{"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3145058,0.002096776,0.6821224,0.000084148516,0.00021401317,0.00087056524,0.00007747721,0.000017230459,0.000011591059],"genre_scores_gemma":[0.5528506,0.000013333038,0.44595313,0.00030075983,0.00036449102,0.00014847374,0.00030926053,0.000045261386,0.000014705346],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982415,0.00010895337,0.00050178065,0.00048943894,0.000070674236,0.0005876513],"domain_scores_gemma":[0.99907285,0.000057789995,0.00025113745,0.00024111803,0.00018352745,0.00019357532],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008493951,0.00030170006,0.0004281091,0.000050017235,0.00026958509,0.00008159013,0.00017113076,0.00030467883,7.720964e-7],"category_scores_gemma":[0.00010416544,0.000297115,0.0001142225,0.0000668532,0.0001719064,0.000008412741,0.00029098458,0.00011576846,3.3621097e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044901785,0.000092472925,0.00044461738,0.00020997554,0.0005582059,0.0000040020227,0.0006219086,0.0018901149,0.88419384,0.0042759227,0.0005056071,0.1067543],"study_design_scores_gemma":[0.0072560534,0.004432183,0.00006303207,0.00017272975,0.00027532515,0.00017895561,0.0010700733,0.78585684,0.11378428,0.064921595,0.0203597,0.0016292549],"about_ca_topic_score_codex":0.00007360665,"about_ca_topic_score_gemma":0.00002465379,"teacher_disagreement_score":0.7839667,"about_ca_system_score_codex":0.000021874741,"about_ca_system_score_gemma":0.00008158067,"threshold_uncertainty_score":0.9999481},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12406406,0.055521365,0.74546397,0.00029510682,0.06488354,0.0049333903,0.0013775013,0.00020672468,0.0032543514],"genre_scores_gemma":[0.41207594,0.003976649,0.16097938,0.0035929552,0.03395932,0.00068267557,0.35440502,0.002092943,0.028235115],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99589527,0.00035041195,0.0007864344,0.0018409744,0.00024156613,0.00088536466],"domain_scores_gemma":[0.9963458,0.0000218189,0.0004513653,0.0024826995,0.00040037397,0.00029789735],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0009035511,0.00069981255,0.0008775831,0.00043864848,0.000118509946,0.000053225976,0.0012667484,0.0019829322,0.000010432687],"category_scores_gemma":[0.00028582738,0.0007489143,0.0002473837,0.00047387855,0.000121211706,0.000014179505,0.0012329868,0.00068146054,0.000008447663],"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":[0.00025545072,0.00009333362,0.00019439259,0.000045067296,0.00046529234,0.000027917129,0.000021433583,0.027388792,0.48064053,0.000008978358,0.48617837,0.0046804403],"study_design_scores_gemma":[0.0015974116,0.0011244687,0.00014628084,0.00037928112,0.000528989,0.000116306896,0.00007269802,0.1747432,0.09553177,0.00034384613,0.72317773,0.002238029],"about_ca_topic_score_codex":0.00008157782,"about_ca_topic_score_gemma":0.00011389654,"teacher_disagreement_score":0.5844846,"about_ca_system_score_codex":0.00019403711,"about_ca_system_score_gemma":0.000559842,"threshold_uncertainty_score":0.99949616},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011084764,0.0005476378,0.98196274,0.000025157125,0.0005691184,0.0006680499,0.015013313,0.000060905968,0.000044578042],"genre_scores_gemma":[0.008668174,0.00004512839,0.979298,0.000114529816,0.00008027116,0.00007087379,0.011681956,0.00003096976,0.000010080329],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99744546,0.00015263328,0.00066849845,0.0010253467,0.0001835088,0.00052457204],"domain_scores_gemma":[0.99609345,0.0001504393,0.00047445015,0.0028654644,0.00026086613,0.00015532889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008489378,0.00027621863,0.0005499246,0.00017288046,0.00012429,0.000018308534,0.0034650334,0.00023319226,0.000018886027],"category_scores_gemma":[0.00009244171,0.00023773802,0.00013140694,0.0002248623,0.00014528412,0.0006397581,0.0016876495,0.000105181105,0.0000020095017],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009039929,0.0007622934,0.00004454578,0.00008333278,0.00014510992,0.000010276958,0.00021906878,0.000002733669,0.06492332,0.021335227,0.0024360234,0.9099477],"study_design_scores_gemma":[0.0026506686,0.0018881388,0.00016732594,0.000071536066,0.00007714093,0.000024764862,0.000047023546,0.7614823,0.17651053,0.018568393,0.038000453,0.0005117165],"about_ca_topic_score_codex":0.0001805842,"about_ca_topic_score_gemma":0.000010477367,"teacher_disagreement_score":0.9094359,"about_ca_system_score_codex":0.00001440164,"about_ca_system_score_gemma":0.00011921055,"threshold_uncertainty_score":0.9694675},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7403701,0.00016915887,0.25794932,0.000115859795,0.0006175078,0.00040222524,0.00021912265,0.000015294649,0.00014144195],"genre_scores_gemma":[0.95345175,0.000027347514,0.045478884,0.000101900456,0.0002738464,0.00006268242,0.00053067884,0.000027710314,0.000045194247],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990065,0.00005318088,0.00025966813,0.00038118148,0.000071592236,0.00022787515],"domain_scores_gemma":[0.99921215,0.000018051618,0.00016531543,0.00039869882,0.0001477358,0.000058077218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021797816,0.00015752406,0.0001749309,0.00006725476,0.00007698134,0.0000076446295,0.00023164699,0.00041490354,0.000021909926],"category_scores_gemma":[0.00018024592,0.00014965625,0.00012184104,0.00007483206,0.00009701445,0.0000035536525,0.0000698136,0.00009939892,0.0000015527735],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047970803,0.000022588787,0.00021384754,0.000013338734,0.000055601413,3.642062e-7,0.000013089345,0.000009245886,0.9741208,0.003998023,0.00006621773,0.021438917],"study_design_scores_gemma":[0.00038669532,0.00038668563,0.00026025824,0.0000049557007,0.000028759683,0.000013156532,0.000010311537,0.00021719863,0.98420656,0.007116677,0.00722521,0.00014354268],"about_ca_topic_score_codex":0.000011570306,"about_ca_topic_score_gemma":0.000007039726,"teacher_disagreement_score":0.21308169,"about_ca_system_score_codex":0.0000052308783,"about_ca_system_score_gemma":0.000045466888,"threshold_uncertainty_score":0.6102805},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70074785,0.0004885953,0.29825187,0.00011983765,0.000082996885,0.0002949512,0.000005247068,0.0000018319314,0.000006845204],"genre_scores_gemma":[0.9764062,0.000025308056,0.023433825,0.00003187061,0.000036483132,0.00004727455,0.0000109117245,0.000005199267,0.0000028828615],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99929816,0.00012069114,0.00022280609,0.00019579989,0.00004200226,0.0001205723],"domain_scores_gemma":[0.99928874,0.00016471202,0.00013813308,0.0002578385,0.00013695812,0.000013600604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006778728,0.000081053215,0.00013657937,0.000023814291,0.000045252953,0.0000032942132,0.00017148533,0.00015337323,8.780461e-7],"category_scores_gemma":[0.0015640759,0.0000486163,0.00005853989,0.00010273918,0.00041412615,0.000003236705,0.00008319147,0.00012544774,5.030278e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014575265,0.000010077659,0.005130161,0.000026325877,0.0000143446305,5.9195596e-8,0.00004133278,0.0009167774,0.9805453,0.00787735,7.324045e-7,0.0052918117],"study_design_scores_gemma":[0.0019565106,0.0009991596,0.012324421,0.00005487327,0.00007577444,0.000027059194,0.000054110173,0.21100044,0.6538403,0.119313076,0.000105262814,0.0002490103],"about_ca_topic_score_codex":0.00021278592,"about_ca_topic_score_gemma":0.0001990128,"teacher_disagreement_score":0.32670498,"about_ca_system_score_codex":0.00000561392,"about_ca_system_score_gemma":0.00006936695,"threshold_uncertainty_score":0.19825152},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8131464,0.0024375948,0.17540956,0.00025274802,0.00056730123,0.002072029,0.00008594605,0.000101384954,0.005927047],"genre_scores_gemma":[0.8204606,0.00009269677,0.17553076,0.0010527233,0.00035356238,0.00039032672,0.0009889002,0.00015084562,0.00097955],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979625,0.00013033308,0.00048280382,0.0006722751,0.00008481641,0.0006673133],"domain_scores_gemma":[0.99913263,0.000027712718,0.00019149606,0.0004454037,0.00009804574,0.000104727864],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00057228137,0.00028520793,0.00032371868,0.00014160962,0.000058861515,0.000013938179,0.00036116762,0.00031027806,0.000055721437],"category_scores_gemma":[0.00029009962,0.0002962628,0.00018019044,0.0001510493,0.00010549327,0.0000057081165,0.0001781247,0.0001224946,0.000048093505],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057277062,0.0001070436,0.0016143713,0.000029260866,0.0001574134,0.00002375173,0.00019465364,0.000014468248,0.98751205,0.00054379395,0.00017822873,0.009567711],"study_design_scores_gemma":[0.0056786975,0.0034668287,0.0024671194,0.00008990552,0.00022957569,0.00013360662,0.00035639494,0.0062327064,0.933174,0.016934777,0.028994886,0.0022414792],"about_ca_topic_score_codex":0.00009833416,"about_ca_topic_score_gemma":0.000024364976,"teacher_disagreement_score":0.054338004,"about_ca_system_score_codex":0.000029563296,"about_ca_system_score_gemma":0.00006215872,"threshold_uncertainty_score":0.999949},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6399492,0.0385433,0.318972,0.00062874146,0.00074392965,0.0005233895,0.00008461824,0.000013562766,0.0005412618],"genre_scores_gemma":[0.65464145,0.0010486558,0.