{"meta":{"query_hash":"6b31ad525f57","filters":{"venue":"Journal on Satisfiability Boolean Modeling and Computation"},"cohort_total":8,"direct_labels_cover":0,"predictions_cover":8,"exported":8,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/6b31ad525f57","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+on+Satisfiability+Boolean+Modeling+and+Computation"},"results":[{"id":"W121484681","doi":"10.3233/sat190001","title":"Semidefinite Optimization Approaches for Satisfiability and Maximum-Satisfiability Problems","year":2005,"lang":"en","type":"article","venue":"Journal on Satisfiability Boolean Modeling and Computation","topic":"Complexity and Algorithms in Graphs","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Semidefinite programming; Semidefinite embedding; Satisfiability; Relaxation (psychology); Mathematics; Quadratically constrained quadratic program; Maximum cut; Linear programming; Large margin nearest neighbor; Mathematical optimization; Combinatorics; Computer science; Discrete mathematics; Quadratic programming; Artificial intelligence","score_opus":0.06582800461354198,"score_gpt":0.267172676926121,"score_spread":0.20134467231257902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W121484681","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015454305,0.0014058006,0.98095655,0.0010681306,0.00013821412,0.000044690987,0.00011895886,0.00008232829,0.014639861],"genre_scores_gemma":[0.19866063,0.0089383265,0.762917,0.0016833993,0.0015209056,0.0007968961,0.0011051485,0.0005798416,0.023797896],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975292,0.0012746131,0.0001062094,0.00028644205,0.00066600717,0.00013751861],"domain_scores_gemma":[0.99394435,0.0046927677,0.00032098556,0.00031775166,0.0005664595,0.00015760887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004291086,0.002241384,0.0014314246,0.0012351654,0.0007449885,0.0025548646,0.0023555625,0.0016581931,0.010047245],"category_scores_gemma":[0.008985318,0.001004769,0.0017368648,0.001996575,0.0020533341,0.004044949,0.0024011414,0.0072023273,0.0018960364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040233168,0.00014545282,0.0001626799,0.00045915376,0.00006895353,0.00008237411,0.00013716094,0.15098149,0.00088230975,0.7864858,0.013091472,0.047462966],"study_design_scores_gemma":[0.00001676169,0.000026598975,0.00004789318,0.00004684436,0.000010310282,0.000046582816,0.000040458766,0.37510338,0.00044668268,0.6171298,0.007069262,0.000015335254],"about_ca_topic_score_codex":0.0010535356,"about_ca_topic_score_gemma":0.0021153884,"teacher_disagreement_score":0.010047245,"about_ca_system_score_codex":0.0016984508,"about_ca_system_score_gemma":0.0014826067,"threshold_uncertainty_score":0.033611417},"labels":[],"label_agreement":null},{"id":"W1488842140","doi":"10.3233/sat190055","title":"QBF-Based Formal Verification: Experience and Perspectives","year":2008,"lang":"en","type":"article","venue":"Journal on Satisfiability Boolean Modeling and Computation","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Strong","keywords":"Formal methods; Formal verification; Computer science; Programming language","score_opus":0.08181267425518404,"score_gpt":0.3148733832200596,"score_spread":0.23306070896487555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1488842140","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030035786,0.23590827,0.5909734,0.041213114,0.000990858,0.00014075647,0.00015693043,0.00077633344,0.09980455],"genre_scores_gemma":[0.39328107,0.21565859,0.36511308,0.004702924,0.0022394557,0.00023314831,0.0005736348,0.0004177411,0.017780397],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9898371,0.005916516,0.0004824648,0.0007249531,0.0025803605,0.00045860783],"domain_scores_gemma":[0.9711158,0.01899288,0.0004403239,0.002437769,0.0057430407,0.0012701242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03474772,0.0016201894,0.0010100987,0.002329179,0.0010108463,0.006292588,0.004108015,0.003102843,0.0059354343],"category_scores_gemma":[0.026799643,0.0006998999,0.00074065593,0.0020162554,0.006515711,0.01404786,0.00336442,0.0048967497,0.0019193589],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048493757,0.00061302027,0.002307947,0.0012992005,0.00007974484,0.00047379846,0.004751356,0.012746081,0.0030547322,0.43106142,0.015022082,0.52810574],"study_design_scores_gemma":[0.0002632258,0.0010072469,0.0011272752,0.002794784,0.000052483592,0.0013080115,0.0041093593,0.039832525,0.009937045,0.5017534,0.43758112,0.00023360246],"about_ca_topic_score_codex":0.003277296,"about_ca_topic_score_gemma":0.0014372735,"teacher_disagreement_score":0.03474772,"about_ca_system_score_codex":0.0032118596,"about_ca_system_score_gemma":0.0022209235,"threshold_uncertainty_score":0.18376571},"labels":[],"label_agreement":null},{"id":"W2098347190","doi":"10.3233/sat190050","title":"Improved