415401,0.003518271,0.02725484,0.1430926,0.10985321,0.0012030784,0.0014848686],"about_ca_topic_score_codex":0.0000039890633,"about_ca_topic_score_gemma":0.000002659446,"teacher_disagreement_score":0.6365924,"about_ca_system_score_codex":0.0000037797358,"about_ca_system_score_gemma":0.00005527864,"threshold_uncertainty_score":0.2857379},"labels":[],"label_agreement":null},{"id":"W2765700971","doi":"10.1142/s0219720017400078","title":"Reconstructing protein and gene phylogenies using reconciliation and soft-clustering","year":2017,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université de Sherbrooke","funders":"","keywords":"Supertree; Phylogenetic tree; Ensembl; Tree (set theory); Gene; Computational biology; Cluster analysis; Biology; Heuristic; Computer science; Phylogenetics; Genetics; Genome; Genomics; Artificial intelligence; Mathematics; Combinatorics","score_opus":0.021867856078774235,"score_gpt":0.2618437589356458,"score_spread":0.2399759028568716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765700971","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9869196,0.001148081,0.011579127,0.00014067387,0.00009040818,0.00006338611,0.000012104944,5.520639e-7,0.000046060075],"genre_scores_gemma":[0.9295486,0.00032113976,0.0699438,0.0000655219,0.00010840185,7.3164233e-7,0.0000036133513,0.00000381578,0.0000043734335],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99948114,0.00001551042,0.0002983879,0.00007743848,0.000038400794,0.000089134846],"domain_scores_gemma":[0.9992701,0.00001850846,0.00047763166,0.00006277088,0.0001269734,0.000044035638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022177282,0.0000843362,0.00014772147,0.000041150863,0.0002766566,0.00006697755,0.00006242598,0.00006534231,5.5106614e-7],"category_scores_gemma":[0.00008559134,0.00007196706,0.00002492593,0.000008806298,0.0001660091,0.0000064721953,0.00014081926,0.000049946346,7.880894e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019035181,0.000023529345,0.10425841,0.00017302399,0.00046640492,0.0000031417514,0.00091848837,0.0021974293,0.68208975,0.0007089167,0.000023937504,0.20894665],"study_design_scores_gemma":[0.008182098,0.004164396,0.25358936,0.00035584968,0.00028637127,0.00681872,0.0029442243,0.629672,0.043786418,0.043769322,0.004797315,0.0016339095],"about_ca_topic_score_codex":0.0000073762053,"about_ca_topic_score_gemma":0.0000037885527,"teacher_disagreement_score":0.6383033,"about_ca_system_score_codex":0.000004974892,"about_ca_system_score_gemma":0.000040340215,"threshold_uncertainty_score":0.29347312},"labels":[],"label_agreement":null},{"id":"W2899162278","doi":"10.1142/s0219720018400267","title":"HisCoM-GGI: Hierarchical structural component analysis of gene–gene interactions","year":2018,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Genetic Associations and Epidemiology","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":"McGill University","funders":"","keywords":"Missing heritability problem; Single-nucleotide polymorphism; Biology; Genome-wide association study; Genetics; Computational biology; Heritability; Genetic association; Gene; SNP; Population; Pairwise comparison; Genotype; Computer science; Medicine","score_opus":0.01236623746561531,"score_gpt":0.2945866825847948,"score_spread":0.2822204451191795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899162278","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9074187,0.00017314473,0.09162352,0.00030840718,0.00021825584,0.000041703064,0.00006831898,0.0000015762712,0.00014633144],"genre_scores_gemma":[0.9300457,0.000063699044,0.06919177,0.00026675223,0.00017521827,8.23711e-7,0.00023958752,0.0000036844933,0.000012760111],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988298,0.00008510708,0.00076211215,0.00009246636,0.00009152971,0.00013900922],"domain_scores_gemma":[0.9986344,0.00010341934,0.0006606357,0.000098092176,0.00042533403,0.00007811985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031622621,0.000102923965,0.00034333696,0.00026430973,0.00008926634,0.000009864133,0.00013233758,0.00010021104,0.000027798087],"category_scores_gemma":[0.00009826504,0.000081084756,0.00017228749,0.00017750781,0.0002497854,0.0000073811916,0.00006739767,0.00009607869,0.0000014558923],"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":[0.0010947434,0.0004992728,0.60280913,0.00008629443,0.018376905,0.000005929616,0.003533989,0.09206022,0.20678616,0.012101727,0.005232927,0.0574127],"study_design_scores_gemma":[0.0013974907,0.0023579786,0.6791529,0.000013913562,0.0007895858,0.0003187848,0.00040040704,0.3004309,0.0037052322,0.006609465,0.0044894502,0.00033392454],"about_ca_topic_score_codex":0.000008653913,"about_ca_topic_score_gemma":0.000012396117,"teacher_disagreement_score":0.20837066,"about_ca_system_score_codex":0.000014469835,"about_ca_system_score_gemma":0.00008247188,"threshold_uncertainty_score":0.33065403},"labels":[],"label_agreement":null},{"id":"W2945564624","doi":"10.1142/s0219720019500173","title":"DSRIG: Incorporating graphical structure in the regularized modeling of SNP data","year":2019,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Agricultural Adaptation Council; Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Agriculture, Food and Rural Affairs","keywords":"Single-nucleotide polymorphism; Boar taint; Selection (genetic algorithm); Lasso (programming language); Candidate gene; Androstenone; SNP; Trait; Regression; Computer science; Biology; Statistics; Mathematics; Computational biology; Genetics; Artificial intelligence; Gene; Genotype","score_opus":0.019015620116786917,"score_gpt":0.265093397625932,"score_spread":0.24607777750914506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945564624","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9329312,0.00028449477,0.066265404,0.00017146974,0.00009194989,0.000080546786,0.000036777375,5.7485016e-7,0.0001375946],"genre_scores_gemma":[0.8847725,0.000017450498,0.114874534,0.00016146949,0.000052361083,2.1959265e-7,0.00011723575,0.0000025068923,0.0000017155745],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992117,0.000056271212,0.00047668032,0.00007434063,0.00010330523,0.00007765828],"domain_scores_gemma":[0.99935406,0.000052938056,0.00030800042,0.00015881986,0.000103429484,0.000022768036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003846716,0.00007238041,0.00015686505,0.000060073413,0.000023921304,0.00001056199,0.0003133036,0.00009566264,0.0000035208272],"category_scores_gemma":[0.000043847856,0.000046049714,0.000032222557,0.00006917164,0.00007339907,0.000009288872,0.00010287938,0.00012717528,2.4451688e-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":[0.00071569893,0.00024213229,0.05252008,0.00030691526,0.00041701956,0.0000018407952,0.0020575216,0.6898945,0.02677893,0.20567785,0.000464671,0.020922815],"study_design_scores_gemma":[0.0025989055,0.0017325983,0.033289474,0.00007308021,0.000047033263,0.00038550043,0.0013434897,0.73052096,0.00020972229,0.22903231,0.00051412,0.0002528291],"about_ca_topic_score_codex":0.0000024549104,"about_ca_topic_score_gemma":0.0000027489957,"teacher_disagreement_score":0.048609134,"about_ca_system_score_codex":0.000001937315,"about_ca_system_score_gemma":0.00008669647,"threshold_uncertainty_score":0.18778528},"labels":[],"label_agreement":null},{"id":"W2964428942","doi":"10.1142/s0219720019400109","title":"Measuring consistency among gene set analysis methods: A systematic study","year":2019,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal University Hospital; University of Saskatchewan","funders":"Canadian Institutes of Health Research","keywords":"Gene; Computational biology; Consistency (knowledge bases); Set (abstract data type); Biology; Microarray analysis techniques; Data mining; Gene expression; Genetics; Bioinformatics; Computer science; Artificial intelligence","score_opus":0.0342293175648849,"score_gpt":0.3299604751487715,"score_spread":0.29573115758388663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964428942","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97112787,0.0021084214,0.026066033,0.00007478392,0.0000688285,0.00037158577,0.0000054219754,0.0000055844275,0.00017145304],"genre_scores_gemma":[0.96191674,0.00027628275,0.037697632,0.00006469616,0.000015419517,0.0000031822776,0.000010395936,0.000003818605,0.000011833144],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99853504,0.0001897781,0.0008354067,0.00006610418,0.00024182456,0.00013182407],"domain_scores_gemma":[0.99852556,0.00037232193,0.0004663198,0.00009720002,0.00041783557,0.00012073383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013500436,0.000094594754,0.00068149064,0.00048986805,0.000058683294,0.00004065105,0.00007351944,0.000042449454,0.000034098637],"category_scores_gemma":[0.00016542923,0.00006238583,0.00015746891,0.00026122437,0.00007287868,0.000118196156,0.000035847846,0.0001424127,0.0000089331825],"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":[0.00038601673,0.00049900904,0.9601163,0.0043186974,0.013403766,0.00005674248,0.00769656,0.0035812145,0.00069519936,0.001983204,0.00004453368,0.0072187213],"study_design_scores_gemma":[0.0110602705,0.008021585,0.49485636,0.0020591319,0.0013121885,0.0026548903,0.021862151,0.45139506,0.00020128652,0.005984411,0.00008812746,0.00050454837],"about_ca_topic_score_codex":0.0000073581755,"about_ca_topic_score_gemma":0.000002286121,"teacher_disagreement_score":0.46526,"about_ca_system_score_codex":0.000021715234,"about_ca_system_score_gemma":0.00009932408,"threshold_uncertainty_score":0.254402},"labels":[],"label_agreement":null},{"id":"W3008341390","doi":"10.1142/s0219720020500122","title":"Reanalysis