34119594,0.0011550854,0.0010328348,0.00010374806,0.00021352379,0.00007296303,0.0005357802],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99861354,0.0001051664,0.00022719872,0.00043759268,0.000043055246,0.0005734381],"domain_scores_gemma":[0.9992668,0.00004670738,0.000051304833,0.00034740046,0.00007039509,0.00021740286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034450687,0.000260147,0.00027787912,0.000051169933,0.00010690689,0.000013764093,0.00018011665,0.00026328076,0.000010366709],"category_scores_gemma":[0.00013972961,0.00023605781,0.00014385434,0.00006518839,0.00014211833,0.0000014515118,0.00023826986,0.00007029508,0.0000043621058],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032290973,0.000034737168,0.004292271,0.000009120632,0.00019416674,5.101294e-7,0.00007283632,0.00000222464,0.9327458,0.0021619743,0.00081217196,0.059641883],"study_design_scores_gemma":[0.0012100784,0.0008103879,0.0035674728,0.000003700531,0.000106468506,0.00006718698,0.00008392418,0.00008664872,0.55207175,0.0032857365,0.43818745,0.0005192035],"about_ca_topic_score_codex":0.000083319916,"about_ca_topic_score_gemma":0.000013083998,"teacher_disagreement_score":0.43737528,"about_ca_system_score_codex":0.00000804253,"about_ca_system_score_gemma":0.000050433242,"threshold_uncertainty_score":0.96261585},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9946092,0.00100016,0.0030915115,0.00012367238,0.00018576017,0.00056906155,0.0002637292,0.000009273826,0.00014765988],"genre_scores_gemma":[0.9695195,0.00006370644,0.029498274,0.00014259438,0.00023319155,0.00016141216,0.00031127894,0.000035510624,0.000034533405],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982908,0.00009508621,0.00033836978,0.00074577203,0.00006590513,0.00046406206],"domain_scores_gemma":[0.9992326,0.00005157408,0.00013181758,0.0003966406,0.00011306317,0.000074306234],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014587479,0.0002902208,0.00039123703,0.0000644851,0.00014134926,0.000010720804,0.00025744486,0.00025112648,0.00001069382],"category_scores_gemma":[0.00007046047,0.00025994948,0.0001234604,0.00010608324,0.00037194716,0.0000016293055,0.00012434674,0.00010160764,0.0000040972786],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031307508,0.00008665432,0.048260763,0.000008123066,0.00023363139,0.000016209138,0.00012592768,0.000097206335,0.94600374,0.00006727538,0.00005542419,0.004731956],"study_design_scores_gemma":[0.0063866656,0.0035791823,0.046116505,0.000029320836,0.00011311059,0.0002466015,0.00015150986,0.0005740562,0.928125,0.0061361706,0.0070304587,0.0015113975],"about_ca_topic_score_codex":0.0006061523,"about_ca_topic_score_gemma":0.000181378,"teacher_disagreement_score":0.026406761,"about_ca_system_score_codex":0.000024184477,"about_ca_system_score_gemma":0.00012411819,"threshold_uncertainty_score":0.9999853},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17557663,0.000041280317,0.82155985,0.000035768484,0.00005755782,0.00047627316,0.00038247168,0.00004107111,0.0018290719],"genre_scores_gemma":[0.876943,0.0000014125021,0.1211914,0.00010157923,0.0000611271,0.00021421426,0.0014334881,0.000031226275,0.00002255582],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99889255,0.000026606724,0.00024260038,0.00045434944,0.000037368754,0.00034651413],"domain_scores_gemma":[0.99930906,0.000019400903,0.000094637704,0.00049184775,0.00003921175,0.00004586504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013473498,0.0001542545,0.00017013392,0.00008049579,0.00006324173,0.000014682927,0.0003585454,0.00006957101,0.00009797402],"category_scores_gemma":[0.0000047914245,0.00015809988,0.00006798496,0.00014412061,0.00005899959,0.000026897933,0.00015578761,0.00009931031,0.000016942522],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001650808,0.00041433805,0.0009549454,0.000010377483,0.000046989273,0.0000025521608,0.000110518646,0.000014971192,0.939082,0.0077511333,0.000114533854,0.05148113],"study_design_scores_gemma":[0.0005660833,0.0002567389,0.00005680038,0.00002573206,0.00003205179,0.0000022217614,0.000079680925,0.016778864,0.95588154,0.025303092,0.0007110837,0.00030609246],"about_ca_topic_score_codex":0.00043992937,"about_ca_topic_score_gemma":0.0000072481284,"teacher_disagreement_score":0.70136636,"about_ca_system_score_codex":0.000022553473,"about_ca_system_score_gemma":0.000020343525,"threshold_uncertainty_score":0.6447126},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8093021,0.0077549974,0.17995584,0.0001576959,0.00048149723,0.00021842522,0.00030155652,0.000037403162,0.001790474],"genre_scores_gemma":[0.9898056,0.000018405632,0.009264231,0.00018928702,0.00009202179,0.000004953719,0.00060424494,0.0000022798606,0.000018985196],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99879533,0.00016696572,0.00020625886,0.00024394695,0.000061606224,0.0005259031],"domain_scores_gemma":[0.9994937,0.00020174091,0.00007983156,0.00010947321,0.000037490514,0.00007774103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043280906,0.00012328105,0.0002735457,0.00022589094,0.00018396915,0.0000054041875,0.00013022343,0.00012419293,0.00012398155],"category_scores_gemma":[0.000050587052,0.00010759448,0.0001258807,0.00050249015,0.00013477416,0.00006912506,0.000021000898,0.000094045674,0.000026547017],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015636837,0.000036002395,0.9948972,0.00000538609,0.00017393568,0.0000017513343,0.00021567878,0.00029128988,0.000018136761,0.00041949522,0.0000141509745,0.0039113644],"study_design_scores_gemma":[0.0003215618,0.000057748388,0.97389776,0.0000025527188,0.00009897241,0.0000051026295,0.00028196062,0.022844223,0.000022393042,0.00052444043,0.001803599,0.0001396929],"about_ca_topic_score_codex":0.0005750736,"about_ca_topic_score_gemma":0.009589319,"teacher_disagreement_score":0.18050347,"about_ca_system_score_codex":0.0000075351622,"about_ca_system_score_gemma":0.000016719181,"threshold_uncertainty_score":0.53510654},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36385527,0.00028649508,0.63128394,0.00031778275,0.00095915276,0.00069350656,0.0012273623,0.000042845408,0.0013336262],"genre_scores_gemma":[0.81248224,0.00002109504,0.17761357,0.0001801455,0.00088729087,0.00012247851,0.0084959,0.000036918176,0.00016039374],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986283,0.00005145751,0.0003355609,0.0005766086,0.0000655129,0.00034253113],"domain_scores_gemma":[0.99840784,0.00003918165,0.0001913603,0.0011489947,0.00011516722,0.00009744681],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003481814,0.00020345746,0.00019557262,0.00006229613,0.00013977081,0.000043432206,0.00063568173,0.00031181588,0.000031542168],"category_scores_gemma":[0.00029393926,0.00019949219,0.00009093255,0.0001201404,0.000105267325,0.0000113374035,0.0002660783,0.000289788,0.000012790049],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003643183,0.00004378321,0.0003934265,0.0000062692716,0.00013849257,7.635868e-7,0.000012358472,0.0000068677305,0.98792297,0.00070864346,0.0003518777,0.01037809],"study_design_scores_gemma":[0.0012151784,0.0004855383,0.0006705334,0.00001702077,0.0001173905,0.000022536993,0.00006250875,0.020337548,0.85959107,0.015633842,0.10116426,0.0006825861],"about_ca_topic_score_codex":0.00009195634,"about_ca_topic_score_gemma":0.000117555996,"teacher_disagreement_score":0.45367038,"about_ca_system_score_codex":0.0000105516565,"about_ca_system_score_gemma":0.00007977833,"threshold_uncertainty_score":0.8135056},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00064648147,0.0012263549,0.9941287,0.0010440788,0.0016733058,0.0004630539,0.000090928406,0.00021420374,0.0005128845],"genre_scores_gemma":[0.02175312,0.000039617342,0.9757945,0.0013826994,0.00059196213,0.0001819108,0.00015801382,0.000033631048,0.00006453508],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99746764,0.00017330938,0.0003727595,0.00068470865,0.00022597921,0.0010756004],"domain_scores_gemma":[0.99820346,0.0001606503,0.00015714049,0.00093604985,0.00017263858,0.00037007921],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006494165,0.00033044716,0.0003761206,0.00014934098,0.00020128289,0.000085061816,0.0009356121,0.00030823963,0.000025580017],"category_scores_gemma":[0.00017797381,0.00027991433,0.00022329461,0.0003304516,0.00012893236,0.0005873966,0.00076842,0.00024433617,0.000103934995],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012319513,0.00033734596,0.000088929635,0.000011667579,0.00011192863,0.000030669093,0.00013159518,0.0000035526211,0.014012302,0.20783965,0.0021342721,0.7752858],"study_design_scores_gemma":[0.0032409586,0.0016952178,0.0014160972,0.00003315489,0.0001341092,0.0010995992,0.00007866615,0.26774636,0.0779603,0.08859631,0.5559506,0.002048647],"about_ca_topic_score_codex":0.000057199988,"about_ca_topic_score_gemma":6.134592e-7,"teacher_disagreement_score":0.7732371,"about_ca_system_score_codex":0.0000537744,"about_ca_system_score_gemma":0.00013790284,"threshold_uncertainty_score":0.9999653},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72757226,0.00015516233,0.27110806,0.00004452309,0.00009785052,0.00031588844,0.00010225106,0.000020534686,0.000583443],"genre_scores_gemma":[0.6536825,0.000045501798,0.34494793,0.000408529,0.00014317581,0.00011043598,0.00053943257,0.000048841925,0.000073664356],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99841875,0.00015