{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1745,"total_is_capped":false,"direct_labels_cover":4,"predictions_cover":1745,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"237059f23efb","filters":{"topic":"Advanced Proteomics Techniques and Applications"}},"results":[{"id":"W2130706354","doi":"10.1093/bioinformatics/bth092","title":"TANDEM: matching proteins with tandem mass spectra","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":2606,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Canadian Institutes of Health Research; University of Chicago","keywords":"Tandem; Matching (statistics); Tandem repeat; Tandem mass spectrometry; Computer science; Computational biology; Chemistry; Biology; Genetics; Mass spectrometry; Chromatography; Mathematics; Genome; Statistics; Materials science","retraction":null,"screen_n_in":null,"score":{"opus":0.01073187936705139,"gpt":0.2430020231674446,"spread":0.2322701438003932,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005671085,0.0001590023,0.000138786,0.00002918737,0.0001573104,0.00005789174,0.0002056064,0.0000939029,0.00008316615],"category_scores_gemma":[0.000006697142,0.0001285405,0.00004058863,0.0001191925,0.00005266445,0.0002144014,0.00003402944,0.0002188698,0.00005027228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001329939,"about_ca_system_score_gemma":0.00007424059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001173502,"about_ca_topic_score_gemma":0.000006587261,"domain_scores_codex":[0.9991833,0.000001192164,0.0002802607,0.0001103555,0.0001796687,0.0002452315],"domain_scores_gemma":[0.9993504,0.00001005,0.0001646088,0.0003570185,0.00003710881,0.00008084349],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001297486,0.0006981508,0.003965604,0.001831311,0.0003213255,0.00006755292,0.007887445,0.01298891,0.441067,0.5061486,0.0008282757,0.0240661],"study_design_scores_gemma":[0.001704992,0.0001152872,0.00005613579,0.000391848,0.00004413615,0.0001237774,0.001219596,0.001798087,0.8383054,0.1385807,0.01682394,0.0008360979],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04117195,0.00001851368,0.9030672,0.0002642554,0.00000871055,0.0003181967,0.00001761064,0.0004136863,0.05471988],"genre_scores_gemma":[0.2012698,0.00003572869,0.7980249,0.0001049349,0.00006054801,0.0001255724,0.0000273916,0.00002424056,0.0003269241],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3972384,"threshold_uncertainty_score":0.524173,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2056499061","doi":"10.1038/nature13302","title":"A draft map of the human proteome","year":2014,"lang":"en","type":"article","venue":"Nature","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":2298,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; National Cancer Institute; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Human proteome project; Proteome; Pseudogene; Computational biology; Proteogenomics; Human genome; Genome; Biology; Gene; Transcriptome; ENCODE; Proteomics; Genetics; Genomics; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.004875348483752633,"gpt":0.2714808862779066,"spread":0.2666055377941539,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003854302,0.00005319187,0.00006123583,0.000006719478,0.00007086212,0.000004551909,0.0002571639,0.0004016268,0.0001183823],"category_scores_gemma":[0.0000172702,0.00003598427,0.00004639435,0.00004315763,0.00003753171,0.00001544101,0.00005807998,0.0008903787,0.000004342273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001146144,"about_ca_system_score_gemma":0.000006560661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003011364,"about_ca_topic_score_gemma":0.000001715568,"domain_scores_codex":[0.999665,0.000003694089,0.0000792431,0.00009845275,0.00008231172,0.00007136293],"domain_scores_gemma":[0.9994918,0.000009772437,0.00007093484,0.0003798784,0.0000327196,0.00001486608],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000001334103,0.00001918697,0.0005229558,0.00005829569,0.000003250737,4.696376e-8,0.00002440599,0.000002367318,0.9434035,0.05343134,0.002066796,0.0004665185],"study_design_scores_gemma":[0.00006711972,0.000003032477,0.0001802991,0.00002687741,0.000003487968,8.116266e-7,0.000004273707,0.00001832933,0.8068998,0.03338629,0.159362,0.00004762598],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8923782,0.0002563731,0.006425197,0.007425522,0.00006861619,0.0006891661,0.00006314439,0.000334126,0.09235962],"genre_scores_gemma":[0.9879982,9.065527e-7,0.008220767,0.0001781452,0.0000837788,0.00007744686,0.000005027829,0.00000977333,0.003425991],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1572952,"threshold_uncertainty_score":0.3868302,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2900884817","doi":"10.1038/s41596-018-0082-x","title":"Single-pot, solid-phase-enhanced sample preparation for proteomics experiments","year":2018,"lang":"en","type":"article","venue":"Nature Protocols","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":2013,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; University of Victoria; Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Chaotropic agent; Sample preparation; Chromatography; Proteomics; Lysis; Protein purification; Reagent; Chemistry; Computer science; Materials science; Nanotechnology; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.03518943859435803,"gpt":0.4472757441547395,"spread":0.4120863055603814,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001082377,0.0002249762,0.0002120002,0.00003702477,0.0002746715,0.00007818499,0.0003348797,0.0004806262,0.0001603786],"category_scores_gemma":[0.0001983938,0.000219718,0.0000921383,0.0001243976,0.00009651911,0.0001743364,0.00006817395,0.0003255265,0.00001213004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001492143,"about_ca_system_score_gemma":0.00006498852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002797481,"about_ca_topic_score_gemma":0.000004170069,"domain_scores_codex":[0.9986477,0.000008729192,0.0003468084,0.0004929476,0.0001755933,0.0003281919],"domain_scores_gemma":[0.9986725,0.00006179125,0.000268257,0.0005898138,0.0003257524,0.0000818631],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005383704,0.0003316046,0.000007774389,0.00008527093,0.00001401669,1.061746e-7,0.000123583,0.000002124458,0.9908189,0.002492337,0.001208232,0.004377731],"study_design_scores_gemma":[0.00124187,0.0003727217,4.08568e-7,0.00008934286,0.00000645099,0.000001382965,0.00001306857,0.0004824059,0.8445006,0.01815705,0.1349116,0.0002230665],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"protocol","genre_scores_codex":[0.01594146,0.00001499637,0.8548861,0.000134442,0.00003603607,0.1218233,0.0002430533,0.0005314752,0.006389117],"genre_scores_gemma":[0.1316169,5.699185e-7,0.3870028,0.0001363058,0.0004956319,0.4801132,0.0001210806,0.00004377985,0.0004696953],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4678833,"threshold_uncertainty_score":0.8959841,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2167844024","doi":"10.1038/nmeth.2557","title":"The CRAPome: a contaminant repository for affinity purification–mass spectrometry data","year":2013,"lang":"en","type":"article","venue":"Nature Methods","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":1804,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto; Université de Montréal; Montreal Clinical Research Institute; Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital","funders":"National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute on Drug Abuse; National Cancer Institute; National Heart, Lung, and Blood Institute; Canadian Institutes of Health Research","keywords":"Computational biology; Mass spectrometry; Tandem affinity purification; Chemistry; Protein purification; Proteome; Chromatography; Affinity chromatography; Biology; Biochemistry; Enzyme","retraction":null,"screen_n_in":null,"score":{"opus":0.02834747888140295,"gpt":0.390944764862205,"spread":0.3625972859808021,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008172279,0.0001475832,0.0001655849,0.00002705424,0.000483719,0.0001107459,0.001137454,0.0003399998,0.00005220613],"category_scores_gemma":[0.0007740139,0.00010386,0.00007167215,0.0001793911,0.00009263693,0.0001422211,0.0001481945,0.0007303248,0.000005340549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006477764,"about_ca_system_score_gemma":0.00004766299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001258647,"about_ca_topic_score_gemma":0.000001468178,"domain_scores_codex":[0.998834,0.00006111724,0.0002834884,0.000443626,0.000124867,0.0002529638],"domain_scores_gemma":[0.996416,0.00112683,0.00021422,0.001995196,0.0001803143,0.00006739314],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001377097,0.00003583892,0.00006011103,0.00003338122,0.00003060023,2.874895e-7,0.00001352146,4.884423e-7,0.9317422,0.01926312,0.008094177,0.0407125],"study_design_scores_gemma":[0.0001223808,0.000009530288,0.0001468958,0.000008739044,0.00002244737,0.000006947897,0.00005285689,0.0009229359,0.6789585,0.04160862,0.2780058,0.000134268],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001758529,0.002303375,0.982827,0.001866239,0.0001537348,0.0006989294,0.00009613654,0.0002111737,0.01008488],"genre_scores_gemma":[0.01849716,0.0001572419,0.975526,0.0001125058,0.0003061267,0.001115564,0.0001068064,0.00002964753,0.004148908],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2699116,"threshold_uncertainty_score":0.4235286,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1971163936","doi":"10.1002/pmic.200900758","title":"Matrigel: A complex protein mixture required for optimal growth of cell culture","year":2010,"lang":"en","type":"article","venue":"PROTEOMICS","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":1514,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Matrigel; Extracellular matrix; Basement membrane; Stem cell; Matrix (chemical analysis); Cell biology; Laminin; Cell culture; Chemistry; Biology; Cell; Biochemistry; Chromatography","retraction":null,"screen_n_in":null,"score":{"opus":0.01397598485287738,"gpt":0.2715550137385753,"spread":0.2575790288856979,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000108003,0.0002137782,0.0002571162,0.00003259486,0.0001295931,0.00002624351,0.0004409527,0.0003149635,0.0001090458],"category_scores_gemma":[0.00006697508,0.0002002874,0.0001457513,0.0001102911,0.0001100923,0.00008594254,0.00009122903,0.0004236104,0.000005092199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002710454,"about_ca_system_score_gemma":0.00005835691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001099374,"about_ca_topic_score_gemma":0.00000301547,"domain_scores_codex":[0.9988962,0.000005009435,0.0003535613,0.0003395923,0.0001236531,0.0002820129],"domain_scores_gemma":[0.9988601,0.00002016938,0.0003106767,0.0004803812,0.0002413188,0.00008736505],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008901978,0.0001044392,0.00003779359,0.000364385,0.000008881447,3.810807e-7,0.00008931497,0.000003718579,0.9840807,0.01455216,0.0005227794,0.0001464832],"study_design_scores_gemma":[0.0005337564,0.00004492112,0.000002950535,0.00002527106,0.00001534523,0.000005591518,0.00002494206,0.0008289927,0.9652224,0.02286761,0.01019462,0.0002335696],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5830734,0.00003037681,0.406595,0.0004342253,0.00003143692,0.003297591,0.0007333492,0.0003468964,0.005457769],"genre_scores_gemma":[0.3063322,0.000007101546,0.690618,0.00002497164,0.0001368067,0.001665756,0.0001132739,0.00004384404,0.001058049],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.284023,"threshold_uncertainty_score":0.8167484,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1971887998","doi":"10.1002/rcm.1196","title":"PEAKS: powerful software for peptide <i>de novo</i> sequencing by tandem mass spectrometry","year":2003,"lang":"en","type":"article","venue":"Rapid Communications in Mass Spectrometry","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":1382,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Bioinformatics Solutions (Canada); Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Tandem mass spectrometry; Chemistry; Software; Mass spectrometry; Peptide; Computational biology; Tandem; Peptide sequence; Sequence (biology); Combinatorial chemistry; Chromatography; Computer science; Biochemistry; Biology; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.02015743695278633,"gpt":0.2917216138285507,"spread":0.2715641768757644,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007757969,0.0004094617,0.0004769959,0.0003675201,0.0004482918,0.000106758,0.001930118,0.0003150106,0.0008632987],"category_scores_gemma":[0.0007193926,0.0004932428,0.0002124499,0.001596196,0.0002293627,0.0002207741,0.0001780375,0.001066248,0.00003255407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001694509,"about_ca_system_score_gemma":0.0002524014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002161114,"about_ca_topic_score_gemma":0.00001310465,"domain_scores_codex":[0.9973931,0.0001021,0.0007564471,0.0006323901,0.0002659791,0.0008499806],"domain_scores_gemma":[0.9952742,0.0007847635,0.0003507398,0.003256598,0.0001599163,0.0001737874],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001851245,0.0002938092,0.007355647,0.00009774525,0.00007380862,0.000002668346,0.0001457619,0.000048781,0.9482968,0.04033745,0.002834527,0.0004945261],"study_design_scores_gemma":[0.001755657,0.000126021,0.00007654083,0.0001910219,0.0000704323,0.00009713064,0.001474035,0.001037477,0.7139164,0.1475871,0.13234,0.001328232],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02604576,0.004910776,0.8901935,0.001225176,0.0000473015,0.0008513951,0.0003446758,0.0007155248,0.07566589],"genre_scores_gemma":[0.3028351,0.002412869,0.6921122,0.0001666704,0.00004894197,0.0006212879,0.0002248482,0.00009577788,0.00148228],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2767894,"threshold_uncertainty_score":0.9997519,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135078307","doi":"10.1074/mcp.m111.010587","title":"PEAKS DB: De Novo Sequencing Assisted Database Search for Sensitive and Accurate Peptide Identification","year":2011,"lang":"en","type":"article","venue":"Molecular & Cellular Proteomics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":1114,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University; University of Waterloo; Bioinformatics Solutions (Canada)","funders":"","keywords":"Computational biology; Identification (biology); Biology; Chemistry; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.04365512402571903,"gpt":0.2846905781843063,"spread":0.2410354541585872,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004352146,0.0002382872,0.0001993311,0.00006711909,0.000241464,0.00007532845,0.0002504587,0.0001767379,0.00002313895],"category_scores_gemma":[0.00007659022,0.000274991,0.00009550723,0.0001281654,0.0001175038,0.0001531909,0.0001608839,0.0003112657,0.000007716238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002116634,"about_ca_system_score_gemma":0.0001317185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009021889,"about_ca_topic_score_gemma":0.000005402852,"domain_scores_codex":[0.998473,0.00004044653,0.0003599755,0.0005685271,0.0001509335,0.0004071392],"domain_scores_gemma":[0.9987505,0.00003595826,0.000191368,0.0006643601,0.0002091505,0.0001486706],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005530503,0.00004135301,0.00005755364,0.0001503211,0.00003232075,0.00004337735,0.0003544603,0.00003157397,0.9951345,0.003373007,0.000007230068,0.0007190512],"study_design_scores_gemma":[0.0003658108,0.00002082465,0.00002601187,0.00005599858,0.00005703155,0.00007132922,0.0002506881,0.005552317,0.9897311,0.003415586,0.0001448054,0.000308436],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4961626,0.00003543657,0.5024247,0.00003638332,0.000006817183,0.0005929589,0.000106591,0.00009102059,0.0005434835],"genre_scores_gemma":[0.6496008,0.00003042311,0.3491869,0.0000604082,0.00003404574,0.0005439689,0.000284698,0.00005955022,0.000199253],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1534382,"threshold_uncertainty_score":0.9999702,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1965942536","doi":"10.1038/nature01510","title":"From genomics to proteomics","year":2003,"lang":"en","type":"article","venue":"Nature","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":1001,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"","keywords":"Proteomics; Genomics; Computational biology; Function (biology); Structural genomics; Biology; Bioinformatics; Genome; Protein structure; Gene; Genetics; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.006567340992558319,"gpt":0.2707646294191663,"spread":0.264197288426608,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003044726,0.00009494728,0.00008391524,0.00001490041,0.00005912353,0.00001894965,0.0001818009,0.0007041472,0.0003705331],"category_scores_gemma":[0.00005488334,0.00009578251,0.0000357206,0.00008146073,0.00001027078,0.00002774659,0.0000308595,0.001083615,0.00007205029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007502424,"about_ca_system_score_gemma":0.00002913399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006205116,"about_ca_topic_score_gemma":0.000002404335,"domain_scores_codex":[0.9994658,0.000002999893,0.00009795887,0.0002253851,0.00006905155,0.0001387625],"domain_scores_gemma":[0.9994715,0.00001601296,0.00003655948,0.0003665192,0.00003518101,0.00007423994],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009863274,0.00002786722,0.0001558177,0.000006567253,0.000008376195,0.000001742202,0.00008129588,0.00003450368,0.9717954,0.02230316,0.004317541,0.00125789],"study_design_scores_gemma":[0.0000605051,0.000002221178,0.000005735109,0.000005308942,0.000002883457,0.000001599835,0.00001912308,0.00001155176,0.6114708,0.02865204,0.3596789,0.00008933499],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8673494,0.0003355222,0.07103804,0.001324806,0.00007991755,0.0004546599,0.0002473456,0.0003477996,0.0588225],"genre_scores_gemma":[0.358649,0.00002099753,0.6382561,0.001096918,0.0001906413,0.0001864608,0.00004259274,0.00003068228,0.00152658],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5672181,"threshold_uncertainty_score":0.5431027,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2947763854","doi":"10.1038/s41592-019-0426-7","title":"Prosit: proteome-wide prediction of peptide tandem mass spectra by deep learning","year":2019,"lang":"en","type":"article","venue":"Nature Methods","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":979,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"IONICS Mass Spectrometry (Canada)","funders":"Bundesministerium für Bildung und Forschung; Agence Nationale de la Recherche; Nvidia","keywords":"Tandem mass spectrometry; Database search engine; Proteome; Computer science; Bottom-up proteomics; Proteomics; Computational biology; Mass spectrometry; Peptide; Deep learning; Artificial intelligence; Chemistry; Chromatography; Search engine; Protein mass spectrometry; Biology; Biochemistry; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.00743944056699306,"gpt":0.3140974849949114,"spread":0.3066580444279183,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004664181,0.0001637108,0.0002418524,0.0000408075,0.00007325201,0.00001558843,0.0002219485,0.0004802508,0.0002922285],"category_scores_gemma":[0.0002107008,0.0001555531,0.00009333423,0.0001978348,0.00003685643,0.00008911801,0.00004590677,0.001341013,0.000006445788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008694639,"about_ca_system_score_gemma":0.00002103382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003310098,"about_ca_topic_score_gemma":3.110755e-7,"domain_scores_codex":[0.9989117,0.000061463,0.0002767952,0.0003499904,0.0001860477,0.0002139779],"domain_scores_gemma":[0.9990621,0.0001640065,0.0002452839,0.0003820834,0.00009130087,0.00005518924],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000164693,0.00002670132,0.009008902,0.00009854829,0.00001789749,2.688962e-7,0.00004491424,0.00006070033,0.9831238,0.0007457185,0.0002122867,0.006643787],"study_design_scores_gemma":[0.000215619,0.00003864289,0.0002752813,0.00005022322,0.00001843363,0.000003258463,0.0000420289,0.001086831,0.9320642,0.007280839,0.05879077,0.0001339041],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04840807,0.0007999536,0.9209361,0.0001631365,0.00005896905,0.0006752239,0.00003381305,0.0003378206,0.0285869],"genre_scores_gemma":[0.1442117,0.00007488621,0.8502774,0.00004006214,0.00008155197,0.0002048438,0.0000595726,0.00003865757,0.005011334],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.09580367,"threshold_uncertainty_score":0.6343271,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2035037428","doi":"10.1021/pr034086h","title":"Mass Spectrometric Quantitation of Peptides and Proteins Using Stable Isotope Standards and Capture by Anti-Peptide Antibodies (SISCAPA)","year":2004,"lang":"en","type":"article","venue":"Journal of Proteome Research","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":801,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Genome British Columbia; University of Victoria","funders":"","keywords":"Peptide; Chemistry; Chromatography; Mass spectrometry; Polyclonal antibodies; Elution; Bottom-up proteomics; Electrospray ionization; Peptide sequence; Protein mass spectrometry; Antibody; Biochemistry; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.04178906183756321,"gpt":0.3771105128330622,"spread":0.335321450995499,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001539954,0.0001482309,0.0003646011,0.0004775484,0.0002319809,0.000109639,0.0002064218,0.0001235636,0.00003382835],"category_scores_gemma":[0.0004459599,0.0001272333,0.00005914498,0.0006017015,0.0002957697,0.0004046475,0.00009652342,0.0007481609,3.462564e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002698312,"about_ca_system_score_gemma":0.0003298696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002730684,"about_ca_topic_score_gemma":0.00001292432,"domain_scores_codex":[0.997986,0.00004776173,0.0005072934,0.0002208687,0.0008952438,0.0003428501],"domain_scores_gemma":[0.9980626,0.00008472197,0.0004192395,0.0002010165,0.001099116,0.0001333345],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006995718,0.00007789225,0.003530267,0.0003913964,0.00003756667,0.000008631606,0.0001425907,0.0000571264,0.9942178,0.001206715,0.00006413614,0.0001959504],"study_design_scores_gemma":[0.0007228612,0.0002826557,0.0004535018,0.0005043146,0.00001904265,0.00008953977,0.0007330211,0.0000929486,0.9776319,0.01874238,0.000575117,0.0001527764],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9474396,0.002503333,0.0485165,0.0003615949,0.00000593861,0.0005409282,0.00009452031,0.00001379967,0.000523849],"genre_scores_gemma":[0.8229483,0.001462723,0.1753689,0.000002325231,0.00004315037,0.00002466791,0.000002849904,0.00002464844,0.000122433],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1268524,"threshold_uncertainty_score":0.5188425,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1977184198","doi":"10.1002/pmic.200500358","title":"Overview of the HUPO Plasma Proteome Project: Results from the pilot phase with 35 collaborating laboratories and multiple analytical groups, generating a core dataset of 3020 proteins and a publicly‐available database","year":2005,"lang":"en","type":"article","venue":"PROTEOMICS","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":792,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Biological Sciences","funders":"U.S. Public Health Service; National Cancer Institute; National Institutes of Health; Michigan Economic Development Corporation; Pfizer; Bristol-Myers Squibb; Abbott Laboratories","keywords":"Proteome; Computational biology; Computer science; Bioinformatics; Database; Chemistry; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.07155267813634265,"gpt":0.3196197676946351,"spread":0.2480670895582924,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000475712,0.0002863101,0.0003744146,0.00003073061,0.0003630168,0.0001151268,0.0004356967,0.00009787309,0.00001633449],"category_scores_gemma":[0.0007899033,0.0001791813,0.00002576346,0.000603687,0.0004293479,0.0003671963,0.0004572446,0.0004001636,5.551607e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004804042,"about_ca_system_score_gemma":0.0003351062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007788316,"about_ca_topic_score_gemma":0.0007968259,"domain_scores_codex":[0.9980577,0.00005066096,0.0007293512,0.0005839117,0.0002956628,0.000282733],"domain_scores_gemma":[0.9975559,0.0002381417,0.0007831631,0.001078719,0.0002626728,0.00008140187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00131893,0.00055987,0.005359978,0.0005346903,0.000107697,0.000002240982,0.0007358374,0.00009452761,0.9861835,0.002597174,0.001461726,0.001043821],"study_design_scores_gemma":[0.004393923,0.0002639272,0.00003010039,0.0005628875,0.00009728256,0.00001546215,0.0004831589,0.06656142,0.9193529,0.0002276524,0.007639552,0.0003716799],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9582281,0.0003807406,0.003147352,0.0005669403,0.00000597826,0.003386802,0.03416517,0.00005719258,0.00006173785],"genre_scores_gemma":[0.5263238,0.0002517781,0.4698974,0.0001059633,0.0001540155,0.001206747,0.001961145,0.00005512856,0.00004397409],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4667501,"threshold_uncertainty_score":0.73068,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2017777108","doi":"10.1038/ncponc1187","title":"Strategies for discovering novel cancer biomarkers through utilization of emerging technologies","year":2008,"lang":"en","type":"review","venue":"Nature Clinical Practice Oncology","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":786,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University Health Network; Mount Sinai Hospital","funders":"","keywords":"Biomarker discovery; Identification (biology); Data science; Computer science; Computational biology; Emerging technologies; Biomarker; Cancer biomarkers; Cancer; Bioinformatics; Risk analysis (engineering); Biology; Medicine; Proteomics; Artificial intelligence; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.1882171952969201,"gpt":0.5661340406730772,"spread":0.3779168453761571,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0003765305,0.0003949171,0.001705275,0.00007548061,0.0001579471,0.0000200705,0.0006351633,0.003606065,0.00002459448],"category_scores_gemma":[0.004672919,0.0003362643,0.0006029873,0.0003657392,0.0004544756,0.0004333656,0.000238635,0.00251412,0.000001471193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002762068,"about_ca_system_score_gemma":0.001338455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003194189,"about_ca_topic_score_gemma":0.0000187687,"domain_scores_codex":[0.9971763,0.00005961478,0.001567474,0.0007239877,0.0001651114,0.0003075132],"domain_scores_gemma":[0.9904065,0.005780123,0.00281724,0.0006419617,0.0003198715,0.00003433703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007571299,0.0003490261,0.000001045023,0.00424786,0.0003940717,0.000003949806,0.00002157783,0.000006851638,0.00006553638,0.02558754,0.00197651,0.9672703],"study_design_scores_gemma":[0.0003073248,0.00009027847,7.90223e-8,0.001849394,0.0007159514,0.00005789173,0.000686914,0.00003208688,0.0001498397,0.002961381,0.9928365,0.0003123552],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000001253065,0.9159896,0.07342484,0.0007653827,0.0002943279,0.0008657824,0.0003639291,0.0002821825,0.008012671],"genre_scores_gemma":[0.0000222579,0.796461,0.2018135,0.00008436824,0.0002354527,0.001088712,0.0001811134,0.00006254193,0.0000510606],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.99086,"threshold_uncertainty_score":0.9999089,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3109082402","doi":"10.1038/s41598-020-76603-3","title":"VolcaNoseR is a web app for creating, exploring, labeling and sharing volcano plots","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":773,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Dalhousie University","keywords":"Plot (graphics); Computer science; Web application; Measure (data warehouse); Data mining; Identification (biology); Information retrieval; World Wide Web; Biology; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.05254093367203964,"gpt":0.2862375818592096,"spread":0.2336966481871699,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002316663,0.0001463267,0.0001659243,0.00003505931,0.0004366447,0.0002314401,0.0001540691,0.00006129189,0.0001663402],"category_scores_gemma":[0.0001508796,0.0001510603,0.0000666484,0.0001865256,0.00009396792,0.0001839531,0.0001767105,0.0001225714,0.000004883322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003377973,"about_ca_system_score_gemma":0.00006570559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001234502,"about_ca_topic_score_gemma":0.00000365145,"domain_scores_codex":[0.9982531,0.000001781422,0.0003794858,0.0009057484,0.0001882316,0.000271671],"domain_scores_gemma":[0.9989078,0.00002171682,0.000239382,0.0005403816,0.0001148509,0.0001758388],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009685062,0.00002699515,0.007435865,0.0002173898,0.00001714648,0.00001969132,0.0009687564,0.00002329976,0.9776803,0.000701397,0.01018214,0.002717359],"study_design_scores_gemma":[0.0001299339,0.00001102964,0.000008340252,0.00007508393,0.00002037054,0.00002408963,0.0001446626,0.003877894,0.673478,0.008452551,0.3135519,0.0002261129],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9831665,0.000236804,0.009403329,0.000622462,0.0002808863,0.0004834408,0.00003099769,0.0005704225,0.005205158],"genre_scores_gemma":[0.9155034,0.00004589294,0.07305577,0.0002575987,0.0002776302,0.00127861,0.00008139199,0.00007961482,0.00942011],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3042023,"threshold_uncertainty_score":0.616006,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2048839385","doi":"10.1038/nrm2208","title":"Analysis