{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":95,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":95,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"0b96b08e201c","filters":{"venue":"Journal of Bioinformatics and Computational Biology"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.005385294288186872,"gpt":0.2418866384724174,"spread":0.2365013441842305,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002576631,0.0001061672,0.000151256,0.00005288361,0.00007044991,0.00002337907,0.0001163795,0.0001170394,0.000004038567],"category_scores_gemma":[0.000102995,0.00008328072,0.00006186367,0.00005031105,0.00008219203,0.00001083333,0.00004283708,0.0001070999,9.980672e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007866383,"about_ca_system_score_gemma":0.0000889607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.784724e-7,"about_ca_topic_score_gemma":2.845483e-7,"domain_scores_codex":[0.9992791,0.00003336788,0.000383409,0.00007567245,0.00008396312,0.0001444369],"domain_scores_gemma":[0.9993857,0.00001575014,0.0002982632,0.00007852899,0.0001479113,0.00007382937],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00167993,0.0007151511,0.01352733,0.0006026555,0.002141629,0.00003098168,0.001715655,0.03206709,0.49441,0.1415784,0.01057184,0.3009593],"study_design_scores_gemma":[0.0114767,0.0165782,0.0008084236,0.00026744,0.0002217833,0.005018349,0.001922018,0.0974772,0.129699,0.07070688,0.6634021,0.002421899],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6413356,0.001180445,0.3567276,0.0001287255,0.0001121436,0.0001563282,0.00001830224,0.000004258682,0.0003366068],"genre_scores_gemma":[0.7163395,0.00005803863,0.2832508,0.0001691749,0.00007875715,0.000002776936,0.0000635551,0.000006907958,0.00003049713],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6528302,"threshold_uncertainty_score":0.3396089,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01108296267543167,"gpt":0.2464544238746993,"spread":0.2353714611992676,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002782641,0.00008451053,0.0002218243,0.0003113805,0.0001203682,0.00005809373,0.0001981006,0.00006405447,0.000003777855],"category_scores_gemma":[0.00003131901,0.00005609251,0.00004844918,0.0002491141,0.0001591194,0.0002783682,0.0002884979,0.0001396548,0.00000569099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001566535,"about_ca_system_score_gemma":0.00005110879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001623403,"about_ca_topic_score_gemma":0.000001389304,"domain_scores_codex":[0.9992189,0.00003493366,0.0003880688,0.00009178992,0.00012091,0.0001453708],"domain_scores_gemma":[0.9992833,0.000156495,0.0001962849,0.0000670593,0.0001995524,0.00009730808],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006415814,0.0002915802,0.005135865,0.00004761014,0.0005157046,0.0001480656,0.004676554,0.0145182,0.0002236602,0.5432392,0.0003595729,0.4307798],"study_design_scores_gemma":[0.006760806,0.009252112,0.2047695,0.0001023922,0.0001340886,0.01087304,0.001609517,0.309951,0.0006665055,0.4505881,0.004314837,0.0009779815],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3620874,0.0001053494,0.6339501,0.003635868,0.00007696646,0.00002287627,0.00001386684,0.000005475261,0.000102118],"genre_scores_gemma":[0.9137625,0.00009322923,0.08505571,0.001030957,0.00003796385,2.533086e-7,0.00000936139,0.00000118988,0.00000887199],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.551675,"threshold_uncertainty_score":0.2287386,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02106295977740671,"gpt":0.2886165250035087,"spread":0.267553565226102,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001546866,0.00009342268,0.0001509491,0.00004530614,0.0001039253,0.00003462086,0.0001263552,0.00007651613,0.00001351616],"category_scores_gemma":[0.00005599511,0.00007448206,0.00003814614,0.00005652034,0.00007203313,0.0001943652,0.00002000048,0.0001277519,0.000001414109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009126718,"about_ca_system_score_gemma":0.0001616882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004250966,"about_ca_topic_score_gemma":0.0000022144,"domain_scores_codex":[0.9992181,0.000005251888,0.0004969251,0.0000801169,0.0000789159,0.0001206959],"domain_scores_gemma":[0.9988296,0.00009905844,0.0006289744,0.00007846984,0.0003060081,0.00005785797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004958736,0.0002445225,0.002711826,0.0004941821,0.0003012584,0.000005732489,0.001975368,0.07340942,0.6475952,0.0464915,0.0004625802,0.2258126],"study_design_scores_gemma":[0.002865173,0.0006378797,0.000241709,0.0004396632,0.0001207791,0.0008416473,0.0008891415,0.4355762,0.2244607,0.313185,0.02002792,0.0007142203],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3158525,0.00005926822,0.6832618,0.0005388982,0.000006612708,0.0001059169,0.0001180227,0.00001636245,0.00004061325],"genre_scores_gemma":[0.3827417,0.00001409225,0.616873,0.0001652071,0.00008021114,0.00002490357,0.00007869518,0.000005571759,0.00001654563],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4231344,"threshold_uncertainty_score":0.3037291,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02648686374133342,"gpt":0.2677644995817309,"spread":0.2412776358403975,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003700813,0.0001250267,0.0003641345,0.0001940672,0.00004441084,0.00001173155,0.00009145174,0.0001622042,4.06508e-7],"category_scores_gemma":[0.00004158734,0.0001071863,0.00009574243,0.0001054914,0.00009727175,0.00001305911,0.00006898602,0.00007064725,5.983001e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001492722,"about_ca_system_score_gemma":0.0001211189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001880653,"about_ca_topic_score_gemma":9.147738e-7,"domain_scores_codex":[0.9987593,0.00005466185,0.0008579495,0.0001043471,0.00009877158,0.0001250213],"domain_scores_gemma":[0.9989079,0.00002938714,0.0005755126,0.00008897077,0.0003404901,0.00005776473],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003846788,0.0000243169,0.0004462575,0.00005999079,0.0002050932,3.737689e-7,0.00009547715,0.9820989,0.01500322,0.001306663,2.535651e-7,0.0007210162],"study_design_scores_gemma":[0.000606047,0.0003142685,0.00001949512,0.00003957002,0.00008137962,0.00007938366,0.0001936753,0.9926808,0.0007288253,0.005153422,0.000005499792,0.00009760578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5098473,0.002071269,0.4879862,0.00001232895,0.00002795496,0.00004117941,0.00000661849,7.877351e-7,0.000006339826],"genre_scores_gemma":[0.9565533,0.0001475745,0.04318351,0.00002190139,0.00004409215,4.913934e-7,0.00004161002,0.00000705885,3.995656e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4467061,"threshold_uncertainty_score":0.437093,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.006049518886673946,"gpt":0.2446643282240557,"spread":0.2386148093373818,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001782181,0.00009858616,0.0001288158,0.0001154868,0.00008270484,0.00004346365,0.00008003208,0.0001038899,0.000005971649],"category_scores_gemma":[0.00001897393,0.00007961861,0.000059303,0.00007871076,0.00009597154,0.00001366746,0.00002584785,0.00007291987,0.000002114461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001503989,"about_ca_system_score_gemma":0.0001113594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005287056,"about_ca_topic_score_gemma":0.000001057667,"domain_scores_codex":[0.999179,0.0000452089,0.0004841624,0.00008640389,0.00009483375,0.0001103865],"domain_scores_gemma":[0.9992211,0.00002186508,0.0003887628,0.00005773277,0.0002572289,0.00005335129],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005031542,0.0002404509,0.006161143,0.000120511,0.0001800041,0.000004986399,0.000404131,0.1189288,0.6316649,0.01197848,0.01419138,0.215622],"study_design_scores_gemma":[0.009976918,0.004402152,0.09738699,0.0003310205,0.0001878333,0.002409625,0.002505798,0.4932606,0.1400431,0.0742644,0.1736167,0.001614887],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.370987,0.000817139,0.6269495,0.0006221251,0.0001807196,0.00005700483,0.00001165103,0.000004348587,0.0003704721],"genre_scores_gemma":[0.9798067,0.00004584371,0.01938833,0.0003273437,0.000213979,0.000001135517,0.0001769486,0.000005987403,0.00003375803],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6088197,"threshold_uncertainty_score":0.3246753,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01300303195621904,"gpt":0.2543864281263891,"spread":0.24138339617017,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000167755,0.00009203564,0.0001623,0.0000652588,0.0001040281,0.0000158463,0.00008685487,0.00008122175,7.64809e-7],"category_scores_gemma":[0.00006242585,0.00007502225,0.00008701363,0.00003531339,0.00009927523,0.000001920914,0.00005210492,0.00005163086,5.753518e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000102006,"about_ca_system_score_gemma":0.0001040605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001489654,"about_ca_topic_score_gemma":0.000001475382,"domain_scores_codex":[0.9994162,0.000009810251,0.0003292037,0.00006850761,0.00004610749,0.0001301923],"domain_scores_gemma":[0.9993196,0.00003975432,0.0002521831,0.00005276962,0.0002796094,0.00005613794],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001489693,0.0005181515,0.005342582,0.0003329444,0.002641482,0.00001644571,0.003825354,0.5137068,0.2433277,0.1908875,0.007325429,0.03058587],"study_design_scores_gemma":[0.04963429,0.04756755,0.0539315,0.0004268811,0.001052059,0.0121509,0.01139934,0.068804,0.06763922,0.4638076,0.2193066,0.004280028],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7205101,0.0007757199,0.2773775,0.0008897817,0.0001807733,0.0001010267,0.00003455039,0.000001240082,0.0001294269],"genre_scores_gemma":[0.8799034,0.0003234087,0.1191946,0.000377112,0.0001502625,0.000002878518,0.0000285483,0.000005422943,0.00001434757],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4449028,"threshold_uncertainty_score":0.3059319,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02296125878695445,"gpt":0.2901927437328728,"spread":0.2672314849459184,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006048594,0.0001604573,0.0003