{"meta":{"query_hash":"6edd568916c6","filters":{"venue":"Algorithms for Molecular Biology"},"cohort_total":49,"direct_labels_cover":0,"predictions_cover":49,"exported":49,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/6edd568916c6","api":"https://metacan.xera.ac/api/v1/cohort?venue=Algorithms+for+Molecular+Biology"},"results":[{"id":"W1039758599","doi":"10.1186/s13015-015-0053-5","title":"Detecting conserved protein complexes using a dividing-and-matching algorithm and unequally lenient criteria for network comparison","year":2015,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Computer science; Protein superfamily; Similarity (geometry); Matching (statistics); Computational biology; Drosophila melanogaster; Data mining; Topology (electrical circuits); Artificial intelligence; Biology; Genetics; Mathematics; Gene","score_opus":0.05642390626907818,"score_gpt":0.33955929739629825,"score_spread":0.2831353911272201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1039758599","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10228138,0.0007007029,0.89293087,0.000111524525,0.000042595377,0.00028602817,0.00016291846,0.0020049282,0.0014789492],"genre_scores_gemma":[0.3124883,0.00034298364,0.68396455,0.00007974855,0.000022793696,0.00025475316,0.0010255734,0.00024141061,0.0015798756],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99702364,0.00064599444,0.0003314021,0.0008828885,0.00085999706,0.0002560298],"domain_scores_gemma":[0.99679714,0.0011140119,0.000581622,0.0005419127,0.00074443675,0.00022081293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031121017,0.0014001469,0.001618411,0.00802498,0.0013115742,0.0018659816,0.0021407013,0.0015658052,0.0019433385],"category_scores_gemma":[0.0081032375,0.0006735438,0.0014440536,0.004020135,0.0011871482,0.0032818129,0.0018396492,0.0008487918,0.00055114744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011344525,0.00043602276,0.026571335,0.0006901235,0.0006692527,0.0008996264,0.000957914,0.09429983,0.091877736,0.01994274,0.004352648,0.7581683],"study_design_scores_gemma":[0.00008662178,0.00019302081,0.008239981,0.00003418251,0.00015827386,0.0006281127,0.00029514797,0.9369275,0.03571688,0.012379595,0.005267006,0.00007374098],"about_ca_topic_score_codex":0.0035948628,"about_ca_topic_score_gemma":0.002911183,"teacher_disagreement_score":0.00802498,"about_ca_system_score_codex":0.0011554318,"about_ca_system_score_gemma":0.0015746999,"threshold_uncertainty_score":0.016458571},"labels":[],"label_agreement":null},{"id":"W1909028472","doi":"10.1186/s13015-015-0055-3","title":"Erratum to: Inferring interaction type in gene regulatory networks using co-expression data","year":2015,"lang":"en","type":"erratum","venue":"Algorithms for Molecular Biology","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Toronto","funders":"","keywords":"Computer science; Expression (computer science); Type (biology); Data type; Computational biology; Data mining; Gene regulatory network; Data science; Gene expression; Gene; Biology; Genetics; Ecology","score_opus":0.04794319886971091,"score_gpt":0.3569521048979705,"score_spread":0.3090089060282596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1909028472","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047810786,0.00290099,0.018720828,0.056372337,0.9078612,0.00006316386,0.005408953,0.0025620318,0.0056325207],"genre_scores_gemma":[0.033394255,0.022379212,0.12473623,0.16420671,0.22592784,0.0006022717,0.03665561,0.015578536,0.37651935],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959882,0.00066411705,0.0006960086,0.00062339316,0.0018302005,0.00019801807],"domain_scores_gemma":[0.9801364,0.007498496,0.0010928387,0.0017731597,0.008706379,0.00079270895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037793287,0.0028663408,0.002086436,0.004236308,0.0031862645,0.004299688,0.0033779158,0.0048246705,0.06560611],"category_scores_gemma":[0.05956685,0.0017140656,0.0018526847,0.003754602,0.0027230694,0.0033771999,0.002567299,0.008589642,0.037304077],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003532688,0.00000907613,0.00011444033,0.0000949035,0.000018417877,0.00019487982,0.000021204993,0.0002008113,0.00007228255,0.0012704047,0.98806375,0.009904411],"study_design_scores_gemma":[0.00006673961,0.000026962178,0.00068849913,0.00043508277,0.000084878906,0.0013397966,0.00009536841,0.0016700296,0.00082868576,0.006694669,0.9879848,0.00008450229],"about_ca_topic_score_codex":0.0169394,"about_ca_topic_score_gemma":0.02885329,"teacher_disagreement_score":0.06560611,"about_ca_system_score_codex":0.0038706851,"about_ca_system_score_gemma":0.0057376786,"threshold_uncertainty_score":0.21947432},"labels":[],"label_agreement":null},{"id":"W1965359119","doi":"10.1186/1748-7188-6-23","title":"ReCoil - an algorithm for compression of extremely large datasets of dna data","year":2011,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Data compression; Redundancy (engineering); Algorithm; Encoding (memory); Compression (physics); Volume (thermodynamics); Data compression ratio; Lossless compression; Compression ratio; Sequence (biology); Data mining; Image compression; Artificial intelligence; Biology; Physics","score_opus":0.10042025754405944,"score_gpt":0.3489168214591663,"score_spread":0.24849656391510688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965359119","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011216672,0.0008912312,0.98154026,0.00019866948,0.00011915559,0.00014197806,0.00033975928,0.004326735,0.001225478],"genre_scores_gemma":[0.050987583,0.0007941766,0.94133395,0.00013485295,0.00007784322,0.0003526822,0.001749144,0.00065903284,0.0039107166],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919444,0.00008505272,0.00009562844,0.00014012423,0.00042152966,0.00006324489],"domain_scores_gemma":[0.99874383,0.00048183237,0.0001294765,0.0002732238,0.00032608298,0.000045583354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089211477,0.0010778476,0.000677414,0.0016711322,0.00074723817,0.0013135062,0.0014337131,0.0009189962,0.0032102054],"category_scores_gemma":[0.0035292257,0.00037120897,0.00062621385,0.0021343457,0.00071541476,0.0019472436,0.0014781661,0.001427954,0.002221529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067196105,0.00013180074,0.0015128239,0.00041157045,0.000101256555,0.00038243085,0.00037809563,0.029566512,0.07874899,0.022335947,0.0179166,0.8478421],"study_design_scores_gemma":[0.0002282465,0.00040146126,0.0017564312,0.00012808133,0.0000649136,0.0019404469,0.00021259741,0.5980841,0.3018737,0.023736779,0.07145295,0.00012027011],"about_ca_topic_score_codex":0.00082282454,"about_ca_topic_score_gemma":0.0010348551,"teacher_disagreement_score":0.0032102054,"about_ca_system_score_codex":0.00050893327,"about_ca_system_score_gemma":0.0007632228,"threshold_uncertainty_score":0.010739267},"labels":[],"label_agreement":null},{"id":"W1978336838","doi":"10.1186/1748-7188-5-39","title":"Sparsification of RNA structure prediction including pseudoknots","year":2010,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"SFU Community Trust Endowment Fund; Natural Sciences and Engineering Research Council of Canada; Mitacs; Deutsche Forschungsgemeinschaft; Michael Smith Health Research BC","keywords":"Computer science; Computational biology; Data mining; Biology","score_opus":0.016752117223052997,"score_gpt":0.28825543100402723,"score_spread":0.27150331378097425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978336838","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0610745,0.00012991817,0.9369856,0.00010825534,0.000014491008,0.000033942386,0.000066388115,0.0006594481,0.0009274891],"genre_scores_gemma":[0.42373714,0.00022559802,0.57375705,0.000069025846,0.000044363063,0.00010549221,0.0005677876,0.0001412684,0.0013523416],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99967456,0.00010501044,0.000018372408,0.00007487743,0.000093041366,0.000034154316],"domain_scores_gemma":[0.99782515,0.0014221967,0.00017818103,0.0003500521,0.0001607182,0.000063726344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068058516,0.00053267874,0.000623235,0.00035434868,0.00023774292,0.00044909085,0.0008039713,0.0006714423,0.0016317212],"category_scores_gemma":[0.0027702963,0.0002664695,0.0006371141,0.0004218336,0.00071365386,0.00096167176,0.0008497147,0.0008718004,0.00048813137],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026414872,0.00006869813,0.001674902,0.00018391763,0.000049355713,0.00019795678,0.00016106914,0.8175046,0.02152788,0.012988744,0.0009080148,0.14447078],"study_design_scores_gemma":[0.0000082151255,0.000021603228,0.00017307645,0.000005894897,0.0000034455666,0.000043589353,0.000010862692,0.9876792,0.005655064,0.006010697,0.00038445846,0.0000040148593],"about_ca_topic_score_codex":0.001734378,"about_ca_topic_score_gemma":0.0017596446,"teacher_disagreement_score":0.001734378,"about_ca_system_score_codex":0.0003004645,"about_ca_system_score_gemma":0.00069563044,"threshold_uncertainty_score":0.0054585934},"labels":[],"label_agreement":null},{"id":"W2017156855","doi":"10.1186/1748-7188-5-35","title":"Estimating the evidence of selection and the reliability of inference in unigenic evolution","year":2010,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario","keywords":"Inference; Computer science; Selection (genetic algorithm); Reliability (semiconductor); Data mining; Data science; Econometrics; Machine learning; Artificial intelligence; Mathematics","score_opus":0.007156918695487575,"score_gpt":0.2929834438655729,"score_spread":0.28582652517008533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017156855","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2596993,0.0011222117,0.736867,0.0003195297,0.000049924278,0.000116876756,0.00019631426,0.00045848518,0.0011703733],"genre_scores_gemma":[0.8758316,0.00026710087,0.12285253,0.00013499518,0.00006718486,0.00015166761,0.0003488829,0.00012210614,0.00022403566],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96498066,0.022975085,0.0020934688,0.0045165187,0.004868459,0.00056564267],"domain_scores_gemma":[0.46218124,0.49269447,0.021870961,0.014758274,0.007266737,0.0012282446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.053922478,0.0014006203,0.0017415358,0.00468706,0.001087431,0.0024475642,0.0028075527,0.0024621414,0.0011667141],"category_scores_gemma":[0.27697566,0.0008559708,0.0018021617,0.0022367311,0.00577983,0.0029183575,0.0034645363,0.0031390362,0.00027871464],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020855675,0.00030281677,0.36094782,0.0016814277,0.0034396972,0.0010873365,0.0022113672,0.40239307,0.024952296,0.03820145,0.0011340451,0.16156307],"study_design_scores_gemma":[0.00012862477,0.0004949409,0.04162192,0.00020848034,0.0003567286,0.0006411128,0.00026847897,0.83941716,0.01992181,0.09565223,0.0011317069,0.0001568568],"about_ca_topic_score_codex":0.001510881,"about_ca_topic_score_gemma":0.0010068355,"teacher_disagreement_score":0.053922478,"about_ca_system_score_codex":0.0013502642,"about_ca_system_score_gemma":0.0010475712,"threshold_uncertainty_score":0.2851727},"labels":[],"label_agreement":null},{"id":"W2039803514","doi":"10.1186/1748-7188-6-11","title":"Listing all sorting reversals in quadratic time","year":2011,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Permutation (music); Sorting; Listing (finance); Computer science; Identity (music); Sorting algorithm; Quadratic equation; Algorithm; Time complexity; Combinatorics; Mathematics","score_opus":0.03749375139985743,"score_gpt":0.3000611005173297,"score_spread":0.26256734911747226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039803514","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09165924,0.0018543652,0.805492,0.0020637193,0.000734928,0.00088960864,0.00887869,0.047360532,0.04106688],"genre_scores_gemma":[0.25066498,0.0007028634,0.69113624,0.0008328294,0.00020190957,0.00044973966,0.015495919,0.0035928767,0.036922716],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99837273,0.00020091429,0.00017840552,0.00030557133,0.000631098,0.00031122248],"domain_scores_gemma":[0.9964193,0.0013498674,0.00028352466,0.0009926859,0.0007677502,0.00018688562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007699687,0.0017416494,0.0013990221,0.0014022953,0.0015251973,0.0032035094,0.0022247138,0.0010001041,0.04062846],"category_scores_gemma":[0.0052713933,0.0006443402,0.0010832389,0.0034824314,0.0005955452,0.00437428,0.0013165133,0.0013412066,0.0119547825],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061141496,0.0004388433,0.0021317352,0.0007880526,0.00008104974,0.00023126697,0.0001546529,0.01648172,0.024565427,0.0166864,0.062701955,0.8751275],"study_design_scores_gemma":[0.0016099779,0.0012933094,0.005519204,0.00026519402,0.00034034997,0.0020342346,0.0010011116,0.28332913,0.1381874,0.34846523,0.21757087,0.00038391846],"about_ca_topic_score_codex":0.0031978758,"about_ca_topic_score_gemma":0.008839201,"teacher_disagreement_score":0.04062846,"about_ca_system_score_codex":0.0012314533,"about_ca_system_score_gemma":0.0037471363,"threshold_uncertainty_score":0.13591576},"labels":[],"label_agreement":null},{"id":"W2040607633","doi":"10.1186/1748-7188-7-3","title":"MRL and SuperFine+MRL: new supertree methods","year":2012,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; John Simon Guggenheim Memorial Foundation; National Science Foundation","keywords":"Supertree; Heuristics; Matrix