{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":8,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":8,"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":"29178c4a3bef","filters":{"venue":"ACM Transactions on Recommender Systems"}},"results":[{"id":"W4391436413","doi":"10.1145/3643138","title":"Measuring Commonality in Recommendation of Cultural Content to Strengthen Cultural Citizenship","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Recommender Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"University College London; Canadian Institute for Advanced Research","keywords":"Citizenship; Content (measure theory); Cultural diversity; Sociology; Political science; Anthropology; Law","retraction":null,"screen_n_in":null,"score":{"opus":0.2429439671267938,"gpt":0.3216424187380756,"spread":0.07869845161128178,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001198428,0.0003322976,0.0005196407,0.0005092114,0.0001426338,0.0004503813,0.001030046,0.0001519956,0.00003201865],"category_scores_gemma":[0.00003954746,0.0002748459,0.0002183418,0.0008602198,0.00002625476,0.0006661338,0.00005031488,0.0004544679,0.00003550461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003920838,"about_ca_system_score_gemma":0.00004888282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001504858,"about_ca_topic_score_gemma":0.0002460314,"domain_scores_codex":[0.9970518,0.0005276948,0.001014276,0.0006599608,0.0003286644,0.0004175753],"domain_scores_gemma":[0.998178,0.0004460942,0.0001392168,0.0008921828,0.000176012,0.0001684857],"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":[0.0001441939,0.001005245,0.002165866,0.00185786,0.00116189,0.00003983684,0.02479143,0.00324398,0.002995429,0.04121766,0.04154966,0.879827],"study_design_scores_gemma":[0.01064804,0.005439493,0.01697841,0.02218125,0.0004274471,0.001466059,0.06370506,0.2897325,0.08789403,0.01821143,0.4727091,0.01060715],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03356733,0.0004235609,0.9392362,0.01588954,0.004521783,0.00146942,0.0001125457,0.000950415,0.003829261],"genre_scores_gemma":[0.9926954,0.00005808868,0.00637262,0.0002074374,0.00006846221,0.000316857,0.00002051527,0.00002597515,0.0002346422],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9591281,"threshold_uncertainty_score":0.9999704,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386136194","doi":"10.1145/3616379","title":"Multi-Interest Multi-Round Conversational Recommendation System with Fuzzy Feedback Based User Simulator","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Recommender Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Preference; Recommender system; Human–computer interaction; Fuzzy logic; Information retrieval; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.08600942693861284,"gpt":0.2924780118068677,"spread":0.2064685848682549,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001098693,0.0005975267,0.0006380631,0.0008439642,0.0006493181,0.0007003603,0.001407885,0.0002985178,0.00006274712],"category_scores_gemma":[0.00002353417,0.0005211759,0.0002433057,0.001331495,0.00005491526,0.001051428,0.00005178977,0.0005035742,0.0004988089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006158156,"about_ca_system_score_gemma":0.0001653612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005658465,"about_ca_topic_score_gemma":0.0002664694,"domain_scores_codex":[0.9960372,0.0006077971,0.0009797616,0.001144185,0.0005082118,0.0007228568],"domain_scores_gemma":[0.9964235,0.0007302842,0.0004296121,0.001790055,0.0003198038,0.0003067837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001855254,0.01511244,0.02184717,0.01177445,0.01050489,0.0005972192,0.0131448,0.2752079,0.005048112,0.05357017,0.2875536,0.303784],"study_design_scores_gemma":[0.0051491,0.0005268776,0.001523579,0.0007805319,0.00006163912,0.00009143843,0.002367056,0.9330304,0.001351222,0.00002991476,0.05389279,0.001195492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001158916,0.00002075154,0.9866225,0.004160675,0.00327182,0.00145482,0.0001080264,0.002847866,0.0003546915],"genre_scores_gemma":[0.9477242,0.0000143012,0.04953411,0.0004579197,0.0001091714,0.0007202214,0.0001181162,0.00009688744,0.001225081],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9465653,"threshold_uncertainty_score":0.999724,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4366598314","doi":"10.1145/3591109","title":"A Framework and Toolkit for Testing the Correctness of Recommendation Algorithms","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Recommender Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Test suite; Correctness; Unit testing; Python (programming language); Algorithm; Recommender system; Suite; White-box testing; Implementation; Surprise; Regression testing; Code coverage; Integration testing; Test case; Software engineering; Software; Programming language; Machine learning; Software system; Software