636507,0.0002235233,0.0001984447,0.00006692867,0.0003798081,0.000132836,0.00002165797],"category_scores_gemma":[0.00008440673,0.0001106849,0.00007552905,0.0003181148,0.0002013604,0.0001974367,0.0001499722,0.0003114966,0.000001526413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002741861,"about_ca_system_score_gemma":0.00007993413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003478577,"about_ca_topic_score_gemma":5.989207e-7,"domain_scores_codex":[0.9986916,0.00002874581,0.0008482718,0.0001245972,0.0001049568,0.0002018167],"domain_scores_gemma":[0.9982275,0.0003326969,0.0009199138,0.0002887583,0.000137823,0.00009333059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002687678,0.0006028108,0.2669654,0.002020537,0.009716545,0.00001561076,0.003777469,0.02081556,0.1266957,0.3752892,0.002056909,0.1917755],"study_design_scores_gemma":[0.002072779,0.0004141727,0.001738615,0.00006967739,0.001387363,0.0003770792,0.00118788,0.695576,0.02603717,0.2542849,0.01594969,0.0009046035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09268314,0.0002971398,0.904947,0.0004961428,0.00002140242,0.0001124843,0.0002795501,0.00001408718,0.001149039],"genre_scores_gemma":[0.3738279,0.0003528227,0.6254478,0.000108631,0.00005953934,0.000003266909,0.0001858608,0.000006133746,0.000007969124],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6747605,"threshold_uncertainty_score":0.4513598,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008418978132512304,"gpt":0.2292975718756665,"spread":0.2208785937431542,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001531719,0.00007185136,0.0001193276,0.00004543195,0.00006277949,0.000006845316,0.0001006438,0.00005561756,0.000002738369],"category_scores_gemma":[0.00005403061,0.0000451483,0.00005377521,0.00003916841,0.0001374757,0.000001178177,0.00005318515,0.00006039352,7.761117e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000481971,"about_ca_system_score_gemma":0.00007535839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005669093,"about_ca_topic_score_gemma":0.000001449919,"domain_scores_codex":[0.9994165,0.00002433555,0.000357934,0.00004647348,0.00007540024,0.00007930068],"domain_scores_gemma":[0.9992841,0.0001236687,0.0003149691,0.00006014808,0.0001971936,0.0000198892],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0009032792,0.0007807867,0.1170683,0.0001581327,0.001173838,0.000005932249,0.0009042171,0.3348611,0.0863542,0.403952,0.01984896,0.03398924],"study_design_scores_gemma":[0.004081783,0.00800884,0.3652798,0.0001425184,0.0001401654,0.0004539498,0.000978361,0.09401352,0.007524954,0.4990018,0.01955968,0.0008146854],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9905886,0.0008389433,0.007581854,0.0003910041,0.00008198225,0.00005292964,0.00002524803,4.524013e-7,0.0004389578],"genre_scores_gemma":[0.9952505,0.0001439105,0.004275058,0.0002424979,0.00006141424,9.567691e-7,0.00001410492,0.000002551319,0.00000904841],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2482115,"threshold_uncertainty_score":0.1841094,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01843663717349181,"gpt":0.3028210396366478,"spread":0.284384402463156,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002586746,0.00008852001,0.0001248368,0.0000645824,0.00006913213,0.00002073622,0.000216878,0.00009202177,0.000004618199],"category_scores_gemma":[0.00003045955,0.00007094177,0.00004625006,0.00003086673,0.00004401294,0.00001788089,0.0000891903,0.00005214856,0.000001557668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001098292,"about_ca_system_score_gemma":0.0001620649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.978795e-8,"about_ca_topic_score_gemma":6.393782e-7,"domain_scores_codex":[0.9993083,0.00001793747,0.0003817946,0.0001092527,0.00007852483,0.0001042253],"domain_scores_gemma":[0.9992405,0.00002575451,0.0003311185,0.0001668624,0.0001710935,0.00006468586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003244095,0.0001115872,0.0001087857,0.00004766103,0.00006389058,2.187426e-7,0.00007250984,0.5115602,0.4041039,0.00008313604,0.007742705,0.07578098],"study_design_scores_gemma":[0.000839658,0.0001999835,0.0001122436,0.00001723272,0.00001682629,0.00002475101,0.00002329751,0.984911,0.005605751,0.0003582248,0.007801624,0.00008941311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05722344,0.0005213713,0.9412156,0.0007270547,0.00007855304,0.00009153145,0.00008848548,0.000003269342,0.00005071945],"genre_scores_gemma":[0.6066876,0.00007843267,0.3920031,0.0004991284,0.0001092945,0.000003341627,0.0005660161,0.000007009536,0.00004606484],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5494642,"threshold_uncertainty_score":0.2892922,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.007141073480087647,"gpt":0.2484371202505589,"spread":0.2412960467704712,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001460087,0.00008851405,0.0001872467,0.00005374977,0.00005163063,0.00001113216,0.0001165331,0.00007872984,0.00002419955],"category_scores_gemma":[0.00002554429,0.0000665144,0.00004474243,0.00006601251,0.0001154054,0.0001017673,0.00001889736,0.000279007,4.537355e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000276214,"about_ca_system_score_gemma":0.0001431038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001374032,"about_ca_topic_score_gemma":0.00000160107,"domain_scores_codex":[0.9992891,0.000004251359,0.0004509207,0.00005468652,0.00008491664,0.0001161088],"domain_scores_gemma":[0.9989781,0.0001101792,0.0005815456,0.00007484738,0.0001920035,0.00006331201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002084565,0.000103572,0.0142151,0.0002651507,0.0001698424,0.00001153779,0.0007297324,0.01379371,0.8761899,0.07239486,0.0001080914,0.02181007],"study_design_scores_gemma":[0.005091833,0.001562127,0.001463277,0.0004927006,0.0001461626,0.004866927,0.00210237,0.1384547,0.3707749,0.457036,0.01707573,0.0009333338],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5961586,0.00003856133,0.4013706,0.0002021799,0.00001611711,0.00004783486,0.00002536115,0.00001282049,0.002127937],"genre_scores_gemma":[0.5034578,0.00003141641,0.4963835,0.00006651954,0.00003342568,0.00000256438,0.000008361105,0.000004113648,0.00001229267],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.505415,"threshold_uncertainty_score":0.2712379,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.007763901412861236,"gpt":0.2454839679968209,"spread":0.2377200665839597,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000120159,0.00008983754,0.0001611715,0.00008290923,0.00004118459,0.000007623138,0.0001071691,0.0001012909,0.000008266835],"category_scores_gemma":[0.00002459878,0.00007495009,0.00009121715,0.00006139471,0.0001488431,0.000009249095,0.00004395836,0.00006991577,0.000002022209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001188231,"about_ca_system_score_gemma":0.0002030983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003255105,"about_ca_topic_score_gemma":0.00000279986,"domain_scores_codex":[0.9992068,0.00001534727,0.0004852763,0.00006860646,0.0001047171,0.0001192067],"domain_scores_gemma":[0.9992401,0.00001297343,0.0003581434,0.00006749828,0.0002508883,0.00007036709],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002402749,0.00239397,0.1415415,0.0007923541,0.00300135,0.0000265276,0.004476315,0.39479,0.1527354,0.07536849,0.02782298,0.1946484],"study_design_scores_gemma":[0.01232273,0.01149973,0.4008241,0.0002334694,0.0002076991,0.002760001,0.001651064,0.06797293,0.008773517,0.4615957,0.03101304,0.001146086],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8777657,0.001434699,0.1194097,0.0007596384,0.0001786326,0.00006222168,0.00007676719,0.000002668608,0.0003100315],"genre_scores_gemma":[0.9145641,0.0004149991,0.08444341,0.0004034665,0.00008757252,5.729445e-7,0.00006787278,0.000004185993,0.00001384201],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3862272,"threshold_uncertainty_score":0.3056376,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03088546029394813,"gpt":0.3064673088030582,"spread":0.2755818485091101,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004576677,0.000139074,0.0005828817,0.0001079394,0.00002253012,0.00000570119,0.0001882361,0.0001413825,0.000001215181],"category_scores_gemma":[0.00002888787,0.0000854844,0.000134015,0.0000856852,0.0001177928,0.000001055009,0.00009085358,0.00009683608,2.022243e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002434206,"about_ca_system_score_gemma":0.0004224159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002645979,"about_ca_topic_score_gemma":0.000001052075,"domain_scores_codex":[0.9986061,0.00005354007,0.001052786,0.00006685424,0.0001211592,0.00009955883],"domain_scores_gemma":[0.9986829,0.00007352425,0.0009955841,0.00006206759,0.0001619702,0.00002391786],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006188507,0.0001353725,0.0001119949,0.00338403,0.0007247809,0.000002271549,0.0007524444,0.001342313,0.000096538,0.002665603,0.00009360957,0.9906291],"study_design_scores_gemma":[0.001612803,0.001685202,0.0004218554,0.002380182,0.0003026372,0.0004003106,0.0008169393,0.00008413057,0.000113523,0.002757497,0.9890941,0.0003308682],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.003619493,0.9922674,0.00324316,0.0000307162,0.00038643,0.0002192839,0.00005584733,2.25159e-7,0.0001774019],"genre_scores_gemma":[0.01880954,0.9747255,0.006279277,0.00003137454,0.00009790238,0.00000301605,0.00004728621,0.000005039507,0.000001009303],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9902983,"threshold_uncertainty_score":0.3485953,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.006003271850188033,"gpt":0.2457398115828957,"spread":0.2397365397327077,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001454139,0.0001036446,0.0001463854,0.00005217872,0.00007505788,0.00003073647,0.00007017442,0.0001681385,0.000006725452],"category_scores_gemma":[0.00003483942,0.0000775356,0.00002829966,0.00003432136,0.00009833793,0.00001194301,0.0000481568,0.0001558369,3.619248e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004667441,"about_ca_system_score_gemma":0.00006934704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001535038,"about_ca_topic_score_