of Alzheimer’s brain sequencing data reveals absence of purported HHV6A and HHV7","year":2020,"lang":"en","type":"letter","venue":"Journal of Bioinformatics and Computational Biology","topic":"HIV Research and Treatment","field":"Immunology and Microbiology","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 British Columbia","funders":"","keywords":"Shotgun sequencing; Variola virus; Smallpox; Biology; Disease; Shotgun; Computational biology; DNA sequencing; Virology; Genetics; Medicine; Gene; Pathology; Vaccination","score_opus":0.06476122469075482,"score_gpt":0.3092507797054867,"score_spread":0.24448955501473188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008341390","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15235133,0.06838877,0.02491318,0.7309605,0.001206198,0.0017490938,0.019141734,0.000046405814,0.0012428049],"genre_scores_gemma":[0.7790407,0.0061642923,0.060139365,0.122754425,0.0006883552,0.000009072309,0.030862054,0.00006551617,0.00027623714],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99805313,0.0001833389,0.0012944753,0.00015578346,0.000110302615,0.00020297932],"domain_scores_gemma":[0.99695563,0.00069945696,0.0017300938,0.00022007692,0.00035241005,0.00004233209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005061186,0.00018930242,0.0008568123,0.00033081986,0.00006360801,0.000012261977,0.00033990425,0.00034102512,0.000054414162],"category_scores_gemma":[0.00025363057,0.00013844277,0.00010977176,0.00014277603,0.00047106098,0.0001203134,0.00024439793,0.00065491966,0.000009511434],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026431872,0.00009776327,0.0034025388,0.0009653423,0.012877244,0.00023195201,0.0013621139,0.00013847018,0.010271413,0.0004463662,0.9327535,0.037188996],"study_design_scores_gemma":[0.02332353,0.01885679,0.021549394,0.003685918,0.009527172,0.0142813735,0.004242344,0.030363481,0.005566673,0.051414687,0.8136679,0.0035207223],"about_ca_topic_score_codex":0.000035120476,"about_ca_topic_score_gemma":0.00000188271,"teacher_disagreement_score":0.6266894,"about_ca_system_score_codex":0.000019124935,"about_ca_system_score_gemma":0.00033870176,"threshold_uncertainty_score":0.56455326},"labels":[],"label_agreement":null},{"id":"W3044308231","doi":"10.1142/s0219720020400077","title":"BENIN: Biologically enhanced network inference","year":2020,"lang":"en","type":"article","venue":"Journal of Bioinformatics and 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":"Concordia University","funders":"","keywords":"Inference; Computer science; Data mining; Resampling; Gene regulatory network; Machine learning; Artificial intelligence; Biological data; Feature selection; Biological network; Computational biology; Bioinformatics; Biology; Gene; Gene expression","score_opus":0.0187800215957247,"score_gpt":0.2738799799279997,"score_spread":0.25509995833227495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3044308231","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":[0.38379955,0.00085692084,0.6118675,0.00228318,0.00020033275,0.00008793243,0.0000109647235,0.0000065764793,0.00088702515],"genre_scores_gemma":[0.9737998,0.00034254885,0.02314672,0.002361072,0.00029198822,0.0000014845841,0.000044804056,0.0000032611424,0.000008278768],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993086,0.000035347482,0.00039470504,0.00008481432,0.00007036699,0.0001061545],"domain_scores_gemma":[0.9992771,0.000033273856,0.0003437452,0.000049355047,0.00018969717,0.0001068247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012947939,0.00008405351,0.00014480275,0.000027949016,0.0000509682,0.000018513936,0.00012749658,0.00009645511,0.000015720236],"category_scores_gemma":[0.00010758337,0.000061699466,0.00005401436,0.00008303032,0.00006995876,0.000007109228,0.00006479578,0.000086478314,0.0000036971885],"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":[0.0014625269,0.00016761404,0.01574854,0.00014235545,0.00047895344,0.0000045271927,0.0013266328,0.09023129,0.587129,0.027259462,0.030002069,0.24604702],"study_design_scores_gemma":[0.012044109,0.023730027,0.08938685,0.00026399377,0.00020277123,0.00046479347,0.0022814733,0.17235442,0.068007156,0.07108121,0.55776554,0.0024176321],"about_ca_topic_score_codex":1.8881191e-7,"about_ca_topic_score_gemma":1.7475438e-7,"teacher_disagreement_score":0.5900003,"about_ca_system_score_codex":0.0000037305078,"about_ca_system_score_gemma":0.000085839776,"threshold_uncertainty_score":0.25160313},"labels":[],"label_agreement":null},{"id":"W3166605709","doi":"10.1142/s0219720021400126","title":"Comparing