construction","retraction":null,"screen_n_in":null,"score":{"opus":0.1268538343049634,"gpt":0.3261905453913853,"spread":0.1993367110864219,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00139476,0.0002207525,0.0003430132,0.0002678496,0.0004642026,0.0002286997,0.0008521737,0.0001486686,0.000005698324],"category_scores_gemma":[0.0001607739,0.0001670127,0.0001083283,0.001043169,0.00003786248,0.0003288381,0.00004442964,0.0002604044,0.000007694377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005276499,"about_ca_system_score_gemma":0.00004071408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002157387,"about_ca_topic_score_gemma":0.00001062523,"domain_scores_codex":[0.9981928,0.0002319572,0.0005794253,0.0004602483,0.0001977141,0.0003378224],"domain_scores_gemma":[0.9951854,0.003364077,0.0002654109,0.0009390975,0.0001720325,0.00007397591],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001501179,0.0001107317,0.0002084147,0.0002559251,0.0001528195,0.00000106067,0.001717247,0.0003460558,0.0001102997,0.00729173,0.009190926,0.9805998],"study_design_scores_gemma":[0.002094925,0.001768638,0.001897107,0.001602092,0.0001390387,0.0002725521,0.006687361,0.7357277,0.004857661,0.04858931,0.1947804,0.001583188],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004971026,0.0000616433,0.9874656,0.00738224,0.002593462,0.001055229,0.00003894775,0.0005633041,0.0003425298],"genre_scores_gemma":[0.880877,0.0001324982,0.1165064,0.0003950536,0.000167216,0.001496433,0.00001620395,0.0000512458,0.000357951],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9790166,"threshold_uncertainty_score":0.681058,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4409168760","doi":"10.1145/3728373","title":"Recall, Robustness, and Lexicographic Evaluation","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Recommender Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Lexicographical order; Robustness (evolution); Recall; Computer science; Artificial intelligence; Cognitive psychology; Mathematics; Psychology; Chemistry; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.05255388057789485,"gpt":0.2979719475362509,"spread":0.2454180669583561,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007612761,0.0001408424,0.0001692025,0.0003320963,0.0002546413,0.0002103505,0.0005531373,0.0001034773,0.00001098537],"category_scores_gemma":[0.0000243766,0.0001367333,0.00005584601,0.0005191104,0.00002060472,0.0003479113,0.00001947096,0.0002008993,0.000005278347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007919181,"about_ca_system_score_gemma":0.0000728432,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009074969,"about_ca_topic_score_gemma":0.0000291439,"domain_scores_codex":[0.9985675,0.0002384555,0.0002930857,0.00044949,0.0002540259,0.000197485],"domain_scores_gemma":[0.9986079,0.0001890791,0.00005736526,0.0009819386,0.0001061275,0.00005761541],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001021137,0.0001528634,0.000246541,0.0001181716,0.0001578036,0.000001363949,0.000363656,0.07333764,0.0000783565,0.01298767,0.001339019,0.9112067],"study_design_scores_gemma":[0.0006893229,0.00004358389,0.0003239692,0.0001411368,0.00004612688,0.00001396509,0.0002133787,0.9875956,0.000174241,0.003614408,0.006936765,0.0002075645],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002848154,0.0005435486,0.9857339,0.006949252,0.002031258,0.0004293341,0.000001906909,0.0001966684,0.001265961],"genre_scores_gemma":[0.9818031,0.000116289,0.01702511,0.0003653767,0.00002756793,0.0002077994,0.000001982822,0.00000802161,0.000444794],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9789549,"threshold_uncertainty_score":0.5575824,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4405194834","doi":"10.1145/3707693","title":"Modelling Concept Drift in Dynamic Data Streams for Recommender Systems","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Recommender Systems","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Recommender system; STREAMS; Computer science; Concept drift; Data stream mining; Dynamic data; Data mining; Data science; Information retrieval; Database; Computer network","retraction":null,"screen_n_in":null,"score":{"opus":0.102916937600841,"gpt":0.3378285326575012,"spread":0.2349115950566602,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001239192,0.0004506963,0.0005494932,0.0006526196,0.0002230986,0.001101797,0.003960086,0.0002653505,0.00001200288],"category_scores_gemma":[0.00002798993,0.0004405583,0.0001593475,0.000778743,0.00004225979,0.001716609,0.0001368311,0.0005880492,0.00003782088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000388943,"about_ca_system_score_gemma":0.0001583232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001403422,"about_ca_topic_score_gemma":0.0001301344,"domain_scores_codex":[0.9962245,0.000296724,0.0009277218,0.001505365,0.0003747741,0.0006709066],"domain_scores_gemma":[0.9942353,0.001213354,0.0001382516,0.004180354,0.00007918914,0.0001535789],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005330777,0.0007984843,0.00002067227,0.001359406,0.0009005929,0.00005834012,0.003636961,0.3675275,0.00004528152,0.01573862,0.1014165,0.5084444],"study_design_scores_gemma":[0.0003735274,0.0001447542,5.596057e-7,0.0007947191,0.00003958237,0.00004902617,0.0006721936,0.9240389,0.00005506324,0.0007760401,0.07261916,0.0004364219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001095551,0.001539187,0.9861482,0.0027804,0.004947324,0.001386411,0.00126118,0.00148518,0.0003425101],"genre_scores_gemma":[0.8818532,0.0003766682,0.1149466,0.0001636547,0.0001296972,0.001033629,0.0005993313,0.0001172737,0.0007800239],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8817436,"threshold_uncertainty_score":0.9999352,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4413167298","doi":"10.1145/3760763","title":"Revisiting LightGCN: Unexpected Inflexibility, Inconsistency, and A Remedy Towards Improved