gemma":0.000008895192,"domain_scores_codex":[0.9993489,0.00002187463,0.0003569401,0.00008336999,0.00008525279,0.0001036367],"domain_scores_gemma":[0.9994379,0.00001628671,0.0002675411,0.00006763884,0.0001419352,0.00006873249],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002715991,0.00007043112,0.005734736,0.00008212331,0.0002369209,0.000008445468,0.0004573252,0.0146515,0.857608,0.01157365,0.003104372,0.1062009],"study_design_scores_gemma":[0.001995186,0.001226095,0.0226522,0.00002031297,0.00004235834,0.001568808,0.00008864135,0.9382048,0.006701337,0.007183588,0.01994916,0.0003675174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9783136,0.0005299079,0.02049849,0.000247202,0.0002256112,0.0000767876,0.00005518024,0.000005517648,0.00004774143],"genre_scores_gemma":[0.941301,0.00006661558,0.05789896,0.0003678608,0.0002103013,8.225106e-7,0.000140353,0.000004766374,0.000009300718],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9235533,"threshold_uncertainty_score":0.316181,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01180921237253446,"gpt":0.2336836803964509,"spread":0.2218744680239164,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003646743,0.0001447007,0.0002310763,0.0001173286,0.0001291911,0.00005968059,0.0001484513,0.000126967,0.000002445671],"category_scores_gemma":[0.00006033335,0.0001160906,0.0001211768,0.00006002243,0.00005219895,0.0000368959,0.00007582019,0.00008757666,7.256054e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001263897,"about_ca_system_score_gemma":0.00008611564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003835446,"about_ca_topic_score_gemma":0.000001434072,"domain_scores_codex":[0.9988431,0.00001736227,0.000767248,0.00008354676,0.00009201493,0.0001967772],"domain_scores_gemma":[0.9988937,0.00008287901,0.0005807391,0.00007624421,0.0003142477,0.00005214364],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003613962,0.001052989,0.03521939,0.002032983,0.003341936,0.000009859443,0.002802706,0.4660527,0.1151376,0.1180273,0.03122634,0.2214823],"study_design_scores_gemma":[0.002999616,0.001634471,0.002519268,0.00006986845,0.00008356909,0.0004787957,0.0008474761,0.9620091,0.00208716,0.02416348,0.002714321,0.0003928595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7965097,0.0005509042,0.2015086,0.0001887357,0.0001318105,0.000174619,0.00006055202,0.000006255749,0.0008688658],"genre_scores_gemma":[0.8145117,0.00008093124,0.1847038,0.0001084202,0.0002228517,0.000005097611,0.000313294,0.00001023988,0.00004369978],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4959565,"threshold_uncertainty_score":0.4734036,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.007831224378292838,"gpt":0.231936087837947,"spread":0.2241048634596542,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001603178,0.0000872258,0.0001367429,0.00007860254,0.00005360661,0.0000296346,0.00006365028,0.00005665355,0.000003072023],"category_scores_gemma":[0.000006607359,0.00006304112,0.00002711649,0.00004264611,0.00006131492,0.00001051612,0.00002939377,0.00006446496,9.496476e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005728385,"about_ca_system_score_gemma":0.00004612316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.410517e-7,"about_ca_topic_score_gemma":6.408018e-7,"domain_scores_codex":[0.9994698,0.00001115856,0.000267875,0.00006587486,0.00007420843,0.0001111433],"domain_scores_gemma":[0.999534,0.00001055538,0.0002099182,0.00004810983,0.0001295077,0.00006795111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.004626334,0.001015873,0.05920548,0.0005577978,0.003042361,0.0001067997,0.005534077,0.03317072,0.469451,0.02573497,0.002516348,0.3950383],"study_design_scores_gemma":[0.03951003,0.04588672,0.6393629,0.0003306172,0.0005519404,0.01613697,0.003046612,0.06384016,0.01342761,0.05154737,0.1231244,0.003234702],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9672565,0.001055841,0.03044087,0.0005145476,0.00004695988,0.00007767787,0.000004613753,0.00000253425,0.0006003969],"genre_scores_gemma":[0.9609852,0.0002951106,0.03821881,0.0003173319,0.0001162046,5.122026e-7,0.00003515781,0.000003888546,0.00002780961],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5801574,"threshold_uncertainty_score":0.2570742,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05674675018465132,"gpt":0.3167456891431366,"spread":0.2599989389584852,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002553419,0.00008575512,0.0001691452,0.0001321653,0.0001587244,0.00002589957,0.00006524268,0.00007709297,0.00000517004],"category_scores_gemma":[0.00007001418,0.00007091786,0.00005145043,0.00005873499,0.0001718486,0.00001551336,0.0000373588,0.00007600983,3.036454e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002043481,"about_ca_system_score_gemma":0.0001636982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000410622,"about_ca_topic_score_gemma":9.241573e-7,"domain_scores_codex":[0.9993125,0.00002550183,0.0003482605,0.00007296166,0.0001016861,0.0001390874],"domain_scores_gemma":[0.9993522,0.00005582882,0.0002168092,0.00004368696,0.0002542903,0.0000772101],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001658427,0.0002467985,0.04346506,0.0007789602,0.00170089,0.00006187313,0.003070306,0.02553691,0.8285954,0.038588,0.002958626,0.05333875],"study_design_scores_gemma":[0.007299418,0.005935107,0.01354953,0.00009876662,0.00006861849,0.008109706,0.002768441,0.8803688,0.02282641,0.04480541,0.01335744,0.0008123317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.646814,0.000465724,0.352312,0.0001196725,0.00005541856,0.00009178754,0.00002082159,0.000001835091,0.0001187043],"genre_scores_gemma":[0.7639095,0.0001752138,0.2355654,0.0001480386,0.000137457,0.000001179785,0.00003769907,0.00000498793,0.00002058201],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8548319,"threshold_uncertainty_score":0.2891946,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.034269504117523,"gpt":0.2854363661434654,"spread":0.2511668620259424,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002572187,0.0000864692,0.0001830705,0.00008565802,0.00003641103,0.00001670061,0.0001723695,0.00008931012,0.000001037343],"category_scores_gemma":[0.0000673428,0.00006844987,0.00004832406,0.00009787626,0.00007931882,0.00003766659,0.00004958754,0.00003437397,1.799498e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001908671,"about_ca_system_score_gemma":0.0002649906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003074434,"about_ca_topic_score_gemma":0.0000117543,"domain_scores_codex":[0.9990954,0.0000256865,0.0005868712,0.0001108225,0.00008955173,0.00009171083],"domain_scores_gemma":[0.9990503,0.00004271323,0.0005124284,0.0001319287,0.000238784,0.00002382154],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.004699189,0.0006146945,0.01313244,0.001297929,0.0009121766,0.000006977176,0.002390344,0.06730875,0.8386256,0.03141135,0.01462414,0.02497637],"study_design_scores_gemma":[0.07441112,0.01155279,0.1100544,0.006765604,0.0009340654,0.003960544,0.04149223,0.1002054,0.2585609,0.1751628,0.2120523,0.004847829],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5612636,0.003155365,0.4346505,0.0004536774,0.0001913824,0.0001145639,0.0001159134,0.000001700279,0.00005324942],"genre_scores_gemma":[0.9468089,0.0004543496,0.05196489,0.0001595036,0.00008573271,0.000004474005,0.0004882803,0.000005117916,0.00002873187],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5800647,"threshold_uncertainty_score":0.2791305,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.009068232204207032,"gpt":0.2492068212457191,"spread":0.2401385890415121,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001377337,0.0001175734,0.0002675501,0.0001599511,0.00005924658,0.00001739038,0.0002355024,0.00009691808,6.747895e-7],"category_scores_gemma":[0.0000385409,0.00007874109,0.00004573367,0.0001781673,0.00007808299,0.00000744731,0.00008832654,0.0001436944,5.237893e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002596194,"about_ca_system_score_gemma":0.0001106229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004195755,"about_ca_topic_score_gemma":0.000162552,"domain_scores_codex":[0.9985815,0.0000603407,0.0009769751,0.00008988349,0.0001004166,0.0001909125],"domain_scores_gemma":[0.9989545,0.00008470586,0.0005758058,0.0001290511,0.0001842423,0.00007169962],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005506688,0.002171526,0.07631602,0.0008860917,0.00226953,0.00001635674,0.05709432,0.6179923,0.007476036,0.1586579,0.01801685,0.05359638],"study_design_scores_gemma":[0.03783951,0.01901896,0.2152863,0.0008430769,0.0005045735,0.001439065,0.117989,0.407518,0.001019809,0.04532921,0.1493347,0.003877877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7654089,0.001109393,0.2308308,0.0001775453,0.0003237046,0.0004377823,0.00002231512,0.000001521808,0.001688002],"genre_scores_gemma":[0.9845402,0.00003857335,0.01504798,0.0001998728,0.0001155675,0.000003937052,0.00002473382,0.000005106796,0.00002407],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2191312,"threshold_uncertainty_score":0.3210968,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01356187905384033,"gpt":0.2921849387862475,"spread":0.2786230597324071,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001643144,0.00006342452,0.0001524372,0.0001074955,0.00003372741,0.00001148893,0.0000846939,0.00007574931,0.00001114393],"category_scores_gemma":[0.00002055669,0.00005488031,0.00004926947,0.00007905176,0.00005578341,0.00009499652,0.00001668877,0.00007074267,2.649907e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003047078,"about_ca_system_score_gemma":0.0000505149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004033224,"about_ca_topic_score_gemma":0.000003018405,"domain_scores_codex":[0.9991208,0.000005427759,0.000687585,0.00005375602,0.00005425725,0.0000782085],"domain_scores_gemma":[0.9989685,0.00009395341,0.0006854217,0.00005187582,0.0001801242,0.00002007141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007435241,0.0007155718,0.4504823,0.00103963,0.0002282904,0.00000202815,0.000758633,0.01699517,0.2230283,0.1968301,0.001301698,0.1078747],"study_design_scores_gemma":[0.003622414,0.0003178154,0.1268157,0.0003394679,0