the topology of phylogenetic network generators","year":2021,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Genomics and Phylogenetic Studies","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":"Simon Fraser University","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Government of Canada; Australian Government","keywords":"Phylogenetic network; Phylogenetic tree; Phylogenetics; Computational phylogenetics; Prior probability; Reticulate; Reticulate evolution; Bayesian network; Horizontal gene transfer","score_opus":0.013106485682164168,"score_gpt":0.23954018837405458,"score_spread":0.22643370269189042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3166605709","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98377293,0.0067569613,0.00858868,0.00028117292,0.00025728118,0.000037057438,0.000007727866,4.1394256e-7,0.00029778923],"genre_scores_gemma":[0.9808675,0.00080126396,0.017709835,0.00037158243,0.00022331154,8.139542e-7,0.00001382426,0.0000039374454,0.000007896871],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99923563,0.000058896898,0.00045807866,0.00006504374,0.00006164524,0.00012072828],"domain_scores_gemma":[0.9991774,0.000065026325,0.00033768103,0.000087697284,0.00029603142,0.000036161964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002322677,0.000083238396,0.00020979252,0.000025911364,0.00008128066,0.000010244966,0.00011417941,0.000064655775,0.000004062549],"category_scores_gemma":[0.00004220951,0.000057182246,0.00007708302,0.00006666324,0.00016814265,9.504775e-7,0.00012582779,0.00006554114,3.8077724e-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":[0.00031702546,0.0002352453,0.43650526,0.00017086665,0.0024007529,0.000013024908,0.0013619321,0.27200344,0.19370563,0.051378757,0.0063751074,0.03553297],"study_design_scores_gemma":[0.0073418613,0.0058616507,0.6176688,0.00013997573,0.00057453697,0.0043984405,0.003891365,0.061646815,0.07465638,0.11605614,0.1063863,0.001377736],"about_ca_topic_score_codex":0.000001488581,"about_ca_topic_score_gemma":0.0000052651153,"teacher_disagreement_score":0.21035662,"about_ca_system_score_codex":0.0000035363419,"about_ca_system_score_gemma":0.00011300365,"threshold_uncertainty_score":0.23318243},"labels":[],"label_agreement":null},{"id":"W3189850282","doi":"10.1142/s0219720021400096","title":"Small parsimony for natural genomes in the DCJ-indel model","year":2021,"lang":"en","type":"preprint","venue":"Journal of Bioinformatics and 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":"Simon Fraser University","funders":"","keywords":"Indel; Genome; Phylogenetic tree; Tree (set theory); Maximum parsimony; Biology; Gene duplication; Computational biology; Gene; Evolutionary biology; Genetics; Computer science; Algorithm; Combinatorics; Mathematics","score_opus":0.026352074951493613,"score_gpt":0.26751098967713766,"score_spread":0.24115891472564405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3189850282","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79377955,0.007963656,0.19629681,0.0009439637,0.00041509914,0.00039844526,0.000095039184,0.0000021116268,0.0001053273],"genre_scores_gemma":[0.84584475,0.001152864,0.15116823,0.000810359,0.00024072711,0.00001668261,0.0007323035,0.000011090638,0.000022973385],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988853,0.00005315211,0.0006348498,0.0001347122,0.00011453634,0.00017749675],"domain_scores_gemma":[0.99891,0.00007247556,0.0005146015,0.0001333807,0.00032955594,0.000039988117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055182807,0.00017689998,0.00029647932,0.00012141539,0.000051268256,0.000073429335,0.00032279943,0.00022763091,0.000001089985],"category_scores_gemma":[0.000051036935,0.0001247715,0.00018223662,0.000046244346,0.00007044049,0.000005498611,0.00024118621,0.0002839761,2.2632577e-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":[0.0004766244,0.0005045582,0.0044094194,0.0011460162,0.0016405403,0.000020802303,0.005776588,0.854935,0.005897915,0.0030383323,0.0026965241,0.11945772],"study_design_scores_gemma":[0.0019433217,0.0006660376,0.0023613374,0.00008867993,0.000111272406,0.00024412418,0.0021324675,0.967231,0.00021253769,0.021935701,0.0026357614,0.00043778773],"about_ca_topic_score_codex":0.0000017608797,"about_ca_topic_score_gemma":0.000009392935,"teacher_disagreement_score":0.11901993,"about_ca_system_score_codex":0.00001880039,"about_ca_system_score_gemma":0.00030710406,"threshold_uncertainty_score":0.50880337},"labels":[],"label_agreement":null},{"id":"W3201936911","doi":"10.1142/s0219720021500268","title":"Compression