of protein complexes using mass spectrometry","year":2007,"lang":"en","type":"review","venue":"Nature Reviews Molecular Cell Biology","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":698,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University Health Network; University of Toronto; Mount Sinai Hospital; Lunenfeld-Tanenbaum Research Institute","funders":"National Heart, Lung, and Blood Institute","keywords":"Mass spectrometry; Chemistry; Proteomics; Supramolecular chemistry; Fractionation; Protein–protein interaction; Characterization (materials science); Chromatography; Computational biology; Biochemistry; Nanotechnology; Molecule; Biology; Materials science; Organic chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.03775440111769055,"gpt":0.3855465297747507,"spread":0.3477921286570602,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0004475604,0.000621183,0.003973683,0.0006865535,0.00005340901,0.00001020088,0.0007857505,0.002010878,0.0003082422],"category_scores_gemma":[0.0000772988,0.0004957434,0.002088466,0.002294114,0.0001361395,0.00001649699,0.0001511425,0.001690642,0.00001101308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000179859,"about_ca_system_score_gemma":0.00009425603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007106391,"about_ca_topic_score_gemma":0.000001031868,"domain_scores_codex":[0.9970936,0.0001581828,0.001391691,0.0008091615,0.0001322969,0.0004150394],"domain_scores_gemma":[0.9966944,0.0000867909,0.001768493,0.001267606,0.00009172554,0.00009094222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003160454,0.00007933591,0.000003896047,0.02622585,0.001035936,0.00001282284,0.000001770422,0.000002494728,0.2463427,0.003794282,0.00001046472,0.7224873],"study_design_scores_gemma":[0.00004211666,0.00001326607,1.410053e-8,0.002449919,0.004617583,0.000004622545,7.230665e-7,0.0000137857,0.02469283,0.0004079,0.967338,0.0004192721],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001062592,0.9024621,0.09132912,0.000002332241,0.00001694898,0.001120076,0.0002205475,0.00004961207,0.004788643],"genre_scores_gemma":[0.00001674086,0.8215581,0.1770129,0.00002848347,0.00005538241,0.0001838169,0.001003747,0.00005772318,0.00008305991],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9673275,"threshold_uncertainty_score":0.9997494,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2045117578","doi":"10.1038/nmeth.3255","title":"DIA-Umpire: comprehensive computational framework for data-independent acquisition proteomics","year":2015,"lang":"en","type":"article","venue":"Nature Methods","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":695,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Lunenfeld-Tanenbaum Research Institute","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of General Medical Sciences; Canadian Institutes of Health Research","keywords":"Workflow; Computer science; Multiplex; Proteomics; Tandem mass spectrometry; Mass spectrometry; Software; Fragmentation (computing); Data acquisition; Database search engine; Data mining; Computational biology; Chemistry; Chromatography; Bioinformatics; Database; Information retrieval; Biology; Search engine; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.09065455223700448,"gpt":0.4644961570090743,"spread":0.3738416047720698,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005026348,0.0001916629,0.0002389811,0.00003865585,0.0001325416,0.00005025668,0.0005723297,0.000633844,0.00003900533],"category_scores_gemma":[0.0004082139,0.0001891431,0.00007022611,0.0001397906,0.00005713895,0.0001447282,0.0002515843,0.0008644162,0.000005982631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001263898,"about_ca_system_score_gemma":0.0001054493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003336304,"about_ca_topic_score_gemma":5.880856e-7,"domain_scores_codex":[0.9986862,0.00005659466,0.0002736873,0.0005163812,0.0002400015,0.0002271588],"domain_scores_gemma":[0.997845,0.000610527,0.0002066132,0.0008156369,0.0003851898,0.0001370397],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006421226,0.0004910066,0.0003564244,0.0004407459,0.0002575212,0.000007368324,0.0004225469,0.004533911,0.2266515,0.5955649,0.0180052,0.1526268],"study_design_scores_gemma":[0.0004789953,0.00002457143,0.00003018892,0.00003998312,0.00003710625,0.00001537355,0.00006500587,0.01782152,0.1821547,0.7187673,0.08029769,0.0002675756],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002419049,0.000559959,0.9938924,0.0008174122,0.0001301659,0.0006342768,0.0003908897,0.0002305471,0.0009253307],"genre_scores_gemma":[0.01506503,0.00001443112,0.9816936,0.0006628899,0.000443226,0.0004616996,0.001507427,0.00004263114,0.0001091029],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1523592,"threshold_uncertainty_score":0.7713032,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2031095666","doi":"10.1021/pr049882h","title":"Open Source System for Analyzing, Validating, and Storing Protein Identification Data","year":2004,"lang":"en","type":"article","venue":"Journal of Proteome Research","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":692,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Research Manitoba","funders":"","keywords":"Server; Computer science; Identification (biology); Database; Database server; Open source; Relational database; Interface (matter); Proteome; World Wide Web; Operating system; Bioinformatics; Software","retraction":null,"screen_n_in":null,"score":{"opus":0.1731126030223852,"gpt":0.457940666299246,"spread":0.2848280632768608,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004221252,0.0001005707,0.0002204766,0.000162378,0.0004126734,0.000408358,0.001729072,0.00008811005,0.00001181113],"category_scores_gemma":[0.0005762397,0.00009057212,0.0000397041,0.0002462571,0.00007563364,0.0006244173,0.0008939125,0.000537939,0.000002778453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003248169,"about_ca_system_score_gemma":0.0002400361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000766497,"about_ca_topic_score_gemma":0.000003480827,"domain_scores_codex":[0.9983404,0.00004509356,0.0005697215,0.0003190696,0.0004425313,0.0002831284],"domain_scores_gemma":[0.9978796,0.00007911406,0.0005336644,0.0007421377,0.000631713,0.0001338128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007720966,0.00006560187,0.0001082677,0.0005961691,0.00003382732,0.000004287874,0.0001075684,0.00006263493,0.9897138,0.003237428,0.00008925446,0.005903968],"study_design_scores_gemma":[0.0009440308,0.0001042893,0.00001552006,0.0009066714,0.00001878697,0.00009870689,0.0005286421,0.0004209625,0.9759896,0.009461148,0.01136955,0.000142127],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3818308,0.0003495009,0.6137486,0.001025283,0.00001904663,0.00244736,0.00006460602,0.0000507957,0.0004640379],"genre_scores_gemma":[0.75765,0.00004596399,0.2403195,0.000001983511,0.0003193929,0.0006229792,0.00002018842,0.00004074368,0.0009792568],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3758192,"threshold_uncertainty_score":0.3937806,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2139564441","doi":"10.1074/mcp.r400007-mcp200","title":"Mass Spectrometry as a Diagnostic and a Cancer Biomarker Discovery Tool","year":2004,"lang":"en","type":"review","venue":"Molecular & Cellular Proteomics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":631,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Mount Sinai Hospital","funders":"","keywords":"Biomarker discovery; Prostate cancer; Proteomics; Breast cancer; Medicine; Cancer biomarkers; Biomarker; Mass spectrometry; Computational biology; Profiling (computer programming); Oncology; Cancer; Bioinformatics; Internal medicine; Computer science; Biology; Chemistry; Chromatography","retraction":null,"screen_n_in":null,"score":{"opus":0.01417122209993779,"gpt":0.2951488462402526,"spread":0.2809776241403148,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001637,0.0009379435,0.001444747,0.0002007567,0.0001762237,0.0002688149,0.0006471697,0.0008050934,0.0001858502],"category_scores_gemma":[0.000186164,0.0009067612,0.0006376137,0.0004623277,0.0001938762,0.0001506578,0.0003679067,0.0009869629,0.00005118307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006554466,"about_ca_system_score_gemma":0.0006133426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009191743,"about_ca_topic_score_gemma":0.000001181116,"domain_scores_codex":[0.9969085,0.00005068435,0.0008209366,0.00122055,0.0003410621,0.0006582463],"domain_scores_gemma":[0.9977822,0.0001313946,0.0005999926,0.001242535,0.00005695745,0.0001868599],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003477356,0.0003493488,0.00001207799,0.06241952,0.001134976,0.001178406,0.00004117687,0.00002754782,0.4859565,0.02062773,0.00005619227,0.4281617],"study_design_scores_gemma":[0.0005202948,0.00004474132,1.596055e-7,0.01689815,0.001482127,0.0001988245,0.000008266865,0.00002535358,0.4434491,0.025735,0.5096619,0.001976185],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0009945895,0.844559,0.1510327,0.00004381342,0.00004238934,0.002073463,0.0003290712,0.0001935583,0.0007314144],"genre_scores_gemma":[0.0001185989,0.916463,0.07680066,0.0000463524,0.0001194765,0.004948199,0.0003847825,0.0002891239,0.0008298742],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.5096056,"threshold_uncertainty_score":0.9993383,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2950557897","doi":"10.1038/s41467-017-00249-5","title":"Multi-laboratory assessment of reproducibility, qualitative and quantitative performance of SWATH-mass spectrometry","year":2017,"lang":"en","type":"article","venue":"Nature Communications","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":617,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Sinai Health System; Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"Core Research for Evolutional Science and Technology; National Cancer Institute; National Human Genome Research Institute; National Institute of General Medical Sciences; Functional Genomics Center Zurich; National Institutes of Health; Ontario Genomics; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Australian Government; European Commission; National Center for Research Resources; Japan Agency for Medical Research and Development; National Science Foundation; Canadian Institutes of Health Research; Genome Canada; Buck Institute for Research on Aging; Government of Canada","keywords":"Mass spectrometry; Reproducibility; Proteomics; Quantitative proteomics; Computer science; Data acquisition; Label-free quantification; Scale (ratio); Data mining; Chemistry; Chromatography","retraction":null,"screen_n_in":null,"score":{"opus":0.06112049668265888,"gpt":0.4529367233399413,"spread":0.3918162266572824,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008561705,0.0001129407,0.0002418208,0.00005342267,0.0003948054,0.00001779453,0.001130591,0.000175274,0.00001335747],"category_scores_gemma":[0.0008951829,0.0001120542,0.00004619141,0.0001173143,0.0007289894,0.0001847582,0.0004661111,0.0007455336,4.882811e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005166,"about_ca_system_score_gemma":0.0000832711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002576689,"about_ca_topic_score_gemma":0.0000329604,"domain_scores_codex":[0.9989936,0.00006338557,0.00035707,0.000351393,0.0001325809,0.0001019283],"domain_scores_gemma":[0.9927712,0.0003458449,0.0006969478,0.005683943,0.0004650653,0.00003697914],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001516814,0.0003094177,0.03697691,0.0001693507,0.0000593567,8.644458e-8,0.001218086,0.000004203929,0.8673406,0.09350865,0.00004402027,0.0003541156],"study_design_scores_gemma":[0.0007322608,0.0001340715,0.08269055,0.0002643704,0.00007735634,0.000001574314,0.002879559,0.006775029,0.8971658,0.007081441,0.001800462,0.0003974678],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9792081,0.002697602,0.007946793,0.001549956,0.00002254991,0.0003370609,0.0004492332,0.00006308983,0.007725623],"genre_scores_gemma":[0.5525725,0.0008987207,0.4463934,0.00000704508,0.000004621956,0.00005206114,0.00002133937,0.000007811024,0.00004247186],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4384466,"threshold_uncertainty_score":0.4569439,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2156355974","doi":"10.1016/j.cell.2006.03.022","title":"A Mammalian Organelle Map by Protein Correlation Profiling","year":2006,"lang":"en","type":"article","venue":"Cell","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":585,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Biology; Organelle; Protein subcellular localization prediction; Organelle biogenesis; Biogenesis; Subcellular localization; Proteomics; Computational biology; Cell biology; Genomics; Gene expression profiling; Membrane protein; Gene; Genome; Genetics; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.00507826701196031,"gpt":0.2146425254952226,"spread":0.2095642584832623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00002760436,0.00008321786,0.00006097449,0.00001073479,0.00008355313,0.00001618831,0.00009439255,0.00008420267,0.000373895],"category_scores_gemma":[0.000002339049,0.00008842386,0.00002451441,0.00005437988,0.00001898577,0.00003974702,0.0000240271,0.0001209498,0.0001203894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004006736,"about_ca_system_score_gemma":0.00001213994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003369266,"about_ca_topic_score_gemma":9.258776e-7,"domain_scores_codex":[0.9994882,0.000002842014,0.0001362302,0.0001747253,0.00006307926,0.0001349201],"domain_scores_gemma":[0.9996672,0.000006659485,0.0000754358,0.0001999218,0.00002395159,0.00002683631],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000003134606,0.000045411,0.0003110468,0.00004472846,5.443785e-7,6.627576e-7,0.000006081665,0.00003001282,0.9942889,0.001143959,0.00400128,0.0001242381],"study_design_scores_gemma":[0.0001154748,0.000004252317,0.000002370828,0.000009692797,0.000003163198,8.082769e-7,0.0000156293,0.0005357026,0.9426984,0.006331039,0.05017746,0.0001060507],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5453089,0.0002826375,0.2959249,0.0003530639,0.00002701682,0.0007297322,0.00007432794,0.0006087524,0.1566906],"genre_scores_gemma":[0.8756368,0.000002129835,0.06112799,0.00001643517,0.00008851353,0.000232693,0.0002661129,0.00002765247,0.06260164],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3303279,"threshold_uncertainty_score":0.4093888,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1970172743","doi":"10.1021/ac0013709","title":"Charting