.00007887297,0.00006419711,0.0001220519,0.08739066,0.1306704,0.6474863,0.002669125,0.000423056],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.817774,0.0001189065,0.1813758,0.0003441703,0.00002255215,0.0001535818,0.000101494,0.000004040208,0.0001054639],"genre_scores_gemma":[0.8805007,0.0001026108,0.1192018,0.00001875271,0.00003339351,0.00008659015,0.00003787927,0.000004488163,0.000013724],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4506561,"threshold_uncertainty_score":0.2237954,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06476122469075482,"gpt":0.3092507797054867,"spread":0.2444895550147319,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005061186,0.0001893024,0.0008568123,0.0003308199,0.00006360801,0.00001226198,0.0003399042,0.0003410251,0.00005441416],"category_scores_gemma":[0.0002536306,0.0001384428,0.0001097718,0.000142776,0.000471061,0.0001203134,0.0002443979,0.0006549197,0.000009511434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001912493,"about_ca_system_score_gemma":0.0003387018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003512048,"about_ca_topic_score_gemma":0.00000188271,"domain_scores_codex":[0.9980531,0.0001833389,0.001294475,0.0001557835,0.0001103026,0.0002029793],"domain_scores_gemma":[0.9969556,0.000699457,0.001730094,0.0002200769,0.00035241,0.00004233209],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002643187,0.00009776327,0.003402539,0.0009653423,0.01287724,0.000231952,0.001362114,0.0001384702,0.01027141,0.0004463662,0.9327535,0.037189],"study_design_scores_gemma":[0.02332353,0.01885679,0.02154939,0.003685918,0.009527172,0.01428137,0.004242344,0.03036348,0.005566673,0.05141469,0.8136679,0.003520722],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1523513,0.06838877,0.02491318,0.7309605,0.001206198,0.001749094,0.01914173,0.00004640581,0.001242805],"genre_scores_gemma":[0.7790407,0.006164292,0.06013937,0.1227544,0.0006883552,0.000009072309,0.03086205,0.00006551617,0.0002762371],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6266894,"threshold_uncertainty_score":0.5645533,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008312882145458547,"gpt":0.2507371658138717,"spread":0.2424242836684131,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001968858,0.0001084484,0.0001482634,0.00006049262,0.00006089979,0.00002963646,0.0002444657,0.0002118857,0.00001245341],"category_scores_gemma":[0.00007665728,0.00008487247,0.00003719984,0.00004433625,0.0001238247,0.00002483563,0.000185586,0.0002913497,3.419504e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005156357,"about_ca_system_score_gemma":0.0001975957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001976218,"about_ca_topic_score_gemma":0.00000360217,"domain_scores_codex":[0.9992114,0.00001782124,0.0004486659,0.0001086526,0.00009642766,0.000117069],"domain_scores_gemma":[0.9992583,0.00001411306,0.0003503268,0.0001714548,0.0001309853,0.00007485961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001912023,0.00003945937,0.00253361,0.00008035478,0.0001999969,0.000003417669,0.0001185695,0.001220358,0.9595103,0.004034407,0.0003411123,0.03172722],"study_design_scores_gemma":[0.006407556,0.00235839,0.01686379,0.0001179537,0.0002392753,0.006629527,0.0002649079,0.7120618,0.06296705,0.1516778,0.03915593,0.001256094],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9442757,0.0001398019,0.0547713,0.0001071393,0.0002106983,0.00009181132,0.0003344355,0.000003073111,0.00006604294],"genre_scores_gemma":[0.8778135,0.000008900454,0.1210946,0.0001555793,0.0003575649,3.831035e-7,0.0005613443,0.000005772107,0.000002348405],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8965432,"threshold_uncertainty_score":0.3460999,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008801695579537777,"gpt":0.255764492977427,"spread":0.2469627973978892,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003553726,0.0001179761,0.0001618743,0.0000718079,0.0000689714,0.00004241706,0.0002305959,0.000136278,0.000002490723],"category_scores_gemma":[0.0002854051,0.0001014457,0.00003647925,0.00008326494,0.00005224743,0.00002436414,0.0001107194,0.000114214,0.000001706626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002089434,"about_ca_system_score_gemma":0.0001446395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.752463e-7,"about_ca_topic_score_gemma":2.186824e-7,"domain_scores_codex":[0.9990085,0.00003487546,0.0005792698,0.0001446191,0.0001048992,0.000127835],"domain_scores_gemma":[0.9989492,0.00002943284,0.0004834482,0.0001822353,0.0002403588,0.0001153555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007433339,0.0003899081,0.002946455,0.000162939,0.0003058699,0.000003345466,0.0003540392,0.02364968,0.901889,0.004465205,0.0209862,0.04410401],"study_design_scores_gemma":[0.005153855,0.01379074,0.02373145,0.0004822005,0.0002662505,0.001025781,0.0004286852,0.6168774,0.04593784,0.2594752,0.03122229,0.001608365],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4650797,0.0003556094,0.5328799,0.0008260678,0.0001477606,0.0002931322,0.0003750052,0.000005559005,0.00003724639],"genre_scores_gemma":[0.6820177,0.0000184789,0.3163375,0.0006508407,0.0002158487,0.000002214761,0.0007466407,0.000005863244,0.000004922199],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8559512,"threshold_uncertainty_score":0.4136837,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03741714244687239,"gpt":0.3012285470245092,"spread":0.2638114045776369,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000897323,0.00008549756,0.0002907615,0.0003749553,0.0001152033,0.000007433179,0.00008520013,0.0001025441,0.000009972848],"category_scores_gemma":[0.00004532759,0.00007188873,0.0000526589,0.0003136626,0.0003633522,0.00008420611,0.00004612466,0.0001328471,1.238621e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001756068,"about_ca_system_score_gemma":0.00008107179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002864501,"about_ca_topic_score_gemma":2.348182e-7,"domain_scores_codex":[0.9992076,0.00001184608,0.0005654378,0.00006389667,0.0000696311,0.0000816239],"domain_scores_gemma":[0.9987873,0.0001485458,0.0007063362,0.00006181352,0.0002506723,0.00004533797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002873201,0.0003588457,0.04945229,0.0002698459,0.003507833,0.000007192256,0.003381671,0.2469718,0.4235281,0.2641622,0.00005118007,0.00802167],"study_design_scores_gemma":[0.0003744816,0.0001615228,0.0007651672,0.00002807754,0.0002467413,0.0001763621,0.0001605947,0.9187155,0.01605158,0.06316711,0.00003568597,0.000117198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4726763,0.00005499226,0.5271153,0.00006610152,0.000004503461,0.00004291565,0.00001994036,0.000004755756,0.00001523055],"genre_scores_gemma":[0.4189281,0.0001039535,0.5809249,0.0000136631,0.00000594492,0.00000292748,0.00001650475,0.000002543096,0.000001450934],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6717436,"threshold_uncertainty_score":0.2931538,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01041361670249012,"gpt":0.2526595291995905,"spread":0.2422459124971004,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002357575,0.0001437386,0.0002564093,0.00003753928,0.0001724081,0.00005744811,0.0001496168,0.0001042884,0.00001321622],"category_scores_gemma":[0.00003886393,0.0001078994,0.00005812121,0.00008502609,0.0001282854,0.00002497407,0.0001697949,0.00008679581,0.00000309609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002884547,"about_ca_system_score_gemma":0.0001576637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003134055,"about_ca_topic_score_gemma":0.000006603056,"domain_scores_codex":[0.9989986,0.00002769798,0.0005298245,0.0001062447,0.0001223415,0.0002153023],"domain_scores_gemma":[0.9992256,0.0000282846,0.0004409761,0.00006447163,0.0001527394,0.00008795952],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009851005,0.0002089031,0.06932995,0.0001472641,0.0008805199,0.0000202594,0.001428252,0.4017654,0.4855525,0.0004183883,0.006767537,0.03249586],"study_design_scores_gemma":[0.01688952,0.009069947,0.07235552,0.0008000563,0.0004181207,0.004525914,0.005593046,0.06842452,0.6939567,0.01259127,0.111162,0.004213407],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9045839,0.001174227,0.09396716,0.00006151083,0.0000839847,0.0000541952,0.00002395085,0.000004961817,0.00004608642],"genre_scores_gemma":[0.8633828,0.0003013563,0.1356497,0.0001100525,0.0002039424,0.000001312402,0.0002243132,0.000008130109,0.0001184408],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3333409,"threshold_uncertainty_score":0.4400011,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.006985693473040731,"gpt":0.2295840473966514,"spread":0.2225983539236106,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002993459,0.0000821992,0.0001453585,0.00004963332,0.00010797,0.00002109826,0.0001026009,0.00007149722,0.000001308269],"category_scores_gemma":[0.00001904371,0.0000455591,0.00008362134,0.00008924319,0.0001269205,0.00001583448,0.0000315611,0.00008258767,3.168813e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001333886,"about_ca_system_score_gemma":0.00005526756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001716958,"about_ca_topic_score_gemma":8.322947e-7,"domain_scores_codex":[0.9992998,0.00004725809,0.000397909,0.00006959643,0.00009005405,0.00009541136],"domain_scores_gemma":[0.9993176,0.00001870879,0.0004370863,0.00006668035,0.0001293642,0.00003050935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0008065637,0.0002183641,0.0333946,0.00009856813,0.001245824,0.000001470284,0.001486976,0.06332263,0.7182212,0.01011325,0.00005762447,0.1710329],"study_design_scores_gemma":[0.01092726,0.003005509,0.79907,0.00006699454,0.0003931373,0.003360506,0.001045845,0.0635705,0.007932851,0.1080419,0.001942162,0.0006433253],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9556701,0.0008711602,0.04170215,0.001408343,0.0001236307,0.0001423149,0.00001116425,0.000001750622,0.00006939858],"genre_scores_gemma":[0.9931951,0.0002295239,0.006205643,0.0002160627,0.0001093871,0.000001135934,0.00002956909,0.000003002204,0.00001059059],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7656754,"threshold_uncertainty_score