for population genetic data through finite-state entropy","year":2021,"lang":"en","type":"article","venue":"Journal of Bioinformatics and 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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data compression; Computation; Population; Entropy (arrow of time); Data mining; Theoretical computer science; Artificial intelligence; Algorithm","score_opus":0.03354631748808762,"score_gpt":0.3029123453269183,"score_spread":0.2693660278388307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201936911","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":[0.00904484,0.00062825077,0.98925763,0.00048581863,0.00037904238,0.000065067725,0.000108308835,0.000008714611,0.000022330967],"genre_scores_gemma":[0.08164447,0.00023390999,0.917107,0.00045485597,0.00009535207,9.041375e-7,0.00045159674,0.0000034373388,0.00000847801],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989768,0.000042839572,0.0005728714,0.00012961496,0.0001506018,0.00012723789],"domain_scores_gemma":[0.99853045,0.00038675635,0.0004648614,0.00024213904,0.00031773868,0.000058076894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002026307,0.000089959976,0.00019868951,0.000062452316,0.00012580321,0.00011368756,0.00045893792,0.00004820405,0.0000043497053],"category_scores_gemma":[0.000091532565,0.000067693036,0.000041978456,0.00010414252,0.000028294224,0.0007404661,0.00043973743,0.00008654092,0.0000017258066],"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":[0.00012852426,0.00031063397,0.0030572065,0.00023491606,0.0002415369,0.000061380815,0.001338602,0.11228961,0.00048509752,0.100902684,0.008998459,0.7719514],"study_design_scores_gemma":[0.00060511206,0.00014294357,0.0028916523,0.000035443292,0.000009207252,0.00022489854,0.000020312338,0.9077984,0.000044637378,0.07821823,0.009924853,0.00008428916],"about_ca_topic_score_codex":0.00000395009,"about_ca_topic_score_gemma":6.653696e-7,"teacher_disagreement_score":0.7955088,"about_ca_system_score_codex":0.000010317073,"about_ca_system_score_gemma":0.00010338433,"threshold_uncertainty_score":0.2760442},"labels":[],"label_agreement":null},{"id":"W3204767928","doi":"10.1142/s0219720021400102","title":"Colorful orthology clustering in bounded-degree similarity graphs","year":2021,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Bioinformatics and Genomic Networks","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":"Université de Sherbrooke","funders":"","keywords":"Cluster analysis; Bounded function; Similarity (geometry); Single-linkage clustering; Graph; Complete-linkage clustering; Computer science; Cluster (spacecraft); Combinatorics; Mathematics; Theoretical computer science; Correlation clustering; Artificial intelligence; CURE data clustering algorithm","score_opus":0.015041494555418982,"score_gpt":0.2547225072202825,"score_spread":0.23968101266486352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204767928","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8380928,0.0016787732,0.15707359,0.0007165219,0.00048045526,0.00010525107,0.00003078213,0.0000041508642,0.0018176965],"genre_scores_gemma":[0.94122267,0.0004976265,0.056820523,0.0012074425,0.00010129207,0.0000015323745,0.00011452637,0.0000074600785,0.000026943964],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988159,0.00005355573,0.0007399915,0.00010137163,0.000086128275,0.00020307493],"domain_scores_gemma":[0.99915165,0.000054407235,0.00036194743,0.0001062454,0.00024333158,0.000082417115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000424568,0.00012816547,0.00026589798,0.000119657416,0.0000637416,0.000036697995,0.00012638525,0.00020137729,0.000011468679],"category_scores_gemma":[0.00006601974,0.000113921364,0.00009228985,0.00011941778,0.00012661649,0.0000145940585,0.00015684878,0.00019904562,0.0000018931556],"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":[0.0020551526,0.0012910457,0.17582601,0.0009899964,0.0019694497,0.00043446932,0.0046488834,0.11107612,0.022029135,0.13550386,0.0119473515,0.5322285],"study_design_scores_gemma":[0.015462748,0.005610112,0.12377393,0.00032446557,0.00019742246,0.013695523,0.0041006333,0.34648687,0.0021152573,0.38479593,0.10127793,0.0021591666],"about_ca_topic_score_codex":0.0000026650414,"about_ca_topic_score_gemma":0.000059463877,"teacher_disagreement_score":0.53006935,"about_ca_system_score_codex":0.000014962283,"about_ca_system_score_gemma":0.00020726069,"threshold_uncertainty_score":0.46455786},"labels":[],"label_agreement":null},{"id":"W3214208812","doi":"10.1142/s0219720021400072","title":"BOPAL 