653968,0.00033901437,0.00057749875,0.00006127138,0.0004469378],"domain_scores_gemma":[0.9988909,0.000040621366,0.00022753725,0.0005052509,0.00022480042,0.00011088913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031618398,0.00025856908,0.00035560722,0.00006719536,0.000083379746,0.000005422429,0.00030249203,0.000353101,0.00002713327],"category_scores_gemma":[0.000102612416,0.00021796983,0.00015223195,0.000099111865,0.0002033834,0.0000031854024,0.000061301784,0.00009344156,0.000008047684],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006656965,0.001040165,0.08999366,0.000051188308,0.0010989486,0.000018281688,0.0004354039,0.00014049455,0.78262454,0.00557798,0.00028247942,0.11807115],"study_design_scores_gemma":[0.005710718,0.02255971,0.050964776,0.00006176414,0.00044671222,0.00024276237,0.00080073916,0.004086131,0.8878351,0.017425701,0.0077639176,0.0021020055],"about_ca_topic_score_codex":0.00010952684,"about_ca_topic_score_gemma":0.0000467459,"teacher_disagreement_score":0.11596914,"about_ca_system_score_codex":0.000010932499,"about_ca_system_score_gemma":0.00006993676,"threshold_uncertainty_score":0.88885516},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9509392,0.0024407534,0.045298003,0.000073271076,0.0002388207,0.0008831868,0.00005503299,0.000011605644,0.000060152714],"genre_scores_gemma":[0.9846121,0.000041296054,0.014848231,0.0000832622,0.00007844514,0.00011824688,0.00012511447,0.0000324903,0.000060796538],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99866676,0.00013875187,0.00042552094,0.00036145092,0.00009524013,0.00031229891],"domain_scores_gemma":[0.9989763,0.000022334978,0.00024952646,0.00038425642,0.0003032422,0.00006435623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013653228,0.0002360816,0.00040883303,0.000071959286,0.000049908038,0.000010096374,0.00031273885,0.00031088793,0.00004219378],"category_scores_gemma":[0.00019217074,0.00017838726,0.00022031426,0.000082687264,0.00022979977,0.0000054363127,0.00008491053,0.00006058166,0.0000021341143],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015200819,0.000021502496,0.000067669615,0.000061777006,0.00019440644,3.9892112e-7,0.000028659928,0.000020884543,0.9836279,0.001441097,0.000028908235,0.014354747],"study_design_scores_gemma":[0.0009874478,0.0009722673,0.00017991013,0.000018390874,0.000041442658,0.000011978185,0.00004963202,0.00029553563,0.98972034,0.0072845584,0.00022435052,0.00021415415],"about_ca_topic_score_codex":0.00013218923,"about_ca_topic_score_gemma":0.000003583921,"teacher_disagreement_score":0.03367294,"about_ca_system_score_codex":0.0000061823594,"about_ca_system_score_gemma":0.00006312025,"threshold_uncertainty_score":0.7274421},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3438032,0.001490983,0.6533366,0.000028214936,0.00078211195,0.00033154554,0.000041679108,0.000014010965,0.00017165906],"genre_scores_gemma":[0.95508087,0.0000695769,0.04080808,0.00032357394,0.00045913216,0.000015475045,0.003179896,0.00003845209,0.000024948136],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987515,0.00007129809,0.00034047553,0.00042096095,0.00006294245,0.00035279876],"domain_scores_gemma":[0.9989256,0.000013480528,0.00014105318,0.0007110065,0.00009919537,0.00010961286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050176366,0.00018426284,0.00020266756,0.00007708932,0.000050264563,0.000021621445,0.00037750648,0.00035681267,0.0000027024819],"category_scores_gemma":[0.000079668556,0.00018200539,0.000051826853,0.000100675614,0.000067533496,0.000012866845,0.00036493104,0.00014413412,0.0000027983297],"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":[0.00033595486,0.000077268814,0.0011610932,0.000015055932,0.000098373916,0.000008341454,0.00006111813,0.025798062,0.947659,0.00029956765,0.0018052163,0.022680927],"study_design_scores_gemma":[0.0028635606,0.00083888124,0.00019984387,0.0000642977,0.000054130694,0.000117179436,0.00017501629,0.7244883,0.23793405,0.0020799686,0.030385174,0.0007995746],"about_ca_topic_score_codex":0.000032856187,"about_ca_topic_score_gemma":0.000013997452,"teacher_disagreement_score":0.70972496,"about_ca_system_score_codex":0.00003934882,"about_ca_system_score_gemma":0.000101047386,"threshold_uncertainty_score":0.74219644},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5255697,0.0026739882,0.4683041,0.00055994414,0.00079982553,0.0014485786,0.000056912777,0.000071477225,0.00051547226],"genre_scores_gemma":[0.79469323,0.0005288451,0.19849664,0.0010617139,0.0010085899,0.0009168734,0.0018724181,0.00016645697,0.001255219],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99798954,0.00020248847,0.00038800188,0.00078183674,0.00010301525,0.0005351047],"domain_scores_gemma":[0.998984,0.00005146137,0.00016107055,0.00043347757,0.0002109994,0.00015899465],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005171353,0.00033059338,0.0003128301,0.00016921766,0.00018847409,0.00006718929,0.00022349198,0.00037907605,0.00006849908],"category_scores_gemma":[0.0001521316,0.00032301768,0.00016561753,0.00015470428,0.00019450807,0.000017191325,0.00016307115,0.0001262511,0.000024761466],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055105684,0.000054112024,0.0030690862,0.000036085632,0.0002963767,0.00000272659,0.00004312048,0.000034379016,0.5428882,0.004776669,0.00022933079,0.44851476],"study_design_scores_gemma":[0.01546735,0.0072932374,0.029942695,0.00017629229,0.00074248324,0.0020378302,0.0021485758,0.0199335,0.55919623,0.26314178,0.09350741,0.006412616],"about_ca_topic_score_codex":0.00011863173,"about_ca_topic_score_gemma":0.000008980289,"teacher_disagreement_score":0.44210213,"about_ca_system_score_codex":0.000024932284,"about_ca_system_score_gemma":0.00003290236,"threshold_uncertainty_score":0.9999222},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5908912,0.00018142321,0.4058388,0.00012323345,0.0013864796,0.0004531953,0.00017457128,0.000021678268,0.0009294463],"genre_scores_gemma":[0.97313255,0.000041851647,0.025611905,0.00012166698,0.00035156636,0.00012589621,0.00040236046,0.000032192842,0.0001799884],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990284,0.000055841654,0.0002644692,0.00035756192,0.000063443076,0.00023031246],"domain_scores_gemma":[0.9992693,0.000019591424,0.00015151632,0.00035833998,0.00013902225,0.00006221528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023122296,0.00015792392,0.00017841689,0.0000683644,0.000056078676,0.000008233464,0.0001987317,0.00035165192,0.000031436004],"category_scores_gemma":[0.00014430736,0.0001496726,0.00017229436,0.000059279177,0.000093441246,0.0000042550564,0.00006347122,0.00010936079,0.0000052333507],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000070677066,0.000042892527,0.00005708891,0.000010744212,0.00007108461,6.8696625e-7,0.000011860177,0.0000051051484,0.9385285,0.0016960304,0.00015010222,0.05935526],"study_design_scores_gemma":[0.0004290994,0.000723845,0.00006571922,0.0000058467144,0.00002773996,0.000020037114,0.000025373061,0.00020904564,0.96936345,0.0016707623,0.027330723,0.00012836336],"about_ca_topic_score_codex":0.000020413583,"about_ca_topic_score_gemma":0.000008954949,"teacher_disagreement_score":0.3822414,"about_ca_system_score_codex":0.0000051667425,"about_ca_system_score_gemma":0.000038344388,"threshold_uncertainty_score":0.6103472},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19476004,0.00088840135,0.80190617,0.00008610407,0.00015198193,0.00090325216,0.0012457259,0.000022783595,0.000035559402],"genre_scores_gemma":[0.6185726,0.000023086744,0.37290353,0.00028577994,0.00025989139,0.0004683997,0.0073359143,0.000067157765,0.00008364963],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985782,0.00008794398,0.00039080664,0.0005328713,0.000074353695,0.0003358404],"domain_scores_gemma":[0.99895316,0.00003362194,0.0002186336,0.0003998379,0.00031131852,0.000083423605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026165327,0.00021930653,0.00027852418,0.00010107269,0.00015037542,0.0000040198893,0.00021741423,0.00033449652,0.0000096095355],"category_scores_gemma":[0.00012336766,0.00022757142,0.00033843386,0.00008996386,0.00019893021,0.000003598925,0.000045838773,0.000051874806,9.4443214e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001227785,0.00009068467,0.00030037976,0.000055163466,0.0001400307,0.0000018377403,0.00001455491,0.00013004233,0.9960843,0.00055689085,0.0006088109,0.0018945512],"study_design_scores_gemma":[0.0017658471,0.0012230376,0.0004724823,0.000010259474,0.00007382063,0.000025211495,0.0000064461096,0.0027750207,0.9793164,0.0015118928,0.012611459,0.00020811884],"about_ca_topic_score_codex":0.000023758908,"about_ca_topic_score_gemma":0.000003878298,"teacher_disagreement_score":0.4290026,"about_ca_system_score_codex":0.000029895526,"about_ca_system_score_gemma":0.00015122128,"threshold_uncertainty_score":0.9280093},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48208535,0.00016178368,0.5121605,0.0021525645,0.0000631239,0.0028727257,0.00037219864,0.000032515287,0.00009926079],"genre_scores_gemma":[0.82228225,0.0000044566073,0.17183797,0.0025972077,0.00021561654,0.00091432035,0.0010026104,0.00009018912,0.0010553459],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977501,0.00007590496,0.00030176627,0.0009631297,0.00018769935,0.00072137045],"domain_scores_gemma":[0.9983663,0.0000063121183,0.00018925212,0.0007291992,0.0004633815,0.000