":0.1857846,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02253895089369068,"gpt":0.3214746440522242,"spread":0.2989356931585335,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001016189,0.0000692998,0.0001153789,0.0001011675,0.00003534539,0.00001652184,0.00005019143,0.00006944427,0.000001271263],"category_scores_gemma":[0.00002729116,0.00005659747,0.00001671735,0.0001041041,0.00005691615,0.00002029467,0.00004230317,0.00004861022,4.623874e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003258478,"about_ca_system_score_gemma":0.0001204712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006641359,"about_ca_topic_score_gemma":0.00001460287,"domain_scores_codex":[0.999212,0.00003729003,0.0003864325,0.00007628779,0.0001974931,0.00009046883],"domain_scores_gemma":[0.9992111,0.00001189503,0.0002699911,0.0000444854,0.0004242536,0.00003830095],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008972292,0.0001610399,0.01013192,0.0001789305,0.0001350054,4.272803e-7,0.00244242,0.690017,0.1862059,0.0005040435,0.00001136388,0.1093147],"study_design_scores_gemma":[0.002648435,0.0008518738,0.07989139,0.000138068,0.00004096875,0.0001924602,0.001358448,0.9062721,0.008138754,0.0002791774,0.00004278577,0.0001455881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4718595,0.0002730677,0.5275559,0.00002575869,0.0000197185,0.00006620064,0.000002654641,7.314964e-7,0.0001964965],"genre_scores_gemma":[0.9331539,0.00008199451,0.06665275,0.00003469178,0.00003513529,0.000001739088,0.00003438717,0.000002766568,0.000002635195],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4612944,"threshold_uncertainty_score":0.2307978,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01220415146865176,"gpt":0.2475589559974527,"spread":0.2353548045288009,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001771838,0.0001150847,0.0001829342,0.00009645111,0.0001192294,0.00001494923,0.0001381615,0.0001009417,0.000006286696],"category_scores_gemma":[0.00007276281,0.00009315135,0.00007144585,0.00008046375,0.00007972094,0.000009837197,0.000087382,0.0001074792,0.000005280712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009128998,"about_ca_system_score_gemma":0.00009839479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002605853,"about_ca_topic_score_gemma":9.387114e-7,"domain_scores_codex":[0.9991689,0.00002549524,0.0004474293,0.00009060775,0.0001100821,0.0001574318],"domain_scores_gemma":[0.9992653,0.00002415918,0.0002883696,0.00008470676,0.0002295374,0.0001078952],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002066569,0.0005073745,0.0270421,0.0005921457,0.002014896,0.0001324987,0.01037356,0.02207061,0.7032769,0.06060263,0.02134095,0.1499797],"study_design_scores_gemma":[0.01438037,0.02039874,0.05122068,0.0004673394,0.0002132267,0.02226487,0.001602134,0.2853824,0.05421188,0.08213256,0.463722,0.004003782],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8955364,0.0003125997,0.1027121,0.0008466638,0.00009066521,0.0001366037,0.00003584243,0.000003617408,0.0003255305],"genre_scores_gemma":[0.8911097,0.00007344106,0.1059433,0.002552889,0.0002012693,0.000002658297,0.00003792365,0.000007308503,0.00007152573],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6490651,"threshold_uncertainty_score":0.3798602,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.005349491978337566,"gpt":0.2317646768235121,"spread":0.2264151848451746,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003298754,0.0001003398,0.0001711751,0.0001009813,0.00006478011,0.0000248375,0.00009949714,0.0001052286,0.000006331051],"category_scores_gemma":[0.00001272027,0.00007916201,0.00006148995,0.0000386798,0.00005359345,0.00001042308,0.00003086752,0.00007255462,3.069861e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009300976,"about_ca_system_score_gemma":0.00008863234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004821608,"about_ca_topic_score_gemma":0.000005028414,"domain_scores_codex":[0.9991722,0.0000329874,0.0004842705,0.00008522058,0.00007804781,0.0001473077],"domain_scores_gemma":[0.9994378,0.00004607969,0.0002876555,0.00004929974,0.0001284607,0.00005069043],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002819542,0.0001065374,0.004281472,0.00008036461,0.0001252093,0.000006450987,0.0002743248,0.1008817,0.02101852,0.002975954,0.0001770273,0.8697904],"study_design_scores_gemma":[0.002240867,0.00176352,0.008022478,0.0000290294,0.00002268254,0.0003725376,0.0004956906,0.96507,0.007385693,0.01288522,0.001459731,0.0002525203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6357769,0.0008139494,0.3630127,0.0000497272,0.000117928,0.00009515358,0.00004406685,0.000002063541,0.00008751389],"genre_scores_gemma":[0.8860983,0.00002700379,0.1134029,0.0000994575,0.0002267155,0.000003062969,0.000129217,0.000006247567,0.00000706247],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8695379,"threshold_uncertainty_score":0.3228133,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01236623746561531,"gpt":0.2945866825847948,"spread":0.2822204451191795,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003162262,0.000102924,0.000343337,0.0002643097,0.00008926634,0.000009864133,0.0001323376,0.000100211,0.00002779809],"category_scores_gemma":[0.00009826504,0.00008108476,0.0001722875,0.0001775078,0.0002497854,0.000007381192,0.00006739767,0.00009607869,0.000001455892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001446984,"about_ca_system_score_gemma":0.00008247188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008653913,"about_ca_topic_score_gemma":0.00001239612,"domain_scores_codex":[0.9988298,0.00008510708,0.0007621121,0.00009246636,0.00009152971,0.0001390092],"domain_scores_gemma":[0.9986344,0.0001034193,0.0006606357,0.00009809218,0.000425334,0.00007811985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001094743,0.0004992728,0.6028091,0.00008629443,0.01837691,0.000005929616,0.003533989,0.09206022,0.2067862,0.01210173,0.005232927,0.0574127],"study_design_scores_gemma":[0.001397491,0.002357979,0.6791529,0.00001391356,0.0007895858,0.0003187848,0.000400407,0.3004309,0.003705232,0.006609465,0.00448945,0.0003339245],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9074187,0.0001731447,0.09162352,0.0003084072,0.0002182558,0.00004170306,0.00006831898,0.000001576271,0.0001463314],"genre_scores_gemma":[0.9300457,0.00006369904,0.06919177,0.0002667522,0.0001752183,8.23711e-7,0.0002395875,0.000003684493,0.00001276011],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2083707,"threshold_uncertainty_score":0.330654,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01310648568216417,"gpt":0.2395401883740546,"spread":0.2264337026918904,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002322677,0.0000832384,0.0002097925,0.00002591136,0.00008128066,0.00001024497,0.0001141794,0.00006465577,0.000004062549],"category_scores_gemma":[0.00004220951,0.00005718225,0.00007708302,0.00006666324,0.0001681427,9.504775e-7,0.0001258278,0.00006554114,3.807772e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003536342,"about_ca_system_score_gemma":0.0001130036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001488581,"about_ca_topic_score_gemma":0.000005265115,"domain_scores_codex":[0.9992356,0.0000588969,0.0004580787,0.00006504374,0.00006164524,0.0001207283],"domain_scores_gemma":[0.9991774,0.00006502632,0.000337681,0.00008769728,0.0002960314,0.00003616196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003170255,0.0002352453,0.4365053,0.0001708667,0.002400753,0.00001302491,0.001361932,0.2720034,0.1937056,0.05137876,0.006375107,0.03553297],"study_design_scores_gemma":[0.007341861,0.005861651,0.6176688,0.0001399757,0.000574537,0.00439844,0.003891365,0.06164682,0.07465638,0.1160561,0.1063863,0.001377736],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9837729,0.006756961,0.00858868,0.0002811729,0.0002572812,0.00003705744,0.000007727866,4.139426e-7,0.0002977892],"genre_scores_gemma":[0.9808675,0.000801264,0.01770983,0.0003715824,0.0002233115,8.139542e-7,0.00001382426,0.000003937445,0.000007896871],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2103566,"threshold_uncertainty_score":0.2331824,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.006251284061139019,"gpt":0.2390686562936064,"spread":0.2328173722324674,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001716302,0.00008303494,0.0001811844,0.00005958844,0.00003577673,0.00001305045,0.00007440344,0.0001151571,0.000006515092],"category_scores_gemma":[0.00005023288,0.0000617636,0.00004374597,0.00003351327,0.00008036075,0.000007389184,0.00002691896,0.00007728226,1.762107e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003246099,"about_ca_system_score_gemma":0.0001071915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.986034e-7,"about_ca_topic_score_gemma":4.496011e-7,"domain_scores_codex":[0.9993528,0.00003103558,0.000404711,0.00005568054,0.00007055166,0.00008526215],"domain_scores_gemma":[0.9993749,0.00003697682,0.0003261747,0.00004968272,0.000151769,0.0000605161],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005243713,0.00008402442,0.0008979324,0.00009607513,0.0003220651,0.000005550417,0.0003487231,0.001294162,0.5917214,0.03735149,0.0007701222,0.3665841],"study_design_scores_gemma":[0.007911973,0.01922272,0.1194766,0.0002208213,0.0002674245,0.003830655,0.001026373,0.01575987,0.4445037,0.369823,0.01664546,0.001311357],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9811152,0.00141093,0.01661592,0.0003086491,0.0000900798,0.00005686709,0.00002206044,0.000001571493,0.0003787472],"genre_scores_gemma":[0.9661605,0.0002694411,0.03312938,0.0003472153,0.00006224874,1.638496e-7,0.00002200706,0.00000256669,0.000006496214],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3652727,"threshold_uncertainty_score":0.2518646,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0106751635985702,"gpt":0.2744912583305859,"spread":0.2638160947320157,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005581848,0.00008358482,0.0001539797,0.00006738797,0.00007007292,0.0000159316,0.0000945482,0.0001141439,0.000007685958],"category_scores_gemma":[0.000100515,0.00006997578,0.000061185,0.00004789958,0.00006113898,0.00002469696,0.00005804629,0.0000712