2.0 and a study of tRNA and rRNA gene evolution in <i>Clostridium</i>","year":2021,"lang":"en","type":"article","venue":"Journal of Bioinformatics and 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":"University of Manitoba","funders":"","keywords":"Gene; Transfer RNA; Ribosomal RNA; Genome; Phylogenetics; Genome evolution; Molecular evolution","score_opus":0.00720873067538824,"score_gpt":0.2322406395318946,"score_spread":0.22503190885650637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214208812","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99484515,0.003824425,0.0010655287,0.000098252465,0.000054453685,0.00005635697,0.000013911889,2.5357954e-7,0.000041682415],"genre_scores_gemma":[0.9940916,0.00092714134,0.004866748,0.00006127861,0.000039315506,8.039978e-7,0.000007667593,0.0000025720926,0.0000029147589],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993684,0.000036080975,0.00039404293,0.00007300944,0.00005343196,0.00007500685],"domain_scores_gemma":[0.99951756,0.00003428025,0.0002121029,0.00004245917,0.00015619416,0.000037400925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017502405,0.00007193396,0.00018427019,0.000063836895,0.00003283891,0.0000093666595,0.000034985347,0.00005241693,6.1695494e-7],"category_scores_gemma":[0.000037533493,0.00006104453,0.000021923177,0.0000525032,0.00006732135,0.0000022732377,0.00009047072,0.000052570773,5.3425723e-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":[0.0005437373,0.00082025066,0.5559367,0.00018690442,0.00075085583,0.000026147369,0.0037871858,0.0045811995,0.40256715,0.002402574,0.00017957552,0.0282177],"study_design_scores_gemma":[0.0077344957,0.005869769,0.9497138,0.000050837294,0.000112671914,0.0013533127,0.006136617,0.007339737,0.01030083,0.010072181,0.00094282354,0.00037289702],"about_ca_topic_score_codex":0.0000078188295,"about_ca_topic_score_gemma":0.000016059344,"teacher_disagreement_score":0.3937771,"about_ca_system_score_codex":0.0000049405007,"about_ca_system_score_gemma":0.00006832312,"threshold_uncertainty_score":0.24893236},"labels":[],"label_agreement":null},{"id":"W3216894728","doi":"10.1142/s0219720021400084","title":"The monoploid chromosome complement of reconstructed ancestral genomes in a phylogeny","year":2021,"lang":"en","type":"article","venue":"Journal of Bioinformatics and 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 Saskatchewan; University of Ottawa","funders":"","keywords":"Genome; Extant taxon; Phylogenetics; Ancestor; Complement (music); Ploidy","score_opus":0.011550101814240892,"score_gpt":0.2524576239165685,"score_spread":0.2409075221023276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216894728","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99361175,0.0032698673,0.0025210297,0.0002440378,0.00012408158,0.00006606494,0.000028269153,7.5641503e-7,0.00013411984],"genre_scores_gemma":[0.9734649,0.0014979284,0.024829915,0.00007201597,0.00006159914,0.0000015180744,0.00005812878,0.0000034473615,0.000010570984],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99913776,0.0000429734,0.0005564419,0.000060254588,0.000081593054,0.00012095794],"domain_scores_gemma":[0.9992599,0.000047866462,0.00035366122,0.00006948264,0.00023324316,0.00003588434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024100252,0.00007347194,0.00016468538,0.00005451957,0.000043777534,0.000014931234,0.00010677975,0.000048439102,0.000007242775],"category_scores_gemma":[0.00003050967,0.000052955147,0.000056224977,0.0000850531,0.000118617725,0.0000054701336,0.000065267566,0.00006730675,4.986005e-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":[0.0005024431,0.00049245055,0.15755594,0.0003284414,0.0016314954,0.000038114784,0.0016464415,0.013810238,0.44522625,0.013067073,0.00090943405,0.36479166],"study_design_scores_gemma":[0.019514307,0.008844026,0.617441,0.000333016,0.00022938657,0.005017853,0.010887678,0.078325294,0.08649759,0.075328946,0.09587673,0.0017041715],"about_ca_topic_score_codex":0.000001353681,"about_ca_topic_score_gemma":0.00000885214,"teacher_disagreement_score":0.45988506,"about_ca_system_score_codex":0.000010439403,"about_ca_system_score_gemma":0.00015656192,"threshold_uncertainty_score":0.21594483},"labels":[],"label_agreement":null},{"id":"W4281385537","doi":"10.1142/s0219720022500123","title":"Invariant transformers of Robinson and Foulds distance matrices for Convolutional