245529],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000077731536,0.00051596254,0.00038354244,0.00011751914,0.00018742974,0.0001392106,0.0005389457,0.0005732273,0.000041894666],"category_scores_gemma":[0.00008957604,0.00040542375,0.00015052543,0.00024737083,0.00016385513,0.000022487939,0.00021200217,0.00017769232,0.0000052554583],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001458643,0.000019118377,0.00006185415,0.00004569028,0.00015438744,0.0000035242451,0.000068425434,0.001127916,0.9865697,0.00487875,0.0014100203,0.005514741],"study_design_scores_gemma":[0.0012606011,0.0016681101,0.00007911341,0.000027578397,0.000043431737,0.00004377234,0.00007158493,0.009021794,0.9450987,0.036301374,0.005572095,0.00081182754],"about_ca_topic_score_codex":0.000071249226,"about_ca_topic_score_gemma":0.00006380388,"teacher_disagreement_score":0.3403225,"about_ca_system_score_codex":0.000031077496,"about_ca_system_score_gemma":0.00021072218,"threshold_uncertainty_score":0.9998398},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94778764,0.0005420474,0.045856655,0.00044450743,0.00020821772,0.001031843,0.0038637246,0.000102149585,0.00016322764],"genre_scores_gemma":[0.99185777,0.000084513464,0.006670718,0.00035635717,0.0000754996,0.00022548373,0.0004239435,0.000059102935,0.00024664274],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981297,0.00025285376,0.000510146,0.00037469738,0.00008268032,0.0006498893],"domain_scores_gemma":[0.99825674,0.00051194796,0.00039095143,0.00061802834,0.000086452,0.00013587509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009036174,0.0003224936,0.0005875739,0.0001130978,0.00016856233,0.000013728509,0.0004158045,0.00029554163,0.00007021544],"category_scores_gemma":[0.00014876005,0.00023510879,0.00033500718,0.00019738637,0.00022009696,0.00008820268,0.0001622436,0.00016225257,0.0000077913155],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002278925,0.001108298,0.0004760757,0.00009466494,0.00051490485,0.0000044928897,0.00049416325,2.371981e-7,0.6436481,0.34976277,0.0023019374,0.0013664481],"study_design_scores_gemma":[0.0008811026,0.00030451376,0.0006957148,0.00003079764,0.00016085936,0.000036276615,0.0004565895,0.00009646119,0.7934501,0.19379796,0.009691183,0.0003984014],"about_ca_topic_score_codex":0.000039683466,"about_ca_topic_score_gemma":0.000042019456,"teacher_disagreement_score":0.15596482,"about_ca_system_score_codex":0.000028285185,"about_ca_system_score_gemma":0.00003410821,"threshold_uncertainty_score":0.9587458},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22148956,0.001170362,0.77575666,0.000020082807,0.00025866172,0.0010703874,0.00013109067,0.00001338188,0.00008978997],"genre_scores_gemma":[0.2808745,0.000027106458,0.71806014,0.00012319481,0.00035145544,0.0002640782,0.00015205998,0.00006083289,0.00008667837],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99839246,0.00006115629,0.00034118188,0.0006049545,0.00005584933,0.0005443677],"domain_scores_gemma":[0.99914324,0.00001641076,0.00018150885,0.00032109043,0.0002265558,0.00011122011],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023105851,0.00029064683,0.00030493783,0.000078481426,0.00021423145,0.000015430855,0.00024227529,0.00028508107,0.0000050639005],"category_scores_gemma":[0.00006359027,0.00029498115,0.0002412136,0.00008542882,0.00010151522,0.0000018218192,0.00014962749,0.00007220916,0.0000015825842],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008326887,0.00004243088,0.00016537427,0.000017242612,0.00019983585,0.0000010409506,0.000075238255,0.000016583908,0.8913823,0.00033203137,0.000056393386,0.10762831],"study_design_scores_gemma":[0.0016058898,0.0022192923,0.00016325602,0.000016567414,0.00009381504,0.000028956492,0.00012266924,0.0074427878,0.96408325,0.015344705,0.008350375,0.00052843516],"about_ca_topic_score_codex":0.00030029097,"about_ca_topic_score_gemma":0.00003693217,"teacher_disagreement_score":0.107099876,"about_ca_system_score_codex":0.000027748527,"about_ca_system_score_gemma":0.00012103842,"threshold_uncertainty_score":0.99995023},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056942314,0.00008927801,0.9385893,0.0017073133,0.0006813085,0.0015292468,0.00004616953,0.0001958803,0.00021919404],"genre_scores_gemma":[0.15987134,3.8824436e-7,0.8384521,0.000288822,0.00022835906,0.0008861756,0.00013023189,0.000026220878,0.00011636239],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979555,0.0003175338,0.0003497614,0.00076037104,0.00022055622,0.0003962856],"domain_scores_gemma":[0.9988726,0.000076699645,0.00012590646,0.0004994525,0.00019601343,0.00022935822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083367375,0.0002314428,0.00024032031,0.00026617487,0.000085492524,0.000101082944,0.00059106166,0.00014269976,0.000001945199],"category_scores_gemma":[0.00027419068,0.00022937018,0.0001269708,0.00046641062,0.000047033653,0.0003431788,0.0003521765,0.00015602239,0.00006229861],"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":[0.0001617014,0.00031903284,0.000049786082,0.000049790888,0.00019223682,0.000027884009,0.0011602252,0.036525343,0.14753418,0.30751413,0.00047040277,0.5059953],"study_design_scores_gemma":[0.00091737567,0.0011356989,0.00007517886,0.000029272582,0.000014166231,0.00005393131,0.00004703998,0.7866747,0.08798602,0.10966589,0.0130075235,0.0003932281],"about_ca_topic_score_codex":0.00005422751,"about_ca_topic_score_gemma":0.0000034081388,"teacher_disagreement_score":0.7501493,"about_ca_system_score_codex":0.00016271173,"about_ca_system_score_gemma":0.00016266746,"threshold_uncertainty_score":0.93534446},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18247826,0.00010208583,0.8162019,0.00014367138,0.00042063254,0.0005645189,0.000028150178,0.000052964337,0.000007788253],"genre_scores_gemma":[0.5290615,0.0000011487178,0.47069123,0.00008581219,0.000038117832,0.000086658605,0.000016978025,0.000016832735,0.000001735376],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820507,0.00009709285,0.00045033902,0.00059886905,0.00014901318,0.000499624],"domain_scores_gemma":[0.99865216,0.00042898973,0.00026818799,0.0003494026,0.00020309922,0.00009813903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007773076,0.00024962556,0.00036587912,0.00017134345,0.00025179854,0.000091326045,0.00047464945,0.00020370647,9.070944e-7],"category_scores_gemma":[0.00018838249,0.00021013428,0.00013975531,0.0002347176,0.00018618033,0.00011046408,0.00008868791,0.0002009705,1.1995137e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002853083,0.000036737947,0.0000015481053,0.00002644828,0.00009125689,0.0000018795378,0.027590048,0.09988469,0.07233888,0.020017287,0.0000014119059,0.77998126],"study_design_scores_gemma":[0.00063705334,0.00025918905,0.0000054940087,0.000030144076,0.000046411315,0.00004913033,0.0014792458,0.9663659,0.0019784106,0.028905785,0.0000027079636,0.00024054073],"about_ca_topic_score_codex":0.00002202593,"about_ca_topic_score_gemma":0.0000044613207,"teacher_disagreement_score":0.8664812,"about_ca_system_score_codex":0.000020026844,"about_ca_system_score_gemma":0.0001430368,"threshold_uncertainty_score":0.8569027},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69931555,0.0045625786,0.2935932,0.00016337447,0.0012753012,0.00062707416,0.00010786793,0.000007718997,0.00034735064],"genre_scores_gemma":[0.9766351,0.0005051292,0.020972958,0.0002422929,0.0005659746,0.0002561159,0.00036930377,0.000024617664,0.00042850277],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991097,0.00003319164,0.00018318139,0.00030875765,0.0000324285,0.0003327275],"domain_scores_gemma":[0.99948996,0.00005388665,0.00008661867,0.0001785774,0.00012062014,0.00007030462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019584202,0.00016643519,0.00017790947,0.0000405614,0.0001125154,0.000011384461,0.000085936794,0.000182606,0.000002052403],"category_scores_gemma":[0.00019332986,0.00016001998,0.000098998,0.00003959536,0.00009016963,0.0000016371067,0.00006806121,0.000035121862,0.0000011693244],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006204983,0.00003041057,0.006024023,0.000009344064,0.00010434834,7.881426e-8,0.000053743723,0.000008282848,0.93615395,0.00065767614,0.00037806432,0.056518033],"study_design_scores_gemma":[0.0012092036,0.0012297361,0.017778754,0.0000038950197,0.00008452309,0.0000177683,0.000091562884,0.0006798354,0.8860848,0.0016055941,0.09083707,0.00037724763],"about_ca_topic_score_codex":0.0000106420075,"about_ca_topic_score_gemma":0.000032059987,"teacher_disagreement_score":0.27731958,"about_ca_system_score_codex":0.000013584282,"about_ca_system_score_gemma":0.000027050039,"threshold_uncertainty_score":0.65254253},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6699132,0.008868223,0.30925497,0.009526385,0.00094937603,0.0007436992,0.00021402884,0.00001599047,0.0005141594],"genre_scores_gemma":[0.99311227,0.001054638,0.0039045264,0.00012794945,0.0007407738,0.00014981587,0.000050655115,0.000027981301,0.00083136704],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989785,0.000087456545,0.00018707593,0.00042314368,0.000033920598,0.00028988163],"domain_scores_gemma":[0.9992728,0.00014686515,0.0000855245,0.00026881215,0.00016991621,0.000056055786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000193803,0.0001572084,0.00015768658,0.000035330115,0.0003001869,0.000011241901,0.00013191432,0.00020382478,0.0000015763027],