the Proteomes of Organisms with Unsequenced Genomes by MALDI-Quadrupole Time-of-Flight Mass Spectrometry and BLAST Homology Searching","year":2001,"lang":"en","type":"article","venue":"Analytical Chemistry","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":585,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Mass spectrometry; Chemistry; Proteome; Genome; Peptide mass fingerprinting; Computational biology; Sequence database; Mass spectrum; Database search engine; Proteomics; Homology (biology); Chromatography; Biochemistry; Gene; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.006709722073275724,"gpt":0.2438116601709898,"spread":0.2371019380977141,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001330846,0.0001706954,0.000284669,0.000020398,0.000104675,0.00001809661,0.0002913222,0.0001174456,0.001117371],"category_scores_gemma":[0.00004917601,0.0001239313,0.00005110527,0.0002454083,0.0004927684,0.00004188738,0.00009022871,0.0003212425,0.000004623991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003721791,"about_ca_system_score_gemma":0.00004360683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001253353,"about_ca_topic_score_gemma":2.372086e-7,"domain_scores_codex":[0.9988913,0.00000932101,0.0003134824,0.0003081885,0.0001820743,0.000295647],"domain_scores_gemma":[0.9991217,0.0001253563,0.0001943965,0.000395412,0.00006812422,0.00009498996],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002537713,0.00004174797,0.00313123,0.0001214197,0.00005028296,0.000006680828,0.00004889253,0.000007586877,0.9959474,0.0003350652,0.00002821764,0.0002560934],"study_design_scores_gemma":[0.0001813653,0.00002872045,0.00002719261,0.00004160009,0.00003917324,0.00006410429,0.000172857,0.0009305877,0.9959726,0.002031722,0.0003598229,0.0001502387],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9764339,0.0001919023,0.01220437,0.0006582194,0.000001141662,0.0001346331,0.00003637585,0.00005768965,0.01028181],"genre_scores_gemma":[0.9863367,0.00008824956,0.01149216,0.00002704868,0.0000441155,0.00003810379,0.00002257502,0.00002769887,0.00192332],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009902868,"threshold_uncertainty_score":0.9997957,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2101629470","doi":"10.1038/nprot.2006.288","title":"Silver staining of proteins in polyacrylamide gels","year":2006,"lang":"en","type":"article","venue":"Nature Protocols","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":572,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Silver stain; Staining; Polyacrylamide; Stain; Electrophoresis; Chromatography; Polyacrylamide gel electrophoresis; Mass spectrometry; Chemistry; Fixation (population genetics); Molecular biology; Biology; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.008249985199709202,"gpt":0.3112988602053018,"spread":0.3030488750055926,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001129121,0.000132643,0.00018361,0.00006017993,0.00003707028,0.00001359537,0.0002409062,0.0003403538,0.00009781158],"category_scores_gemma":[0.00003823983,0.0001274271,0.00005550874,0.0002097652,0.000044821,0.00007986314,0.00006084181,0.0006347308,0.000002491036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007418408,"about_ca_system_score_gemma":0.00005153304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008255258,"about_ca_topic_score_gemma":0.00002969226,"domain_scores_codex":[0.9990365,0.000008175697,0.0003259324,0.0002411344,0.0001683991,0.0002198598],"domain_scores_gemma":[0.9993333,0.00003005133,0.000179534,0.0003627447,0.00006883054,0.00002556776],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005646035,0.000168166,0.008582104,0.0002071256,0.000003741872,0.000004236789,0.00002667516,0.00006122721,0.9563333,0.03128267,0.0001781144,0.003096133],"study_design_scores_gemma":[0.0004446675,0.00001843432,0.0004547237,0.000212523,0.000001851099,0.000002080302,0.00001290198,0.00006365591,0.9353607,0.03553092,0.02775217,0.000145382],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4742154,0.0004203763,0.0309498,0.001095092,0.00002396803,0.3026974,0.0002787121,0.001120115,0.1891991],"genre_scores_gemma":[0.7030859,9.340941e-7,0.06643692,0.00004038974,0.0000882579,0.2295619,0.00001690573,0.00002824039,0.000740581],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2288705,"threshold_uncertainty_score":0.5196327,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1968063944","doi":"10.1021/pr9006365","title":"Repeatability and Reproducibility in Proteomic Identifications by Liquid Chromatography−Tandem Mass Spectrometry","year":2009,"lang":"en","type":"article","venue":"Journal of Proteome Research","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":562,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland","funders":"National Cancer Institute; U.S. Public Health Service","keywords":"Repeatability; Reproducibility; Chromatography; Proteomics; Biomarker discovery; Tandem mass spectrometry; Peptide; Proteome; Chemistry; Orbitrap; Mass spectrometry; Label-free quantification; Quantitative proteomics; Liquid chromatography–mass spectrometry; Computational biology; Biology; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.03830414990698112,"gpt":0.3766268700147317,"spread":0.3383227201077506,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007882781,0.0001663954,0.0003691626,0.0004449664,0.0002148251,0.00009835963,0.0005662884,0.0001726537,0.0001183842],"category_scores_gemma":[0.00168327,0.0001533586,0.0001196742,0.001102924,0.0002828146,0.0003435512,0.00009170522,0.001496113,0.000003399876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003434734,"about_ca_system_score_gemma":0.0001754096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002545529,"about_ca_topic_score_gemma":0.000002243917,"domain_scores_codex":[0.9968356,0.000166761,0.0009842658,0.0008588205,0.0006832164,0.0004713319],"domain_scores_gemma":[0.9971119,0.0001255951,0.0003869313,0.001652099,0.0005187546,0.0002047136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001590266,0.0003286637,0.009128995,0.00008499926,0.0000118716,0.000008581441,0.00006132838,0.000001487352,0.9889142,0.0003532394,0.0002282112,0.0007194023],"study_design_scores_gemma":[0.0004762443,0.0003374526,0.01105263,0.0001445931,0.000007281508,0.0000787439,0.0001105635,0.00003138973,0.9254947,0.06132856,0.0007597241,0.0001781284],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9889677,0.0007383229,0.005397554,0.002853651,0.00001384033,0.000983505,0.00002146,0.00004366748,0.0009803205],"genre_scores_gemma":[0.953152,0.0005354533,0.0456904,0.00001091058,0.0001195696,0.0001808401,0.000005704469,0.00001841119,0.0002867192],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06341951,"threshold_uncertainty_score":0.649995,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2785428883","doi":"10.1016/j.cels.2017.12.004","title":"Unification of Protein Abundance Datasets Yields a Quantitative Saccharomyces cerevisiae Proteome","year":2018,"lang":"en","type":"review","venue":"Cell Systems","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":551,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Cancer Society Research Institute","keywords":"Proteome; Abundance (ecology); Saccharomyces cerevisiae; Biology; Eukaryote; Proteomics; Computational biology; Protein biosynthesis; Messenger RNA; Function (biology); Yeast; Quantitative proteomics; Cell biology; Genetics; Gene; Ecology; Genome","retraction":null,"screen_n_in":null,"score":{"opus":0.05615227228850884,"gpt":0.3456731795813155,"spread":0.2895209072928067,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003267384,0.0004875371,0.001435191,0.0001074071,0.0001194378,0.00006499331,0.0009188671,0.00051655,0.00009067471],"category_scores_gemma":[0.00005305669,0.0004232303,0.0002627656,0.0003584588,0.0001627992,0.0001228199,0.0001360113,0.0004195835,0.0001486298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001497195,"about_ca_system_score_gemma":0.0002038182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008596933,"about_ca_topic_score_gemma":0.000001693151,"domain_scores_codex":[0.9973871,0.00008955901,0.001234643,0.0007398829,0.0002584328,0.0002903892],"domain_scores_gemma":[0.9959008,0.0001090447,0.002205227,0.001523753,0.0001686389,0.0000925435],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003997703,0.0006564871,0.000002516447,0.7941048,0.0004326761,0.00001076534,0.0002866124,0.000006648198,0.03010985,0.03309061,0.006572213,0.1346869],"study_design_scores_gemma":[0.00007557857,0.00004200118,2.18637e-8,0.025064,0.0001527647,0.000009675474,0.00004522829,0.00002714762,0.008258079,0.0001844049,0.9657223,0.0004187819],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002088602,0.9803023,0.008257333,0.000005799334,0.00004791018,0.003909231,0.002852157,0.000155113,0.004449235],"genre_scores_gemma":[0.0002200447,0.9750928,0.01296136,0.000001413139,0.0002234415,0.006809559,0.002301813,0.0001085362,0.002281085],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9591501,"threshold_uncertainty_score":0.999822,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1979340580","doi":"10.1038/nmeth.2650","title":"TCPA: a resource for cancer functional proteomics data","year":2013,"lang":"en","type":"letter","venue":"Nature Methods","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":538,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Cancer Institute; Canada's Michael Smith Genome Sciences Centre; University of Miami; Susan G. Komen for the Cure","keywords":"Proteomics; Computational biology; Resource (disambiguation); Biology; Computer science; Bioinformatics; Genetics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.07253778142216777,"gpt":0.4263131586805006,"spread":0.3537753772583328,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0004809427,0.0004381581,0.0004776054,0.00007279951,0.0001969538,0.00007678077,0.001451078,0.003756021,0.0008689103],"category_scores_gemma":[0.0004088131,0.0004011043,0.0001717436,0.0001407651,0.00008472947,0.0001103426,0.0004856008,0.006194572,0.000007968683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001898754,"about_ca_system_score_gemma":0.0001776432,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003106676,"about_ca_topic_score_gemma":0.00000226304,"domain_scores_codex":[0.9977199,0.00006257481,0.0003804631,0.001125222,0.0002640266,0.0004477475],"domain_scores_gemma":[0.9962987,0.0006171704,0.0004156706,0.002353686,0.0002535881,0.0000611653],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001815255,0.00001202089,0.000001957145,0.0003573648,0.00007883001,0.000001496209,0.000004925468,0.000004068756,0.0138511,0.000291294,0.9600409,0.02533788],"study_design_scores_gemma":[0.0001787293,0.000006057358,6.174972e-7,0.00009025944,0.0001139562,0.000009994615,0.000003052162,0.0006664991,0.04926479,0.01235248,0.9368786,0.0004349799],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000003726054,0.002160989,0.6913798,0.2976168,0.0002301612,0.001210084,0.003394533,0.0002946897,0.003709093],"genre_scores_gemma":[3.508981e-7,0.0001019483,0.7553843,0.198641,0.008032396,0.00554375,0.007418703,0.0001394684,0.02473813],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.09897584,"threshold_uncertainty_score":0.9998441,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1974500649","doi":"10.1074/mcp.m800540-mcp200","title":"Multiple Reaction Monitoring-based, Multiplexed, Absolute Quantitation of 45 Proteins in Human Plasma","year":2009,"lang":"en","type":"article","venue":"Molecular & Cellular Proteomics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":511,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria; Genome British Columbia","funders":"Genome British Columbia; Genome Canada","keywords":"Chemistry; Chromatography; Trypsin; Peptide; Analyte; Selected reaction monitoring; Quantitative proteomics; Mass spectrometry; Bottom-up proteomics; Peptide mass fingerprinting; Amino acid; Coefficient of variation; Standard curve; Tandem mass spectrometry; Quantitative analysis (chemistry); Capillary electrophoresis; Proteomics; Protein mass spectrometry; Biochemistry; Enzyme","retraction":null,"screen_n_in":null,"score":{"opus":0.01475995282149117,"gpt":0.2696057480718039,"spread":0.2548457952503127,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000206255,0.0002813886,0.0002999724,0.0001680314,0.0001199868,0.00002879178,0.0003161217,0.0002857262,0.00001102945],"category_scores_gemma":[0.00008807769,0.0003368751,0.0001520943,0.0002769621,0.00006409665,0.0001310262,0.00003925572,0.000433353,0.000006060955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001951897,"about_ca_system_score_gemma":0.00006046184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001770444,"about_ca_topic_score_gemma":0.00001669611,"domain_scores_codex":[0.9982373,0.00003309699,0.0006161531,0.0004858963,0.0002786437,0.0003489383],"domain_scores_gemma":[0.9986888,0.00002513028,0.0003976331,0.0006782971,0.0001246864,0.00008547155],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007977501,0.0003028195,0.000962394,0.00008789512,0.000009035263,0.00001578836,0.00005538728,0.003554256,0.9922189,0.001585648,0.000001779497,0.001126285],"study_design_scores_gemma":[0.00112187,0.00009506863,0.0002827179,0.0001527455,0.00001586555,0.000002529243,0.00003548304,0.01183478,0.9832146,0.002751894,0.0001720066,0.0003203994],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8566333,0.00006146756,0.1415516,0.00009282205,0.00001906405,0.00105398,0.00001957525,0.0001505616,0.0004176628],"genre_scores_gemma":[0.8004063,0.0000102727,0.1988867,0.0000136954,0.00004198818,0.0004265659,0.0001117235,0.00004473997,0.00005802304],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05733513,"threshold_uncertainty_score":0.9999083,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2082006641","doi":"10.1021/ac0258709","title":"A Method for Assessing the