SAT-based Reachability Analysis with Observability Don’t Cares","year":2008,"lang":"en","type":"article","venue":"Journal on Satisfiability Boolean Modeling and Computation","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Observability; Reachability; Mathematics; Computer science; Theoretical computer science; Applied mathematics","score_opus":0.04621811252362271,"score_gpt":0.2875096499397546,"score_spread":0.24129153741613188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098347190","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012487546,0.0001328502,0.9771428,0.00025517933,0.0000880058,0.00009682836,0.00027377263,0.003225635,0.006297426],"genre_scores_gemma":[0.46489275,0.00031963034,0.5242916,0.00036480973,0.00010532498,0.0002651593,0.0015150636,0.00068455894,0.0075610806],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973124,0.0006545528,0.00014159559,0.0005162826,0.0010826129,0.00029262193],"domain_scores_gemma":[0.9946614,0.0031773928,0.000206382,0.0012238562,0.0006571868,0.00007382951],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017557065,0.0012096537,0.0010330067,0.0019153521,0.00083573034,0.0014744793,0.00245246,0.000946948,0.010943937],"category_scores_gemma":[0.0077372068,0.0007863738,0.0024914,0.0013941526,0.0015884277,0.0035523102,0.0020780119,0.002589486,0.0017220785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061723957,0.00041022236,0.0034033528,0.0004646784,0.00026587048,0.00057058386,0.00027750732,0.4301204,0.020931987,0.24660914,0.00876113,0.2875679],"study_design_scores_gemma":[0.000052708052,0.000051417785,0.0003625841,0.000028535349,0.000077934754,0.00007407989,0.00002085331,0.92506063,0.0066507114,0.065044425,0.0025485083,0.000027599706],"about_ca_topic_score_codex":0.009166699,"about_ca_topic_score_gemma":0.015590231,"teacher_disagreement_score":0.010943937,"about_ca_system_score_codex":0.0011148422,"about_ca_system_score_gemma":0.0022117314,"threshold_uncertainty_score":0.03661114},"labels":[],"label_agreement":null},{"id":"W2126735726","doi":"10.3233/sat190045","title":"A Switching Criterion for Intensification and Diversification in Local Search for SAT12","year":2008,"lang":"en","type":"article","venue":"Journal on Satisfiability Boolean Modeling and Computation","topic":"Constraint Satisfaction and Optimization","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; Technische Universiteit Delft","keywords":"Diversification (marketing strategy); Business; Economics; Marketing","score_opus":0.060497287460256816,"score_gpt":0.2991865808051254,"score_spread":0.23868929334486857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126735726","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051376805,0.0003342792,0.938663,0.00042548493,0.00003668845,0.00017091655,0.00006120912,0.00040311157,0.008528413],"genre_scores_gemma":[0.6315013,0.0002146283,0.3633893,0.00044576536,0.00012530368,0.0005623744,0.0001760599,0.000284643,0.0033006826],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976579,0.0009704009,0.00017003453,0.0002970728,0.0006780388,0.00022650533],"domain_scores_gemma":[0.9924204,0.0048524644,0.00047108028,0.0008707953,0.0009209926,0.00046420892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005304999,0.0006783611,0.001369763,0.0019748397,0.000838933,0.0016623591,0.0018274542,0.0013207739,0.004105168],"category_scores_gemma":[0.01653216,0.00044774095,0.00073507323,0.0013850742,0.0021361,0.002679283,0.0036505852,0.002164185,0.00049633556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005777077,0.00023908797,0.0054801977,0.00026885894,0.0001701061,0.0002800067,0.0007641963,0.33541337,0.02365376,0.3355913,0.0042437133,0.2933178],"study_design_scores_gemma":[0.00011464784,0.00030531178,0.0011854753,0.000049153266,0.000043982025,0.00014935253,0.00007327042,0.86789197,0.0053568487,0.122394666,0.0023887418,0.000046572804],"about_ca_topic_score_codex":0.00070623227,"about_ca_topic_score_gemma":0.00087449764,"teacher_disagreement_score":0.005304999,"about_ca_system_score_codex":0.0013983325,"about_ca_system_score_gemma":0.0007918209,"threshold_uncertainty_score":0.028055787},"labels":[],"label_agreement":null},{"id":"W2159832387","doi":"10.3233/sat190066","title":"Algorithms