"category_scores_gemma":[0.0002569393,0.00009764516,0.0001019944,0.00005197087,0.00033759486,7.7754345e-7,0.000120768396,0.000052455176,0.0000038040341],"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":[0.000056513334,0.000007255035,0.006651106,0.0000010702993,0.0003170809,0.0000010059962,0.000066140085,0.0000038342437,0.8519154,0.0044539287,0.00027082063,0.13625585],"study_design_scores_gemma":[0.0037729328,0.004291968,0.054484397,0.000015286127,0.00031828138,0.00013969227,0.00061975006,0.00014301327,0.3885236,0.05993802,0.48676905,0.0009839986],"about_ca_topic_score_codex":0.000029451165,"about_ca_topic_score_gemma":0.00006797307,"teacher_disagreement_score":0.4864982,"about_ca_system_score_codex":0.000020439455,"about_ca_system_score_gemma":0.00004653446,"threshold_uncertainty_score":0.39818543},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027377178,0.74698687,0.24813443,0.000043580247,0.00095368735,0.0010007722,0.0026561713,0.000041650484,0.00015546198],"genre_scores_gemma":[0.00013251248,0.9830919,0.010638766,0.00014443934,0.0015643812,0.00055408204,0.0031121657,0.00022469586,0.00053704093],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961393,0.00043718817,0.000842212,0.0015350746,0.00019562071,0.00085059955],"domain_scores_gemma":[0.9972898,0.0000886024,0.0006513115,0.0015769389,0.00017613161,0.0002172479],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00038103852,0.000913048,0.00148368,0.00026591853,0.00017982125,0.0000435085,0.0009979416,0.0018852268,0.0000610921],"category_scores_gemma":[0.00034756397,0.0006936216,0.0011220316,0.00019993454,0.0001502752,0.0000038063154,0.0004649629,0.00019468619,0.000012908278],"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":[0.00003598704,0.00003849135,2.2283429e-7,0.00090025103,0.0007384155,0.000014037011,0.00000369426,0.000003095398,0.1661607,0.004771606,0.0013933888,0.82594013],"study_design_scores_gemma":[0.0005551931,0.00060298416,6.5260494e-8,0.0014216072,0.0005440373,0.00010637669,0.0000033207436,0.000032016294,0.064579785,0.0022463447,0.92917615,0.0007321466],"about_ca_topic_score_codex":0.000009928135,"about_ca_topic_score_gemma":0.0000023852226,"teacher_disagreement_score":0.9277827,"about_ca_system_score_codex":0.00007710626,"about_ca_system_score_gemma":0.0002463262,"threshold_uncertainty_score":0.9995515},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056543488,0.001183028,0.93793404,0.0010560687,0.00015335488,0.0017156968,0.001140681,0.000035370806,0.00023826485],"genre_scores_gemma":[0.6040577,0.0006054549,0.3876633,0.0011310172,0.00074203557,0.002175168,0.0024294888,0.00020982692,0.0009859342],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977945,0.000067694695,0.00033865092,0.0009616715,0.00014599063,0.000691499],"domain_scores_gemma":[0.9988543,0.000060779148,0.00014625282,0.00042734656,0.00031532825,0.00019598776],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036806145,0.00038845662,0.00035893166,0.00011741956,0.00015900569,0.000028914224,0.00026524538,0.0002885809,0.0000241996],"category_scores_gemma":[0.000045190456,0.0002829697,0.0001739227,0.00007880978,0.0005178722,0.0000124067265,0.00013378265,0.000058353875,0.000004733683],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027865975,0.000088238645,0.0000933875,0.000037138172,0.00051690015,0.0000063508814,0.00002574646,0.00003377543,0.94604164,0.0053331093,0.00016118433,0.047383837],"study_design_scores_gemma":[0.046811957,0.025253052,0.0022144772,0.00024284764,0.0010828464,0.001070471,0.00039035245,0.0056876424,0.6014639,0.09060687,0.21957687,0.005598721],"about_ca_topic_score_codex":0.0000068967884,"about_ca_topic_score_gemma":0.000005654251,"teacher_disagreement_score":0.55027074,"about_ca_system_score_codex":0.00004019689,"about_ca_system_score_gemma":0.0001048484,"threshold_uncertainty_score":0.9999623},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37786147,0.0012055356,0.61819464,0.00068811444,0.00040757938,0.0006375565,0.000049419898,0.000035427976,0.0009202267],"genre_scores_gemma":[0.9339694,0.000121695695,0.06477245,0.00039293047,0.00022575441,0.00014489992,0.000112291425,0.00004235195,0.00021822758],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986429,0.00007262327,0.00019013225,0.0005873843,0.000095261355,0.00041165398],"domain_scores_gemma":[0.99876285,0.000026144855,0.0002325144,0.00075277867,0.00013805005,0.00008765213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034006924,0.00024104936,0.0002529379,0.000045229564,0.00057049893,0.000093136274,0.0004981319,0.000275209,0.000010833485],"category_scores_gemma":[0.00023598985,0.00019198058,0.0001285749,0.000023189124,0.00027419013,0.000008891769,0.0001584188,0.0000754634,0.000006035633],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010239094,0.000016169004,0.00032904072,0.000014216823,0.00009779232,0.0000150573915,0.000018892946,0.000008940064,0.9806019,0.0044421297,0.00006238452,0.014291084],"study_design_scores_gemma":[0.0005940526,0.0010449139,0.00018592307,0.000040630162,0.000040808845,0.000054340442,0.00006375302,0.000125581,0.9821503,0.00512851,0.010225992,0.00034515123],"about_ca_topic_score_codex":0.000062864725,"about_ca_topic_score_gemma":0.000016697797,"teacher_disagreement_score":0.55610794,"about_ca_system_score_codex":0.000008233796,"about_ca_system_score_gemma":0.00006627128,"threshold_uncertainty_score":0.7828741},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85887885,0.0016127026,0.13719,0.00069280877,0.0004239015,0.0006602527,0.00004077041,0.000013037363,0.00048765852],"genre_scores_gemma":[0.977585,0.00022025974,0.021439318,0.000096914635,0.000105030864,0.00011251686,0.000198093,0.000026500382,0.0002163595],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989201,0.0001024845,0.00027535539,0.0003987351,0.000047437457,0.00025589752],"domain_scores_gemma":[0.99897665,0.000052498108,0.0003007819,0.00049944135,0.00012051372,0.00005010096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033060633,0.00016649431,0.00023011779,0.000056798766,0.00040876446,0.000024628085,0.00022108444,0.0002468972,0.0000045350484],"category_scores_gemma":[0.00020571533,0.00013076815,0.0000708978,0.00003925788,0.0005889432,0.0000058847536,0.00021932038,0.00009648102,0.0000010217557],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011003804,0.00006924754,0.026445223,0.00004095523,0.0004266329,0.0000040257883,0.00017675298,0.000015024903,0.8667229,0.0063179336,0.00023165785,0.09943962],"study_design_scores_gemma":[0.0128297,0.007296402,0.164276,0.00009522825,0.0010742308,0.00089051994,0.0009537284,0.07104128,0.6142832,0.050107747,0.07474507,0.0024068935],"about_ca_topic_score_codex":0.00005329914,"about_ca_topic_score_gemma":0.000029916624,"teacher_disagreement_score":0.25243968,"about_ca_system_score_codex":0.000005703349,"about_ca_system_score_gemma":0.000029947154,"threshold_uncertainty_score":0.533257},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5897421,0.0012591662,0.4068106,0.0002611019,0.00037561698,0.0012623906,0.00021987426,0.000011267756,0.00005786049],"genre_scores_gemma":[0.9077614,0.000024155624,0.09071238,0.00018503584,0.00025314977,0.00059689797,0.00034016007,0.00004452132,0.000082304425],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99877656,0.00006577962,0.00024616072,0.00039670127,0.000061496554,0.00045329568],"domain_scores_gemma":[0.999012,0.00007676947,0.00019300803,0.00039753327,0.00027930297,0.00004140211],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029004746,0.00020407359,0.00023127497,0.000025772286,0.00031310497,0.000013336625,0.00028852944,0.00012907563,0.0000017005958],"category_scores_gemma":[0.00014909025,0.00014881165,0.00015222804,0.00011737708,0.00034590237,0.000001030599,0.0001777291,0.000052695097,2.9262316e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004319809,0.00013862656,0.0031411585,0.00003750655,0.0019231571,0.0000011883535,0.00019985839,0.0030452018,0.9547591,0.0009621209,0.00078063423,0.034579434],"study_design_scores_gemma":[0.013952502,0.03740048,0.011660208,0.00022723463,0.0015629609,0.00006282108,0.0021047504,0.06366935,0.7913462,0.009065318,0.06619002,0.0027581647],"about_ca_topic_score_codex":0.0000160273,"about_ca_topic_score_gemma":0.000070054906,"teacher_disagreement_score":0.3180193,"about_ca_system_score_codex":0.000019085426,"about_ca_system_score_gemma":0.000049580165,"threshold_uncertainty_score":0.6068363},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95901847,0.006628571,0.033222552,0.00016262611,0.00022037543,0.00051171146,0.00011604771,0.0000067047777,0.000112927104],"genre_scores_gemma":[0.9807357,0.00056251365,0.017737908,0.00030331846,0.00012247842,0.00012410624,0.00024497372,0.000027231827,0.00014172714],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999031,0.000028375442,0.00018080648,0.00046779664,0.000033310098,0.00025870252],"domain_scores_gemma":[0.9994857,0.000035335208,0.00006690693,0.00027940725,0.000075237775,0.00005745687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000094670264,0.00017132248,0.00018262185,0.00003614863,0.00009565891,0.0000138050455,0.00013321411,0.00014598007,0.000005898137],"category_scores_gemma":[0.00003271383,0.00016495284,0.00009746581,0.000040160037,0.00010266558,9.2855015e-7,0.00013807304,0.00003846356,0.0000072356556],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023973387