734,0.000007555896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001623715,"about_ca_system_score_gemma":0.00003904246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001297869,"about_ca_topic_score_gemma":7.023807e-7,"domain_scores_codex":[0.9991848,0.00005710803,0.0004532109,0.00005317633,0.00007935458,0.0001723671],"domain_scores_gemma":[0.9992282,0.00003944725,0.0004142273,0.00005428648,0.0001696476,0.00009417954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002762241,0.001099837,0.4507515,0.0002275789,0.001089838,0.000002868582,0.002819656,0.006076093,0.3600425,0.01193638,0.02906753,0.13661],"study_design_scores_gemma":[0.004154628,0.00330182,0.6595273,0.00004226557,0.0002118508,0.001212879,0.001610896,0.0221082,0.001675199,0.02061445,0.2844884,0.001052064],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7531664,0.001574244,0.2443459,0.0003868053,0.0002304726,0.00005743627,0.00004076259,0.000002118512,0.00019593],"genre_scores_gemma":[0.9690433,0.0002492731,0.02973568,0.0005227883,0.0002076565,0.000001442581,0.0002027913,0.000004797467,0.00003234452],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3583673,"threshold_uncertainty_score":0.2853529,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0342293175648849,"gpt":0.3299604751487715,"spread":0.2957311575838866,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001350044,0.00009459475,0.0006814906,0.000489868,0.00005868329,0.00004065105,0.00007351944,0.00004244945,0.00003409864],"category_scores_gemma":[0.0001654292,0.00006238583,0.0001574689,0.0002612244,0.00007287868,0.0001181962,0.00003584785,0.0001424127,0.000008933182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002171523,"about_ca_system_score_gemma":0.00009932408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007358175,"about_ca_topic_score_gemma":0.000002286121,"domain_scores_codex":[0.998535,0.0001897781,0.0008354067,0.00006610418,0.0002418246,0.0001318241],"domain_scores_gemma":[0.9985256,0.0003723219,0.0004663198,0.00009720002,0.0004178356,0.0001207338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003860167,0.000499009,0.9601163,0.004318697,0.01340377,0.00005674248,0.00769656,0.003581214,0.0006951994,0.001983204,0.00004453368,0.007218721],"study_design_scores_gemma":[0.01106027,0.008021585,0.4948564,0.002059132,0.001312188,0.00265489,0.02186215,0.4513951,0.0002012865,0.005984411,0.00008812746,0.0005045484],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9711279,0.002108421,0.02606603,0.00007478392,0.0000688285,0.0003715858,0.000005421975,0.000005584428,0.000171453],"genre_scores_gemma":[0.9619167,0.0002762827,0.03769763,0.00006469616,0.00001541952,0.000003182278,0.00001039594,0.000003818605,0.00001183314],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.46526,"threshold_uncertainty_score":0.254402,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01005030312995211,"gpt":0.2603520993494437,"spread":0.2503017962194916,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000810258,0.000101152,0.0001613699,0.00005905198,0.0001128731,0.00003006158,0.0001689726,0.00007061998,0.000003971152],"category_scores_gemma":[0.00003694592,0.00006687733,0.00006896436,0.00007399693,0.0001272068,0.000006681767,0.00008734412,0.0001030381,0.000002392571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001109731,"about_ca_system_score_gemma":0.00006541013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001435377,"about_ca_topic_score_gemma":0.00000414703,"domain_scores_codex":[0.9990364,0.00003012278,0.0005630335,0.00007181855,0.0001184034,0.000180262],"domain_scores_gemma":[0.9991288,0.00009782628,0.0004175711,0.00008006692,0.0002064062,0.00006934345],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003317612,0.0001481178,0.1482437,0.0001319065,0.001251064,0.0000142489,0.002100413,0.01151696,0.007534981,0.008211573,0.001771089,0.8187442],"study_design_scores_gemma":[0.007308446,0.005166297,0.5691591,0.0001300817,0.0003127909,0.001273952,0.003604442,0.05345199,0.004616927,0.02918479,0.3243571,0.001434153],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4436067,0.001098741,0.554161,0.0005129727,0.0001364781,0.00009179366,0.00001384421,0.000003055338,0.0003754519],"genre_scores_gemma":[0.9711661,0.0001121476,0.02804985,0.0002615895,0.0003403672,2.998465e-7,0.0000499719,0.000005769355,0.00001390299],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8173101,"threshold_uncertainty_score":0.2727178,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01585278375623772,"gpt":0.2320088704675143,"spread":0.2161560867112766,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002170282,0.0001023163,0.0003588092,0.0002431458,0.00003985063,0.000003716381,0.00004868737,0.0001077356,0.00001645152],"category_scores_gemma":[0.000006196585,0.00007662251,0.0001038534,0.0001086115,0.00004540695,0.0001341458,0.000006265445,0.000156664,0.000001099319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001670779,"about_ca_system_score_gemma":0.0001348927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004645549,"about_ca_topic_score_gemma":0.00000508516,"domain_scores_codex":[0.9988012,0.00001215818,0.0008107563,0.00006282819,0.0001852727,0.0001277612],"domain_scores_gemma":[0.999312,0.00001723541,0.000267595,0.00004115369,0.0002843796,0.00007758026],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.02533421,0.002897588,0.04666124,0.003534588,0.002382495,0.001332319,0.01749333,0.7303729,0.05203607,0.0894313,0.0001713629,0.0283526],"study_design_scores_gemma":[0.005482654,0.00146653,0.01758908,0.0002300079,0.0001365209,0.000629781,0.0004491383,0.9569428,0.0009450373,0.01592531,0.00004647103,0.0001566681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7868397,0.0003542844,0.2123156,0.0001745225,0.0001672261,0.00008964637,0.000008246582,0.000004091096,0.00004665528],"genre_scores_gemma":[0.9872498,0.0004266099,0.01204252,0.0001821157,0.00004289148,9.585087e-7,0.00003807796,0.000005712276,0.00001129996],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2265699,"threshold_uncertainty_score":0.3124575,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.005996132849436699,"gpt":0.2523833834124025,"spread":0.2463872505629658,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001655767,0.0001274816,0.0001504755,0.0001030359,0.00007805106,0.00003284016,0.0001088556,0.0001259874,0.000008337935],"category_scores_gemma":[0.00004240623,0.0001001474,0.00005870816,0.00006816148,0.00006691066,0.0000199941,0.00002847695,0.000106178,0.000001009029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002990936,"about_ca_system_score_gemma":0.0001635591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004483004,"about_ca_topic_score_gemma":0.000005199305,"domain_scores_codex":[0.9990776,0.00004514775,0.0004385445,0.0001227912,0.0001943521,0.000121527],"domain_scores_gemma":[0.9991759,0.00001481355,0.0003865553,0.0001199316,0.0002054693,0.00009734467],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001328654,0.0003649495,0.003846424,0.00009843498,0.0002440995,0.00001865636,0.000685429,0.8073387,0.1260715,0.02569526,0.0001918417,0.03411608],"study_design_scores_gemma":[0.0295079,0.03088186,0.0464741,0.0003656505,0.0002445365,0.001466154,0.002305058,0.2979598,0.1767529,0.4067875,0.005052255,0.002202346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8110396,0.00004354105,0.1881591,0.0003109502,0.0001233285,0.0001834474,0.00004464745,0.000003755698,0.00009165038],"genre_scores_gemma":[0.9366941,0.00001034169,0.06224418,0.0005875441,0.0001249002,0.000003037799,0.0003229914,0.000006842889,0.000006025452],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5093789,"threshold_uncertainty_score":0.4083891,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01181630914459508,"gpt":0.2614766387186723,"spread":0.2496603295740772,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008112586,0.00008189337,0.0001480986,0.00005537328,0.00006595979,0.00002067065,0.00009937409,0.00006626244,0.0001556564],"category_scores_gemma":[0.00001543243,0.00006253685,0.00004537732,0.00006534089,0.0001097006,0.0001677413,0.00001540586,0.000139875,0.000004699585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002563092,"about_ca_system_score_gemma":0.0001442503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000010078,"about_ca_topic_score_gemma":5.247089e-7,"domain_scores_codex":[0.9992676,0.000006411384,0.000479859,0.00005220965,0.00009434982,0.00009960569],"domain_scores_gemma":[0.9987141,0.0001370463,0.0004466041,0.00006772902,0.0005745994,0.00005994809],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003058424,0.0005087451,0.05421053,0.000674761,0.0006932686,0.000004147891,0.005268567,0.09466606,0.3697613,0.4277264,0.000722934,0.04545738],"study_design_scores_gemma":[0.0040179,0.0006957842,0.01443949,0.0004337337,0.0002212552,0.005453524,0.003965451,0.488034,0.02757416,0.4475031,0.006580418,0.001081206],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6371413,0.00003024252,0.3593969,0.0007214065,0.00000604819,0.00006688395,0.00005400249,0.000009990978,0.002573129],"genre_scores_gemma":[0.6003989,0.00002314194,0.3993539,0.0001297274,0.00002086239,0.000007516803,0.00004051808,0.000004187958,0.00002126386],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3933679,"threshold_uncertainty_score":0.2550178,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02186785607877424,"gpt":0.2618437589356458,"spread":0.2399759028568716,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002217728,0.0000843362,0.0001477215,0.00004115086,0.0002766566,0.00006697755,0.00006242598,0.00006534231,5.510661e-7],"category_scores_gemma":[0.00008559134,0.00007196706,0.00002492593,0.000008806298,0.0001660091,0.000006472195,0.0001408193,0.00004994635,7.880894e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004974892,"about_ca_system_score_gemma":0.00004034022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007376205,"about_ca_topic_score_gemma":0.000003788553,"domain_scores_codex":[0.9994811,0.00001551042,0.0002983879,0.00007743848,0.00003840079,0.00008913485],"domain_scores_gemma":[0.9992701,0.00001850846,0.0004776317,0.00006277088,0.0001269734,0.00004403564],