representation; Heuristic; Matrix (chemical analysis); Tree (set theory); Representation (politics); Set (abstract data type); Computer science; Algorithm; Range (aeronautics); Mathematical optimization; Mathematics; Combinatorics; Artificial intelligence; Biology; Phylogenetic tree; Engineering; Chemistry","score_opus":0.026864003492504198,"score_gpt":0.3475609793836081,"score_spread":0.3206969758911039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040607633","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004989733,0.0009843371,0.9868412,0.00051922613,0.00007604611,0.00010744655,0.00058466004,0.0043113455,0.0015859797],"genre_scores_gemma":[0.029650975,0.00035525442,0.9651207,0.00045556293,0.00011503994,0.00025836044,0.0015774118,0.0015393655,0.00092730724],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99513865,0.0021610432,0.00027397787,0.00090061594,0.0013264065,0.0001992629],"domain_scores_gemma":[0.9822801,0.010442045,0.0015941992,0.0029520409,0.0022713458,0.00046040045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006875926,0.0017958952,0.0016228241,0.0054555945,0.0015931946,0.0026746653,0.004865044,0.0029238472,0.009882542],"category_scores_gemma":[0.022585254,0.0013306513,0.002975983,0.00437537,0.0014863767,0.007684549,0.0038907751,0.0045738188,0.0047039725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033867834,0.00022260669,0.0047450988,0.001105417,0.00044601466,0.00037139936,0.0008662182,0.18688259,0.007113055,0.06251036,0.030337123,0.70506144],"study_design_scores_gemma":[0.000095431875,0.00008929882,0.0008675513,0.0001566018,0.0000827257,0.00038488692,0.0001410295,0.8601162,0.003065268,0.10827842,0.026637264,0.00008540193],"about_ca_topic_score_codex":0.0029469333,"about_ca_topic_score_gemma":0.006165359,"teacher_disagreement_score":0.009882542,"about_ca_system_score_codex":0.0019276133,"about_ca_system_score_gemma":0.0022106562,"threshold_uncertainty_score":0.03636384},"labels":[],"label_agreement":null},{"id":"W2089039157","doi":"10.1186/1748-7188-3-1","title":"Reconstructing phylogenies from noisy quartets in polynomial time with a high success probability","year":2008,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Polynomial; Time complexity; Data science; Algorithm; Mathematics","score_opus":0.01217716393102334,"score_gpt":0.2379344202067291,"score_spread":0.22575725627570578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089039157","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09027831,0.00037972286,0.9044914,0.0005351148,0.000038948532,0.00007808558,0.00026664458,0.0024825735,0.0014491803],"genre_scores_gemma":[0.5515291,0.00032146616,0.4443842,0.0002383379,0.00008086288,0.00022075429,0.0013157594,0.00046653615,0.0014430105],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99730116,0.00060444354,0.0002017795,0.000654867,0.000971937,0.00026592964],"domain_scores_gemma":[0.9717235,0.020626413,0.0017611005,0.003875153,0.0014114316,0.00060251006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034653696,0.000871464,0.0012995927,0.00074277434,0.00097502617,0.0019920678,0.0020655007,0.0014568606,0.0030684713],"category_scores_gemma":[0.019096255,0.0005595773,0.0014952979,0.0012553656,0.0011957916,0.003012011,0.0017986824,0.0022443517,0.0013667048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012080012,0.00038348755,0.016318968,0.0008049202,0.00022796135,0.0005295329,0.0007205277,0.7170675,0.026836716,0.02218099,0.0054700053,0.20825148],"study_design_scores_gemma":[0.000051521598,0.00004674812,0.00077457825,0.00001216264,0.00002067609,0.00022379064,0.000042144165,0.97995615,0.0035665121,0.01455858,0.0007333563,0.000013730793],"about_ca_topic_score_codex":0.0024694048,"about_ca_topic_score_gemma":0.0032385373,"teacher_disagreement_score":0.0034653696,"about_ca_system_score_codex":0.0013643801,"about_ca_system_score_gemma":0.00257575,"threshold_uncertainty_score":0.018326819},"labels":[],"label_agreement":null},{"id":"W2098784730","doi":"10.1186/1748-7188-6-16","title":"Efficient unfolding pattern recognition in single molecule force spectroscopy data","year":2011,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Force Microscopy Techniques and Applications","field":"Physics and Astronomy","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Bundesministerium für Bildung und Forschung","keywords":"Bacteriorhodopsin; Pairwise comparison; Algorithm; Force spectroscopy; Molecule; Computer science; Sequence (biology); Biological system; Chemistry; Physics; Crystallography; Membrane; Artificial intelligence; Biology","score_opus":0.052064920589266546,"score_gpt":0.32267397343574095,"score_spread":0.2706090528464744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098784730","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05646852,0.00020974586,0.9264839,0.00019908989,0.00003862144,0.0002181919,0.0014177216,0.014573321,0.00039080819],"genre_scores_gemma":[0.12189729,0.00008185412,0.87375927,0.000074542535,0.000027615139,0.0002166761,0.0031921212,0.00032325528,0.00042743827],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877685,0.00015367544,0.00013316431,0.0004331055,0.00040921965,0.00009406084],"domain_scores_gemma":[0.99615884,0.0018575168,0.0005978349,0.0005352031,0.00070468633,0.00014595751],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014609979,0.0013154291,0.0012236853,0.0029646915,0.0006485231,0.0014384188,0.0018721313,0.0016974986,0.0019542547],"category_scores_gemma":[0.006164027,0.00043791783,0.0011818678,0.002140022,0.00052779855,0.0012547073,0.00088380434,0.0012005834,0.0023787662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053146796,0.0004622539,0.014431533,0.0005604525,0.00024205742,0.00045265013,0.00021996048,0.102404974,0.087604836,0.0022506872,0.006879905,0.7839592],"study_design_scores_gemma":[0.000024724728,0.00006294982,0.0032917268,0.000017184138,0.000017189677,0.00027104543,0.00005700781,0.9628299,0.026246287,0.0049506105,0.0022088808,0.000022501003],"about_ca_topic_score_codex":0.002162217,"about_ca_topic_score_gemma":0.0020493162,"teacher_disagreement_score":0.0029646915,"about_ca_system_score_codex":0.0007254329,"about_ca_system_score_gemma":0.0010209968,"threshold_uncertainty_score":0.0077266097},"labels":[],"label_agreement":null},{"id":"W2104168759","doi":"10.1186/1748-7188-7-6","title":"Computing evolutionary distinctiveness indices in large scale analysis","year":2012,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Evolution and Paleontology Studies","field":"Earth and Planetary Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Simon Fraser University; Natural Sciences and Engineering Research Council of Canada; Isaac Newton Institute for Mathematical Sciences","keywords":"Optimal distinctiveness theory; Phylogenetic tree; Taxon; Extinction (optical mineralogy); Endangered species; Supertree; Clade; Evolutionary biology; Sister group; Tree (set theory); Set (abstract data type); Biology; Computer science; Ecology; Combinatorics; Mathematics; Paleontology","score_opus":0.015726275067789,"score_gpt":0.2905335002008223,"score_spread":0.2748072251330333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104168759","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062343027,0.00018417237,0.9353372,0.00015907493,0.000022290586,0.000064106,0.00015330686,0.0010041024,0.0007327048],"genre_scores_gemma":[0.367281,0.000082766,0.6312091,0.00007507059,0.00004353392,0.00018454732,0.00053260976,0.000118904,0.0004725702],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99819475,0.00076625927,0.00012969614,0.00034568063,0.00044238445,0.000121169425],"domain_scores_gemma":[0.9850904,0.010992049,0.0011841364,0.0015373632,0.00074266695,0.00045339952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005226947,0.00096384535,0.0011401811,0.003283217,0.00082044874,0.0020457385,0.0017784982,0.00090468203,0.0021532553],"category_scores_gemma":[0.020297922,0.00057143986,0.00104766,0.002881007,0.0015129052,0.0029636486,0.0027600455,0.0015612727,0.00050930213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028291254,0.00021220464,0.02188387,0.00019863475,0.00025440138,0.00022944347,0.00036293187,0.54406005,0.006405225,0.045223087,0.003185519,0.37770176],"study_design_scores_gemma":[0.000022410939,0.000039460087,0.0013085282,0.000007720794,0.0000125238075,0.000030933526,0.000046167977,0.9342855,0.00075224694,0.063091844,0.00038941664,0.00001311793],"about_ca_topic_score_codex":0.0014716295,"about_ca_topic_score_gemma":0.002405535,"teacher_disagreement_score":0.005226947,"about_ca_system_score_codex":0.0012136417,"about_ca_system_score_gemma":0.0010790532,"threshold_uncertainty_score":0.027643025},"labels":[],"label_agreement":null},{"id":"W2110150937","doi":"10.1186/1748-7188-5-34","title":"Predicting direct protein interactions from affinity purification mass spectrometry data","year":2010,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Air Force Office of Scientific Research; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Probabilistic logic; Set (abstract data type); Identification (biology); Data mining; Algorithm; Sensitivity (control systems); Graph; Artificial intelligence; Theoretical computer science; Biology","score_opus":0.017337887929958603,"score_gpt":0.2870760176882253,"score_spread":0.2697381297582667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110150937","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3198604,0.00047264833,0.673646,0.00039542644,0.000012218204,0.00017032117,0.001592964,0.002514884,0.0013352131],"genre_scores_gemma":[0.67673296,0.00040944933,0.31715834,0.000106289706,0.000023783825,0.0001431507,0.00438681,0.00014563705,0.00089349266],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994221,0.00013841077,0.00003743356,0.00021064143,0.00015619615,0.000035349836],"domain_scores_gemma":[0.9956793,0.003047455,0.0005984282,0.0002566063,0.00028597986,0.00013222545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010375417,0.0011886066,0.00064703554,0.002131282,0.0005009715,0.00086555205,0.0011338022,0.0013571972,0.0012219441],"category_scores_gemma":[0.004856341,0.000425995,0.00068573706,0.0012302441,0.00048023037,0.0009934201,0.00067320175,0.0008899575,0.00086652004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006514582,0.0005581711,0.08270056,0.000623273,0.00032732316,0.0006602641,0.00011965608,0.67285836,0.084225655,0.0055051595,0.0027601132,0.14900991],"study_design_scores_gemma":[0.000020371821,0.000052906944,0.0065432214,0.000010141812,0.00003471943,0.00025655265,0.000019557658,0.96240294,0.019477928,0.010283904,0.0008831879,0.000014613293],"about_ca_topic_score_codex":0.0017658016,"about_ca_topic_score_gemma":0.0024632672,"teacher_disagreement_score":0.002131282,"about_ca_system_score_codex":0.000793159,"about_ca_system_score_gemma":0.0007406111,"threshold_uncertainty_score":0.005754769},"labels":[],"label_agreement":null},{"id":"W2110922051","doi":"10.1186/1748-7188-7-32","title":"Towards a practical O(n logn) phylogeny algorithm","year":2012,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Phylogenetics; Algorithm; Biology","score_opus":0.03332692126473845,"score_gpt":0.3493959329378441,"score_spread":0.31606901167310564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110922051","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01342851,0.00042664117,0.97477573,0.001148787,0.000119310746,0.00011526834,0.00030097846,0.006327308,0.003357491],"genre_scores_gemma":[0.07903437,0.0002539037,0.9147625,0.00047395623,0.000102637656,0.00021163041,0.0012851069,0.0006540452,0.0032218324],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976439,0.0005671125,0.00015573547,0.0006652991,0.0006987705,0.00026913476],"domain_scores_gemma":[0.9939839,0.0021973015,0.00031461174,0.0022465542,0.0010381632,0.0002194786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025072931,0.0009875656,0.0011864608,0.0011805625,0.0011010413,0.0022859473,0.003628804,0.0024836077,0.012358628],"category_scores_gemma":[0.012380274,0.0007528992,0.00072915613,0.002784581,0.0010085482,0.005787378,0.002954961,0.0025767968,0.009857686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011028085,0.00032453806,0.002510292,0.00070748525,0.00007605806,0.00024745535,0.00047041927,0.064167276,0.0225781,0.07555318,0.04582485,0.7864376],"study_design_scores_gemma":[0.0005421766,0.00019525665,0.0009539848,0.00009169448,0.000041325013,0.00074947457,0.00020191791,0.77948684,0.012123653,0.17373951,0.031824734,0.00004933143],"about_ca_topic_score_codex":0.0017807964,"about_ca_topic_score_gemma":0.0024140691,"teacher_disagreement_score":0.012358628,"about_ca_system_score_codex":0.0011353651,"about_ca_system_score_gemma":0.002340284,"threshold_uncertainty_score":0.04134375},"labels":[],"label_agreement":null},{"id":"W2115843315","doi":"10.1186/1748-7188-6-8","title":"An FPT haplotyping algorithm on pedigrees with a small number of sites","year":2011,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pedigree chart; Computer science; Algorithm; Haplotype; Data