Statistical Significance of Mass Spectrometry-Based Protein Identifications Using General Scoring Schemes","year":2003,"lang":"en","type":"article","venue":"Analytical Chemistry","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":496,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Genome Canada","funders":"","keywords":"Identification (biology); Representation (politics); Data mining; Scoring algorithm; Simple (philosophy); Computer science; Statistical analysis; Machine learning; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03911847149694674,"gpt":0.3819344892939808,"spread":0.342816017797034,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003722765,0.0001852794,0.0002591843,0.00002444151,0.0002199083,0.00007709812,0.0002891387,0.0001268708,0.0003142275],"category_scores_gemma":[0.0005139493,0.0001628882,0.0001424189,0.0003082331,0.0001989817,0.00006562825,0.00002398781,0.000281261,9.612477e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001260008,"about_ca_system_score_gemma":0.0002094439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001155468,"about_ca_topic_score_gemma":2.118623e-7,"domain_scores_codex":[0.9985504,0.00002369988,0.0004588713,0.000420626,0.0002231369,0.0003233006],"domain_scores_gemma":[0.9985563,0.0003910143,0.000228124,0.0005577396,0.0001672536,0.00009961639],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000006175642,0.00006536319,0.000252394,0.0002296997,0.00002931032,7.749541e-7,0.000002829877,0.0003579229,0.9635376,0.03535752,0.00001955097,0.0001408332],"study_design_scores_gemma":[0.0001736887,0.000003383297,0.000006252836,0.00004862649,0.00008179331,0.000003213743,0.00005050192,0.09960394,0.8816301,0.01722305,0.001005843,0.000169555],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08246279,0.00003635677,0.9144664,0.0001199078,0.000004742973,0.0002536011,0.00008862576,0.00005523769,0.002512366],"genre_scores_gemma":[0.3708462,9.651708e-7,0.6284103,0.00001451958,0.00005211123,0.0002155896,0.00002672281,0.00002294335,0.0004105741],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2883835,"threshold_uncertainty_score":0.6642389,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2045234988","doi":"10.1016/j.cell.2006.01.044","title":"Global Survey of Organ and Organelle Protein Expression in Mouse: Combined Proteomic and Transcriptomic Profiling","year":2006,"lang":"en","type":"article","venue":"Cell","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":493,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Hospital for Sick Children; University of Toronto","funders":"Canadian Institutes of Health Research; National Science Council; Ontario Genomics Institute; Genome Canada","keywords":"Biology; Proteome; Organelle; Transcriptome; Protein subcellular localization prediction; Cell biology; Mitochondrion; Computational biology; Proteomics; Bioinformatics; Gene expression; Biochemistry; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.008515690859558712,"gpt":0.2327943708156017,"spread":0.2242786799560429,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001011723,0.0001145034,0.000161269,0.00002046315,0.00004180109,0.0000115519,0.00008936012,0.0001020051,0.00002134582],"category_scores_gemma":[0.000009387591,0.0001140423,0.0000116126,0.000112354,0.00006220763,0.00004505,0.00004248743,0.00009917757,5.935436e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003487408,"about_ca_system_score_gemma":0.00002711692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004344156,"about_ca_topic_score_gemma":0.00007689726,"domain_scores_codex":[0.9993121,0.00001685909,0.0002348989,0.0002366862,0.0000601281,0.0001393462],"domain_scores_gemma":[0.9996549,0.00001229016,0.00009133038,0.0001756657,0.00003246159,0.00003333179],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004716227,0.00007996718,0.03049027,0.0001691912,7.577908e-7,5.22152e-7,0.00001749745,0.000007856868,0.9690195,0.00009745817,0.00001322698,0.00005661434],"study_design_scores_gemma":[0.0006991457,0.00001716257,0.003397594,0.00005084536,0.000002267472,0.000001275959,0.00001820649,0.000180484,0.9935747,0.001923721,0.00001642383,0.0001181686],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9959234,0.0001433382,0.002457366,0.00001568495,0.00000261366,0.0005661143,0.00008479721,0.00005389399,0.0007527673],"genre_scores_gemma":[0.9804139,0.0000213674,0.01896594,0.000002828818,0.000007532425,0.0001192059,0.00005344311,0.00001723118,0.0003986055],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02709267,"threshold_uncertainty_score":0.4650509,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1975721281","doi":"10.1038/nmeth0910-681","title":"Mass spectrometry in high-throughput proteomics: ready for the big time","year":2010,"lang":"en","type":"article","venue":"Nature Methods","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":486,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Mass spectrometry; Proteomics; Proteome; Computational biology; Throughput; Computer science; Chemistry; Data science; Biology; Chromatography; Bioinformatics; Biochemistry; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.01797668750083652,"gpt":0.3789911240259536,"spread":0.3610144365251171,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009137513,0.0001789596,0.0002225997,0.00006108494,0.0001256764,0.0000347083,0.0005118666,0.0006318166,0.0001832666],"category_scores_gemma":[0.0004831883,0.0001308729,0.00008507969,0.0002842664,0.00007748658,0.0000482157,0.00006882119,0.001940881,0.000009423387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005995821,"about_ca_system_score_gemma":0.00004723283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002038594,"about_ca_topic_score_gemma":0.00001041318,"domain_scores_codex":[0.9989518,0.00003063907,0.0002436121,0.0003756479,0.0001078641,0.000290469],"domain_scores_gemma":[0.998236,0.0007118757,0.0001337659,0.0008015056,0.00007197441,0.00004490107],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002644652,0.00002747563,0.00004655798,0.00002201026,0.00001229664,5.301176e-7,0.00001505266,0.000003795243,0.9451541,0.02915928,0.0003618596,0.02517054],"study_design_scores_gemma":[0.0002467363,0.00001103714,0.00004064795,0.00000848784,0.00001495426,0.000005257637,0.000009097501,0.000601897,0.7765502,0.1478722,0.07448664,0.0001529333],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01298497,0.000288305,0.9761545,0.001991088,0.0002215044,0.0009432669,0.0001014216,0.0002145892,0.00710033],"genre_scores_gemma":[0.01267575,0.00003859251,0.9832661,0.0002136556,0.0006320854,0.001030936,0.00003782033,0.00004729362,0.002057771],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.168604,"threshold_uncertainty_score":0.8432269,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1985255881","doi":"10.1371/journal.pone.0121314","title":"A Mass Spectrometric-Derived Cell Surface Protein Atlas","year":2015,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":476,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Neuroscience Center Zurich, University of Zurich; SystemsX.ch; Universität Zürich; China Scholarship Council; Eidgenössische Technische Hochschule Zürich; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Cancer Institute; National Institutes of Health; National Science Foundation","keywords":"Cell; Cell type; Biology; Cell biology; Cell surface receptor; Proteomics; Computational biology; Cell signaling; Signal transduction; Biochemistry; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.0463227475383715,"gpt":0.2434077183016628,"spread":0.1970849707632913,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006709216,0.0001230474,0.0001683844,0.00003160598,0.00004742683,0.00002493184,0.0002260194,0.00008834113,0.0002458414],"category_scores_gemma":[0.00005048858,0.0001293671,0.00003464644,0.0002520315,0.00002856706,0.00006169546,0.00006249677,0.0002091194,0.0001921049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001112928,"about_ca_system_score_gemma":0.00004124059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001810806,"about_ca_topic_score_gemma":7.59842e-7,"domain_scores_codex":[0.9991218,0.000006604841,0.0001591037,0.0002476966,0.000241523,0.0002232581],"domain_scores_gemma":[0.9992272,0.00001873162,0.00009531743,0.0004183114,0.00009928835,0.000141133],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001321397,0.0004796691,0.0002092094,0.00005849828,0.00001764194,0.000002199078,0.00002621858,0.000006492045,0.9986244,0.0004142749,0.0001207544,0.00002741876],"study_design_scores_gemma":[0.000292867,0.0000338914,0.000002371183,0.00003742768,0.00002008374,5.008499e-7,0.00003344793,0.0002472026,0.9886311,0.00981139,0.0007248733,0.0001649036],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9321857,0.0001381909,0.01087545,0.0003254918,0.000002531362,0.0003562243,0.00002320413,0.0003477243,0.05574549],"genre_scores_gemma":[0.6146467,0.00002333194,0.3785425,0.00001528666,0.00006050905,0.0001576105,0.00001715585,0.00002738954,0.006509511],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.367667,"threshold_uncertainty_score":0.5275438,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2736859409","doi":"10.1073/pnas.1705691114","title":"De novo peptide sequencing by deep learning","year":2017,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":470,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Bioinformatics Solutions (Canada); University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Deep learning; Convolutional neural network; Deep sequencing; Computer science; Artificial intelligence; Computational biology; Artificial neural network; DNA sequencing; Deep neural networks; Genome; Biology; Biochemistry; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.03678936650367517,"gpt":0.3297278703280723,"spread":0.2929385038243971,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005031504,0.00005962981,0.00007843651,0.00002534925,0.0006678557,0.00004941203,0.0010544,0.00006480641,0.0000237168],"category_scores_gemma":[0.0005585594,0.00004553709,0.00004352005,0.00008283347,0.0005772178,0.0003187137,0.0001645634,0.0002113766,5.82857e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000629542,"about_ca_system_score_gemma":0.00002067929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008502332,"about_ca_topic_score_gemma":2.807102e-8,"domain_scores_codex":[0.9991632,8.266015e-7,0.0001654457,0.0001568719,0.0003903449,0.0001233579],"domain_scores_gemma":[0.9992738,0.00004055877,0.0005288467,0.0000113497,0.0001206483,0.00002478244],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000001774623,0.000006125481,0.007008863,0.00002593492,0.000002900996,1.350801e-9,0.00005468729,0.00007330871,0.9642572,0.02785838,0.0001078773,0.0006029043],"study_design_scores_gemma":[0.00004860062,0.000004465188,0.0009444483,0.00005562057,0.000003685483,0.000005859659,0.0001080792,0.001594024,0.911873,0.08423556,0.001072398,0.00005422641],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9270106,0.00005214524,0.00009439182,0.001609969,0.000002049728,0.00006047998,0.000008050358,0.00002657044,0.07113575],"genre_scores_gemma":[0.9787144,0.00003584064,0.02028997,0.0000672751,0.00004106715,0.00001960382,9.931942e-8,0.000003941707,0.0008277638],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07030798,"threshold_uncertainty_score":0.5136673,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2122460910","doi":"10.1093/jxb/erj168","title":"A perspective on the use of iTRAQTM reagent technology for protein complex and profiling studies","year":2006,"lang":"en","type":"review","venue":"Journal of Experimental Botany","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":469,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Syddansk Universitet; York University; University of Washington","keywords":"Computational biology; Reagent; Isobaric labeling; Protein function; Protein expression; Proteomics; Biology; Quantitative proteomics; Computer science; Chemistry; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.1756761304157956,"gpt":0.4286855041208048,"spread":0.2530093737050092,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001104511,0.0002466721,0.0008929371,0.00008999619,0.0001113038,0.00001805937,0.0002232979,0.000153258,0.00001110336],"category_scores_gemma":[0.000101144,0.0001531194,0.0002981824,0.0001059571,0.0002182913,0.00004696762,0.00009056368,0.0003596653,2.373616e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003960137,"about_ca_system_score_gemma":0.00005694264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002494095,"about_ca_topic_score_gemma":2.886555e-7,"domain_scores_codex":[0.9988311,0.000018865,0.0006826314,0.0001956877,0.0001340512,0.0001376945],"domain_scores_gemma":[0.9981662,0.0001516995,0.001208202,0.0002434332,0.0002027688,0.00002766769],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002090364,0.001045426,0.000002267829,0.003695425,0.001454509,0.00002238606,0.0003615516,0.000001476734,0.7890824,0.1145699,0.001959213,0.08759641],"study_design_scores_gemma":[0.0002724476,0.0003393701,4.246237e-8,0.00679562,0.0002199909,0.0001281917,0.001978687,0.000007169117,0.4478094,0.002965452,0.5392508,0.0002328046],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001583522,0.9963884,0.0003367355,0.0001610102,0.00001238193,0.001234491,0.00008954809,0.00001766619,0.00017627],"genre_scores_gemma":[0.001696993,0.9169047,0.08007235,0.00001576573,0.0001266009,0.0009455604,0.000003633171,0.00004949251,0.0001849284],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.5372916,"threshold_uncertainty_score":0.6244029,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3005901855","doi":"10.1074/mcp.tir119.001906","title":"A Compact Quadrupole-Orbitrap Mass Spectrometer with FAIMS Interface Improves Proteome Coverage in Short LC Gradients","year":2020,"lang":"en","type":"article","venue":"Molecular & Cellular Proteomics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":463,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Thermo Fisher Scientific (Canada)","funders":"Novo Nordisk; European Commission","keywords":"Orbitrap; Mass spectrometry; Chemistry; Ion-mobility spectrometry; Chromatography; Proteome; Analytical Chemistry (journal); Hybrid mass spectrometer; Triple quadrupole mass spectrometer; Spectrometer; Tandem mass spectrometry; Selected reaction