,0.000023857121,0.020075994,0.000009504917,0.00012663724,3.8663637e-7,0.000018549792,0.000040036022,0.95982957,0.00014844064,0.00003441048,0.019668665],"study_design_scores_gemma":[0.0016512662,0.0010696248,0.008309515,0.0000065726467,0.000061038525,0.000050564297,0.00013705362,0.0020035314,0.9283919,0.0013814047,0.05642706,0.00051050144],"about_ca_topic_score_codex":0.00003177261,"about_ca_topic_score_gemma":0.000041498977,"teacher_disagreement_score":0.05639265,"about_ca_system_score_codex":0.000008062449,"about_ca_system_score_gemma":0.000026680975,"threshold_uncertainty_score":0.67265815},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5632573,0.00047220368,0.43472585,0.00012821548,0.00016431154,0.00084158167,0.00037915516,0.00000953638,0.000021891608],"genre_scores_gemma":[0.98882645,0.000032315944,0.008127507,0.00013512,0.00010550555,0.00021337387,0.002475225,0.000031098898,0.000053411277],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987095,0.000050517992,0.00029889212,0.0005120881,0.00007201343,0.00035697024],"domain_scores_gemma":[0.99912745,0.000067037465,0.00019710162,0.0002877356,0.00025890232,0.00006176394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024208889,0.00020463855,0.00029978176,0.00006934174,0.00005710179,0.000010188719,0.00019649255,0.00026793845,0.000007741454],"category_scores_gemma":[0.00018985312,0.0002062703,0.00013387785,0.000099490295,0.0001394985,0.000004994067,0.00005868919,0.00006221517,0.0000019376516],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027048725,0.00013799315,0.019038165,0.0002900008,0.00020745439,0.0000010462667,0.00004471116,0.00031675954,0.9666096,0.0032998142,0.00003315112,0.009750791],"study_design_scores_gemma":[0.006724248,0.004636963,0.0044998378,0.00004855981,0.00014643301,0.000023405675,0.00008940699,0.01154832,0.94969857,0.01011034,0.01164261,0.00083132327],"about_ca_topic_score_codex":0.000014846252,"about_ca_topic_score_gemma":0.0000061217875,"teacher_disagreement_score":0.42659834,"about_ca_system_score_codex":0.000016626287,"about_ca_system_score_gemma":0.000110659705,"threshold_uncertainty_score":0.8411459},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7857751,0.0018875177,0.20947458,0.00013217948,0.00046226324,0.001665473,0.0004913226,0.000015820324,0.00009574482],"genre_scores_gemma":[0.91971016,0.000028769737,0.07851701,0.00019256063,0.00014663955,0.00027347228,0.0010176012,0.00004839895,0.00006538661],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985617,0.00004447517,0.00035323136,0.0005555947,0.00008490556,0.00040013122],"domain_scores_gemma":[0.99897647,0.000059607777,0.00020793063,0.00040952858,0.0002493257,0.00009714006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025082866,0.00024030135,0.0004152311,0.000058388243,0.000064001964,0.000012408738,0.00028573128,0.00023160693,0.0000054709312],"category_scores_gemma":[0.00021091504,0.00022486832,0.00028882275,0.000070743816,0.000107118314,0.0000028444142,0.00014093326,0.00008010007,0.0000017404066],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048449158,0.00021608903,0.008138595,0.00006593859,0.00015949424,0.0000013529865,0.000015717023,0.00007302127,0.9801797,0.0007099971,0.00020420382,0.009751369],"study_design_scores_gemma":[0.007915832,0.0030115086,0.003034006,0.00005735792,0.0001306658,0.000017569779,0.00003840306,0.016494375,0.9476663,0.00075954024,0.020302415,0.00057203294],"about_ca_topic_score_codex":0.000021004942,"about_ca_topic_score_gemma":0.00009705697,"teacher_disagreement_score":0.13393505,"about_ca_system_score_codex":0.00002225353,"about_ca_system_score_gemma":0.00014024814,"threshold_uncertainty_score":0.91698635},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06969948,0.011399888,0.91274714,0.0006622706,0.0011080909,0.0036969993,0.000533474,0.000028465362,0.00012416995],"genre_scores_gemma":[0.2516938,0.0022236055,0.7307538,0.0018993083,0.0021217023,0.0037541704,0.004693109,0.00044842926,0.0024121092],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978553,0.00008040982,0.00049710216,0.0007323525,0.00016069488,0.0006741312],"domain_scores_gemma":[0.9983023,0.00012798524,0.00025600923,0.0008899378,0.00031891596,0.00010488266],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00057581393,0.0003719539,0.0005051466,0.000117083866,0.00011550045,0.000019573827,0.00073921157,0.0003660994,0.000050984214],"category_scores_gemma":[0.000075709155,0.00028638064,0.00055824936,0.00017412197,0.00023518616,0.0000049513533,0.00019892493,0.0001038174,0.00001586482],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001202136,0.00007871547,0.00046022097,0.000056131354,0.0008902061,0.0000012208684,0.00003883112,0.00009206147,0.75624883,0.0013442955,0.00038706514,0.2402822],"study_design_scores_gemma":[0.011649076,0.0041985405,0.00045825093,0.000024386605,0.00053645315,0.00005011141,0.00017048593,0.049240932,0.6271867,0.011423257,0.29378346,0.0012783329],"about_ca_topic_score_codex":0.000045466695,"about_ca_topic_score_gemma":0.000025094281,"teacher_disagreement_score":0.29339638,"about_ca_system_score_codex":0.000022646589,"about_ca_system_score_gemma":0.00012877284,"threshold_uncertainty_score":0.9999588},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17415662,0.0019074085,0.8213707,0.0009958174,0.00009499831,0.00089526386,0.00017228715,0.000037696518,0.0003691826],"genre_scores_gemma":[0.8747342,0.0001670532,0.12037965,0.0012711302,0.00039095653,0.00042086717,0.0025035534,0.00005222281,0.000080371516],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986123,0.00006344821,0.00024559707,0.00067793694,0.000079017715,0.00032168932],"domain_scores_gemma":[0.99941957,0.000011851538,0.000085373555,0.0002574649,0.00011229457,0.000113472364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011841578,0.00021794575,0.00019983889,0.00003340186,0.00012238054,0.00002351437,0.00018534392,0.00023047488,0.000008275613],"category_scores_gemma":[0.000087637054,0.00022547337,0.00011668024,0.00013541177,0.00014205855,0.000009632851,0.0001335154,0.00007869864,0.000009975574],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050662482,0.00008113417,0.0011013553,0.000045644083,0.00015972283,8.497879e-7,0.00017982915,0.0000755735,0.989991,0.0036128757,0.0004714923,0.004229864],"study_design_scores_gemma":[0.01262431,0.0078109493,0.0041110944,0.000026417581,0.00061334495,0.00023479019,0.0024405748,0.05840942,0.6762274,0.012789918,0.2215699,0.0031418677],"about_ca_topic_score_codex":0.000026344056,"about_ca_topic_score_gemma":0.0000028071333,"teacher_disagreement_score":0.7009911,"about_ca_system_score_codex":0.00003091088,"about_ca_system_score_gemma":0.00005976975,"threshold_uncertainty_score":0.91945374},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8797195,0.012190509,0.09852935,0.001137428,0.002150351,0.0017967287,0.0025189538,0.000023547804,0.0019336278],"genre_scores_gemma":[0.92338705,0.0019491581,0.070456035,0.00037970993,0.00094079843,0.0002979673,0.0019977826,0.00010787835,0.00048359486],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982958,0.000084237545,0.00047851304,0.00077561045,0.00007137271,0.00029450457],"domain_scores_gemma":[0.99881005,0.000020896992,0.0003454114,0.000513387,0.00023107338,0.00007919392],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013615358,0.00035857342,0.00058929244,0.00007180036,0.000056930017,0.000012928029,0.00035053774,0.00053561723,0.000012780407],"category_scores_gemma":[0.0001289271,0.00035953027,0.00050189026,0.000051457137,0.00030568213,3.2137274e-7,0.00068999955,0.00014959737,0.000004455711],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064192696,0.00003374521,0.00033112123,0.00007044486,0.0007199514,0.000001486503,0.000030452717,0.00014343916,0.9874586,0.00047065516,0.0004410356,0.0102348775],"study_design_scores_gemma":[0.0010641153,0.0015327442,0.001333629,0.000049421833,0.0003402405,0.000037768434,0.00008208515,0.00075765187,0.9475589,0.015488368,0.030951329,0.00080375164],"about_ca_topic_score_codex":0.000026237296,"about_ca_topic_score_gemma":0.0000109573075,"teacher_disagreement_score":0.04366757,"about_ca_system_score_codex":0.000015925463,"about_ca_system_score_gemma":0.00014501972,"threshold_uncertainty_score":0.9998857},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0756222,0.0034877681,0.9011319,0.017138578,0.00007531593,0.0020761308,0.0001681935,0.000031193806,0.00026870612],"genre_scores_gemma":[0.9655007,0.00042752858,0.030152166,0.0021731989,0.00019376595,0.0008132875,0.0005333999,0.00006874539,0.00013716618],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984596,0.000106054045,0.00028062402,0.0005835151,0.00011887518,0.00045135702],"domain_scores_gemma":[0.99916375,0.00006582122,0.00011573502,0.00045798032,0.00009477088,0.00010196661],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027084694,0.0002478381,0.00019647265,0.00003117519,0.00019631117,0.000056513436,0.0004751017,0.00015859361,0.0000012416348],"category_scores_gemma":[0.00012495084,0.0001427216,0.00007026335,0.00022612713,0.00033823863,0.0000053682465,0.00011591479,0.00013128592,0.000001821459],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018932536,0.00016229699,0.00031415134,0.00003764236,0.00016349897,0.000009244377,0.0005669069,0.001360601,0.97629774,0.0015190137,0.00029520676,0.019084405],"study_design_scores_gemma":[0.011774066,0.016805159,0.