Neural Network","year":2022,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Evolution and Paleontology Studies","field":"Earth and Planetary Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Fonds de Recherche du Québec - Santé","keywords":"Phylogenetic tree; Tree rearrangement; Distance matrices in phylogeny; Distance matrix; Convolutional neural network; Tree (set theory); Artificial intelligence; Supertree; Phylogenetic network; Set (abstract data type); Invariant (physics); Phylogenetics; Inference; Computer science; Mathematics; Algorithm; Biology; Combinatorics; Gene","score_opus":0.014108761810670247,"score_gpt":0.23022461871044725,"score_spread":0.216115856899777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281385537","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.834041,0.02064851,0.13850664,0.003249359,0.0010631608,0.00033725915,0.0009504771,0.000008993943,0.0011945853],"genre_scores_gemma":[0.9860883,0.00027277303,0.013268122,0.00025998682,0.000043575288,7.550011e-7,0.00006033231,7.0564886e-7,0.000005454217],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993363,0.000038866576,0.00038510657,0.00004383748,0.000089625086,0.000106263156],"domain_scores_gemma":[0.9991677,0.00037670686,0.0003214013,0.000014928521,0.00007955285,0.000039751645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033632587,0.00005867263,0.00017809721,0.000066867266,0.00023523631,0.0000073166875,0.000058725087,0.000026297655,0.000043147378],"category_scores_gemma":[0.000014620548,0.000045124783,0.000043446777,0.00007647661,0.00015162352,0.00008775568,0.000009085545,0.00008546707,1.8181568e-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":[0.00073388865,0.000034973094,0.634489,0.0001446861,0.00025576193,0.000002380991,0.0012549406,0.2919827,0.000005118404,0.030304816,0.0025985627,0.038193196],"study_design_scores_gemma":[0.0010435837,0.0012320641,0.33955196,0.000009227388,0.0000382024,0.00028733155,0.001029429,0.6314551,4.7227977e-7,0.017253395,0.007998395,0.000100838806],"about_ca_topic_score_codex":0.000015224889,"about_ca_topic_score_gemma":0.00010983191,"teacher_disagreement_score":0.33947238,"about_ca_system_score_codex":0.0000032573648,"about_ca_system_score_gemma":0.00005106194,"threshold_uncertainty_score":0.18401352},"labels":[],"label_agreement":null},{"id":"W4397003240","doi":"10.1142/s0219720024500112","title":"Body plan evolvability: The role of variability in gene regulatory networks","year":2024,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Animal Genetics and Reproduction","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":"British Columbia Institute of Technology","funders":"","keywords":"Evolvability; Body plan; Gene regulatory network; Gene; Plan (archaeology); Biology; Computational biology; Regulator gene; Genetics; Evolutionary biology; Regulation of gene expression; Gene expression","score_opus":0.004502595958025534,"score_gpt":0.22243530743384907,"score_spread":0.21793271147582352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4397003240","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.943568,0.004618977,0.051087204,0.00020039482,0.00023278,0.00008828969,0.000011721118,0.0000020330401,0.00019063614],"genre_scores_gemma":[0.9967263,0.00031631894,0.0026957425,0.000042556192,0.00018352394,0.00000105071,0.00002396706,0.0000037517364,0.0000067851074],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992096,0.00007927364,0.00046312448,0.000089486006,0.000073234325,0.00008527618],"domain_scores_gemma":[0.999518,0.00007734515,0.00015801952,0.00009551811,0.0001223923,0.000028730958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011456356,0.00007085423,0.00012891351,0.000057763726,0.000029122943,0.00001427101,0.00009006413,0.00009527586,0.0000032777912],"category_scores_gemma":[0.00006380385,0.000044881035,0.000062533334,0.00007947056,0.00014405373,0.000006039475,0.00005452005,0.000111741625,3.2417773e-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":[0.0008822865,0.00046187843,0.066958845,0.0003422934,0.0008484889,0.0000072078406,0.0017292089,0.17124186,0.29268238,0.05181647,0.0009485285,0.41208053],"study_design_scores_gemma":[0.00057949463,0.0015274114,0.09290576,0.0000772582,0.00006782775,0.0005068621,0.0005014419,0.8205125,0.013908128,0.05644061,0.012709607,0.0002631325],"about_ca_topic_score_codex":0.0000029096623,"about_ca_topic_score_gemma":9.198127e-7,"teacher_disagreement_score":0.6492706,"about_ca_system_score_codex":0.000009153926,"about_ca_system_score_gemma":0.00009236994,"threshold_uncertainty_score":0.18301955},"labels":[],"label_agreement":null},{"id":"W4410642778","doi":"10.1142/s0219720025500076","title":"An