monitoring; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.01030516893583103,"gpt":0.2377012550979397,"spread":0.2273960861621087,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001425928,0.0005683635,0.0005652328,0.0001089802,0.0001084744,0.0001340048,0.0007017357,0.0002466453,0.00008050189],"category_scores_gemma":[0.00002979973,0.0005533001,0.0001958301,0.0004686832,0.0001444178,0.0001935914,0.0001465357,0.0009762361,0.00003019997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002501195,"about_ca_system_score_gemma":0.00009068246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005848178,"about_ca_topic_score_gemma":0.000006536384,"domain_scores_codex":[0.997262,0.00004520106,0.000594685,0.0009806105,0.0003882539,0.000729238],"domain_scores_gemma":[0.9986331,0.00001732275,0.0001599977,0.0008024343,0.00006992511,0.0003171782],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002251955,0.0001413729,0.0007336052,0.0001765219,0.00006999829,0.0001522779,0.0002318371,0.0005239292,0.9971755,0.0003420204,0.00001640177,0.0002113376],"study_design_scores_gemma":[0.0008532799,0.0002423709,0.00002879206,0.0001027167,0.00003690436,0.00002001866,0.0000659559,0.00301966,0.9918839,0.002002988,0.001061519,0.0006819202],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.652248,0.00009881042,0.344058,0.0005502269,0.00001254401,0.001484399,0.00004404534,0.0002059368,0.001298035],"genre_scores_gemma":[0.9158418,0.00002944084,0.08282982,0.0002731786,0.00007503431,0.0006040869,0.00009447021,0.0001518762,0.000100345],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2635938,"threshold_uncertainty_score":0.9996918,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2027222148","doi":"10.1038/sdata.2014.31","title":"A repository of assays to quantify 10,000 human proteins by SWATH-MS","year":2014,"lang":"en","type":"article","venue":"Scientific Data","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":458,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Spinal Cord Injury BC","funders":"National Center for Research Resources; National Institute of General Medical Sciences; Suomen Kulttuurirahasto; Eidgenössische Technische Hochschule Zürich; National Human Genome Research Institute; SystemsX.ch; Kommission für Technologie und Innovation; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; European Molecular Biology Organization; National Institutes of Health; National Science Foundation","keywords":"UniProt; Computational biology; Proteome; Computer science; Human proteins; Mass spectrometry; Human proteome project; Quantitative proteomics; Tandem mass tag; Label-free quantification; Tandem mass spectrometry; Proteomics; Compendium; Data mining; Bioinformatics; Chemistry; Biology; Chromatography; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.0338103432655551,"gpt":0.316685081902095,"spread":0.2828747386365399,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006058047,0.0001145007,0.0001486892,0.00004774235,0.0003616654,0.000126299,0.001660411,0.00007568687,0.0003361716],"category_scores_gemma":[0.0001138604,0.0001123876,0.0000316016,0.0002302711,0.0002035915,0.0001541969,0.0007226968,0.000128051,0.00006555283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002521244,"about_ca_system_score_gemma":0.00002880652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001078957,"about_ca_topic_score_gemma":0.00001584874,"domain_scores_codex":[0.9984258,0.00001513795,0.0003184794,0.0007478725,0.0002723788,0.0002203715],"domain_scores_gemma":[0.996201,0.00002491402,0.0001683093,0.003404773,0.00009256523,0.0001084298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000003272037,0.0000592708,0.0000544173,0.00003850667,0.000004027866,2.342962e-7,0.000030573,0.000002020926,0.877018,0.001662895,0.1196503,0.001476503],"study_design_scores_gemma":[0.0000547423,0.000009946832,0.000008662037,0.00003053007,0.000005845116,0.000001066065,0.000009653272,0.000249987,0.5564508,0.0009346473,0.4421516,0.00009250574],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5064597,0.0002175361,0.2687805,0.00184692,0.0005885308,0.002480518,0.02884113,0.001281253,0.1895039],"genre_scores_gemma":[0.8253529,0.000002067454,0.08990715,0.00004211338,0.0002039768,0.0003022744,0.005890697,0.00005088648,0.07824796],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3225014,"threshold_uncertainty_score":0.4583034,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2015407064","doi":"10.1083/jcb.200805092","title":"Identifying specific protein interaction partners using quantitative mass spectrometry and bead proteomes","year":2008,"lang":"en","type":"article","venue":"The Journal of Cell Biology","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":446,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Biotechnology and Biological Sciences Research Council; Directorate for Biological Sciences; Medical Research Council; Engineering and Physical Sciences Research Council; Wellcome Trust; University of Dundee","keywords":"Tandem affinity purification; Stable isotope labeling by amino acids in cell culture; Proteome; Biology; Protein–protein interaction; Quantitative proteomics; Immunoprecipitation; Mass spectrometry; Affinity chromatography; Plasma protein binding; Fusion protein; Computational biology; Biochemistry; Proteomics; Chemistry; Chromatography; Recombinant DNA; Enzyme","retraction":null,"screen_n_in":null,"score":{"opus":0.07324135592246396,"gpt":0.3588865964644963,"spread":0.2856452405420323,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002098244,0.00009364216,0.0001623639,0.0000688226,0.0001587754,0.000009926261,0.0001496568,0.00006507798,0.000097248],"category_scores_gemma":[0.00002141769,0.00006472713,0.00004591179,0.00008659902,0.0001689555,0.00009579527,0.00003493463,0.0003424279,0.000003722726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006271345,"about_ca_system_score_gemma":0.00002633024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006117674,"about_ca_topic_score_gemma":2.740112e-7,"domain_scores_codex":[0.9993782,0.000045342,0.0002905596,0.0000917437,0.00006086625,0.0001332594],"domain_scores_gemma":[0.999203,0.00008212094,0.0004794654,0.0001224056,0.00007789907,0.00003517184],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006981107,0.00001762802,0.0001292497,0.00001509918,0.00001479772,0.000003773227,0.0001955771,0.00001804028,0.9987139,0.0006561286,0.000009823914,0.000156155],"study_design_scores_gemma":[0.0001742347,0.00008071461,0.00002190726,0.00003625328,0.00001303304,0.0001936119,0.0005119271,0.000107489,0.9860241,0.01182274,0.0009375362,0.00007638016],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8799964,0.0005634718,0.1184228,0.00008119555,0.00002270348,0.0001238129,0.000002627506,0.0000120529,0.000774911],"genre_scores_gemma":[0.8701191,0.0007933338,0.1288863,0.000009387971,0.00008917358,0.000006871719,0.000001177312,0.00001027182,0.00008437994],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01268975,"threshold_uncertainty_score":0.2639496,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2066449582","doi":"10.1155/2014/361590","title":"The Design of a Quantitative Western Blot Experiment","year":2014,"lang":"en","type":"review","venue":"BioMed Research International","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":407,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Bio-Rad (Canada)","funders":"","keywords":"Blot; Western blot; Quantitative analysis (chemistry); Biology; Chemistry; Biochemistry; Chromatography","retraction":null,"screen_n_in":null,"score":{"opus":0.3063487841845102,"gpt":0.545969136444218,"spread":0.2396203522597078,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001166673,0.0001907063,0.0004472561,0.0001959153,0.0001861964,0.00007446593,0.001402282,0.0001725463,0.0001547238],"category_scores_gemma":[0.000316861,0.0001230906,0.0001974363,0.0002222194,0.0004357095,0.00003300934,0.0003664021,0.0004958536,0.00007395399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002616326,"about_ca_system_score_gemma":0.0002326995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000151993,"about_ca_topic_score_gemma":0.000001083492,"domain_scores_codex":[0.9978971,0.0001685018,0.0005686451,0.0003352029,0.0007427825,0.0002877162],"domain_scores_gemma":[0.9970008,0.001646761,0.0003463856,0.0005234132,0.0004098678,0.00007283656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000617354,0.0002338516,0.000001122109,0.003124224,0.0005453132,0.000004386007,0.0000981937,0.000003055547,0.003648259,0.0611264,0.008133295,0.9230202],"study_design_scores_gemma":[0.00007678075,0.00003590191,4.23134e-8,0.001974305,0.00001444243,0.000005636702,0.00002836024,0.0001002889,0.003383292,0.001603982,0.9926606,0.0001164113],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000001345695,0.9488612,0.04700896,0.0002244392,0.0001271757,0.0007073234,0.0001541055,0.00004507217,0.002870404],"genre_scores_gemma":[0.00001249249,0.9753018,0.01789371,0.00000277563,0.0002371452,0.002322556,0.0001208632,0.00004081388,0.00406785],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9845273,"threshold_uncertainty_score":0.501949,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2105017286","doi":"10.1093/jnci/djh056","title":"Analysis of Serum Proteomic Patterns for Early Cancer Diagnosis: Drawing Attention to Potential Problems","year":2004,"lang":"en","type":"article","venue":"JNCI Journal of the National Cancer Institute","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":404,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Mount Sinai Hospital","funders":"","keywords":"Medicine; Biobank; Prostate cancer; Proteomics; Cancer; Bioinformatics; Internal medicine; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.03029167014376219,"gpt":0.3357734470454592,"spread":0.305481776901697,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001895408,0.0001221327,0.0002482176,0.0001867719,0.0001642078,0.00003110669,0.000407961,0.00007370893,0.00007395063],"category_scores_gemma":[0.00005554277,0.00009584444,0.000379601,0.0004571528,0.00004185699,0.0002704228,0.00005783775,0.0001897836,3.94094e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000634885,"about_ca_system_score_gemma":0.0003442836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003132716,"about_ca_topic_score_gemma":0.0003030484,"domain_scores_codex":[0.9986455,0.000006887328,0.0005430183,0.0001617965,0.0004898141,0.0001529251],"domain_scores_gemma":[0.9982502,0.00001539083,0.000734489,0.0001272294,0.0008091317,0.000063585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001173667,0.0001763466,0.1158755,0.0001727089,0.001308452,8.576558e-7,0.0002430659,0.7142546,0.1625183,0.001226069,0.0002022157,0.003904477],"study_design_scores_gemma":[0.002960608,0.0001224348,0.1716094,0.001830083,0.002423365,0.00001885162,0.00004410933,0.001406246,0.7959215,0.01617831,0.006922714,0.0005623761],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9420204,0.00008538851,0.05313284,0.002958247,0.0002419477,0.0004205336,0.001090884,0.00001260196,0.00003718711],"genre_scores_gemma":[0.9914594,0.0001349418,0.00638426,0.0001916282,0.0005082139,0.001189645,0.000008635739,0.00001531008,0.0001080115],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7128484,"threshold_uncertainty_score":0.3908423,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148342716","doi":"10.1074/mcp.r600004-mcp200","title":"Discovery of Urinary Biomarkers","year":2006,"lang":"en","type":"review","venue":"Molecular & Cellular Proteomics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":403,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National Institutes of Health","keywords":"Urinary system; Proteomics; Biomarker discovery; Biomarker; Urine; Chemistry; Proteome; Exosome; Medicine; Internal medicine; Microvesicles; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.01631311989694141,"gpt":0.2853193313789505,"spread":0.2690062114820091,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001614693,0.0007244758,0.001547866,0.0001765069,0.00008788654,0.00005996366,0.0009074707,0.000762273,0.00003691507],"category_scores_gemma":[0.0000243833,0.0007148355,0.001133419,0.0003594332,0.0002007411,0.0000990146,0.0003852727,0.000648709,0.000020249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002119962,"about_ca_system_score_gemma":0.0002671767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004299908,"about_ca_topic_score_gemma":4.843733e-7,"domain_scores_codex":[0.9972653,0.00005474899,0.001120638,0.0008086583,0.0003002882,0.0004503414],"domain_scores_gemma":[0.997403,0.00003884354,0.0008578618,0.001553359,0.00006860329,0.00007835196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003992156,0.00107568,0.000004471238,0.08702602,0.00110551,0.0004738734,0.00001607756,0.00005235373,0.5920889,0.0107379,0.0004811025,0.3068982],"study_design_scores_gemma":[0.0001221372,0.00002311043,1.679262e-8,0.003200969,0.0004766064,0.00005902078,0.000002404416,0.00002574699,0.5425907,0.001177598,0.4517066,0.000615091],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0005959492,0.8818656,0.112447,0.000007145952,0.00003053209,0.001325782,0.0003667356,0.0001519286,0.003209315],"genre_scores_gemma":[0.00009133211,0.9098553,0.08596683,0.000007632147,0.0000947345,0.001247504,0.001363456,0.0002474252,0.001125754],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4512255,"threshold_uncertainty_score":0.9995303,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2020018374","doi":"10.1038/nrm1711","title":"Proteomics of organelles and large cellular structures","year":2005,"lang":"en","type":"review","venue":"Nature Reviews Molecular Cell Biology","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":390,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Proteomics; Organelle; Computational biology; Identification (biology); Biology; Systems biology; Cell biology; Chemistry; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.01424334515701929,"gpt":0.3313732263286726,"spread":0.3171298811716532,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0002345277,0.0006547724,0.002386791,0.00010855,0.00006717626,0.00001225486,0.0006100714,0.002314074,0.0002005069],"category_scores_gemma":[0.00008299726,0.0004933588,0.0004889239,0.0002250974,0.0001346108,0.00002019952,0.0002902286,0.001707488,0.00001299218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005660511,"about_ca_system_score_gemma":0.0001014032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001407476,"about_ca_topic_score_gemma":6.811919e-7,"domain_scores_codex":[0.9976276,0.000128709,0.001015472,0.0007673139,0.00008556282,0.0003754078],"domain_scores_gemma":[0.9976573,0.00006387415,0.001155627,0.0009588164,0.00006497248,0.00009942381],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002064908,0.00004410133,7.193377e-7,0.02301011,0.00005244084,0.00000489953,0.000005760078,9.920508e-8,0.03596435,0.008179003,0.000107075,0.9326293],"study_design_scores_gemma":[0.0001009577,0.00001836987,4.966552e-9,0.001787909,0.0003924635,0.00001738497,0.000001335168,0.000001241965,0.03368184,0.001446939,0.962135,0.000416611],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001162663,0.9889448,0.006840052,0.00001219258,0.00002917739,0.001466367,0.0002763485,0.00005623938,0.002363235],"genre_scores_gemma":[0.00003136507,0.933271,0.06514243,0.00006379744,0.0001387027,0.0003882014,0.000732997,0.00008946019,0.0001420738],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9620278,"threshold_uncertainty_score":0.9997518,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2139574601","doi":"10.1074/mcp.m100015-mcp200","title":"2D