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001903518,0.00002352934,0.1042584,0.000173024,0.0004664049,0.000003141751,0.0009184884,0.002197429,0.6820897,0.0007089167,0.0000239375,0.2089466],"study_design_scores_gemma":[0.008182098,0.004164396,0.2535894,0.0003558497,0.0002863713,0.00681872,0.002944224,0.629672,0.04378642,0.04376932,0.004797315,0.00163391],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9869196,0.001148081,0.01157913,0.0001406739,0.00009040818,0.00006338611,0.00001210494,5.520639e-7,0.00004606007],"genre_scores_gemma":[0.9295486,0.0003211398,0.0699438,0.0000655219,0.0001084019,7.316423e-7,0.000003613351,0.00000381578,0.000004373434],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6383033,"threshold_uncertainty_score":0.2934731,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02993371998511228,"gpt":0.3003840088938977,"spread":0.2704502889087854,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000235836,0.00007185477,0.0001139916,0.00007808816,0.00003941718,0.000032876,0.0001228592,0.000067971,0.000001530984],"category_scores_gemma":[0.00002984029,0.00005759976,0.00002071742,0.00002614075,0.0000320825,0.00003529543,0.0001714131,0.00005107798,1.818297e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008175761,"about_ca_system_score_gemma":0.00003818204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001101176,"about_ca_topic_score_gemma":0.00001033344,"domain_scores_codex":[0.9993717,0.00001862114,0.0003658748,0.0001022374,0.00005234594,0.00008919711],"domain_scores_gemma":[0.9995468,0.00002857938,0.0002287778,0.0001027878,0.00005307997,0.00004003728],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006603385,0.0001418578,0.01266661,0.0002531416,0.0001006858,0.00000167465,0.0009113804,0.0396308,0.4106428,0.00009639492,0.003721135,0.5311732],"study_design_scores_gemma":[0.003862578,0.0007641216,0.012902,0.0001725977,0.00002441265,0.0002206469,0.0007290419,0.9376189,0.01761029,0.0006971735,0.02504389,0.0003543891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3248626,0.0006999281,0.6737098,0.0004872506,0.00009200687,0.00007870701,0.00003619148,0.000001286261,0.00003219246],"genre_scores_gemma":[0.9398024,0.0004064361,0.05909467,0.0003336391,0.0001795624,0.000002775269,0.0001608195,0.000004740981,0.00001496241],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8979881,"threshold_uncertainty_score":0.234885,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03657747354787876,"gpt":0.3069283622176294,"spread":0.2703508886697506,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003702205,0.000121731,0.0001587845,0.0001288185,0.00008934493,0.00006105519,0.0003989899,0.0001641237,0.000006334879],"category_scores_gemma":[0.00009961386,0.00009580465,0.00003985421,0.00009194776,0.00006786118,0.00004361151,0.0002040563,0.0001735083,0.000006340562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000679995,"about_ca_system_score_gemma":0.0001322607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003766912,"about_ca_topic_score_gemma":0.000001988605,"domain_scores_codex":[0.9989132,0.00003918432,0.0006266283,0.0001628034,0.0001394242,0.0001187657],"domain_scores_gemma":[0.9987118,0.00002584497,0.0005295646,0.0003029258,0.0002956767,0.0001342164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008476693,0.0000874374,0.0005016988,0.00000988498,0.00004635064,1.994262e-7,0.0003481895,0.002125067,0.9834535,0.0001450803,0.001859893,0.0113379],"study_design_scores_gemma":[0.005074531,0.001070895,0.08696079,0.0000596254,0.0001062394,0.0004103609,0.0026583,0.3445515,0.5135908,0.003076722,0.04143171,0.001008478],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4902285,0.0001479469,0.5088108,0.0001167037,0.0002586303,0.0001212383,0.0001748221,0.000004097445,0.0001372207],"genre_scores_gemma":[0.7401431,0.00007271158,0.2579666,0.0002686846,0.0001843075,0.00000497278,0.001334208,0.000005904928,0.00001951326],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4698627,"threshold_uncertainty_score":0.39068,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008442928588421848,"gpt":0.2469463873028332,"spread":0.2385034587144114,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002986048,0.00008072728,0.0001201786,0.00004532528,0.0001470605,0.0000373983,0.0001032839,0.00006154419,0.000002313944],"category_scores_gemma":[0.00006081737,0.00005765223,0.00008824673,0.00005059274,0.00001813947,0.000006486657,0.00005856063,0.00006314479,3.700378e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000576159,"about_ca_system_score_gemma":0.00005801661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002141863,"about_ca_topic_score_gemma":7.645592e-7,"domain_scores_codex":[0.9994045,0.00002689633,0.0003153643,0.00006528669,0.00007975573,0.0001082345],"domain_scores_gemma":[0.999405,0.00006847534,0.0002868303,0.00005911286,0.0001232968,0.00005728205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005110651,0.00001452229,0.00477912,0.00001553043,0.0001709698,2.981142e-7,0.000352338,0.7379429,0.0004498778,0.00743459,0.0007785542,0.2480101],"study_design_scores_gemma":[0.0009741693,0.0002875747,0.00385598,0.00001450826,0.00003482221,0.00004902162,0.000101834,0.9729902,0.0001791583,0.001678187,0.01973285,0.0001017412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1471427,0.0001257354,0.8521914,0.0001471797,0.0002492144,0.00007864589,0.000004757384,0.000002057004,0.00005825246],"genre_scores_gemma":[0.8645493,0.00001821294,0.1345622,0.0004682334,0.0003039516,9.843989e-7,0.00007610981,0.000004506457,0.00001648244],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7176293,"threshold_uncertainty_score":0.235099,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.006882667899141399,"gpt":0.2114519272650906,"spread":0.2045692593659492,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001937627,0.00005364069,0.0001506476,0.00006330055,0.00004326803,0.00001718641,0.0003181719,0.00004008028,0.000001496542],"category_scores_gemma":[0.00001145826,0.00003175221,0.00005029171,0.0001347227,0.00007806774,0.0002332203,0.0001383561,0.00006507678,1.921313e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005420426,"about_ca_system_score_gemma":0.00005006151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004069701,"about_ca_topic_score_gemma":5.83978e-7,"domain_scores_codex":[0.9991847,0.00002879397,0.0005520617,0.00003971095,0.0001302,0.00006457884],"domain_scores_gemma":[0.9986913,0.00008449754,0.000867984,0.00009405576,0.0002429247,0.0000192092],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009323607,0.0003850738,0.02110798,0.0001935654,0.0001428337,0.000003494868,0.0009816139,0.07574245,0.01721854,0.5512646,0.0007831182,0.3320834],"study_design_scores_gemma":[0.0002999096,0.0001445709,0.08389577,0.00005381482,0.000006456354,0.00006618031,0.00001122462,0.8969101,0.0004698741,0.01772798,0.0003631263,0.00005103229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1346397,0.00008187368,0.8647225,0.0001786083,0.0001836896,0.00003612829,0.000007869589,0.000002157351,0.0001474904],"genre_scores_gemma":[0.9032946,0.00003916066,0.096522,0.00007317871,0.00005116328,2.675652e-7,0.00001250469,0.000001310713,0.000005785118],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8211676,"threshold_uncertainty_score":0.1294818,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0187800215957247,"gpt":0.2738799799279997,"spread":0.2550999583322749,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001294794,0.00008405351,0.0001448027,0.00002794902,0.0000509682,0.00001851394,0.0001274966,0.00009645511,0.00001572024],"category_scores_gemma":[0.0001075834,0.00006169947,0.00005401436,0.00008303032,0.00006995876,0.000007109228,0.00006479578,0.00008647831,0.000003697189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003730508,"about_ca_system_score_gemma":0.00008583978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":1.888119e-7,"about_ca_topic_score_gemma":1.747544e-7,"domain_scores_codex":[0.9993086,0.00003534748,0.000394705,0.00008481432,0.00007036699,0.0001061545],"domain_scores_gemma":[0.9992771,0.00003327386,0.0003437452,0.00004935505,0.0001896972,0.0001068247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001462527,0.000167614,0.01574854,0.0001423554,0.0004789534,0.000004527193,0.001326633,0.09023129,0.587129,0.02725946,0.03000207,0.246047],"study_design_scores_gemma":[0.01204411,0.02373003,0.08938685,0.0002639938,0.0002027712,0.0004647935,0.002281473,0.1723544,0.06800716,0.07108121,0.5577655,0.002417632],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3837996,0.0008569208,0.6118675,0.00228318,0.0002003328,0.00008793243,0.00001096472,0.000006576479,0.0008870251],"genre_scores_gemma":[0.9737998,0.0003425489,0.02314672,0.002361072,0.0002919882,0.000001484584,0.00004480406,0.000003261142,0.000008278768],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5900003,"threshold_uncertainty_score":0.2516031,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008049881864178819,"gpt":0.227180576823814,"spread":0.2191306949596352,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003421142,0.0001071059,0.0001631067,0.00009265792,0.0001209801,0.00003007415,0.0001132442,0.0001136844,0.000004336053],"category_scores_gemma":[0.000129183,0.00007173943,0.0000809306,0.00007683248,0.0001714526,0.00001767703,0.00005038372,0.0001249825,0.000001386048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001091272,"about_ca_system_score_gemma":0.00009508416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008329919,"about_ca_topic_score_gemma":0.000007440208,"domain_scores_codex":[0.9988325,0.00005106268,0.0007656799,0.00006642843,0.0001412779,0.0001429984],"domain_scores_gemma":[0.998928,0.0001105825,0.0004919851,0.00009720508,0.0003183423,0.00005386554],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00243713,0.000351253,0.01182224,0.0003292639,0.0007194647,0.000003229441,0.0005691905,0.495281,0.3241194,0.07425997,0.01383089,0.07627694],"study_design_scores_gemma":[0.007170112,0.01285836,0.06499058,0.0001328679,0.0002007917,0.001384101,0.0005194242,0.3374091,0.02119122,0.02402413,0.5292183,0.000900996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6507185,0.0001320