algorithm for peptide de novo sequencing from a group of SILAC labeled MS/MS spectra","year":2025,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Stable isotope labeling by amino acids in cell culture; Shotgun proteomics; Tandem mass spectrometry; Proteomics; Peptide; Mass spectrometry; Computational biology; Chemistry; Bottom-up proteomics; Peptide sequence; Shotgun; Biology; Chromatography; Protein mass spectrometry; Biochemistry","score_opus":0.01027624271425914,"score_gpt":0.28816092053916004,"score_spread":0.2778846778249009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410642778","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":[0.22704427,0.000083459025,0.7722468,0.00010598336,0.000019444244,0.000058960413,0.00014888692,0.000008572144,0.00028364488],"genre_scores_gemma":[0.1976627,0.000057794045,0.80196935,0.00014181639,0.00005910614,0.000007394063,0.000087551954,0.0000038018577,0.000010471526],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925935,0.000006677332,0.0005176806,0.00006117546,0.00005099923,0.0001041268],"domain_scores_gemma":[0.9990847,0.000205425,0.00041807943,0.0000713081,0.00017571184,0.000044773416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015036981,0.00007971981,0.00020188358,0.00007296363,0.00006184686,0.000015326887,0.00013161426,0.000085732434,0.00001442548],"category_scores_gemma":[0.00002133036,0.0000694207,0.00006181189,0.00006225071,0.000060787745,0.000087345696,0.000023168173,0.00011692366,1.8198675e-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":[0.00028570602,0.00039691242,0.0036479426,0.0004811636,0.00062263774,0.0000051095394,0.0014768683,0.009317867,0.5353606,0.16674122,0.00053069484,0.2811333],"study_design_scores_gemma":[0.0011888338,0.00026237828,0.00022306688,0.00011645317,0.000054696775,0.000064642845,0.000393535,0.5660077,0.04265111,0.38724425,0.0016489195,0.00014441676],"about_ca_topic_score_codex":0.000013587177,"about_ca_topic_score_gemma":0.0000023239702,"teacher_disagreement_score":0.55668986,"about_ca_system_score_codex":0.0000561912,"about_ca_system_score_gemma":0.00012284015,"threshold_uncertainty_score":0.2830894},"labels":[],"label_agreement":null},{"id":"W4412923866","doi":"10.1142/s0219720025500106","title":"Visual-SELEX: a technology ensemble for evaluating aptamer structural similarity via 3D visual spatial conformational analysis","year":2025,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Cell Image Analysis Techniques","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":"Discovery Centre","funders":"","keywords":"Aptamer; Systematic evolution of ligands by exponential enrichment; Artificial intelligence; Similarity (geometry); Visualization; Pattern recognition (psychology); Computer science; Structural similarity; Computational biology; Biology; Genetics; Image (mathematics)","score_opus":0.007414970158243245,"score_gpt":0.3394696976078277,"score_spread":0.3320547274495844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412923866","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":[0.31749237,0.00020332614,0.6817552,0.0001962018,0.000044683817,0.00014260602,0.00001355528,0.000008167238,0.00014391405],"genre_scores_gemma":[0.89357674,0.000039927654,0.10536386,0.0005137622,0.00007246783,0.000009474838,0.00038807257,0.0000057569478,0.000029944236],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846643,0.000052621235,0.00095612457,0.00015525983,0.00016223875,0.0002073034],"domain_scores_gemma":[0.99800324,0.0001220126,0.0007100988,0.000107087064,0.0010006548,0.000056880144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059428305,0.0001814176,0.00043055374,0.0007516514,0.00016760596,0.000051962426,0.00017989312,0.00023857044,0.00001188184],"category_scores_gemma":[0.00023067674,0.00015598765,0.00025069024,0.00043102057,0.00017710579,0.00002669098,0.00013328707,0.00015364711,7.639515e-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":[0.0018502985,0.00046138815,0.054589543,0.00045143533,0.013818342,0.0000053301674,0.00041968832,0.041151628,0.1592204,0.010445516,0.0036671597,0.7139193],"study_design_scores_gemma":[0.0012582218,0.0012584305,0.0033477554,0.00001722046,0.00068793946,0.00006345919,0.00016123673,0.9719887,0.01071864,0.008584422,0.0016753725,0.00023862359],"about_ca_topic_score_codex":0.000008461147,"about_ca_topic_score_gemma":0.000011811563,"teacher_disagreement_score":0.93083704,"about_ca_system_score_codex":0.00002858336,"about_ca_system_score_gemma":0.00021826455,"threshold_uncertainty_score":0.63609916},"labels":[],"label_agreement":null}]}