mining; Biology; Genetics","score_opus":0.03441372841316802,"score_gpt":0.3044060543597645,"score_spread":0.26999232594659645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115843315","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.065353185,0.0004338215,0.9245601,0.0007035362,0.00005945863,0.00030245155,0.0015561976,0.0035148324,0.0035163497],"genre_scores_gemma":[0.13450278,0.00011947506,0.8600463,0.00018614346,0.00003302355,0.0004371898,0.002665229,0.00025421425,0.001755593],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993192,0.0002201858,0.00005607564,0.00020616184,0.000111246736,0.000087109715],"domain_scores_gemma":[0.99691737,0.0021333697,0.00015504684,0.0004156859,0.000267287,0.00011124746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017176487,0.0007437124,0.00097510515,0.0011523576,0.000771151,0.0008550444,0.0017291773,0.001402706,0.006458589],"category_scores_gemma":[0.0075208703,0.00059836556,0.0008482368,0.0017608671,0.00049339776,0.0017505283,0.0014841937,0.0009233091,0.0012735261],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004268803,0.00015284802,0.0056641917,0.00022041285,0.000102500526,0.00041361677,0.00027347266,0.33669513,0.0029922535,0.013195186,0.013345798,0.6265177],"study_design_scores_gemma":[0.00021875264,0.000051882747,0.00091276894,0.000023900671,0.000029651233,0.0003093229,0.000049115977,0.9672974,0.0006731858,0.027948936,0.002474011,0.000011019391],"about_ca_topic_score_codex":0.005769014,"about_ca_topic_score_gemma":0.0047769067,"teacher_disagreement_score":0.006458589,"about_ca_system_score_codex":0.0009432902,"about_ca_system_score_gemma":0.0017955977,"threshold_uncertainty_score":0.021606088},"labels":[],"label_agreement":null},{"id":"W2116920786","doi":"10.1186/1748-7188-8-24","title":"Asymptotic structural properties of quasi-random saturated structures of RNA","year":2013,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"National Science Foundation","keywords":"Pseudoknot; Combinatorics; Mathematics; Distribution (mathematics); Loop (graph theory); Statistical physics; Discrete mathematics; Physics; RNA; Mathematical analysis; Chemistry","score_opus":0.012651922422076592,"score_gpt":0.2524425439793396,"score_spread":0.239790621557263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116920786","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80769414,0.00049492967,0.18366796,0.000517516,0.000019334031,0.00007060584,0.00041110977,0.0005183263,0.006606049],"genre_scores_gemma":[0.9849812,0.0002411385,0.01274645,0.00011339851,0.00004275232,0.00010017888,0.00052481814,0.00012670839,0.0011233403],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99915564,0.00025769183,0.00004560937,0.00018541349,0.00023577889,0.00011974553],"domain_scores_gemma":[0.9775604,0.015306264,0.0030103582,0.0015548236,0.0016192496,0.0009489483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020525858,0.00041550127,0.00042198162,0.0016298519,0.0007845067,0.0013521113,0.0013170996,0.0010168275,0.004533725],"category_scores_gemma":[0.019958662,0.0006565665,0.000575831,0.0008201653,0.0025525738,0.002868885,0.0011617751,0.0010761905,0.00052854134],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005441262,0.00034968142,0.040059943,0.00065313105,0.00017694816,0.0010488117,0.0008071937,0.25321445,0.04401881,0.63149166,0.0041636257,0.023471698],"study_design_scores_gemma":[0.00005042617,0.00018363984,0.0070795654,0.00004800291,0.000038577306,0.0008437289,0.00018390587,0.7047559,0.006914783,0.2788724,0.0009809133,0.000048071164],"about_ca_topic_score_codex":0.00057214726,"about_ca_topic_score_gemma":0.0006807185,"teacher_disagreement_score":0.004533725,"about_ca_system_score_codex":0.0017074926,"about_ca_system_score_gemma":0.00067228364,"threshold_uncertainty_score":0.015166879},"labels":[],"label_agreement":null},{"id":"W2117719890","doi":"10.1186/s13015-015-0054-4","title":"Inferring interaction type in gene regulatory networks using co-expression data","year":2015,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Toronto","funders":"Canadian Institutes of Health Research; National Center for Research Resources; Institute for Research in Fundamental Sciences; National Institute of General Medical Sciences; Directorate for Biological Sciences; National Institutes of Health","keywords":"Gene regulatory network; Computer science; Benchmark (surveying); Computational biology; Systems biology; In silico; Data type; Genomics; Data mining; Biological network; Gene; Genome; Biology; Gene expression; Genetics","score_opus":0.06669697343404381,"score_gpt":0.356877915823286,"score_spread":0.2901809423892422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117719890","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31257752,0.0006300165,0.6822113,0.00019038927,0.000017643722,0.0000826975,0.0012557642,0.0011606456,0.0018740521],"genre_scores_gemma":[0.76791567,0.0003398814,0.22851475,0.000053700478,0.0000164004,0.000069762245,0.0024836194,0.00006127631,0.0005449168],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988808,0.00039170988,0.00005672852,0.00037917335,0.00022729093,0.00006435766],"domain_scores_gemma":[0.9942636,0.0043934835,0.00058771047,0.00035190396,0.00030916958,0.00009407197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016535707,0.00070533267,0.00045822095,0.0026581718,0.0004713096,0.0008363262,0.0007512834,0.00064719684,0.00085904554],"category_scores_gemma":[0.006584062,0.00028115668,0.00074998627,0.0015909206,0.00066523015,0.0009899325,0.00055832876,0.0008025763,0.00034679985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007713122,0.0002655593,0.15973191,0.0005575622,0.00036781564,0.00033763252,0.00033532802,0.5780657,0.06471255,0.012069545,0.0013482311,0.18143682],"study_design_scores_gemma":[0.000010509605,0.000029771376,0.009504589,0.000017551667,0.000039115675,0.00011491848,0.000060102448,0.95961064,0.01832519,0.011289881,0.0009816698,0.000016034803],"about_ca_topic_score_codex":0.002654001,"about_ca_topic_score_gemma":0.004365096,"teacher_disagreement_score":0.0026581718,"about_ca_system_score_codex":0.000832766,"about_ca_system_score_gemma":0.0005559529,"threshold_uncertainty_score":0.008745015},"labels":[],"label_agreement":null},{"id":"W2130654549","doi":"10.1186/1748-7188-8-20","title":"Fast half-sibling population reconstruction: theory and algorithms","year":2013,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario","keywords":"Kinship; Computer science; Heuristic; Population; Inference; Inheritance (genetic algorithm); Cluster analysis; Integer (computer science); Theoretical computer science; Data mining; Machine learning; Artificial intelligence; Biology; Demography","score_opus":0.00999279403419891,"score_gpt":0.26674908478950504,"score_spread":0.25675629075530615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130654549","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007748647,0.0003369909,0.9888713,0.00026202737,0.000022947504,0.00007337811,0.00015801165,0.0009014406,0.001625281],"genre_scores_gemma":[0.09128582,0.0003355918,0.9050992,0.00017164397,0.000053434822,0.0002933533,0.0008847924,0.0002372924,0.0016389601],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986992,0.00047923016,0.00008372525,0.00027070876,0.00033497193,0.00013219172],"domain_scores_gemma":[0.99084693,0.006675729,0.00048106522,0.0010264642,0.0007571218,0.0002126512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034223448,0.0011406449,0.0012060824,0.002033811,0.0013798481,0.0016831052,0.004167564,0.0020738798,0.006487633],"category_scores_gemma":[0.014184856,0.00087193376,0.0015110939,0.0024926967,0.0014223651,0.0036243466,0.0025701944,0.0024919764,0.0017327286],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024306554,0.0001759189,0.005311549,0.00036522263,0.00014265218,0.00020220355,0.00041689433,0.56996405,0.0016881813,0.110382035,0.011214378,0.29989377],"study_design_scores_gemma":[0.000030052744,0.000018771654,0.00026340934,0.00002718998,0.000015633053,0.00010757734,0.000048955088,0.9099054,0.00056882884,0.08758961,0.0014126434,0.000011825819],"about_ca_topic_score_codex":0.005080748,"about_ca_topic_score_gemma":0.004970049,"teacher_disagreement_score":0.006487633,"about_ca_system_score_codex":0.0015957534,"about_ca_system_score_gemma":0.0021098978,"threshold_uncertainty_score":0.021703303},"labels":[],"label_agreement":null},{"id":"W2132081807","doi":"10.1186/1748-7188-5-5","title":"Fast prediction of RNA-RNA interaction","year":2010,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Mitacs; Bundesministerium für Bildung und Forschung; Deutsche Forschungsgemeinschaft; Michael Smith Health Research BC","keywords":"Computer science; RNA; Heuristic; Set (abstract data type); Computational biology; Translation (biology); Class (philosophy); Variety (cybernetics); Nucleic acid structure; Non-coding RNA; Theoretical computer science; Algorithm; Machine learning; Data mining; Artificial intelligence; Messenger RNA; Gene; Biology; Genetics","score_opus":0.011541696454329927,"score_gpt":0.2749254580283451,"score_spread":0.26338376157401516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132081807","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14683135,0.0005595079,0.8446221,0.00015641727,0.000042116328,0.00010291362,0.0007725426,0.0053908024,0.0015223086],"genre_scores_gemma":[0.43709987,0.00018176918,0.5579763,0.00007499187,0.000036544774,0.00019696285,0.0026520202,0.00023413092,0.0015474511],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993845,0.00014012896,0.000027497357,0.0001841251,0.00020981533,0.00005391624],"domain_scores_gemma":[0.9972683,0.0017862256,0.00022626127,0.00021688313,0.00040992393,0.000092410955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086109794,0.0011451107,0.0011836174,0.0012763354,0.0005873353,0.0007488785,0.0014703108,0.0016243375,0.0023225558],"category_scores_gemma":[0.0036350538,0.0005130982,0.0005957672,0.001110443,0.00042737692,0.00087237713,0.0005598064,0.0008876167,0.0012494243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065323117,0.00031081415,0.0095750475,0.00027689687,0.00016767214,0.0002963279,0.00005883219,0.7559415,0.024939721,0.005185364,0.0071625994,0.19543195],"study_design_scores_gemma":[0.000021932303,0.000025072355,0.0006894579,0.0000030403862,0.000008010451,0.00006130669,0.0000057674056,0.9910487,0.005338572,0.0023348108,0.00045617673,0.0000071606964],"about_ca_topic_score_codex":0.0021978228,"about_ca_topic_score_gemma":0.0025756974,"teacher_disagreement_score":0.0023225558,"about_ca_system_score_codex":0.00069235027,"about_ca_system_score_gemma":0.0009784801,"threshold_uncertainty_score":0.007769704},"labels":[],"label_agreement":null},{"id":"W2133004689","doi":"10.1186/1748-7188-3-16","title":"HuMiTar: A sequence-based method for prediction of human microRNA targets","year":2008,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; National Natural Science Foundation of China","keywords":"Computational biology; False positive paradox; Untranslated region; microRNA; Biology; Computer science; Base pair; Sequence (biology); Gene; Pairing; Function (biology); Messenger RNA; Genetics; Data mining; Bioinformatics; Artificial intelligence; Physics","score_opus":0.033532319895611444,"score_gpt":0.32876540670192583,"score_spread":0.2952330868063144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133004689","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0369081,0.0008513545,0.92929137,0.00019739078,0.0000804724,0.00025621848,0.002009046,0.028049484,0.0023566156],"genre_scores_gemma":[0.1671552,0.00028377006,0.82535833,0.00027252632,0.000045401688,0.00058000797,0.0030731414,0.0011435307,0.0020881523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991289,0.0003003047,0.00005567802,0.00021804005,0.00023868763,0.000058517693],"domain_scores_gemma":[0.99887437,0.0007760796,0.0001108011,0.00007255822,0.0001254142,0.00004068331],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016555602,0.0015106479,0.0010267587,0.0026081472,0.00052703416,0.0008564893,0.0014739052,0.0012710128,0.005326834],"category_scores_gemma":[0.0033686915,0.00047674938,0.0012683414,0.0011043046,0.00043084184,0.0005885583,0.0007537672,0.0008595229,0.0017441007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013267543,0.00027106446,0.009493862,0.0006417898,0.00055886235,0.00065994554,0.0001708231,0.31920806,0.02990867,0.0064706346,0.02130452,0.60998505],"study_design_scores_gemma":[0.00004343333,0.000070078495,0.0008237208,0.000018115585,0.00003518848,0.00016601513,0.000018525174,0.98759925,0.005951607,0.0021638833,0.0030871716,0.000022983255],"about_ca_topic_score_codex":0.0024518883,"about_ca_topic_score_gemma":0.0036964111,"teacher_disagreement_score":0.005326834,"about_ca_system_score_codex":0.0006236899,"about_ca_system_score_gemma":0.0010490718,"threshold_uncertainty_score":0.01782006},"labels":[],"label_agreement":null},{"id":"W2147043108","doi":"10.1186/1748-7188-8-5","title":"Protein Structure Idealization: How accurately is it possible to model protein structures with dihedral angles?","year":2013,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada; Killam Trusts; City University of Hong Kong","keywords":"Dihedral angle; Protein structure prediction; Protein structure; Algorithm; Computer science; Gaussian; Idealization; Ideal (ethics); Physics; Computational