276,0.3474564,0.0009091707,0.0002742412,0.0002201486,0.00008662074,0.000004322928,0.0001986636],"genre_scores_gemma":[0.9407985,0.00004891349,0.05821815,0.0003376959,0.0002712855,0.000006511097,0.0001605875,0.000008727017,0.0001495815],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5153874,"threshold_uncertainty_score":0.2925449,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.00792344490157071,"gpt":0.2412425179802683,"spread":0.2333190730786976,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001672362,0.000108579,0.0001963039,0.0000830822,0.0000640136,0.000009424323,0.0001147011,0.0001039929,0.000004314609],"category_scores_gemma":[0.00005311156,0.00008503535,0.00006094778,0.00005590719,0.0001343948,0.00001102317,0.0001016137,0.0001122108,9.128582e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001189783,"about_ca_system_score_gemma":0.00008209158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004603805,"about_ca_topic_score_gemma":0.000001781783,"domain_scores_codex":[0.9991196,0.0000313174,0.000556393,0.00007547241,0.0001076839,0.0001095431],"domain_scores_gemma":[0.9990576,0.00001764079,0.000563218,0.00007387403,0.000239264,0.00004840047],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001725577,0.000321122,0.001933729,0.0005196311,0.0006532148,0.00001871081,0.001730193,0.2602776,0.6687782,0.003223775,0.0004328863,0.06038539],"study_design_scores_gemma":[0.00504591,0.007337684,0.004015047,0.0004814718,0.00008146034,0.004381702,0.001005114,0.812494,0.1521634,0.004877683,0.007230107,0.0008864194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8377453,0.0003941402,0.1613531,0.00006417432,0.0001109946,0.0001147701,0.00001277411,0.000002303857,0.0002023991],"genre_scores_gemma":[0.9482773,0.00007049969,0.05145152,0.00007362659,0.00007983313,0.000002064127,0.00002450585,0.000005193001,0.00001547701],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5522164,"threshold_uncertainty_score":0.3467641,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008403906487245838,"gpt":0.2224337522941265,"spread":0.2140298458068807,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002394451,0.0001044494,0.0002652641,0.00007345748,0.00005056004,0.000005345193,0.0001392053,0.0001025669,0.000001671516],"category_scores_gemma":[0.00002960808,0.000063953,0.0001578576,0.00004940389,0.0001246786,0.00000704348,0.00007205642,0.00003508403,1.773761e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001046095,"about_ca_system_score_gemma":0.0001048718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.662184e-7,"about_ca_topic_score_gemma":0.000001051441,"domain_scores_codex":[0.9989938,0.00003228252,0.0006385566,0.00009317231,0.0001289537,0.0001132128],"domain_scores_gemma":[0.9986972,0.00003671789,0.0007608222,0.0001133514,0.0003350226,0.00005688156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002426344,0.00001796108,0.001430543,0.00002159944,0.0001298374,5.828128e-8,0.00004609887,0.1661766,0.826559,0.0002970751,0.00005332817,0.005025314],"study_design_scores_gemma":[0.004197219,0.0007770481,0.002276822,0.00008810108,0.0001920116,0.00009490984,0.00005150434,0.2735936,0.7089553,0.009274835,0.0002485471,0.0002500421],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4777852,0.00005142436,0.5218452,0.0000998191,0.00006243648,0.0000842386,0.00006628982,6.299036e-7,0.000004821915],"genre_scores_gemma":[0.9357207,0.00002928183,0.0639583,0.0001304371,0.0001259509,0.000003698333,0.00002175166,0.000006219199,0.000003651784],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4579355,"threshold_uncertainty_score":0.2607928,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.106559983716119,"gpt":0.3925495000729928,"spread":0.2859895163568738,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002442266,0.00007865937,0.0002780332,0.0003072011,0.00006145388,0.000006501278,0.00005088727,0.00005528613,0.000009534405],"category_scores_gemma":[0.0002115225,0.00005540979,0.00004924676,0.0001251296,0.0001556025,0.0001131536,0.00004739936,0.0001765133,0.000008649957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004937253,"about_ca_system_score_gemma":0.0001906888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008476743,"about_ca_topic_score_gemma":0.00000123724,"domain_scores_codex":[0.9990003,0.00002467441,0.0005921339,0.0000441796,0.0001920021,0.0001466863],"domain_scores_gemma":[0.9992095,0.0001517177,0.0002347122,0.00004327321,0.0002797233,0.00008112463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001711855,0.0004694472,0.9545217,0.0002243417,0.000582794,0.000340068,0.004661204,0.002353478,0.000599559,0.003157591,0.002382411,0.02899559],"study_design_scores_gemma":[0.009092961,0.002995149,0.9386663,0.0002182613,0.00004811142,0.004572566,0.0005746554,0.01485625,0.0002044699,0.006987896,0.02154737,0.000235998],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9973395,0.0009124962,0.0005563121,0.0002239922,0.00005471762,0.0001008205,0.000007846469,0.000004374152,0.0007999371],"genre_scores_gemma":[0.9777198,0.0006358406,0.01850384,0.003044614,0.00007273313,0.000002375859,0.000004282576,0.000004690473,0.00001183495],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02875959,"threshold_uncertainty_score":0.2259546,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.007871627652280947,"gpt":0.2403951557979113,"spread":0.2325235281456304,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002620742,0.00006747199,0.0001791708,0.0001233789,0.00001819579,0.000004812183,0.00005325641,0.00006726084,0.000001929342],"category_scores_gemma":[0.000005841251,0.00006009823,0.000033172,0.00006235004,0.00003812524,0.00001364035,0.000008731882,0.00003083968,3.429792e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007378032,"about_ca_system_score_gemma":0.00004297521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007873443,"about_ca_topic_score_gemma":0.00001057972,"domain_scores_codex":[0.9991164,0.00002689878,0.0006520111,0.00006853692,0.00007548744,0.00006068596],"domain_scores_gemma":[0.999291,0.0000160623,0.0004411042,0.00004013496,0.0001846047,0.00002711504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001838364,0.00004073951,0.0009484497,0.00004357687,0.00002683384,1.153953e-7,0.0002908877,0.008415645,0.9825503,0.004326137,0.000006198368,0.003167316],"study_design_scores_gemma":[0.001801487,0.001021169,0.2826375,0.00007512489,0.00005401122,0.00008754236,0.0002260109,0.06141545,0.6314104,0.02028742,0.0007352091,0.0002486307],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8539762,0.0002887834,0.145405,0.00008946913,0.00002417634,0.0001446603,0.00004487834,6.081017e-7,0.00002624387],"genre_scores_gemma":[0.9930228,0.00005914561,0.00676339,0.0000245607,0.0000270098,0.00000395712,0.0000898276,0.000002902624,0.000006377666],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3511398,"threshold_uncertainty_score":0.2450735,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.00786710609598433,"gpt":0.2470661261058875,"spread":0.2391990200099032,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001801715,0.00009877421,0.0001448672,0.00006170566,0.00007401246,0.00001916174,0.0001002657,0.00009561419,0.000001141601],"category_scores_gemma":[0.00005858983,0.00007925885,0.00007856661,0.00003968019,0.00008202123,0.000008110153,0.00002975416,0.00006911252,4.940247e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002512609,"about_ca_system_score_gemma":0.0001978376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001241606,"about_ca_topic_score_gemma":0.000001363397,"domain_scores_codex":[0.999329,0.00001092636,0.0003687405,0.00007781045,0.00008419347,0.0001293601],"domain_scores_gemma":[0.9993743,0.00001493886,0.0003045478,0.00006454847,0.0001840305,0.00005759919],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002396922,0.0004810241,0.004279522,0.0007347714,0.0005840805,0.00001305167,0.0004165458,0.1664622,0.2221271,0.1475171,0.0008401904,0.4541474],"study_design_scores_gemma":[0.0245339,0.01329604,0.004594253,0.0006797469,0.0001791529,0.0007598543,0.0003811435,0.1210487,0.1188616,0.3490658,0.3647464,0.001853389],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2452005,0.0009465626,0.753168,0.000338169,0.00007726662,0.0001837647,0.00002301858,0.000002986074,0.00005965091],"genre_scores_gemma":[0.7450342,0.00002254898,0.2544381,0.0003266402,0.0001025613,0.000008376524,0.00005222497,0.000005358241,0.00001002275],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4998337,"threshold_uncertainty_score":0.3232082,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04200507321570857,"gpt":0.324280688309369,"spread":0.2822756150936604,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002759259,0.0001629151,0.0002869601,0.0002262464,0.0001130309,0.00003512691,0.0001598636,0.000158452,0.00001150066],"category_scores_gemma":[0.00004396917,0.0001020512,0.0001893332,0.0001661044,0.0001089481,0.00003335437,0.0000285184,0.00006528159,2.823543e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004919911,"about_ca_system_score_gemma":0.0002750355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001057229,"about_ca_topic_score_gemma":0.000009160169,"domain_scores_codex":[0.9990487,0.00004984085,0.0004460092,0.0001744764,0.0001128056,0.0001682026],"domain_scores_gemma":[0.9987075,0.00007119942,0.0006120833,0.0001297055,0.0003655669,0.0001139878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001562546,0.0004532226,0.02625725,0.0001026014,0.002248159,0.000001067813,0.0007410508,0.04262433,0.802986,0.0003890305,0.002631233,0.1200035],"study_design_scores_gemma":[0.006277584,0.002581329,0.01408541,0.000102347,0.0009467544,0.00009209957,0.001066976,0.4133759,0.5482839,0.001513171,0.01072801,0.0009465591],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5314922,0.0001988112,0.4676932,0.0001250478,0.00007000979,0.00009658169,0.0003128273,0.000002126501,0.000009202172],"genre_scores_gemma":[0.9313293,0.0002545055,0.06762753,0.0003003752,0.0001553319,0.00004409613,0.0002695167,0.000008842723,0.0000105025],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4000657,"threshold_uncertainty_score":0.4161528,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}