Differential In-gel Electrophoresis for the Identification of Esophageal Scans Cell Cancer-specific Protein Markers","year":2002,"lang":"en","type":"article","venue":"Molecular & Cellular Proteomics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":388,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Chemistry; Gel electrophoresis; Molecular biology; Proteomics; Cancer cell; Difference gel electrophoresis; Two-dimensional gel electrophoresis; Laser capture microdissection; Cancer; Biology; Biochemistry; Gene expression; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.008907768747219987,"gpt":0.2239316847580961,"spread":0.2150239160108761,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000184232,0.0002755238,0.0002728087,0.00008506663,0.0001744088,0.00005528175,0.0006134202,0.0001979495,0.0002198165],"category_scores_gemma":[0.00002305977,0.0002579511,0.000218759,0.0002817605,0.0001305735,0.00005771546,0.00008082465,0.0003346097,0.000005410025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001845669,"about_ca_system_score_gemma":0.00003701763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000678695,"about_ca_topic_score_gemma":0.000007446819,"domain_scores_codex":[0.9980944,0.00003337106,0.000684085,0.0005144132,0.0002553257,0.0004184458],"domain_scores_gemma":[0.998544,0.0000391299,0.0004328378,0.0008074384,0.0001134401,0.00006315736],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007731842,0.0001661537,0.00005595664,0.000159453,0.0000253496,0.000003540365,0.00006900475,0.0004630665,0.9954574,0.001365135,0.00007596683,0.002081723],"study_design_scores_gemma":[0.0005897366,0.00002764967,0.00002091474,0.00003668864,0.000041015,0.000001209423,0.00002998698,0.01620712,0.9799315,0.00186924,0.000995305,0.0002495699],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6250612,0.001571631,0.3708425,0.000219723,0.00002279139,0.001956181,0.00009301543,0.00004944986,0.0001835632],"genre_scores_gemma":[0.9728273,0.0005708052,0.02058277,0.00001768631,0.00007303755,0.004974773,0.00005560407,0.00008347158,0.0008145936],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3502597,"threshold_uncertainty_score":0.9999872,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2529750106","doi":"10.1038/nbt.3685","title":"A multicenter study benchmarks software tools for label-free proteome quantification","year":2016,"lang":"en","type":"article","venue":"Nature Biotechnology","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":385,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Sciex (Canada); Spinal Cord Injury BC","funders":"National Institute of General Medical Sciences; Biotechnology and Biological Sciences Research Council; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Computer science; Software; Robustness (evolution); Quantitative proteomics; Proteome; Data mining; Label-free quantification; Proteomics; Bioinformatics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01740569968362773,"gpt":0.3051490742741625,"spread":0.2877433745905348,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0001283971,0.0002014601,0.0002082417,0.00009866258,0.0001428957,0.00002783572,0.0007778284,0.001310953,0.0001285015],"category_scores_gemma":[0.001220307,0.0001467541,0.00005882823,0.0001650261,0.0001149959,0.0001395193,0.0002115382,0.0005447462,0.00001223951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001048995,"about_ca_system_score_gemma":0.00002614613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003446556,"about_ca_topic_score_gemma":0.00001632156,"domain_scores_codex":[0.9986714,0.000008447309,0.0002876478,0.0006003436,0.0001169182,0.0003152954],"domain_scores_gemma":[0.9981096,0.0001893173,0.0001882388,0.001329415,0.0001430756,0.00004034555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009761645,0.0003866093,0.0004815675,0.00004218656,0.00003467532,0.000001511471,0.00001748724,1.655851e-7,0.9028048,0.01211631,0.00176952,0.08224758],"study_design_scores_gemma":[0.001685328,0.000124482,0.00009651855,0.00004808504,0.00002465648,0.000003500424,0.00006493505,0.00002002996,0.9018021,0.01446349,0.08141253,0.0002544037],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4976624,0.0005274172,0.4714977,0.02102473,0.0001778607,0.005346733,0.0009493917,0.002416388,0.0003974104],"genre_scores_gemma":[0.7903253,0.00006126567,0.2056794,0.00009291758,0.00009358578,0.003173125,0.00007919879,0.00004110217,0.0004540887],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.292663,"threshold_uncertainty_score":0.9999856,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1974024002","doi":"10.1038/nbt0502-512","title":"Quantitative proteome analysis by solid-phase isotope tagging and mass spectrometry","year":2002,"lang":"en","type":"article","venue":"Nature Biotechnology","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":383,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Center for Research Resources; National Institute of General Medical Sciences; National Cancer Institute; Canadian Institute for Theoretical Astrophysics","keywords":"Chemistry; Mass spectrometry; Chromatography; Peptide; Proteome; Tandem mass spectrometry; Isotopic labeling; Tandem mass tag; Isobaric labeling; Proteomics; Protein mass spectrometry; Quantitative proteomics; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.009084657288015448,"gpt":0.3198791462130797,"spread":0.3107944889250643,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000677062,0.0002119154,0.0003330035,0.0003507863,0.0001486714,0.0000270853,0.000307014,0.001219711,0.0004406152],"category_scores_gemma":[0.00009616907,0.000207162,0.00008762911,0.001127864,0.0002127435,0.00007166481,0.00009883947,0.001291592,0.00001380153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007073962,"about_ca_system_score_gemma":0.000005138934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005430571,"about_ca_topic_score_gemma":0.000002260849,"domain_scores_codex":[0.9987687,0.000008364832,0.0002320883,0.0005530723,0.0001139956,0.0003238032],"domain_scores_gemma":[0.9991505,0.00004543031,0.0001704766,0.0005279857,0.0000428265,0.00006281833],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001298289,0.00008798271,0.00008131441,0.00001885527,0.0001596872,0.000006844896,0.00001734915,0.000001733294,0.9804286,0.01634911,0.0008714561,0.001964125],"study_design_scores_gemma":[0.0003721515,0.00008907125,0.000002397795,0.000009792465,0.0001140279,0.00001269708,0.00007048562,0.004570016,0.952588,0.006320667,0.03559045,0.0002602516],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4558746,0.01148728,0.5043628,0.01851926,0.00003971959,0.0007996179,0.0005220559,0.002037931,0.006356791],"genre_scores_gemma":[0.801365,0.0009161117,0.1965946,0.0002067364,0.00002807879,0.0001557066,0.00005041402,0.00002754188,0.000655839],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3454904,"threshold_uncertainty_score":0.9407529,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2046461084","doi":"10.1016/s1367-5931(00)00250-7","title":"Analysis of phosphorylated proteins and peptides by mass spectrometry","year":2001,"lang":"en","type":"review","venue":"Current Opinion in Chemical Biology","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":382,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Center for Research Resources; National Cancer Institute; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Phosphorylation; Mass spectrometry; Protein phosphorylation; Serine; Threonine; Peptide; Chemistry; Phosphopeptide; Biochemistry; Computational biology; Chromatography; Proteomics; Biology; Protein kinase A","retraction":null,"screen_n_in":null,"score":{"opus":0.0504918496087894,"gpt":0.3889434227922931,"spread":0.3384515731835037,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00008640055,0.0003313933,0.001503584,0.0002651905,0.00001906971,0.000007007021,0.0003265631,0.0005628011,0.0001967824],"category_scores_gemma":[0.00006093987,0.0002915921,0.000314843,0.001198212,0.000200269,0.00001806905,0.0001344941,0.0006251747,0.000002531419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001246785,"about_ca_system_score_gemma":0.00003920704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000866021,"about_ca_topic_score_gemma":1.442149e-7,"domain_scores_codex":[0.9982511,0.00002495673,0.0007817265,0.0006060798,0.00006736112,0.0002687897],"domain_scores_gemma":[0.998858,0.0001541153,0.0004870527,0.0003906017,0.00003354556,0.00007663188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000089713,0.0002051316,0.000454635,0.008593172,0.0004038617,1.52107e-7,0.000006151709,1.973205e-7,0.02550335,0.0007697655,0.0002142114,0.9638404],"study_design_scores_gemma":[0.0001234193,0.00001343002,3.77884e-7,0.002286101,0.0003943566,0.000002915527,0.000002289022,0.00002813271,0.009380786,0.001181849,0.986248,0.0003384134],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001750267,0.995952,0.002543475,0.00001019936,0.00005562783,0.0003446474,0.0006725799,0.00005299197,0.0001935231],"genre_scores_gemma":[0.0001013497,0.9923059,0.003361713,0.000001160471,0.00007591448,0.0004780009,0.003634489,0.0000240511,0.00001746681],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9860337,"threshold_uncertainty_score":0.9999536,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1991953772","doi":"10.1002/pmic.201100523","title":"Affinity‐purification coupled to mass spectrometry: Basic principles and strategies","year":2012,"lang":"en","type":"review","venue":"PROTEOMICS","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":370,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"Canadian Institutes of Health Research","keywords":"Mass spectrometry; Tandem affinity purification; Proteomics; Computational biology; Protein–protein interaction; Function (biology); Chemistry; Protein function; Protein purification; Identification (biology); Protein ligand; Affinity chromatography; Biochemical engineering; Chromatography; Biochemistry; Biology; Enzyme; Cell biology; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.06479757224059426,"gpt":0.331549183403524,"spread":0.2667516111629297,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002542842,0.0005218139,0.0009699119,0.0001625804,0.000164712,0.0001785793,0.0004907066,0.0004677884,0.0001200467],"category_scores_gemma":[0.00005454559,0.0004931754,0.000170884,0.000343219,0.00007276004,0.0001635414,0.000189135,0.0006410569,0.00007615666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002483061,"about_ca_system_score_gemma":0.0002139968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009209897,"about_ca_topic_score_gemma":0.00000335391,"domain_scores_codex":[0.9980915,0.00002356944,0.0006321234,0.0006286241,0.0001758144,0.0004483702],"domain_scores_gemma":[0.9982387,0.00008691378,0.000521587,0.0008635258,0.00006795924,0.0002213026],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004283814,0.0003552498,0.00003373537,0.05597541,0.0003473922,0.000005665752,0.0002111355,0.00001895338,0.04183965,0.1932182,0.00007528204,0.7078765],"study_design_scores_gemma":[0.00009053631,0.00001932085,0.000001247038,0.001498954,0.0002872606,0.00002404226,0.00003225822,0.0000388127,0.005551185,0.004092057,0.9876837,0.0006806115],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00012438,0.8764187,0.1164771,0.00006051797,0.00003349736,0.002280379,0.0001637532,0.0003629468,0.004078791],"genre_scores_gemma":[0.00002892109,0.6551986,0.3412482,0.000009028501,0.0002357261,0.00254139,0.0001468196,0.0000870283,0.0005043607],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9876084,"threshold_uncertainty_score":0.999752,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2998913628","doi":"10.1038/s41467-019-13973-x","title":"Robust, reproducible and quantitative analysis of thousands of proteomes by micro-flow LC–MS/MS","year":2020,"lang":"en","type":"article","venue":"Nature Communications","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":362,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Sinai Health System; Lunenfeld-Tanenbaum Research Institute","funders":"Canadian Institutes of Health Research; Carl Friedrich von Siemens Stiftung; Bundesministerium für Bildung und Forschung; Government of Ontario; National Natural Science Foundation of China; Government of Canada; Deutsche Forschungsgemeinschaft; Ontario Genomics Institute; China Scholarship Council; Ontario Genomics; Genome Canada; Alexander von Humboldt-Stiftung","keywords":"Proteome; Chromatography; Tandem mass spectrometry; Chemistry; Mass spectrometry; Reproducibility; Coefficient of variation; Proteomics; Quantitative proteomics; Tandem; Analytical Chemistry (journal); Materials science; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.03653844875497578,"gpt":0.3262155515964422,"spread":0.2896771028414664,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001364384,0.0001199298,0.0003267046,0.00007542237,0.0001230038,0.00001083708,0.0007165267,0.0001951513,0.00008423359],"category_scores_gemma":[0.0002364333,0.0001183324,0.0001057976,0.0008817904,0.0002326843,0.00006631092,0.0003036864,0.0005497218,8.192514e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001653941,"about_ca_system_score_gemma":0.00003005393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003384319,"about_ca_topic_score_gemma":0.0000213917,"domain_scores_codex":[0.9990982,0.00003087012,0.0003543424,0.0003070613,0.0001078351,0.0001017345],"domain_scores_gemma":[0.9974474,0.0001827508,0.0003380821,0.001745616,0.0002291314,0.00005696851],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003358035,0.0002233932,0.007448688,0.0001171797,0.0005763833,1.191486e-7,0.0009724119,0.0005113625,0.9727034,0.01270822,0.003799165,0.0009061028],"study_design_scores_gemma":[0.0003258995,0.00005960672,0.0007162074,0.00006135584,0.0007275451,0.000001088702,0.0003555103,0.02047471,0.9375101,0.001251928,0.03821369,0.0003023788],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6477559,0.08743404,0.1644316,0.04891197,0.00003119073,0.002917043,0.007261079,0.0008997651,0.04035744],"genre_scores_gemma":[0.6229045,0.001631169,0.3748714,0.00008187873,0.000007579082,0.0001181939,0.0002963631,0.00001439803,0.00007447209],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2104398,"threshold_uncertainty_score":0.4825454,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2060769471","doi":"10.1074/mcp.m111.009993","title":"The