chemistry; Chemistry","score_opus":0.0163310326278924,"score_gpt":0.2876081307289795,"score_spread":0.27127709810108713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147043108","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.079588175,0.0009906326,0.91439563,0.00068213604,0.00005243055,0.00008086429,0.0004082768,0.0012066504,0.0025952146],"genre_scores_gemma":[0.5618686,0.0011427392,0.43224776,0.00035641668,0.00003726869,0.00028118916,0.0016392808,0.000888117,0.0015386839],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977551,0.00096042093,0.00013463161,0.00045307493,0.00050980924,0.0001870086],"domain_scores_gemma":[0.99586356,0.0018769681,0.0006332532,0.0009947334,0.00045935967,0.00017218498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037377595,0.0012274869,0.0011191075,0.0008673159,0.0006264461,0.0013476016,0.0019669947,0.0013190769,0.0018266957],"category_scores_gemma":[0.011244317,0.00067726173,0.0007718131,0.0012277302,0.0015769738,0.0039257836,0.0013072111,0.0013048005,0.0011453169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006368222,0.00015173279,0.0076183667,0.00034023618,0.00016596942,0.0002538188,0.0002135378,0.8721422,0.01636051,0.033239305,0.0027950297,0.06608259],"study_design_scores_gemma":[0.00006119044,0.000093272065,0.0006048652,0.000052832525,0.00002145235,0.00021495266,0.00007994868,0.9473766,0.01104036,0.035612237,0.0048037493,0.000038538186],"about_ca_topic_score_codex":0.0029793114,"about_ca_topic_score_gemma":0.0017732177,"teacher_disagreement_score":0.0037377595,"about_ca_system_score_codex":0.0012582372,"about_ca_system_score_gemma":0.0012865228,"threshold_uncertainty_score":0.019767404},"labels":[],"label_agreement":null},{"id":"W2158093499","doi":"10.1186/1748-7188-7-14","title":"Ubiquity of synonymity: almost all large binary trees are not uniquely identified by their spectra or their immanantal polynomials","year":2012,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Graph theory and applications","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Division of Mathematical Sciences; Pacific Institute for the Mathematical Sciences; National Science Foundation","keywords":"Adjacency matrix; Combinatorics; Mathematics; Eigenvalues and eigenvectors; Laplacian matrix; Adjacency list; Binary tree; Binary number; Characteristic polynomial; Weight-balanced tree; Invariant (physics); Tree (set theory); Spectrum (functional analysis); Discrete mathematics; Polynomial; Binary search tree; Graph; Arithmetic","score_opus":0.06327891369287991,"score_gpt":0.3557059889395285,"score_spread":0.29242707524664857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158093499","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78845453,0.0010132643,0.19758545,0.0018788086,0.0001337785,0.0000504631,0.00065373175,0.00048139028,0.009748627],"genre_scores_gemma":[0.97942495,0.00019409522,0.018771082,0.0001938002,0.00007425165,0.000038795097,0.0004139614,0.00009537011,0.0007936735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99623895,0.0008604466,0.0002861624,0.0014906112,0.0007641178,0.00035960219],"domain_scores_gemma":[0.9552104,0.026488261,0.006439702,0.0083715385,0.0021038598,0.0013862492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037417463,0.0003410794,0.001478297,0.0028860853,0.0026419982,0.003489768,0.0013061253,0.0017846548,0.0052516027],"category_scores_gemma":[0.0509974,0.0005373827,0.0006710469,0.0034711622,0.0039904416,0.010218174,0.0033956023,0.0018118728,0.00092352455],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009913462,0.00019527783,0.09165532,0.0009905295,0.0002644544,0.0014912952,0.00500681,0.012930324,0.021027938,0.7026323,0.009894415,0.15292007],"study_design_scores_gemma":[0.000047386835,0.00008336341,0.015663471,0.00013683189,0.000089608344,0.004138531,0.0016520618,0.061500844,0.0062614875,0.9004328,0.009904448,0.0000890873],"about_ca_topic_score_codex":0.00048672562,"about_ca_topic_score_gemma":0.00044237575,"teacher_disagreement_score":0.0052516027,"about_ca_system_score_codex":0.0008742698,"about_ca_system_score_gemma":0.0006819769,"threshold_uncertainty_score":0.019788444},"labels":[],"label_agreement":null},{"id":"W2158241520","doi":"10.1186/1748-7188-6-17","title":"A new, fast algorithm for detecting protein coevolution using maximum compatible cliques","year":2011,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Ontario Institute for Cancer Research; University of Toronto","funders":"","keywords":"Coevolution; Computer science; Algorithm; Data mining; Biology; Evolutionary biology","score_opus":0.0354444934789004,"score_gpt":0.29094755398260824,"score_spread":0.25550306050370786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158241520","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057501867,0.00013666124,0.98999876,0.0001368416,0.000046339446,0.0001665444,0.00027864566,0.0023486603,0.0011372727],"genre_scores_gemma":[0.033161845,0.00007197261,0.9637028,0.00007433775,0.000029693343,0.0002714131,0.00087706675,0.00036733045,0.0014434779],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985942,0.00027643362,0.00007859161,0.000425564,0.00048773433,0.00013745933],"domain_scores_gemma":[0.9977958,0.0009278135,0.00017455284,0.00043587325,0.00050074776,0.00016525811],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017409115,0.0013841558,0.0013689382,0.0029034973,0.0014453159,0.0016966187,0.003260681,0.0015636069,0.0092975795],"category_scores_gemma":[0.0062141325,0.0010269675,0.0018640546,0.0032398691,0.000725323,0.0027751417,0.0027973957,0.0017604126,0.0027328234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036811776,0.00032197646,0.0034943665,0.0005575888,0.00032453611,0.0002746559,0.00032597227,0.103067264,0.028339181,0.030638507,0.027869089,0.80441874],"study_design_scores_gemma":[0.00013247479,0.00006939947,0.0010194387,0.000031504882,0.00004609069,0.00035958728,0.000076530036,0.94482905,0.006772044,0.031727117,0.014893674,0.000043017455],"about_ca_topic_score_codex":0.0044264025,"about_ca_topic_score_gemma":0.006671683,"teacher_disagreement_score":0.0092975795,"about_ca_system_score_codex":0.0011242519,"about_ca_system_score_gemma":0.0020536722,"threshold_uncertainty_score":0.031103492},"labels":[],"label_agreement":null},{"id":"W2163879391","doi":"10.1186/s13015-015-0033-9","title":"Algorithmic approaches to protein-protein interaction site prediction","year":2015,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Identification (biology); Field (mathematics); Data science; Machine learning; Artificial intelligence; Data mining; Biology","score_opus":0.13522349676244755,"score_gpt":0.3403664008324722,"score_spread":0.20514290407002467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163879391","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052981735,0.0017097484,0.9906007,0.00032773145,0.000030890384,0.000093852956,0.0002768311,0.00041269473,0.0012494116],"genre_scores_gemma":[0.089183465,0.0032192443,0.90344095,0.00021122178,0.000186762,0.00062779494,0.0021876302,0.000120357196,0.00082259456],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99752766,0.0010216162,0.00024085332,0.0004173277,0.00067926117,0.00011332242],"domain_scores_gemma":[0.9915706,0.0066491356,0.00036822062,0.0005537312,0.0007361382,0.00012213273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004228677,0.0014060383,0.0017355087,0.0035243242,0.00093455246,0.0027160433,0.0038756486,0.0018872065,0.0016902561],"category_scores_gemma":[0.015770862,0.0008872988,0.001230131,0.004352605,0.0012831612,0.0027357594,0.002409909,0.0022361863,0.00082367094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066515,0.00015360545,0.0024788075,0.00052293803,0.00014269142,0.00006465461,0.0000801333,0.7625976,0.00074731035,0.055928845,0.0032545314,0.1739624],"study_design_scores_gemma":[0.000018241559,0.000029228766,0.00025002848,0.000032243206,0.000016822694,0.000046995807,0.000024281835,0.9305039,0.00040655522,0.066846125,0.0018139713,0.000011718358],"about_ca_topic_score_codex":0.0024560462,"about_ca_topic_score_gemma":0.0030066075,"teacher_disagreement_score":0.004228677,"about_ca_system_score_codex":0.0010990661,"about_ca_system_score_gemma":0.0022256656,"threshold_uncertainty_score":0.022363663},"labels":[],"label_agreement":null},{"id":"W2165398449","doi":"10.1186/1748-7188-5-38","title":"Efficient algorithms for training the parameters of hidden Markov models using stochastic expectation maximization (EM) training and Viterbi training","year":2010,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Viterbi algorithm; Computer science; Hidden Markov model; Iterative Viterbi decoding; Forward algorithm; Markov model; Markov chain; Soft output Viterbi algorithm; Expectation–maximization algorithm; Training (meteorology); Machine learning; Algorithm; Maximum-entropy Markov model; Artificial intelligence; Variable-order Markov model; Maximum likelihood; Decoding methods; Mathematics","score_opus":0.07937526116788873,"score_gpt":0.3143771748915459,"score_spread":0.23500191372365714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165398449","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009747596,0.00010909311,0.99748874,0.00007907666,0.000016404225,0.000032707372,0.000033433385,0.0009165839,0.00034922382],"genre_scores_gemma":[0.037778158,0.00023832671,0.9593405,0.00013316327,0.00004751924,0.00038247072,0.0003859993,0.00041544647,0.0012784746],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980111,0.00090024393,0.00016875753,0.0004244826,0.00038580678,0.000109645815],"domain_scores_gemma":[0.98998535,0.008199654,0.0004249411,0.0005863508,0.0006964695,0.000107212705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036308286,0.002072046,0.0012969465,0.0015037468,0.0008566525,0.0013610123,0.0037273087,0.0024155164,0.007979573],"category_scores_gemma":[0.02424678,0.0013984771,0.0009918181,0.0015307836,0.0011191613,0.0027019316,0.0023513988,0.0043153907,0.0035825537],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001452482,0.00012758105,0.001120786,0.00026115443,0.00011643838,0.000077876946,0.00019428914,0.53837615,0.003098573,0.036404762,0.005655903,0.41442126],"study_design_scores_gemma":[0.00002131052,0.0000138120095,0.00009528042,0.000022538145,0.000010979931,0.000037059286,0.000013070913,0.9762873,0.0019930305,0.01996518,0.0015276012,0.000012807443],"about_ca_topic_score_codex":0.005618033,"about_ca_topic_score_gemma":0.0072845896,"teacher_disagreement_score":0.007979573,"about_ca_system_score_codex":0.0016451417,"about_ca_system_score_gemma":0.002626404,"threshold_uncertainty_score":0.026694298},"labels":[],"label_agreement":null},{"id":"W2165484374","doi":"10.1186/1748-7188-7-31","title":"Gene tree correction for reconciliation and species tree inference","year":2012,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Tree rearrangement; Tree (set theory); Inference; Heuristic; Vertex (graph theory); Gene duplication; Set (abstract data type); Time complexity; Phylogenetic tree; Computer science; Phylogenetic network; Combinatorics; Phylogenomics; Biology; Mathematics; Gene; Artificial intelligence; Genetics; Graph; Clade","score_opus":0.025599518577247682,"score_gpt":0.2857459621330662,"score_spread":0.2601464435558185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165484374","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030285347,0.00055757404,0.96126425,0.00044425874,0.00013984083,0.0001806445,0.0008381516,0.005032916,0.0012569445],"genre_scores_gemma":[0.10230904,0.00009278747,0.8934228,0.00011596919,0.000061343344,0.0001300928,0.0023215394,0.00060050865,0.0009459499],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976997,0.00067768875,0.00014887725,0.00079872913,0.00047293652,0.0002021169],"domain_scores_gemma":[0.98898005,0.0057036043,0.0011920936,0.0025655404,0.0013272063,0.00023157166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032232301,0.0012881474,0.001233204,0.0029988105,0.0018526996,0.0013919531,0.0033792132,0.0019868568,0.0075736274],"category_scores_gemma":[0.018511677,0.00059533695,0.0022512432,0.003327831,0.0013199043,0.0022168537,0.0018609352,0.0025367783,0.0027176684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007345652,0.0002924494,0.014859156,0.0008892327,0.00036956696,0.0006751945,0.0007018608,0.20188479,0.020423824,0.0340943,0.022895064,0.70217997],"study_design_scores_gemma":[0.0001354938,0.00012375668,0.0040037134,0.00006857611,0.00010617407,0.0011462503,0.00017693087,0.8854189,0.02190609,0.06908522,0.017772226,0.00005666788],"about_ca_topic_score_codex":0.0034818288,"about_ca_topic_score_gemma":0.005078745,"teacher_disagreement_score":0.0075736274,"about_ca_system_score_codex":0.00155048,"about_ca_system_score_gemma":0.0026491813,"threshold_uncertainty_score":0.025336325},"labels":[],"label_agreement":null},{"id":"W2339182468","doi":"10.1186/s13015-016-0067-7","title":"The link between orthology relations and gene trees: a correction perspective","year":2016,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Tree (set theory); Converse; Set (abstract data type); Phylogenetic tree; Relation (database); Tree rearrangement; Gene; Perspective (graphical); Computer science; Similarity (geometry); Computational biology; Combinatorics; Biology; Mathematics; Genetics; Data mining; Artificial