0006847589,0.00008661173,0.0004695391,0.00040640114,0.002335441,0.14999932,0.4535613,0.016833935,0.3439086,0.0031348458],"about_ca_topic_score_codex":0.000009739445,"about_ca_topic_score_gemma":0.0002258115,"teacher_disagreement_score":0.8898786,"about_ca_system_score_codex":0.000017962258,"about_ca_system_score_gemma":0.000072012335,"threshold_uncertainty_score":0.58200186},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75179195,0.007983208,0.20533368,0.028303152,0.0007655711,0.0026120164,0.00031982252,0.0001747417,0.0027158586],"genre_scores_gemma":[0.824704,0.00038822502,0.1595093,0.007867853,0.00056266884,0.0018929015,0.0020291577,0.00014220536,0.0029036787],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99729013,0.00033398476,0.0005549111,0.0008118228,0.000107229804,0.0009019274],"domain_scores_gemma":[0.99814093,0.0006639702,0.00008944659,0.0005237205,0.00032548216,0.00025644747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009776338,0.00023589574,0.000675405,0.00019760264,0.00010173531,0.000017479682,0.0001841981,0.00032144503,0.00003558069],"category_scores_gemma":[0.0030224791,0.00021973756,0.00027130073,0.00029934113,0.00014432326,0.00008209826,0.00008079334,0.00033078212,0.000005129259],"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":[0.0033251857,0.0014330872,0.09273923,0.0010840752,0.001553247,0.0004968015,0.0015212884,0.000067213354,0.79310733,0.030258829,0.018782206,0.05563151],"study_design_scores_gemma":[0.020775532,0.0036291773,0.01658701,0.00089426705,0.0006986395,0.0004953375,0.0019112229,0.09130501,0.28340822,0.05230581,0.5259593,0.002030459],"about_ca_topic_score_codex":0.00015486417,"about_ca_topic_score_gemma":0.00071145024,"teacher_disagreement_score":0.5096991,"about_ca_system_score_codex":0.00013772104,"about_ca_system_score_gemma":0.00022968694,"threshold_uncertainty_score":0.89606375},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93653554,0.00026900583,0.06121333,0.000082739025,0.00017325475,0.0007546977,0.00093998836,0.000010315263,0.00002113565],"genre_scores_gemma":[0.9838135,0.000036917165,0.0057524825,0.00012356591,0.00007697014,0.00031585887,0.009774067,0.000035975605,0.000070621085],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987458,0.000106698055,0.00031472647,0.000444435,0.00010683258,0.00028153797],"domain_scores_gemma":[0.9993873,0.000010050595,0.00018402282,0.00030752577,0.00007269258,0.000038396935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017308546,0.00017208346,0.00021032523,0.00016098659,0.000093353316,0.000007204369,0.00027462258,0.00012246887,0.000038429556],"category_scores_gemma":[0.000028670705,0.00019402393,0.00010141333,0.00020271302,0.00006522267,0.00000456022,0.00024039687,0.00009400321,9.3843954e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063354186,0.00008536788,0.0027671407,0.000016345215,0.000058032107,0.0000012119422,0.0000719422,0.00033618094,0.99190104,0.00012350126,0.000004889654,0.0045709917],"study_design_scores_gemma":[0.0023297209,0.0012652512,0.019674718,0.000003422845,0.00003211703,0.000029239503,0.00023781974,0.0023673852,0.9607378,0.0004592745,0.012431967,0.00043125663],"about_ca_topic_score_codex":0.000017991451,"about_ca_topic_score_gemma":0.000010517536,"teacher_disagreement_score":0.055460848,"about_ca_system_score_codex":0.000049093665,"about_ca_system_score_gemma":0.00004880096,"threshold_uncertainty_score":0.7912066},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99510384,0.000024686511,0.00047218535,0.0034229541,0.00008822572,0.00051347894,0.00020161628,0.000056328077,0.000116694704],"genre_scores_gemma":[0.9983745,0.0000048859984,0.0007124404,0.00036054023,0.000050948405,0.00007712017,0.00037465314,0.0000026411874,0.000042254505],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99902284,0.000100531994,0.00018724888,0.00029875815,0.00010524769,0.00028539207],"domain_scores_gemma":[0.9993807,0.00034230622,0.00005162977,0.00010303368,0.00008260367,0.000039743467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026235604,0.00014347406,0.00020220171,0.000021897398,0.00012679546,0.000008574276,0.00026027948,0.000115440336,0.00005058567],"category_scores_gemma":[0.000049746384,0.00004804333,0.00013813013,0.00040588784,0.00025504924,0.000020392663,0.000027676093,0.0000820659,0.000022872755],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006438886,0.000043414748,0.0002393885,0.000004678665,0.00006082371,0.0000032985029,0.00003604634,0.0000021879216,0.9855954,0.004294415,0.000102659535,0.0095533],"study_design_scores_gemma":[0.00047718605,0.0025379243,0.01871366,0.000015031844,0.000043623877,0.0000070352553,0.00007945777,0.0010369277,0.9655238,0.011148013,0.00021183772,0.00020554535],"about_ca_topic_score_codex":0.00011598184,"about_ca_topic_score_gemma":0.0000830461,"teacher_disagreement_score":0.020071642,"about_ca_system_score_codex":0.00001785927,"about_ca_system_score_gemma":0.000010954858,"threshold_uncertainty_score":0.19591501},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8690407,0.0013398537,0.12625833,0.0010581745,0.0003945296,0.0011824849,0.00013496021,0.000079149926,0.00051180896],"genre_scores_gemma":[0.95331514,0.00064519775,0.040384892,0.0006632029,0.00016536332,0.0004951426,0.0039702575,0.000052949614,0.00030787237],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99880505,0.00008135899,0.00029261023,0.00034910918,0.00006410106,0.0004077752],"domain_scores_gemma":[0.999518,0.000032280223,0.000088635774,0.00021214208,0.000088417575,0.000060567752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032346213,0.00017409706,0.0001838937,0.00028088913,0.00007894129,0.000011589787,0.00013341605,0.00028895368,0.0000052863006],"category_scores_gemma":[0.00018597172,0.00018229475,0.000072318864,0.0002718244,0.00013157792,0.000016306549,0.00018616521,0.00010227569,0.000032108375],"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":[0.00036742564,0.00014605971,0.033146113,0.00016493081,0.0005223102,0.00006424625,0.0009610136,0.0016826491,0.782557,0.015208674,0.0023473876,0.16283219],"study_design_scores_gemma":[0.021657959,0.00818051,0.13932757,0.00014547695,0.0002976772,0.00062441966,0.0024942376,0.081748076,0.08400148,0.070400774,0.58666617,0.0044556744],"about_ca_topic_score_codex":0.000027501437,"about_ca_topic_score_gemma":0.000012991266,"teacher_disagreement_score":0.6985555,"about_ca_system_score_codex":0.000023905406,"about_ca_system_score_gemma":0.000063393716,"threshold_uncertainty_score":0.74337643},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5305285,0.007378761,0.46093985,0.000103845756,0.00036675608,0.0003880154,0.00013845674,0.000020004303,0.00013584369],"genre_scores_gemma":[0.9920989,0.0005059999,0.006000704,0.0001786489,0.000524401,0.00021138223,0.0003373679,0.0000800237,0.00006253525],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99847174,0.000052077125,0.00022206185,0.00069133687,0.000067292516,0.000495522],"domain_scores_gemma":[0.99954003,0.000029845887,0.000014503961,0.0002536023,0.000068363275,0.00009368207],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001787905,0.0003011115,0.00024773958,0.00005994118,0.0001281369,0.000035698926,0.00018661658,0.00025585826,0.0000048462794],"category_scores_gemma":[0.000010642659,0.0002475304,0.00023690365,0.00011540636,0.00016003737,0.0000012228409,0.00003954334,0.00012807977,0.0000018309962],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016293129,0.000031329484,0.0007902434,0.00003184954,0.000644095,0.0000228172,0.000075606404,0.0009868686,0.9743982,0.0010406298,0.000062011866,0.021753436],"study_design_scores_gemma":[0.0028647713,0.012428613,0.00072484923,0.00006324564,0.0005839138,0.000425618,0.0001751837,0.02304442,0.9064635,0.0007441531,0.051033508,0.0014482108],"about_ca_topic_score_codex":0.000027142294,"about_ca_topic_score_gemma":0.00003838236,"teacher_disagreement_score":0.46157047,"about_ca_system_score_codex":0.000015151058,"about_ca_system_score_gemma":0.000077664365,"threshold_uncertainty_score":0.9999977},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11068624,0.004461508,0.88152224,0.000777122,0.0006583693,0.00090080703,0.0001316558,0.00010345326,0.00075861346],"genre_scores_gemma":[0.6994084,0.0002717393,0.29682848,0.0007898516,0.00061614177,0.0005784667,0.0006439723,0.00015053032,0.0007123757],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982114,0.000118769036,0.000297339,0.0007788484,0.00011832204,0.00047533074],"domain_scores_gemma":[0.9989593,0.00006266317,0.00008451993,0.0006637,0.00011522965,0.00011457932],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035067543,0.00032642958,0.00030260152,0.000109469285,0.00013413093,0.000093217706,0.00034328803,0.00034736417,0.000040180483],"category_scores_gemma":[0.00017186001,0.00027510594,0.00020750707,0.00012779109,0.00011792879,0.000009827811,0.00014176972,0.00010583955,0.000016633312],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018011259,0.000029578241,0.000010888406,0.000033707274,0.00028863424,0.00005005748,0.00002226077,0.00015820656,0.9745099,0.010678895,0.00083869963,0.013199066],"study_design_scores_gemma":[0.0012501873,0.0010750167,0.0000048306506,0.00005192344,0.000111585134,0.00013960728,0.000031030115,0.0019413523,0.95308787,0.008967196,0.032903224,0.0004361993],"about_ca_topic_score_codex":0.00002694693,"about_ca_topic_score_gemma":0.00001151