Human Proteome Project: Current State and Future Direction","year":2011,"lang":"en","type":"article","venue":"Molecular & Cellular Proteomics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":356,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Genome British Columbia; University of Victoria; McGill University","funders":"","keywords":"Current (fluid); Proteome; State (computer science); Computational biology; Human proteome project; Data science; Computer science; Proteomics; Chemistry; Biology; Bioinformatics; Engineering; Biochemistry; Electrical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01490619823095905,"gpt":0.2578159499142334,"spread":0.2429097516832744,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002094251,0.0002766041,0.0001727824,0.00004568366,0.0005984106,0.00009055849,0.0003314864,0.0001120206,0.00002909639],"category_scores_gemma":[0.00001143909,0.0002246581,0.00009495684,0.0001577276,0.0001610694,0.0000879827,0.0001726843,0.0005046854,0.00001014065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007153853,"about_ca_system_score_gemma":0.00004896636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004143694,"about_ca_topic_score_gemma":0.00000602046,"domain_scores_codex":[0.9985916,0.00003378431,0.0003393397,0.000469855,0.0001877134,0.0003777189],"domain_scores_gemma":[0.9989233,0.000007894332,0.0002248828,0.0006630711,0.00009149809,0.00008933094],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002217592,0.00007264093,0.00009263626,0.00007481465,0.00002206437,0.000007661504,0.0002491369,9.25817e-7,0.970018,0.005217063,0.00003695043,0.02418596],"study_design_scores_gemma":[0.0002033624,0.00003021342,0.00003724532,0.00002457173,0.00002111428,0.00001148381,0.00003725742,0.00009594544,0.9297132,0.02206375,0.0474834,0.0002784822],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9239377,0.00177527,0.06645265,0.0001686182,0.00007847175,0.002137336,0.00003256733,0.0002403317,0.005177055],"genre_scores_gemma":[0.814163,0.003231995,0.1690875,0.0000925635,0.0007671289,0.009210862,0.0001748915,0.000330175,0.002941822],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1097747,"threshold_uncertainty_score":0.9161292,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2088363255","doi":"10.1038/nmeth.1333","title":"A HUPO test sample study reveals common problems in mass spectrometry–based proteomics","year":2009,"lang":"en","type":"article","venue":"Nature Methods","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":356,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University Health Centre; University of British Columbia; McGill University","funders":"U.S. Public Health Service; National Cancer Institute; University of California, Los Angeles; Ontario Genomics; National Institutes of Health; Canadian Institutes of Health Research; Genome Canada; National Center for Research Resources; Ontario Genomics Institute; University College Dublin; National Heart, Lung, and Blood Institute; McGill University","keywords":"Mass spectrometry; Proteomics; Chromatography; Sample (material); Chemistry; Computational biology; Sampling (signal processing); Database search engine; Computer science; Information retrieval; Biology; Biochemistry; Search engine","retraction":null,"screen_n_in":null,"score":{"opus":0.02050270483724225,"gpt":0.3914492445158091,"spread":0.3709465396785668,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001096384,0.0002717171,0.0004266235,0.0001595676,0.0001018578,0.00004646633,0.0004833083,0.0004596205,0.00008865304],"category_scores_gemma":[0.0008114665,0.000260308,0.00008975774,0.0007878175,0.00003097796,0.00007191503,0.00004502218,0.001670185,0.000002166257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002132719,"about_ca_system_score_gemma":0.00004254398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000031089,"about_ca_topic_score_gemma":0.00001790815,"domain_scores_codex":[0.9982964,0.000116649,0.0004625005,0.0005334693,0.0002103078,0.0003806939],"domain_scores_gemma":[0.9980959,0.0006839248,0.0002185871,0.0008433833,0.00007014152,0.0000880997],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002260147,0.0008045579,0.02021275,0.00004609681,0.00000783788,0.000004587886,0.00006600453,0.00008324248,0.972562,0.000928005,0.00008342492,0.005178864],"study_design_scores_gemma":[0.001087679,0.0002634412,0.004066271,0.0001008468,0.0000295903,0.000005212485,0.00007723177,0.0008794088,0.8185362,0.1714906,0.002952805,0.000510752],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07666021,0.000286203,0.914825,0.0008287487,0.00003319527,0.001997564,0.00008616351,0.0004052951,0.004877574],"genre_scores_gemma":[0.3331366,0.000008344346,0.6660137,0.0002260059,0.00007784597,0.0003735724,0.00002730377,0.00002559236,0.0001110041],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2564764,"threshold_uncertainty_score":0.9999849,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2004114046","doi":"10.1021/pr100656u","title":"A Quantitative Study of the Effects of Chaotropic Agents, Surfactants, and Solvents on the Digestion Efficiency of Human Plasma Proteins by Trypsin","year":2010,"lang":"en","type":"article","venue":"Journal of Proteome Research","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":348,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"National Cancer Institute","keywords":"Chemistry; Chaotropic agent; Chromatography; Digestion (alchemy); Sodium dodecyl sulfate; Mass spectrometry; Trypsin; Tandem mass spectrometry; Urea; Sample preparation; Bottom-up proteomics; Biochemistry; Protein mass spectrometry; Enzyme","retraction":null,"screen_n_in":null,"score":{"opus":0.04506829861933076,"gpt":0.3818884193054882,"spread":0.3368201206861574,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001052074,0.0001078941,0.0002602484,0.0001037188,0.0002177542,0.00001486358,0.0005514233,0.00008543595,0.00002271791],"category_scores_gemma":[0.0008190929,0.00006087859,0.00007266489,0.0003030127,0.0003391235,0.00006203391,0.0001430129,0.00103642,3.336962e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003784012,"about_ca_system_score_gemma":0.00007907195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007136891,"about_ca_topic_score_gemma":0.00001081716,"domain_scores_codex":[0.9981627,0.0001784096,0.0005060431,0.000144971,0.0008181779,0.0001897071],"domain_scores_gemma":[0.9979652,0.0004285733,0.0007212558,0.0003864392,0.000445554,0.00005296057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001270327,0.001131843,0.002952813,0.0002646347,0.00003834207,0.000001194316,0.0006380396,0.000003355332,0.993236,0.001297236,0.00003550527,0.000273981],"study_design_scores_gemma":[0.0007321254,0.002029325,0.003946668,0.0003946659,0.00001414904,0.000003753671,0.0004760076,0.00007138575,0.9903286,0.00192555,0.00002463751,0.0000531395],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9977125,0.00004770753,0.0001504059,0.0002028577,0.00001614013,0.001737311,0.00001629289,0.000003874793,0.0001129322],"genre_scores_gemma":[0.9988027,0.00004330285,0.0008883198,0.00000125628,0.00001824703,0.0001340266,5.06411e-7,0.00001447842,0.00009715235],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002907428,"threshold_uncertainty_score":0.4502785,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2039231543","doi":"10.1038/nprot.2006.273","title":"Tissue subcellular fractionation and protein extraction for use in mass-spectrometry-based proteomics","year":2006,"lang":"en","type":"article","venue":"Nature Protocols","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":346,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Canadian Institutes of Health Research; National Science Council","keywords":"Fractionation; Proteome; Differential centrifugation; Proteomics; Cell fractionation; Golgi apparatus; Mass spectrometry; Chemistry; Chromatography; Sample preparation; Endoplasmic reticulum; Centrifugation; Protein subcellular localization prediction; Tandem mass spectrometry; Extraction (chemistry); Protein purification; Cytosol; Biochemistry; Membrane; Enzyme","retraction":null,"screen_n_in":null,"score":{"opus":0.0131235428332883,"gpt":0.3257979094989947,"spread":0.3126743666657064,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001696228,0.0001808471,0.0001625145,0.0001335881,0.0001138564,0.0000958317,0.0001104198,0.0005292034,0.00003692971],"category_scores_gemma":[0.00008876444,0.000191454,0.0000416684,0.0002207584,0.00003164572,0.0002894592,0.00001347837,0.0006359285,0.000001702973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002047176,"about_ca_system_score_gemma":0.00005044585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004721406,"about_ca_topic_score_gemma":0.00003430393,"domain_scores_codex":[0.9988929,0.00001276751,0.0002998197,0.0004048643,0.0001692538,0.0002204152],"domain_scores_gemma":[0.9992658,0.00007732448,0.0002215139,0.000271777,0.0001268975,0.00003669807],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001565142,0.0001330198,0.001347517,0.0001830557,0.000002442903,0.000001585387,0.000001932991,0.00008477247,0.9881278,0.009051038,0.00007879698,0.000831479],"study_design_scores_gemma":[0.0008814901,0.00004031284,0.0002619173,0.00009952747,0.000004285223,0.00000310368,0.000002764491,0.001758832,0.9270076,0.02874988,0.04098381,0.0002064589],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04185538,0.0000337331,0.8626705,0.0003752438,0.000008317478,0.09421336,0.00008012565,0.0002246845,0.0005386959],"genre_scores_gemma":[0.1076072,6.955409e-7,0.5661593,0.00002449293,0.0001105369,0.3254465,0.0001245348,0.00003153926,0.0004951972],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2965112,"threshold_uncertainty_score":0.7807266,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2105869274","doi":"10.1002/rcm.525","title":"<sup>18</sup> O Labeling: a tool for proteomics","year":2001,"lang":"en","type":"article","venue":"Rapid Communications in Mass Spectrometry","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":328,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Muscular Dystrophy Canada","funders":"","keywords":"Chemistry; Peptide; Trypsin; Quantitative proteomics; Linear relationship; Chromatography; Detection limit; Proteomics; Enzyme; Biochemistry; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03623277268844937,"gpt":0.3226549953876611,"spread":0.2864222226992117,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003699728,0.0002383062,0.000291343,0.0002561296,0.000331794,0.00006614895,0.001689338,0.0002049952,0.0005444497],"category_scores_gemma":[0.000207557,0.0002753621,0.0001409196,0.0008605296,0.0001440971,0.0001553099,0.0002948487,0.0006134225,0.00002452755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003398665,"about_ca_system_score_gemma":0.00007082291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000164603,"about_ca_topic_score_gemma":0.000006746058,"domain_scores_codex":[0.998411,0.00003356055,0.0005659199,0.000396298,0.000147955,0.0004452816],"domain_scores_gemma":[0.9962891,0.0003548875,0.000195065,0.002980652,0.0001121916,0.00006813901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001953875,0.001486086,0.01654539,0.0002161889,0.0001410376,0.00000363338,0.0003746321,0.00136587,0.6906628,0.2678032,0.001591458,0.01961427],"study_design_scores_gemma":[0.003301021,0.0001634236,0.000277778,0.0002700172,0.00009299206,0.00007553947,0.0008295983,0.09950215,0.2203888,0.4219463,0.2514697,0.001682735],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1768703,0.002414568,0.7274424,0.007224858,0.00002802088,0.002999114,0.0002483,0.001123624,0.08164875],"genre_scores_gemma":[0.2971214,0.004106536,0.6949897,0.00009254067,0.0000750727,0.002761854,0.0001518577,0.0000535744,0.0006474784],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4702741,"threshold_uncertainty_score":0.9999698,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2041686750","doi":"10.1038/nprot.2011.382","title":"Identifying and quantifying proteolytic events and the natural N terminome by terminal amine isotopic labeling of substrates","year":2011,"lang":"en","type":"article","venue":"Nature Protocols","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":327,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Proteome; Isotopic labeling; Chemistry; Biochemistry; Protease; Peptide; Isobaric labeling; Stable isotope labeling by amino acids in cell culture; Amine gas treating; Amino acid; Label-free quantification; Lysine; Quantitative proteomics; Proteomics; Enzyme","retraction":null,"screen_n_in":null,"score":{"opus":0.03292652992043294,"gpt":0.3334002278752797,"spread":0.3004736979548468,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001930632,0.0001727036,0.0002308982,0.0000318771,0.0001474398,0.00003343822,0.00024297,0.0001975801,0.00001914538],"category_scores_gemma":[0.0000495963,0.0001214784,0.0000427068,0.00008648096,0.0001846157,0.0001399565,0.0001201093,0.0006367582,5.172024e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001495747,"about_ca_system_score_gemma":0.00001600367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002636959,"about_ca_topic_score_gemma":0.000003924342,"domain_scores_codex":[0.9990613,0.00001754128,0.000307661,0.0002874551,0.0001357992,0.0001901858],"domain_scores_gemma":[0.9993096,0.00005980177,0.000251129,0.0002751901,0.00006237843,0.00004191653],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000361909,0.0001180639,0.02867573,0.001616741,0.00005279394,0.000005823074,0.0008774122,1.096863e-7,0.9503794,0.007264378,0.00002753,0.01062008],"study_design_scores_gemma":[0.001594792,0.00003290505,0.001321305,0.0005860607,0.00003099939,0.00005635762,0.0001125822,0.0001974512,0.9797912,0.01557489,0.0004632083,0.0002382619],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9610947,0.001276972,0.0006907642,0.0001184507,0.00001594352,0.03602222,0.00003144206,0.0001085088,0.0006410312],"genre_scores_gemma":[0.9314566,0.00002290078,0.02133702,0.00003413626,0.00003188987,0.04683723,0.00000748722,0.00001984224,0.0002528691],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02963804,"threshold_uncertainty_score":0.4953744,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}