intelligence","score_opus":0.011886679407437713,"score_gpt":0.27709827393003883,"score_spread":0.2652115945226011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2339182468","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032216106,0.0013118833,0.9536955,0.0070752613,0.00020062609,0.00012248225,0.0003042865,0.0006979074,0.004376032],"genre_scores_gemma":[0.4207141,0.0012404965,0.56925905,0.001186352,0.0004802305,0.0001943606,0.0009622823,0.0006549597,0.005308137],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99229574,0.0028838944,0.00048643746,0.0020198543,0.001969037,0.00034510877],"domain_scores_gemma":[0.92223436,0.06010595,0.0039718496,0.009903073,0.0028824657,0.0009022002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064796284,0.00089083466,0.0012110082,0.0012180633,0.0015696648,0.00291017,0.0040474567,0.0027279698,0.005534007],"category_scores_gemma":[0.042707343,0.0006312245,0.0016425374,0.0026104082,0.0047567324,0.008101103,0.0033812837,0.006602511,0.0007223113],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005824937,0.0002591996,0.008170402,0.0012682758,0.00017465433,0.0010705426,0.0015778153,0.1697232,0.01183102,0.5360786,0.012312993,0.25695089],"study_design_scores_gemma":[0.000069761874,0.000096299205,0.0010785112,0.00011607796,0.000099409146,0.0014657244,0.00030145983,0.24433447,0.011599249,0.7128614,0.027916156,0.000061492],"about_ca_topic_score_codex":0.0026942038,"about_ca_topic_score_gemma":0.001895993,"teacher_disagreement_score":0.0064796284,"about_ca_system_score_codex":0.002570709,"about_ca_system_score_gemma":0.0018807354,"threshold_uncertainty_score":0.03426802},"labels":[],"label_agreement":null},{"id":"W2339509753","doi":"10.1186/s13015-016-0071-y","title":"Sparse RNA folding revisited: space-efficient minimum free energy structure prediction","year":2016,"lang":"en","type":"review","venue":"Algorithms for Molecular Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Institute for Nanotechnology","funders":"German Network for Bioinformatics Infrastructure; Universität Leipzig; Bundesministerium für Bildung und Forschung; Deutsche Forschungsgemeinschaft","keywords":"Algorithm; Computer science; Energy minimization; Folding (DSP implementation); TRACE (psycholinguistics); RNA; Bounded function; Computational complexity theory; Mathematics; Theoretical computer science; Physics","score_opus":0.018561930328967562,"score_gpt":0.29063778884713126,"score_spread":0.2720758585181637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2339509753","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03838526,0.00046418997,0.95817626,0.0003472568,0.000033846678,0.000024354682,0.00008479454,0.00092545885,0.0015586462],"genre_scores_gemma":[0.46967447,0.00052663084,0.52632034,0.00023825014,0.000051602015,0.00009271822,0.0005220222,0.00028982086,0.0022841746],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9997377,0.00007174024,0.000012656712,0.00005392824,0.00009205236,0.000032038082],"domain_scores_gemma":[0.9994398,0.0002739401,0.000038703376,0.00014939984,0.000066160166,0.000031981253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005182321,0.0005117535,0.00079980685,0.0004972725,0.00028911317,0.00056189013,0.00087076606,0.0008884574,0.001590399],"category_scores_gemma":[0.0024961198,0.0003004433,0.00044918136,0.0005444265,0.0006331315,0.000983187,0.0010334059,0.0009332067,0.0006208976],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033987995,0.00008361261,0.0017207573,0.00023107922,0.000041231095,0.00029088627,0.00018712171,0.6852705,0.037203662,0.054424528,0.0040183305,0.21618843],"study_design_scores_gemma":[0.000008049459,0.000017234934,0.0000845499,0.000006088457,0.000002156956,0.000053057876,0.0000090602325,0.98327994,0.003962105,0.011927736,0.00064535876,0.0000046461887],"about_ca_topic_score_codex":0.0011737652,"about_ca_topic_score_gemma":0.0011872923,"teacher_disagreement_score":0.001590399,"about_ca_system_score_codex":0.00031748912,"about_ca_system_score_gemma":0.00058584166,"threshold_uncertainty_score":0.00532043},"labels":[],"label_agreement":null},{"id":"W2405206615","doi":"10.1186/s13015-016-0065-9","title":"Models and algorithms for genome rearrangement with positional constraints","year":2016,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Generalization; Weighting; Set (abstract data type); Computer science; Function (biology); Polynomial; Binary number; Representation (politics); Algorithm; Time complexity; Combinatorics; Simple (philosophy); Mathematics; Biology","score_opus":0.020969453984812,"score_gpt":0.27897863154934466,"score_spread":0.2580091775645327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2405206615","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069154967,0.00037374126,0.98850995,0.000587783,0.000034890825,0.0000776826,0.00020737578,0.00036134777,0.0029318116],"genre_scores_gemma":[0.12459045,0.00078327395,0.8661587,0.0002624658,0.00015081861,0.0007226091,0.0011721674,0.00033941746,0.005820074],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840707,0.0006264406,0.00007915512,0.00039558843,0.0003014666,0.0001903131],"domain_scores_gemma":[0.9936666,0.0049842233,0.0004080465,0.00043047057,0.00036032152,0.00015030682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024166014,0.001495357,0.0014680156,0.0014174167,0.0012416051,0.0024165763,0.0039527537,0.0035021438,0.007754796],"category_scores_gemma":[0.010075551,0.0010793415,0.00219528,0.0033877352,0.0015850102,0.0050266893,0.0024708984,0.0037963723,0.0014405643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059562684,0.000085048596,0.0005306013,0.0001906484,0.000053994892,0.000051636067,0.00014186715,0.78804123,0.0003881616,0.16354626,0.004311215,0.04259986],"study_design_scores_gemma":[0.000027349428,0.000011816892,0.000057699366,0.000016876593,0.000010840872,0.000027444821,0.000022736245,0.79950434,0.00016448309,0.1982223,0.0019264523,0.000007729696],"about_ca_topic_score_codex":0.0043932856,"about_ca_topic_score_gemma":0.0053392663,"teacher_disagreement_score":0.007754796,"about_ca_system_score_codex":0.0033872295,"about_ca_system_score_gemma":0.0021275927,"threshold_uncertainty_score":0.025942385},"labels":[],"label_agreement":null},{"id":"W2544103171","doi":"10.1186/s13015-017-0101-4","title":"Aligning coding sequences with frameshift extension penalties","year":2017,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Canada Research Chairs; Université de Sherbrooke","keywords":"Frameshift mutation; Coding (social sciences); Extension (predicate logic); Gene; Homologous chromosome; Encoding (memory); Efficient algorithm","score_opus":0.025004154265229707,"score_gpt":0.3100925058355515,"score_spread":0.28508835157032175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2544103171","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05267472,0.00026630601,0.9439727,0.000048359747,0.000040281804,0.00009390915,0.0001412801,0.002072217,0.0006902389],"genre_scores_gemma":[0.18673266,0.0001571641,0.81049746,0.00004624888,0.000036207188,0.000114852424,0.000851356,0.00037460684,0.0011895732],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991757,0.00019515687,0.00006461999,0.00023579328,0.0002584462,0.000070208116],"domain_scores_gemma":[0.99871135,0.0004993089,0.00021129393,0.00020791814,0.0003102276,0.00005983995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088075607,0.00092124264,0.00064779416,0.0011407064,0.00044556422,0.0005483655,0.0008699744,0.0007201284,0.0024986225],"category_scores_gemma":[0.0029653343,0.00022171743,0.00064310647,0.0014467398,0.00037472043,0.000685123,0.0007087664,0.0008221301,0.0013504494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052658893,0.00022154223,0.006349471,0.0004676387,0.00015885709,0.00029016193,0.00017162465,0.1785689,0.10000074,0.01066274,0.0040084263,0.6985732],"study_design_scores_gemma":[0.000057529247,0.00021349815,0.0025787863,0.00003465729,0.000055105913,0.00045140306,0.000068485184,0.92244846,0.04776149,0.019706193,0.006595909,0.000028482193],"about_ca_topic_score_codex":0.0012647845,"about_ca_topic_score_gemma":0.0012871724,"teacher_disagreement_score":0.0024986225,"about_ca_system_score_codex":0.00037604035,"about_ca_system_score_gemma":0.00088239997,"threshold_uncertainty_score":0.008358717},"labels":[],"label_agreement":null},{"id":"W2592818772","doi":"10.1186/s13015-017-0096-x","title":"Approximating the correction of weighted and unweighted orthology and paralogy relations","year":2017,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Ottawa","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Combinatorics; Maximization; Mathematics; Conjecture; Converse; Approximation algorithm; Graph; Tree (set theory); Satisfiability; Discrete mathematics; Mathematical optimization","score_opus":0.013963136237448284,"score_gpt":0.2910071363754212,"score_spread":0.2770440001379729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592818772","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28180718,0.0004978069,0.7104416,0.0015832286,0.0000871162,0.00019987512,0.00067620014,0.001567945,0.0031390649],"genre_scores_gemma":[0.5369205,0.00017450655,0.4570745,0.00029460777,0.00006893063,0.00013173842,0.0014297185,0.00037626218,0.0035293142],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971455,0.0007656392,0.00015248504,0.0010205656,0.00051899493,0.00039685247],"domain_scores_gemma":[0.9820294,0.012370197,0.0017600805,0.002212563,0.0011635922,0.00046408817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002949107,0.0010952725,0.0013034622,0.0011452242,0.0009055858,0.0017214164,0.004200686,0.0020767406,0.004673067],"category_scores_gemma":[0.022224724,0.00079998333,0.0017293659,0.002098175,0.0016871144,0.005155816,0.0023653316,0.0021888523,0.0005525669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007346104,0.00026941122,0.006202093,0.00048416023,0.00012785304,0.00029253296,0.00050259806,0.8054592,0.007949971,0.038049787,0.005183961,0.13474382],"study_design_scores_gemma":[0.0000490366,0.000069031055,0.0006183683,0.000019528195,0.000038744485,0.00016912313,0.00012640237,0.9470967,0.0038700453,0.04705356,0.0008756497,0.000013765533],"about_ca_topic_score_codex":0.008793586,"about_ca_topic_score_gemma":0.009922403,"teacher_disagreement_score":0.008793586,"about_ca_system_score_codex":0.0028765365,"about_ca_system_score_gemma":0.0021469092,"threshold_uncertainty_score":0.020870805},"labels":[],"label_agreement":null},{"id":"W2789974803","doi":"10.1186/s13015-018-0123-6","title":"Derivative-free neural network for optimizing the scoring functions associated with dynamic programming of pairwise-profile alignment","year":2018,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics","keywords":"Computer science; Pairwise comparison; Cosine similarity; Artificial neural network; Similarity (geometry); Multiple sequence alignment; Artificial intelligence; Data mining; Smith–Waterman algorithm; Function (biology); Solver; Sequence alignment; Pattern recognition (psychology); Sequence (biology); Algorithm; Machine learning; Image (mathematics)","score_opus":0.015860483250547504,"score_gpt":0.2656652575393171,"score_spread":0.24980477428876957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789974803","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03327204,0.000235714,0.96352273,0.00013466427,0.00003525042,0.000054793,0.00003178457,0.00042765168,0.0022853878],"genre_scores_gemma":[0.5821576,0.00027171295,0.41241962,0.00017422928,0.000032287353,0.0003519827,0.00020671118,0.00013345329,0.0042523798],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996735,0.000086654225,0.00001949509,0.000095972755,0.000083858664,0.000040488256],"domain_scores_gemma":[0.99933857,0.00037745005,0.000060908576,0.00002722665,0.00017300462,0.000022862117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009955633,0.0010773224,0.0005838004,0.000487377,0.00035752833,0.0005646704,0.0009681511,0.0010645792,0.0017447418],"category_scores_gemma":[0.0025235214,0.00044293105,0.0005357364,0.00053303194,0.00045254917,0.0007696842,0.00059110887,0.0011542867,0.00027441882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044947486,0.000038247632,0.00049910985,0.000050593004,0.00002362662,0.00003464988,0.000026034504,0.94238657,0.0026433787,0.0027058735,0.00048258438,0.051064298],"study_design_scores_gemma":[0.0000013580537,0.0000064346264,0.000026446807,0.0000013812697,0.0000017858669,0.000002429395,0.0000010742176,0.9994029,0.0002588649,0.00023904427,0.00005698907,0.000001243498],"about_ca_topic_score_codex":0.008580235,"about_ca_topic_score_gemma":0.008104019,"teacher_disagreement_score":0.008580235,"about_ca_system_score_codex":0.0011809984,"about_ca_system_score_gemma":0.001348395,"threshold_uncertainty_score":0.017060578},"labels":[],"label_agreement":null},{"id":"W2940808208","doi":"10.1186/s13015-019-0139-6","title":"Reconciling multiple genes trees via segmental duplications and losses","year":2019,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal; Université de Montréal; Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Gene duplication; Segmental duplication; Tree (set theory); Genome; Gene; Set (abstract data type); Time complexity; Computer science; Computational biology; Biology; Gene