and Complexity Results for Input and Unit Resolution","year":2009,"lang":"en","type":"article","venue":"Journal on Satisfiability Boolean Modeling and Computation","topic":"graph theory and CDMA systems","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Resolution (logic); Completeness (order theory); Space (punctuation); PSPACE; Computer science; Algorithm; Mathematics; Computational complexity theory; Artificial intelligence; Mathematical analysis","score_opus":0.05055338728897672,"score_gpt":0.27397125337858336,"score_spread":0.22341786608960662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159832387","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022596063,0.0008080018,0.9567423,0.001672519,0.00006403776,0.00025666333,0.00042813743,0.0010870695,0.016345218],"genre_scores_gemma":[0.33038908,0.0015533386,0.65695715,0.00068127987,0.00035951237,0.0006456629,0.0015390598,0.0008258875,0.007049004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98741037,0.0041696313,0.0008319226,0.0018708407,0.0043285065,0.0013887245],"domain_scores_gemma":[0.94461405,0.04495379,0.0017223536,0.006589426,0.0016401057,0.00048034717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068144086,0.001339341,0.0015825363,0.0021453633,0.002046832,0.008039156,0.0057526953,0.0024606744,0.02011345],"category_scores_gemma":[0.03892464,0.000959091,0.0037583334,0.003559553,0.0032684184,0.015637072,0.005350575,0.0075581386,0.0016876728],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030334777,0.00036979947,0.0014652987,0.0014836001,0.0001742892,0.00027689885,0.0006608172,0.08776175,0.0048038308,0.78208697,0.005909213,0.11470417],"study_design_scores_gemma":[0.00006439943,0.0000650973,0.00034926567,0.00013037409,0.00010236108,0.00030833483,0.00019016393,0.25614652,0.010746764,0.7251694,0.006684862,0.000042492615],"about_ca_topic_score_codex":0.0011896266,"about_ca_topic_score_gemma":0.0014385072,"teacher_disagreement_score":0.02011345,"about_ca_system_score_codex":0.003152332,"about_ca_system_score_gemma":0.0023213848,"threshold_uncertainty_score":0.067286134},"labels":[],"label_agreement":null},{"id":"W2163348426","doi":"10.3233/sat190036","title":"An Extended Semidefinite Relaxation for Satisfiability","year":2007,"lang":"en","type":"article","venue":"Journal on Satisfiability Boolean Modeling and Computation","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Technische Universiteit Delft","keywords":"Semidefinite programming; Relaxation (psychology); Satisfiability; Semidefinite embedding; Mathematics; Class (philosophy); Extension (predicate logic); Combinatorics; Mathematical optimization; Discrete mathematics; Computer science; Quadratically constrained quadratic program; Quadratic programming; Artificial intelligence","score_opus":0.046582195121019944,"score_gpt":0.35056300591015194,"score_spread":0.30398081078913197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163348426","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008588866,0.00024707298,0.97369087,0.00063906424,0.00011505729,0.00011250126,0.00022222078,0.00019719503,0.016187226],"genre_scores_gemma":[0.22240566,0.0008895507,0.75937366,0.0008429088,0.00042971905,0.00057279074,0.0011818575,0.00029063036,0.014013206],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980603,0.0007925613,0.00009871099,0.00032165338,0.00057063135,0.00015608735],"domain_scores_gemma":[0.9974511,0.0015936827,0.0002024954,0.00033977086,0.00029817145,0.00011469383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031394255,0.0011765929,0.00068080216,0.0006043916,0.0005008402,0.0014401068,0.0014461371,0.00082931295,0.007652834],"category_scores_gemma":[0.005826679,0.0006848325,0.0014941833,0.00075149426,0.0015182877,0.0030312974,0.0016966576,0.00481453,0.001217604],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024549343,0.00027079787,0.0003099505,0.0005602697,0.00008496317,0.00031986972,0.00043730641,0.22816153,0.008291162,0.6438201,0.011544208,0.105954275],"study_design_scores_gemma":[0.00008458431,0.00020250375,0.00018504677,0.00012290757,0.00002907142,0.00024285437,0.000099843615,0.55545336,0.0034864137,0.4162477,0.023796197,0.000049508308],"about_ca_topic_score_codex":0.000764162,"about_ca_topic_score_gemma":0.001002585,"teacher_disagreement_score":0.007652834,"about_ca_system_score_codex":0.00089059153,"about_ca_system_score_gemma":0.0010589346,"threshold_uncertainty_score":0.025601327},"labels":[],"label_agreement":null},{"id":"W2580735446","doi":"10.3233/sat190111","title":"Hard