Recommendation","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Recommender Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.02887191956557714,"gpt":0.2931055492405019,"spread":0.2642336296749248,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001455363,0.0004351881,0.0006284509,0.0006656381,0.0006004567,0.0006564917,0.001042878,0.0002937597,0.00002638119],"category_scores_gemma":[0.0001185201,0.0004078981,0.0001783842,0.001068595,0.00005017301,0.0008003274,0.0001286863,0.0005518218,0.00001037616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003334691,"about_ca_system_score_gemma":0.0001626603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009822591,"about_ca_topic_score_gemma":0.00009390263,"domain_scores_codex":[0.9964641,0.0006513942,0.001118077,0.001035994,0.0002365314,0.0004938524],"domain_scores_gemma":[0.9969893,0.0004981393,0.0003193663,0.001761745,0.0002549072,0.0001765778],"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":[0.00003455408,0.0002337995,0.0003925878,0.0004548843,0.0003217499,0.000004913447,0.000848035,0.00001513385,0.0007923419,0.008752807,0.003335987,0.9848132],"study_design_scores_gemma":[0.008886474,0.001845104,0.006872477,0.005483892,0.0004428178,0.0007350136,0.00676907,0.1857539,0.02676139,0.03528364,0.7159429,0.005223353],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001199585,0.0003791422,0.9588867,0.02408798,0.002357464,0.00118101,0.00001732058,0.001109722,0.01078102],"genre_scores_gemma":[0.966481,0.0002696106,0.03046951,0.001125406,0.00009878037,0.0005154604,0.00001554748,0.00003268108,0.0009920419],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9795899,"threshold_uncertainty_score":0.9998373,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4412841400","doi":"10.1145/3757327","title":"A Comparative Survey Of Algorithmic Feed Recommendation System Designs","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Recommender Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Information retrieval; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.102181417286145,"gpt":0.3294324895136431,"spread":0.227251072227498,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019277,0.0004047931,0.0009398984,0.0007932249,0.0003549205,0.0002404947,0.001568903,0.0002327322,0.00001741656],"category_scores_gemma":[0.00002832122,0.0003809545,0.0001939357,0.001563591,0.00004541846,0.0005242018,0.00005143546,0.0003748653,0.000029326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004143634,"about_ca_system_score_gemma":0.0001839348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003884355,"about_ca_topic_score_gemma":0.000263074,"domain_scores_codex":[0.9957732,0.00152949,0.001223676,0.0007371948,0.0003098321,0.00042659],"domain_scores_gemma":[0.9961624,0.001139982,0.0004778842,0.00164735,0.0004534927,0.0001188681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005902902,0.005238275,0.004457243,0.004651382,0.006523965,0.00002365614,0.009305003,0.004261125,0.002604519,0.0945284,0.1443938,0.7234223],"study_design_scores_gemma":[0.01247623,0.003752335,0.02852773,0.007758338,0.0005508575,0.0003745423,0.01459936,0.7268342,0.09482791,0.003426037,0.1011293,0.005743132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004212749,0.0001513998,0.9875606,0.001141161,0.003187802,0.00124048,0.0000916775,0.0006498516,0.005555781],"genre_scores_gemma":[0.9790024,0.00003803937,0.01981346,0.0001294617,0.00002452832,0.0004436403,0.00003521898,0.00002175636,0.000491533],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9785811,"threshold_uncertainty_score":0.9998642,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407654895","doi":"10.1145/3718488","title":"Balancing Embedding Spectrum for Recommendation","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Recommender Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Embedding; Spectrum (functional analysis); Artificial intelligence; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.02706613366870131,"gpt":0.3083818690799667,"spread":0.2813157354112654,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009528586,0.0003182808,0.0004350453,0.0005918039,0.0005821033,0.0004809943,0.001153193,0.000183821,0.00002767656],"category_scores_gemma":[0.00003544611,0.0003106844,0.0002327512,0.0006482645,0.00001495787,0.0006123244,0.00003563155,0.0002906815,0.00002109596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003377813,"about_ca_system_score_gemma":0.0000844943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001872828,"about_ca_topic_score_gemma":0.00004218187,"domain_scores_codex":[0.9976845,0.0002091873,0.0007109169,0.0007156517,0.0001735132,0.000506186],"domain_scores_gemma":[0.9976428,0.0006795718,0.0002014198,0.001276522,0.0001001688,0.00009957986],"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":[0.00007000907,0.0006583611,0.0002687388,0.000745254,0.000749342,0.000003633015,0.00102578,0.0019426,0.000404493,0.1023122,0.1239651,0.7678545],"study_design_scores_gemma":[0.002105588,0.0004617247,0.0001169881,0.0007484464,0.00007383178,0.00005351555,0.0009579018,0.2291335,0.01054819,0.02342192,0.731346,0.001032416],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00006529279,0.00009018782,0.9683535,0.01802962,0.005733314,0.001162201,0.00002257253,0.0008668066,0.005676585],"genre_scores_gemma":[0.9163582,0.00008603506,0.07771216,0.001510135,0.0001598196,0.00134462,0.00002373854,0.00004318091,0.002762098],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9162929,"threshold_uncertainty_score":0.9999346,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}