family; Algorithm; Mathematics; Genetics; Combinatorics","score_opus":0.012185853466804855,"score_gpt":0.26362863126578584,"score_spread":0.251442777798981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2940808208","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33785945,0.0040673106,0.6317744,0.0042654,0.00038569217,0.0003536999,0.0064240913,0.008707343,0.006162577],"genre_scores_gemma":[0.50728536,0.00077916746,0.46890938,0.0008857854,0.00017996765,0.0002445593,0.017079132,0.0012757729,0.0033609162],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979772,0.0005579354,0.00012309111,0.00085340295,0.0003142097,0.0001741876],"domain_scores_gemma":[0.9950722,0.0026944643,0.00045703282,0.0012236612,0.00035501388,0.00019758705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031016616,0.0013337554,0.0017667288,0.002872509,0.0021020842,0.0023462577,0.003126131,0.0025690577,0.0034662818],"category_scores_gemma":[0.010748225,0.00081154605,0.002546472,0.0034982269,0.0012730277,0.005292403,0.0029237068,0.003240408,0.0014162328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00147668,0.00038303735,0.03157804,0.0012544445,0.0006575361,0.0020574387,0.0024934907,0.3837783,0.02379269,0.07134378,0.037973005,0.4432116],"study_design_scores_gemma":[0.00015941467,0.00011587793,0.0046333466,0.00011542945,0.00023687433,0.0013604502,0.0011450322,0.7741045,0.012700716,0.17382824,0.031520605,0.00007948671],"about_ca_topic_score_codex":0.0025595753,"about_ca_topic_score_gemma":0.0039934595,"teacher_disagreement_score":0.0034662818,"about_ca_system_score_codex":0.0016513427,"about_ca_system_score_gemma":0.0016452507,"threshold_uncertainty_score":0.016403377},"labels":[],"label_agreement":null},{"id":"W2964468345","doi":"10.1186/s13015-019-0153-8","title":"A branching process for homology distribution-based inference of polyploidy, speciation and loss","year":2019,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inference; Genome; Biology; Gene; Branching process; Computational biology; Divergence (linguistics); Evolutionary biology; Genetics; Mathematics; Computer science; Statistics; Artificial intelligence","score_opus":0.010480602920940392,"score_gpt":0.30435643497677517,"score_spread":0.2938758320558348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964468345","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025867978,0.00019226735,0.9728521,0.00017195546,0.000016834327,0.000048926788,0.000112558286,0.00040192727,0.00033541166],"genre_scores_gemma":[0.5095795,0.0003176928,0.48557147,0.00025399055,0.00011726771,0.0003866933,0.0013426172,0.00042177038,0.0020089445],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99771726,0.0010715293,0.00012501914,0.00064787327,0.00030248272,0.000135841],"domain_scores_gemma":[0.9647015,0.031181222,0.0013343396,0.0012072914,0.00095937954,0.00061632926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012344079,0.0008236764,0.0013987502,0.0025135751,0.001311343,0.0018241787,0.0038245015,0.0020313621,0.0035819972],"category_scores_gemma":[0.04248474,0.0011376581,0.0018580059,0.0020062726,0.002473436,0.0027052755,0.0028640425,0.003132716,0.00059542916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002884971,0.00010757315,0.013022783,0.00013867203,0.00024921977,0.00028488284,0.00048633563,0.79559636,0.0035133325,0.10559892,0.0013365389,0.07937687],"study_design_scores_gemma":[0.000018646955,0.0000103476705,0.00042698413,0.0000105950985,0.000012954203,0.000035775753,0.000010359538,0.9571552,0.00034426787,0.04169212,0.0002743055,0.000008512167],"about_ca_topic_score_codex":0.00742316,"about_ca_topic_score_gemma":0.005544443,"teacher_disagreement_score":0.012344079,"about_ca_system_score_codex":0.002308335,"about_ca_system_score_gemma":0.0013457187,"threshold_uncertainty_score":0.06528252},"labels":[],"label_agreement":null},{"id":"W2965510019","doi":"10.1186/s13015-019-0152-9","title":"A multi-labeled tree dissimilarity measure for comparing “clonal trees” of tumor progression","year":2019,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institute of General Medical Sciences; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"clone (Java method); Tree (set theory); Measure (data warehouse); Vertex (graph theory); Mutation; Biology; Computational biology; Computer science; Granularity; Combinatorics; Mathematics; Genetics; Gene; Data mining; Graph","score_opus":0.022834755708476404,"score_gpt":0.3166128142024556,"score_spread":0.29377805849397914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965510019","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.105140515,0.0005760584,0.8914808,0.00014581703,0.00007156905,0.00008020223,0.00062314695,0.0003612749,0.0015205898],"genre_scores_gemma":[0.5353949,0.00022791699,0.4612284,0.00010662575,0.00013570255,0.00016193725,0.0016959886,0.00016487578,0.0008836673],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836046,0.00033468718,0.00016048516,0.00040060555,0.00061958627,0.00012416918],"domain_scores_gemma":[0.99539125,0.0018880963,0.0009125606,0.0005918719,0.00084663933,0.00036954158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015478316,0.0004506954,0.00088729116,0.004801199,0.00071526447,0.0014579216,0.0012795104,0.0010759563,0.0013155612],"category_scores_gemma":[0.008541027,0.00023405591,0.00086676236,0.0033949567,0.0008910613,0.0029342556,0.001367133,0.0010420424,0.00028393426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069948967,0.00040165536,0.039323963,0.0006670174,0.00043348028,0.00046981938,0.0007122126,0.27810383,0.08116603,0.15028374,0.006574357,0.44116437],"study_design_scores_gemma":[0.00003214733,0.0002931346,0.012974022,0.00004682029,0.0000600266,0.00073124096,0.00016773178,0.8778915,0.010673314,0.090070106,0.0069732796,0.00008658177],"about_ca_topic_score_codex":0.0011708947,"about_ca_topic_score_gemma":0.0016502441,"teacher_disagreement_score":0.004801199,"about_ca_system_score_codex":0.0012539804,"about_ca_system_score_gemma":0.0006267262,"threshold_uncertainty_score":0.009098291},"labels":[],"label_agreement":null},{"id":"W2965995818","doi":"10.1186/s13015-019-0150-y","title":"A cubic algorithm for the generalized rank median of three genomes","year":2019,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Fundação de Amparo à Pesquisa do Estado de São Paulo; Genome Canada; Alfred P. Sloan Foundation","keywords":"Genome; Linear subspace; Heuristics; Time complexity; Combinatorics; Rank (graph theory); Matrix (chemical analysis); Computer science; Algorithm; Omega; Polynomial; Upper and lower bounds; Mathematics; Mathematical optimization; Biology; Pure mathematics; Physics; Genetics","score_opus":0.014778039241469792,"score_gpt":0.2761304000805498,"score_spread":0.26135236083908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965995818","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02571553,0.0001589679,0.9614118,0.00034210118,0.00005452918,0.00019499366,0.0005397375,0.005821044,0.0057613994],"genre_scores_gemma":[0.097474255,0.000065455606,0.89687634,0.0000958886,0.000026259826,0.00018254828,0.0012963802,0.00056913064,0.0034137585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895823,0.00015323587,0.00006668293,0.00036645232,0.00026002442,0.00019528045],"domain_scores_gemma":[0.9989483,0.00041267334,0.00009825412,0.0002720015,0.00018112744,0.000087674256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009039096,0.0010003896,0.0013698335,0.0016779238,0.0013717964,0.0018202792,0.001769919,0.0012401491,0.016887596],"category_scores_gemma":[0.003617077,0.00056262704,0.0017107431,0.0019531017,0.000961147,0.0019619912,0.0030264808,0.0020819353,0.0031337691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006379602,0.00031608006,0.0017095943,0.00038106213,0.000118375814,0.00021329137,0.00048962067,0.16555268,0.015816256,0.064909525,0.018093511,0.7317622],"study_design_scores_gemma":[0.00032919017,0.00027079505,0.0007748917,0.000039110775,0.000043115957,0.00023219145,0.0003624547,0.8292009,0.010017942,0.14191519,0.016742384,0.00007181091],"about_ca_topic_score_codex":0.007175635,"about_ca_topic_score_gemma":0.010216019,"teacher_disagreement_score":0.016887596,"about_ca_system_score_codex":0.0017254567,"about_ca_system_score_gemma":0.003200216,"threshold_uncertainty_score":0.056494653},"labels":[],"label_agreement":null},{"id":"W2976303698","doi":"10.1186/s13015-020-00171-4","title":"Evolution through segmental duplications and losses: a Super-Reconciliation approach","year":2020,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data science","score_opus":0.02459881913070271,"score_gpt":0.2817939826194368,"score_spread":0.25719516348873406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2976303698","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0776674,0.0012268239,0.91506195,0.0010855172,0.00008579519,0.00018929824,0.0008532783,0.0016840685,0.0021459465],"genre_scores_gemma":[0.42222515,0.00054875715,0.5704853,0.00042154154,0.00016536844,0.00031376356,0.0035987343,0.0006186973,0.0016227133],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99664223,0.0017969427,0.0001403203,0.00073764037,0.0005012681,0.00018158797],"domain_scores_gemma":[0.9896633,0.006438697,0.0007417846,0.002245925,0.0006851363,0.0002250658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006283337,0.0011048107,0.0016946661,0.0035827274,0.0013260626,0.0017540358,0.0038378139,0.0019070657,0.0036411693],"category_scores_gemma":[0.014742473,0.00090176624,0.0022558265,0.0039833747,0.0015137381,0.0037849324,0.0027429785,0.0023200677,0.0009435865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000810136,0.00021451128,0.008355783,0.00060292194,0.00050979696,0.00070067274,0.00086518074,0.677962,0.00830077,0.082446605,0.007942196,0.21128947],"study_design_scores_gemma":[0.0000682425,0.00008140496,0.0012521057,0.000041086532,0.00008674021,0.00032596785,0.00013779856,0.8757792,0.003056676,0.11455374,0.004587194,0.00002991824],"about_ca_topic_score_codex":0.0011561293,"about_ca_topic_score_gemma":0.0013952093,"teacher_disagreement_score":0.006283337,"about_ca_system_score_codex":0.0012118996,"about_ca_system_score_gemma":0.0010465847,"threshold_uncertainty_score":0.033229887},"labels":[],"label_agreement":null},{"id":"W2982419655","doi":"10.1186/s13015-020-00175-0","title":"Reconstruction of time-consistent species trees","year":2020,"lang":"en","type":"preprint","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Gene duplication; Event (particle physics); Horizontal gene transfer; Tree (set theory); Gene; Biology; Tree of life (biology); Evolutionary biology; Genetic algorithm; Construct (python library); Phylogenetics; Gene family; Phylogenetic tree; Computational biology; Genetics; Mathematics; Genome; Combinatorics; Computer science; Physics","score_opus":0.024098906808317038,"score_gpt":0.2661840530394918,"score_spread":0.24208514623117475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982419655","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11931724,0.0002961382,0.87557507,0.0006570868,0.00002691738,0.00008983376,0.0012047058,0.0007920551,0.0020408821],"genre_scores_gemma":[0.38856232,0.00018878085,0.60651034,0.00016996477,0.000025604859,0.00010232093,0.0030568999,0.0002846731,0.0010991319],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988017,0.00033636592,0.00008000835,0.00045751478,0.0002271633,0.0000972439],"domain_scores_gemma":[0.9900962,0.006831031,0.000853084,0.001142925,0.00080977497,0.0002669822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017362044,0.00043428427,0.00058964925,0.0008903328,0.00077601935,0.0014241535,0.0019323942,0.0013611944,0.0038807548],"category_scores_gemma":[0.013129085,0.0006234519,0.001174349,0.0011672232,0.0013293732,0.0028314875,0.0013702236,0.001570659,0.00055321323],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008017531,0.00015289575,0.012177201,0.0006237596,0.00014580929,0.00055430335,0.00086007925,0.6710693,0.019120926,0.17829701,0.005453668,0.11074323],"study_design_scores_gemma":[0.00006425193,0.000040228504,0.0010757967,0.00004110198,0.000028758133,0.0002842397,0.00015911182,0.7168157,0.005466534,0.27224332,0.0037593641,0.000021590547],"about_ca_topic_score_codex":0.0018148412,"about_ca_topic_score_gemma":0.0021363269,"teacher_disagreement_score":0.0038807548,"about_ca_system_score_codex":0.0014333356,"about_ca_system_score_gemma":0.0012713512,"threshold_uncertainty_score":0.012982488},"labels":[],"label_agreement":null},{"id":"W3021210550","doi":"10.1186/s13015-020-00169-y","title":"The distance and median problems in the single-cut-or-join model with single-gene duplications","year":2020,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Genome Canada","keywords":"Join (topology); Computer science; Gene duplication; Algorithm; Gene; Data mining; Genetics; Biology; Mathematics; Combinatorics","score_opus":0.0360477283324637,"score_gpt":0.26491551964678256,"score_spread":0.22886779131431886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021210550","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19309635,0.0023987826,0.78404427,0.0039953487,0.00016261815,0.00036031066,0.003613256,0.0011460907,0.011182888],"genre_scores_gemma":[0.5506639,0.0015395904,0.4299246,0.000686036,0.00033169964,0.0004795963,0.005543141,0.00066630705,0.010165145],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99730647,0.0008039596,0.00013912222,0.0010146934,0.00038319136,0.0003525789],"domain_scores_gemma":[0.98147774,0.014995734,0.001272121,0.00086354336,0.0006421332,0.0007487035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034218698,0.0015190555,0.0030255443,0.0012926807,0.0018141562,0.003175415,0.004154549,0.0040325336,0.009695612],"category_scores_gemma":[0.015558191,0.0010158302,0.0023821634,0.0029831666,0.002158234,0.00820599,0.0026530558,0.0044398773,0.0009609977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045044068,0.00025361535,0.0017630211,0.00030269203,0.00009767576,0.00019593936,0.00019007653,0.8935538,0.0008202275,0.06348138,0.006542052,0.032349117],"study_design_scores_gemma":[0.00011414731,0.00008181231,0.00045246864,0.000024364119,0.000028211894,0.00013085194,0.00011091553,0.8267398,0.0006680043,0.16992734,0.0016947507,0.000027274524],"about_ca_topic_score_codex":0.010515474,"about_ca_topic_score_gemma":0.007559365,"teacher_disagreement_score":0.010515474,"about_ca_system_score_codex":0.003798367,"about_ca_system_score_gemma":0.0030421156,"threshold_uncertainty_score":0.03243506},"labels":[],"label_agreement":null},{"id":"W3192846055","doi":"10.1186/s13015-021-00198-1","title":"INGOT-DR: an interpretable classifier for predicting drug resistance in M. tuberculosis","year":2021,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Tuberculosis Research and Epidemiology","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"European and Developing Countries Clinical Trials Partnership; Foreign, Commonwealth and Development Office; Foreign and Commonwealth Office; Medical Research Council; Genome Canada","keywords":"Interpretability; Computer science; Machine learning; Artificial intelligence; Classifier (UML); Tuberculosis; Mycobacterium tuberculosis; Test set; Data mining; Medicine","score_opus":0.030671702060958064,"score_gpt":0.36861889641987766,"score_spread":0.3379471943589196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3192846055","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17891741,0.0015553526,0.78277564,0.0020115841,0.0005015779,0.00034022555,0.0034968215,0.02256999,0.007831395],"genre_scores_gemma":[0.70640093,0.00033376587,0.28352994,0.0010132011,0.00022617438,0.00021229699,0.004919011,0.0004638481,0.0029008803],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989447,0.00029165013,0.000069833004,0.00017566682,0.00040106595,0.00011718205],"domain_scores_gemma":[0.9983866,0.0008483586,0.00018069772,0.00020933914,0.00027853955,0.00009653723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001351433,0.0010786945,0.0008211992,0.0009998326,0.0003557583,0.0008811804,0.0015659089,0.0017577911,0.0031018239],"category_scores_gemma":[0.0070243133,0.0001911402,0.0005838283,0.00046722518,0.0005500021,0.00114222,0.0011877709,0.0011806728,0.0012525808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001261727,0.000508212,0.016882554,0.0005975303,0.00018910434,0.0008796089,0.00031822996,0.22367968,0.033849005,0.009118402,0.03469057,0.6780253],"study_design_scores_gemma":[0.0000530182,0.00016710503,0.0011078422,0.000032761774,0.000020974952,0.0002034154,0.000048819787,0.98004407,0.008297563,0.007549209,0.002452044,0.00002324822],"about_ca_topic_score_codex":0.0024311163,"about_ca_topic_score_gemma":0.002786071,"teacher_disagreement_score":0.0031018239,"about_ca_system_score_codex":0.00055173325,"about_ca_system_score_gemma":0.0008260525,"threshold_uncertainty_score":0.010376632},"labels":[],"label_agreement":null},{"id":"W4221035067","doi":"10.1186/s13015-022-00210-2","title":"Fast characterization of segmental duplication structure in multiple genome assemblies","year":2022,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":87,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Michael Smith Health Research BC; Canada Foundation for Innovation","keywords":"Computer science; Gene duplication; Characterization (materials science); Genome; Segmental duplication; Computational biology; Data mining; Biology; Genetics; Gene; Materials science","score_opus":0.010479508507829034,"score_gpt":0.2527592989903266,"score_spread":0.2422797904824976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221035067","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0848865,0.001996086,0.82216746,0.0006283722,0.00026857236,0.00024562006,0.009524686,0.0749602,0.005322477],"genre_scores_gemma":[0.13800484,0.0006543643,0.8373684,0.00029150947,0.00007928527,0.0001861514,0.01655626,0.004581806,0.0022772744],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985738,0.00019631686,0.000092255505,0.00044565523,0.0005972664,0.000094722185],"domain_scores_gemma":[0.9955669,0.0017217483,0.00070875057,0.0006243394,0.0011274563,0.00025077403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025321506,0.0014823921,0.0013177464,0.003022879,0.00084740506,0.0016104839,0.0019583493,0.001127319,0.0054508797],"category_scores_gemma":[0.0076595726,0.001164875,0.0014776067,0.002163278,0.0005716215,0.0022419037,0.0018529422,0.0017698725,0.005188741],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015303103,0.0002779001,0.03333368,0.003247744,0.00074375316,0.0013909616,0.0009046897,0.081282586,0.3606984,0.018599423,0.046460215,0.45153034],"study_design_scores_gemma":[0.00015060382,0.00035761073,0.017969437,0.00024772875,0.00028310172,0.0012233896,0.00030714917,0.631837,0.26504084,0.023813842,0.058535118,0.00023420533],"about_ca_topic_score_codex":0.0021079758,"about_ca_topic_score_gemma":0.0034062525,"teacher_disagreement_score":0.0054508797,"about_ca_system_score_codex":0.00089642924,"about_ca_system_score_gemma":0.0012222897,"threshold_uncertainty_score":0.018234968},"labels":[],"label_agreement":null},{"id":"W4385397331","doi":"10.1186/s13015-023-00231-5","title":"On the complexity of non-binary tree reconciliation with endosymbiotic gene transfer","year":2023,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Legume Nitrogen Fixing Symbiosis","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Binary number; Tree (set theory); Genome; Gene; Gene duplication; Binary tree; Biology; Genetics; Computational biology; Computer science; Algorithm; Mathematics; Combinatorics","score_opus":0.04071512233507958,"score_gpt":0.253661973143377,"score_spread":0.21294685080829745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385397331","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23362151,0.003447271,0.73480934,0.0064392015,0.00031903532,0.0005097465,0.003312528,0.004373532,0.013167742],"genre_scores_gemma":[0.42951337,0.0016669544,0.5530167,0.0009986714,0.00046224447,0.00064068177,0.0068465355,0.0016482417,0.005206526],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99625456,0.0012669795,0.00022532964,0.001124452,0.0006180494,0.00051060854],"domain_scores_gemma":[0.9575535,0.036803685,0.0016112749,0.0022898247,0.0011370191,0.00060464104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041191047,0.001996533,0.0035625617,0.0016301203,0.0029261964,0.005019647,0.0041488116,0.003240043,0.008771826],"category_scores_gemma":[0.02406197,0.0012714711,0.0035014914,0.0031933268,0.0024363708,0.009204438,0.004565158,0.005086085,0.0015649542],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013088709,0.00040287612,0.0036134946,0.0014309424,0.0003099783,0.0005465429,0.0008065595,0.7740363,0.0052665663,0.06090471,0.015260806,0.13611238],"study_design_scores_gemma":[0.000147994,0.00007658376,0.0006589085,0.0000479762,0.00007923611,0.00019930274,0.00016105217,0.8471652,0.0015001595,0.14792629,0.001995379,0.000041863586],"about_ca_topic_score_codex":0.0060662357,"about_ca_topic_score_gemma":0.007714127,"teacher_disagreement_score":0.008771826,"about_ca_system_score_codex":0.0031513914,"about_ca_system_score_gemma":0.0034110104,"threshold_uncertainty_score":0.029344738},"labels":[],"label_agreement":null},{"id":"W4388490419","doi":"10.1186/s13015-023-00240-4","title":"Relative timing information and orthology in evolutionary scenarios","year":2023,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Stockholms Universitet; Deutsche Forschungsgemeinschaft","keywords":"Extant taxon; Combinatorics; Vertex (graph theory); Graph; Time complexity; Computer science; Biology; Mathematics; Theoretical computer science; Discrete mathematics; Evolutionary biology","score_opus":0.015933397475702864,"score_gpt":0.2869197491809849,"score_spread":0.270986351705282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388490419","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20088714,0.0006116458,0.7811496,0.002070144,0.00008465279,0.0002479497,0.0032633445,0.0017761915,0.009909277],"genre_scores_gemma":[0.7091494,0.00045897273,0.2832461,0.0002788338,0.00008819136,0.00016635197,0.004217862,0.0003195577,0.0020747783],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99815947,0.00058203045,0.00012688628,0.00063158985,0.00031854003,0.00018148722],"domain_scores_gemma":[0.9879631,0.008660353,0.0008837949,0.0014513662,0.00062596676,0.00041547493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00199732,0.00076609966,0.000721015,0.002332053,0.0016442005,0.002411675,0.0017954551,0.0018214786,0.0073671085],"category_scores_gemma":[0.015820507,0.0008292964,0.0013745642,0.0028860166,0.0022386464,0.008618729,0.0019039805,0.0022520828,0.00082876044],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005022267,0.00023143544,0.010793517,0.0007974078,0.00010657808,0.00091720786,0.001371371,0.18497059,0.005766375,0.6813866,0.0062615997,0.10689522],"study_design_scores_gemma":[0.000020444737,0.000034476234,0.0010813925,0.00004651911,0.000031502987,0.00044878927,0.00021211864,0.11739146,0.001797812,0.8749796,0.0039293636,0.000026418173],"about_ca_topic_score_codex":0.0017808363,"about_ca_topic_score_gemma":0.001979034,"teacher_disagreement_score":0.0073671085,"about_ca_system_score_codex":0.0019711272,"about_ca_system_score_gemma":0.0012519367,"threshold_uncertainty_score":0.024645448},"labels":[],"label_agreement":null},{"id":"W4391565229","doi":"10.1186/s13015-023-00242-2","title":"Predicting horizontal gene transfers with perfect transfer networks","year":2024,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Université de Sherbrooke","keywords":"Phylogenetic tree; Character (mathematics); Horizontal gene transfer; Inference; Phylogenetic network; Biology; Set (abstract data type); Similarity (geometry); Phylogenetics; Evolutionary biology; Gene; Genetics; Computational biology; Computer science; Artificial intelligence; Mathematics","score_opus":0.007755730313516916,"score_gpt":0.24346998629287186,"score_spread":0.23571425597935494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391565229","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.324178,0.0013635381,0.66737473,0.0010644933,0.00003597628,0.00008880875,0.0020398004,0.00096322293,0.0028914206],"genre_scores_gemma":[0.86581653,0.00051715766,0.12964247,0.00012519502,0.00007144317,0.00007501066,0.0024865896,0.00008413383,0.0011815614],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992318,0.00019891984,0.00005568004,0.00029909174,0.00013349079,0.000080984784],"domain_scores_gemma":[0.99202347,0.0056326566,0.0011755199,0.00055926276,0.00038283784,0.00022628777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011422813,0.0006171645,0.00048226948,0.001725805,0.0006148911,0.001208716,0.0010136844,0.0012780008,0.0024814007],"category_scores_gemma":[0.008670426,0.00047635965,0.00083173066,0.0012456718,0.0010410954,0.003121072,0.0010102672,0.0011084746,0.00036441445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021506386,0.00007977712,0.019458186,0.00023588649,0.00009871699,0.0002293462,0.0001356396,0.8908937,0.0022013006,0.019713456,0.0016033354,0.06513554],"study_design_scores_gemma":[0.000009184082,0.000021470514,0.0015160032,0.000019025976,0.000016566051,0.00007362511,0.000029754383,0.9492609,0.00070887414,0.04769734,0.00064007397,0.000007171613],"about_ca_topic_score_codex":0.0028355995,"about_ca_topic_score_gemma":0.0033273771,"teacher_disagreement_score":0.0028355995,"about_ca_system_score_codex":0.001389808,"about_ca_system_score_gemma":0.0007504617,"threshold_uncertainty_score":0.010083735},"labels":[],"label_agreement":null},{"id":"W4392343346","doi":"10.1186/s13015-024-00256-4","title":"SparseRNAfolD: optimized sparse RNA pseudoknot-free folding with dangle consideration","year":2024,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pseudoknot; Computer science; Algorithm; Computation; Recursion (computer science); Folding (DSP implementation); Theoretical computer science; Mathematical optimization; Mathematics; RNA","score_opus":0.01835453689503884,"score_gpt":0.28027740899627784,"score_spread":0.261922872101239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392343346","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07071515,0.00040444804,0.9077075,0.00040374935,0.00022890206,0.00011758307,0.00041634886,0.009068672,0.010937566],"genre_scores_gemma":[0.49657902,0.00020468445,0.48889875,0.00045843667,0.000059358343,0.00030434,0.0016223274,0.0019943912,0.009878732],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99968064,0.000103679144,0.00001134864,0.00006242693,0.000103816375,0.000038161143],"domain_scores_gemma":[0.99951446,0.0001689086,0.000023599887,0.00013015911,0.0001003164,0.00006255337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053959846,0.0007380184,0.00097241194,0.00040896412,0.00057913817,0.0006480681,0.0012977232,0.0009814529,0.007130328],"category_scores_gemma":[0.0016989035,0.00030649398,0.0005190035,0.00043273706,0.0005189681,0.00081837404,0.001174141,0.00095656415,0.0020551104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072631176,0.00016584813,0.0010480096,0.00020914686,0.000050637194,0.0002846834,0.00011491493,0.78964907,0.012776969,0.032465532,0.013456864,0.14905207],"study_design_scores_gemma":[0.000031198073,0.000033051372,0.000049160066,0.0000057249513,0.000002873431,0.000018548471,0.000009156214,0.9888214,0.0019431347,0.0074786856,0.0015997523,0.0000072625426],"about_ca_topic_score_codex":0.002746266,"about_ca_topic_score_gemma":0.004487192,"teacher_disagreement_score":0.007130328,"about_ca_system_score_codex":0.0005713037,"about_ca_system_score_gemma":0.0009105756,"threshold_uncertainty_score":0.023853302},"labels":[],"label_agreement":null},{"id":"W4392885478","doi":"10.1186/s13015-024-00258-2","title":"Infrared: a declarative tree decomposition-powered framework for bioinformatics","year":2024,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"HORIZON EUROPE Marie Sklodowska-Curie Actions; Universität Wien; Austrian Science Fund; Agence Nationale de la Recherche","keywords":"Computer science; Theoretical computer science; Feature (linguistics); Tree (set theory); Data mining; Algorithm; Mathematics","score_opus":0.016138103831666847,"score_gpt":0.3277411422206731,"score_spread":0.3116030383890062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392885478","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002770284,0.00015405385,0.9897103,0.00027556941,0.000049472925,0.00006364638,0.0004972476,0.007459536,0.0015130532],"genre_scores_gemma":[0.009650128,0.0004702617,0.981246,0.0006218691,0.00011159084,0.0006126748,0.0019031481,0.003447274,0.0019370602],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9963476,0.0011315276,0.00040058367,0.0006187562,0.0012403748,0.00026112405],"domain_scores_gemma":[0.995363,0.0023013675,0.00028549935,0.0011650801,0.00060022104,0.00028490127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005348738,0.0022489405,0.0016210481,0.0015458056,0.0011906889,0.0048684822,0.0068854108,0.00225313,0.015742406],"category_scores_gemma":[0.01262259,0.0016699203,0.0048716385,0.002074154,0.003024559,0.005680572,0.0051000044,0.008194154,0.0107002575],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018923247,0.0001308739,0.00090555334,0.0013041559,0.00012041168,0.00030117808,0.00050997094,0.097774446,0.0050900667,0.72735757,0.04593893,0.12037776],"study_design_scores_gemma":[0.00008385094,0.000052576866,0.00014939239,0.00025815566,0.000048632657,0.00024486135,0.00006330186,0.33143708,0.0036164806,0.5154392,0.14854315,0.00006321528],"about_ca_topic_score_codex":0.0033026577,"about_ca_topic_score_gemma":0.0052345074,"teacher_disagreement_score":0.015742406,"about_ca_system_score_codex":0.0017788631,"about_ca_system_score_gemma":0.004095228,"threshold_uncertainty_score":0.052663565},"labels":[],"label_agreement":null},{"id":"W4394688386","doi":"10.1186/s13015-024-00260-8","title":"Pfp-fm: an accelerated FM-index","year":2024,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Human Genome Research Institute; Japan Society for the Promotion of Science; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Directorate for Biological Sciences; National Institutes of Health; National Science Foundation","keywords":"Computer science; Parsing; Suffix; Word (group theory); Sorting; Search engine indexing; Prefix; Character (mathematics); Suffix array; Index (typography); Algorithm; Artificial intelligence; Natural language processing; Data structure; Programming language; Mathematics","score_opus":0.03292274683587503,"score_gpt":0.3461846779970787,"score_spread":0.31326193116120366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394688386","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03900819,0.0022157251,0.73498005,0.0007430591,0.0008491033,0.0005293011,0.006515872,0.20147474,0.013683956],"genre_scores_gemma":[0.119742624,0.00038366756,0.8451272,0.0004049069,0.0002692019,0.0005004718,0.014995858,0.0058043646,0.012771661],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868995,0.00011476348,0.000106198095,0.00033068954,0.00059583125,0.00016250517],"domain_scores_gemma":[0.9984372,0.00040807112,0.00010253057,0.000507244,0.00041955188,0.00012545045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074673636,0.001884546,0.0011122397,0.0025427095,0.0011084203,0.0019110062,0.0047758706,0.0013258499,0.018011864],"category_scores_gemma":[0.0042141513,0.000700842,0.0010378284,0.0037088187,0.00063399435,0.00365726,0.0024692111,0.001331249,0.009234801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001409681,0.00032402168,0.0026007483,0.0006118346,0.00009986639,0.00028897962,0.00020054598,0.018371591,0.03265528,0.010451048,0.16927066,0.7637158],"study_design_scores_gemma":[0.0005596659,0.00043236537,0.0024001463,0.000099148056,0.00007761067,0.00074055453,0.00013213229,0.76821285,0.070489354,0.018882742,0.13779825,0.00017509694],"about_ca_topic_score_codex":0.009960888,"about_ca_topic_score_gemma":0.0061245225,"teacher_disagreement_score":0.018011864,"about_ca_system_score_codex":0.0015087288,"about_ca_system_score_gemma":0.0021254849,"threshold_uncertainty_score":0.060255706},"labels":[],"label_agreement":null},{"id":"W4403127906","doi":"10.1186/s13015-024-00267-1","title":"New generalized metric based on branch length distance to compare B cell lineage trees","year":2024,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Chronic Lymphocytic Leukemia Research","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; Université de Sherbrooke","keywords":"Metric (unit); Computer science; Lineage (genetic); Combinatorics; Mathematics; Biology; Genetics","score_opus":0.023887407299647584,"score_gpt":0.3531649598430179,"score_spread":0.3292775525433703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403127906","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051600967,0.0018109294,0.9411709,0.00030628114,0.00016636375,0.00015913798,0.0011484388,0.0005921686,0.0030448148],"genre_scores_gemma":[0.3595735,0.0010328534,0.6335926,0.00023812971,0.00018005565,0.00047868915,0.0030497422,0.0003427544,0.0015115961],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960269,0.0012600417,0.00044790967,0.00070803706,0.0013913525,0.00016578272],"domain_scores_gemma":[0.99032885,0.0042641936,0.0015964098,0.001254635,0.0020542142,0.0005017609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036145668,0.0009898315,0.0013287182,0.0067647416,0.0011126259,0.0024883635,0.0018276976,0.0015425957,0.0016436614],"category_scores_gemma":[0.017973278,0.00030260766,0.0009297636,0.0060549187,0.0014015745,0.0043155546,0.0021700996,0.0015926681,0.00052576896],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040262792,0.00022097901,0.041957054,0.0008104338,0.0005881427,0.00029161057,0.0006712529,0.33668804,0.025313364,0.14617449,0.010170672,0.43671128],"study_design_scores_gemma":[0.000044868328,0.00037722988,0.011922789,0.00010782359,0.00010778965,0.0006837438,0.00022014142,0.84573466,0.007798773,0.111935124,0.02094119,0.00012589911],"about_ca_topic_score_codex":0.0026193522,"about_ca_topic_score_gemma":0.0027837034,"teacher_disagreement_score":0.0067647416,"about_ca_system_score_codex":0.0018695261,"about_ca_system_score_gemma":0.0015214079,"threshold_uncertainty_score":0.019115865},"labels":[],"label_agreement":null},{"id":"W4413110219","doi":"10.1186/s13015-025-00281-x","title":"b-move: faster lossless approximate pattern matching in a run-length compressed index","year":2025,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Institutes of Health; National Human Genome Research Institute; Vlaamse regering; Natural Sciences and Engineering Research Council of Canada; Fonds Wetenschappelijk Onderzoek","keywords":"Computer science; Search engine indexing; Lossless compression; Index (typography); RefSeq; Memory footprint; Pattern matching; Scalability; Matching (statistics); Overhead (engineering); Theoretical computer science; Data mining; Genome; Algorithm; Data compression; Information retrieval; Mathematics; Artificial intelligence; Database","score_opus":0.01169109429062735,"score_gpt":0.2933725954004427,"score_spread":0.2816815011098153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413110219","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08655799,0.0034979945,0.8442172,0.0005339556,0.0005471045,0.00042041874,0.0030019209,0.04745845,0.013764913],"genre_scores_gemma":[0.24938445,0.0009340763,0.7227748,0.00057426054,0.00019188854,0.0005558466,0.012183164,0.002046409,0.011355139],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863666,0.00011602451,0.00011538166,0.00025392938,0.00074768346,0.00013033024],"domain_scores_gemma":[0.99886584,0.0002485649,0.00011635434,0.00044601562,0.0002399875,0.00008332775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062305183,0.0009995074,0.0011530422,0.0016161989,0.00064650545,0.0016812659,0.0025693988,0.00083748926,0.0064414158],"category_scores_gemma":[0.0038558943,0.00048646936,0.00071576325,0.003522665,0.0005898811,0.0041830027,0.0026436702,0.001095511,0.0054587466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019148288,0.0004930982,0.0032353394,0.0006676341,0.00015178465,0.00054728996,0.0005701106,0.020440396,0.10515807,0.027188959,0.06370567,0.77592677],"study_design_scores_gemma":[0.00063736114,0.0010903422,0.0022405477,0.00012622283,0.00014292245,0.0017012852,0.0004779919,0.70949125,0.1484904,0.030196274,0.1051889,0.00021650734],"about_ca_topic_score_codex":0.004679794,"about_ca_topic_score_gemma":0.00520448,"teacher_disagreement_score":0.0064414158,"about_ca_system_score_codex":0.000778043,"about_ca_system_score_gemma":0.0016581416,"threshold_uncertainty_score":0.021548688},"labels":[],"label_agreement":null},{"id":"W4413308490","doi":"10.1186/s13015-025-00284-8","title":"The path-label reconciliation (PLR) dissimilarity measure for gene trees","year":2025,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Consejo Nacional de Ciencia y Tecnología; Université de Sherbrooke","keywords":"Metric (unit); Computer science; Measure (data warehouse); Normalization (sociology); Tree (set theory); Path (computing); Set (abstract data type); Data mining; Artificial intelligence; Algorithm; Mathematics; Combinatorics","score_opus":0.018418810388420546,"score_gpt":0.2945175570745436,"score_spread":0.27609874668612305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413308490","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12506275,0.0015506874,0.86806655,0.0005198706,0.00010845326,0.00013439695,0.0011188965,0.00095132674,0.0024870043],"genre_scores_gemma":[0.49182597,0.00030493835,0.5037017,0.00019012655,0.00017545579,0.00027985076,0.0022879352,0.00045625734,0.00077770394],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9912437,0.0035174051,0.00064675184,0.0021641017,0.002110723,0.00031735646],"domain_scores_gemma":[0.9683091,0.018917263,0.004127525,0.0042827553,0.0035839018,0.0007794959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063737636,0.00090994284,0.0015539718,0.0048156106,0.0013308743,0.002716415,0.0029968082,0.0021106456,0.0021391413],"category_scores_gemma":[0.042100728,0.00039013496,0.0013278832,0.003996951,0.0020856794,0.0050077937,0.0028378034,0.0020253323,0.000621214],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00092175475,0.00020286284,0.031284068,0.0011318396,0.00068686187,0.00045759816,0.0010396632,0.42681268,0.019481808,0.13834251,0.006353276,0.3732851],"study_design_scores_gemma":[0.000047961716,0.00039424232,0.008733965,0.00010576164,0.00007864861,0.0009832939,0.00029109942,0.7955493,0.011713794,0.17112726,0.010856201,0.00011844404],"about_ca_topic_score_codex":0.00096936396,"about_ca_topic_score_gemma":0.0008786743,"teacher_disagreement_score":0.0063737636,"about_ca_system_score_codex":0.0023278422,"about_ca_system_score_gemma":0.0009471244,"threshold_uncertainty_score":0.033708096},"labels":[],"label_agreement":null},{"id":"W4414725606","doi":"10.1186/s13015-025-00283-9","title":"Finding maximum common contractions between phylogenetic networks","year":2025,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Université de Sherbrooke","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Phylogenetic tree; Generalization; Contraction (grammar); Set (abstract data type); Computation; Space (punctuation); Upper and lower bounds","score_opus":0.016061718101455544,"score_gpt":0.307544356855016,"score_spread":0.29148263875356045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414725606","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23275459,0.0007679184,0.7591562,0.0008063522,0.000055465298,0.00015843415,0.0008762847,0.00052085624,0.004903771],"genre_scores_gemma":[0.61315906,0.0005956584,0.37947348,0.0002339518,0.00009428594,0.0002521486,0.0027794628,0.00034661643,0.0030653214],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99634725,0.0010950379,0.00025240405,0.0011534566,0.0008448275,0.00030707507],"domain_scores_gemma":[0.97652733,0.017138159,0.0017289476,0.0024209237,0.0012410639,0.00094355125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029677842,0.0008164646,0.0015422505,0.00244876,0.0015836406,0.002575445,0.0024446074,0.0015785476,0.0030668876],"category_scores_gemma":[0.025985349,0.00078141224,0.0014793419,0.0022668627,0.0026679325,0.011345535,0.0042117084,0.00258958,0.00051887194],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074011803,0.0002209338,0.011967227,0.0012779853,0.00026938535,0.0010161569,0.0039137877,0.20186588,0.022359269,0.5158471,0.00692976,0.23359235],"study_design_scores_gemma":[0.000035318782,0.00013744074,0.002031761,0.00011426819,0.00006144509,0.00058848585,0.000774221,0.27594784,0.0086948,0.7026647,0.008904841,0.00004493439],"about_ca_topic_score_codex":0.0007280275,"about_ca_topic_score_gemma":0.0012610885,"teacher_disagreement_score":0.0030668876,"about_ca_system_score_codex":0.0012582258,"about_ca_system_score_gemma":0.00095730764,"threshold_uncertainty_score":0.015695333},"labels":[],"label_agreement":null}]}