satisfiable 3-SAT instances via autocorrelation","year":2016,"lang":"en","type":"article","venue":"Journal on Satisfiability Boolean Modeling and Computation","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Autocorrelation; Boolean satisfiability problem; Reduction (mathematics); Satisfiability; Computer science; Mathematics; Combinatorics; Algorithm; Statistics","score_opus":0.03937523132885755,"score_gpt":0.2920864361888223,"score_spread":0.25271120485996473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2580735446","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27405092,0.00056811457,0.66127086,0.0035346765,0.00021284181,0.00059939316,0.0033725689,0.00218917,0.054201514],"genre_scores_gemma":[0.7212376,0.00032507742,0.2616428,0.0008452841,0.00014197423,0.0004875436,0.0041307583,0.00066619675,0.010522805],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980939,0.0005515738,0.0001214135,0.00037903368,0.00059267407,0.00026142437],"domain_scores_gemma":[0.99608445,0.002721925,0.0002813981,0.0005537383,0.00022957387,0.00012897248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009975258,0.00078400335,0.0007188983,0.000865557,0.0006826066,0.0017734913,0.0016424028,0.0010554706,0.0088410685],"category_scores_gemma":[0.0067788754,0.0005734655,0.0022261422,0.001307642,0.0010845233,0.0020784964,0.0021896022,0.0035002802,0.0007502161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004169741,0.0006180546,0.002508295,0.0006176132,0.00016483082,0.0008443246,0.0005563725,0.27588722,0.016313193,0.60120684,0.021261264,0.07960489],"study_design_scores_gemma":[0.00017708515,0.000115226125,0.000878475,0.000054118875,0.00006750327,0.00039067245,0.00019263299,0.3684247,0.010357024,0.6074534,0.011844522,0.000044605793],"about_ca_topic_score_codex":0.0025505363,"about_ca_topic_score_gemma":0.004430546,"teacher_disagreement_score":0.0088410685,"about_ca_system_score_codex":0.0013241223,"about_ca_system_score_gemma":0.0013510418,"threshold_uncertainty_score":0.029576302},"labels":[],"label_agreement":null},{"id":"W2995736486","doi":"10.3233/sat190119","title":"MaxSAT Evaluation 2018: New Developments and Detailed Results","year":2019,"lang":"en","type":"article","venue":"Journal on Satisfiability Boolean Modeling and Computation","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Carnegie Mellon Portugal; National Science Foundation","keywords":"Maximum satisfiability problem; Satisfiability; Boolean satisfiability problem; Series (stratigraphy); Computer science; Radiomics; Theoretical computer science; Artificial intelligence; Algorithm; Boolean function","score_opus":0.06352342221819057,"score_gpt":0.3266440326746796,"score_spread":0.26312061045648905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995736486","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.117040165,0.17051272,0.28473824,0.031008694,0.016440084,0.0027440807,0.041384015,0.03763797,0.2984941],"genre_scores_gemma":[0.30201313,0.049676154,0.37368616,0.008381559,0.004644119,0.0026619637,0.18199135,0.029704878,0.047240783],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.96671313,0.012312644,0.0019199229,0.0025262672,0.014161505,0.002366471],"domain_scores_gemma":[0.9734476,0.010097175,0.0007597798,0.0034044427,0.010805093,0.0014859851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027008701,0.0031658467,0.0021900088,0.006257552,0.0015774574,0.008258489,0.0036606847,0.0018244713,0.019200515],"category_scores_gemma":[0.058066588,0.0012934974,0.0021070102,0.0068020886,0.0014969377,0.008768754,0.0046828757,0.0060341656,0.0073813805],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002298959,0.0011407713,0.003521606,0.0034726737,0.00036164426,0.000212982,0.0003529053,0.026077291,0.0054678647,0.0637282,0.40562654,0.48773864],"study_design_scores_gemma":[0.00072510494,0.0014264282,0.0060714497,0.003932602,0.00044107507,0.0005376498,0.00050953805,0.10031489,0.024621813,0.05963809,0.8014976,0.0002838607],"about_ca_topic_score_codex":0.0065272967,"about_ca_topic_score_gemma":0.007308567,"teacher_disagreement_score":0.027008701,"about_ca_system_score_codex":0.0044810507,"about_ca_system_score_gemma":0.006188413,"threshold_uncertainty_score":0.14283735},"labels":[],"label_agreement":null}]}