124,"teacher_disagreement_score":0.58872217,"about_ca_system_score_codex":0.00002240032,"about_ca_system_score_gemma":0.00014026175,"threshold_uncertainty_score":0.99997014},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022601195,0.008439335,0.96540546,0.00034539757,0.0008564592,0.000942582,0.0006996578,0.000023420227,0.0006865091],"genre_scores_gemma":[0.2263244,0.0006025255,0.7680565,0.0012105051,0.00068335806,0.0010601393,0.0015656033,0.00010034805,0.00039660174],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99869156,0.000032490152,0.00033510747,0.00046675664,0.000055194087,0.00041890357],"domain_scores_gemma":[0.9992397,0.00012780297,0.00007290827,0.00032069348,0.00015442653,0.00008451136],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017180963,0.00027111155,0.00026117798,0.000090853675,0.00014537273,0.000054301185,0.00023312554,0.00035200198,0.0000054732864],"category_scores_gemma":[0.00013453134,0.00025024565,0.00031459233,0.000113521965,0.00012777127,0.0000018318258,0.000113210735,0.00009044462,0.000007854422],"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":[0.00025445913,0.00010096574,0.00008107974,0.00020349809,0.0016322393,0.0000069725966,0.00045376955,0.00008405713,0.7707276,0.14352426,0.0039683837,0.078962766],"study_design_scores_gemma":[0.0012958478,0.0030435447,0.000085514686,0.00006464915,0.0002159359,0.000052270527,0.0002651827,0.0076976516,0.32486928,0.31619734,0.34535524,0.00085755927],"about_ca_topic_score_codex":0.0000028247634,"about_ca_topic_score_gemma":0.000004582479,"teacher_disagreement_score":0.44585827,"about_ca_system_score_codex":0.000020086069,"about_ca_system_score_gemma":0.000107519336,"threshold_uncertainty_score":0.999995},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00401137,0.0013809982,0.99119914,0.00060128694,0.0016213219,0.00033490264,0.000084757114,0.00053111924,0.00023508469],"genre_scores_gemma":[0.57339305,0.000067557965,0.42300972,0.001529299,0.00066093955,0.00012063769,0.0008620291,0.000086012624,0.00027072444],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99796337,0.00010409016,0.00029411344,0.0009536455,0.00014449343,0.00054030755],"domain_scores_gemma":[0.9987318,0.000084261665,0.000051812098,0.00083299924,0.00012165066,0.00017746365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029987865,0.0002633124,0.00025814437,0.0001980014,0.00016099705,0.00031772707,0.0011960428,0.00024073088,0.000030271507],"category_scores_gemma":[0.000028608469,0.00021882827,0.00014038653,0.00045497768,0.000077336634,0.00051148544,0.00042197303,0.00020397744,0.00006972239],"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":[0.000013750334,0.00009527356,0.00002825383,0.000027837052,0.000099399585,0.00015856948,0.000117176285,0.00006926236,0.050799824,0.11046198,0.0013808041,0.8367479],"study_design_scores_gemma":[0.00041750653,0.00055181497,0.00007233661,0.000019816616,0.000016531289,0.00008594305,0.000010639803,0.8494522,0.019590706,0.05195629,0.07741966,0.00040656928],"about_ca_topic_score_codex":0.000080963124,"about_ca_topic_score_gemma":0.000004188752,"teacher_disagreement_score":0.84938294,"about_ca_system_score_codex":0.000036277735,"about_ca_system_score_gemma":0.00009874009,"threshold_uncertainty_score":0.8923558},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030554224,0.005550264,0.95784265,0.0022134222,0.0006388261,0.0015290702,0.00017144551,0.00020838917,0.001291706],"genre_scores_gemma":[0.92348367,0.00006860625,0.068481095,0.002409552,0.0005935203,0.00020351603,0.00056084193,0.00010873338,0.0040904814],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979219,0.00008948984,0.00033051535,0.0007466302,0.00028189365,0.0006296035],"domain_scores_gemma":[0.9985077,0.00037863865,0.000034303608,0.0005893447,0.00010717333,0.00038286074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026770637,0.00028405085,0.0005067508,0.00048045386,0.000058318834,0.000040074578,0.0002570598,0.00014438333,0.00013660658],"category_scores_gemma":[0.00020408604,0.00023070489,0.00028513971,0.0009239712,0.00006575566,0.000021186377,0.00006622593,0.00022220782,0.00014316157],"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":[0.0054044686,0.0012228775,0.00029646914,0.0024840042,0.0014266799,0.0031191637,0.0006117457,0.008526041,0.4147099,0.026505418,0.11768027,0.41801295],"study_design_scores_gemma":[0.016563829,0.0020655426,0.000063552194,0.00017087681,0.00017804725,0.00005366309,0.000013896524,0.4244219,0.24284782,0.0003907685,0.31279087,0.00043924034],"about_ca_topic_score_codex":0.00047705712,"about_ca_topic_score_gemma":0.00004219258,"teacher_disagreement_score":0.89292943,"about_ca_system_score_codex":0.0020336336,"about_ca_system_score_gemma":0.002454268,"threshold_uncertainty_score":0.9407872},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012124749,0.00043058518,0.9850541,0.00063734315,0.0007179197,0.00058227393,0.000059417933,0.00012375596,0.00026989632],"genre_scores_gemma":[0.8565545,0.000031646592,0.1402106,0.002471876,0.00008137805,0.00030166353,0.0001926424,0.000034895555,0.00012080128],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977434,0.0001523656,0.00046607564,0.0008649936,0.00014075433,0.0006324051],"domain_scores_gemma":[0.9986802,0.00014671817,0.00013272141,0.00086826127,0.000089664056,0.000082451435],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034109727,0.0003065774,0.00043467933,0.00033481428,0.00013175464,0.00013624526,0.0013824776,0.00024703672,0.000006241036],"category_scores_gemma":[0.000025217774,0.00027634643,0.00013034172,0.00042906252,0.00008400528,0.00024728104,0.0009954813,0.00027641366,0.000008537359],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000603039,0.00042922114,0.0027079836,0.00017255521,0.00016538841,0.00012955065,0.00047150397,0.00078257616,0.019830307,0.066693455,0.00041526754,0.9081419],"study_design_scores_gemma":[0.0033247229,0.00016331124,0.0031804382,0.00018375099,0.000018775774,0.00002300291,0.000066890374,0.8855392,0.0103363,0.08923618,0.0072632194,0.00066422543],"about_ca_topic_score_codex":0.00027425162,"about_ca_topic_score_gemma":0.000017652697,"teacher_disagreement_score":0.9074777,"about_ca_system_score_codex":0.000052616004,"about_ca_system_score_gemma":0.000078184115,"threshold_uncertainty_score":0.9999689},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2960238,0.023231776,0.67168176,0.0038470305,0.0017331596,0.0022271182,0.0007765973,0.000019178657,0.0004596079],"genre_scores_gemma":[0.95736146,0.0012453016,0.036024187,0.0014137548,0.00046848165,0.001472643,0.00079159613,0.000055690343,0.0011669022],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99870867,0.000073418596,0.00028631408,0.00048974913,0.00005118767,0.00039064995],"domain_scores_gemma":[0.9990457,0.00009828805,0.000101984384,0.00042065035,0.0002875933,0.000045769622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043006343,0.0002143396,0.00021566595,0.000032656146,0.00042217653,0.000028027254,0.00030625236,0.00025726936,6.614154e-7],"category_scores_gemma":[0.00035798427,0.0001661081,0.00020216563,0.0000798931,0.00014800968,6.9713644e-7,0.00012069634,0.00006210869,6.9496895e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016845783,0.000048067595,0.00059964525,0.000014548331,0.00039333742,3.213998e-7,0.000017797123,0.000016710257,0.92316145,0.0047473055,0.0016353005,0.06919708],"study_design_scores_gemma":[0.002906386,0.0011491519,0.0021479656,0.000012553571,0.00019019398,0.000005092665,0.00008755674,0.0014650758,0.6043875,0.029295223,0.3578766,0.0004766708],"about_ca_topic_score_codex":0.000015125778,"about_ca_topic_score_gemma":0.00009092964,"teacher_disagreement_score":0.6613376,"about_ca_system_score_codex":0.000021332044,"about_ca_system_score_gemma":0.000119036195,"threshold_uncertainty_score":0.67736924},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4828696,0.0064367587,0.5075736,0.00045673724,0.00075726997,0.0006948644,0.00016396503,0.000014742667,0.0010324557],"genre_scores_gemma":[0.9913281,0.0002876027,0.006495638,0.0006793395,0.00032341114,0.00019465115,0.00040743224,0.00003243485,0.0002513622],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984948,0.000083110666,0.00033428843,0.00054708327,0.00004393387,0.00049680425],"domain_scores_gemma":[0.999223,0.000063090665,0.000104125385,0.00042520263,0.00011134551,0.00007322809],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019616973,0.0002621241,0.0003431652,0.00009590396,0.00024798568,0.00002297889,0.000302017,0.0003454965,0.0000036258482],"category_scores_gemma":[0.00006460033,0.0002682913,0.00022464951,0.00014582167,0.00016445566,6.1225603e-7,0.0001985321,0.00012105799,0.000002752554],"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":[0.00007672521,0.00007980689,0.03276018,0.000024802519,0.0010801615,0.0000033299905,0.000015789872,0.0010412751,0.8907186,0.004063753,0.0010584601,0.06907711],"study_design_scores_gemma":[0.005567741,0.0023124907,0.057602227,0.000056217927,0.0008604285,0.000033606764,0.00016148384,0.0029650591,0.43846217,0.048845097,0.44131118,0.0018223018],"about_ca_topic_score_codex":0.000030137471,"about_ca_topic_score_gemma":0.000022927605,"teacher_disagreement_score":0.50845855,"about_ca_system_score_codex":0.00002011375,"about_ca_system_score_gemma":0.000062823034,"threshold_uncertainty_score":0.99997693},"labels":[],"label_agreement":null}]}