{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":26,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":26,"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":"a6c2b8c45c44","filters":{"venue":"Information Retrieval"}},"results":[{"id":"W1685426458","doi":"10.1007/s10791-011-9162-z","title":"Efficient and effective spam filtering and re-ranking for large web datasets","year":2011,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":277,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"National Institute of Standards and Technology","keywords":"Computer science; Information retrieval; Ranking (information retrieval); Relevance feedback; Relevance (law); Search engine; Learning to rank; Set (abstract data type); Honeypot; Web page; Rank (graph theory); Data mining; World Wide Web; Artificial intelligence; Image retrieval; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01549341487547832,"gpt":0.2325380502429347,"spread":0.2170446353674564,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005093018,0.00007316475,0.00007389486,0.0001053947,0.0001713917,0.0001665918,0.0001183224,0.00004672012,0.000004738821],"category_scores_gemma":[0.0001277638,0.00006858497,0.0000168802,0.0001454826,0.0000138366,0.0008896849,0.0001223201,0.00006469617,0.000008373953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001863065,"about_ca_system_score_gemma":0.00001186123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007726608,"about_ca_topic_score_gemma":0.000002083803,"domain_scores_codex":[0.9994586,0.00001779028,0.0001517762,0.0001098298,0.0001216541,0.0001403407],"domain_scores_gemma":[0.9995837,0.00008314152,0.00008568187,0.0001534636,0.00004587157,0.0000481007],"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":[0.002477747,0.000299279,0.0101947,0.001910445,0.0002748879,0.00001488077,0.1529467,0.0008314913,0.009421865,0.1468808,0.00655584,0.6681914],"study_design_scores_gemma":[0.001972025,0.000484817,0.02228767,0.00006992311,0.00001691188,0.00003548809,0.0001651527,0.9368455,0.01330707,0.0006796208,0.02383004,0.000305803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4219919,0.00003651646,0.5761412,0.00004541995,0.0004704281,0.0004515708,0.00008880603,0.0001193491,0.0006547185],"genre_scores_gemma":[0.9936067,0.000003683439,0.006179343,0.0001449719,0.00002747427,0.000008883775,0.00002412435,0.000002511531,0.000002261113],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.936014,"threshold_uncertainty_score":0.2796814,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2151752770","doi":"10.1023/b:inrt.0000011209.19643.e2","title":"Augmenting Naive Bayes Classifiers with Statistical Language Models","year":2004,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Topic Modeling","field":"Computer Science","cited_by":247,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Naive Bayes classifier; Artificial intelligence; Computer science; Machine learning; Bayes error rate; Bayes classifier; Bayes' theorem; Classifier (UML); Conditional independence; Bayesian programming; Natural language processing; Pattern recognition (psychology); Bayes factor; Bayesian probability; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.01324613556970664,"gpt":0.2371975164125819,"spread":0.2239513808428753,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001926023,0.00009013081,0.00008838175,0.00009451572,0.0000992097,0.0002317691,0.00028488,0.00004685853,0.00001195911],"category_scores_gemma":[0.0000530533,0.0000753612,0.00001898191,0.000223561,0.00002984456,0.002853663,0.00008076937,0.0001286564,0.00006952407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009778347,"about_ca_system_score_gemma":0.0001347022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003422343,"about_ca_topic_score_gemma":0.000002026844,"domain_scores_codex":[0.9990052,0.00001330831,0.0002491017,0.0001175792,0.0004055533,0.000209247],"domain_scores_gemma":[0.9994519,0.0000364254,0.00009963191,0.000247817,0.00008643734,0.00007773283],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000500416,0.0000207407,0.00007901485,0.00004487525,0.00002641756,0.00002097643,0.01684953,0.1065922,0.0000888289,0.8306463,0.00009249901,0.04548853],"study_design_scores_gemma":[0.001193371,0.0001227641,0.0002708093,0.00004549321,0.000007051784,0.00003632784,0.001092968,0.9835308,0.001609518,0.01132223,0.000528303,0.000240426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0353856,0.000009743699,0.9577029,0.0002930962,0.0001128778,0.0001169156,0.000006373999,0.0001663557,0.006206165],"genre_scores_gemma":[0.8069105,0.000001161922,0.1926491,0.0003702589,0.00002383956,0.000002295991,0.00001272458,0.000003116669,0.00002708769],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8769385,"threshold_uncertainty_score":0.307314,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2084946528","doi":"10.1007/s10791-006-9020-6","title":"Knowledge-based query expansion to support scenario-specific retrieval of medical free text","year":2007,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":79,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institutes of Health; McMaster University","keywords":"Computer science; Query expansion; Unified Medical Language System; Information retrieval; Query language; Testbed; Query optimization; Precision and recall; Exploit; Recall; Data mining; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.02053831162805873,"gpt":0.3008048304354492,"spread":0.2802665188073905,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001845927,0.0001684048,0.0002200137,0.0002204123,0.00007492588,0.00002826837,0.0005355745,0.0005789432,0.0002320197],"category_scores_gemma":[0.00191095,0.0001480837,0.0001149798,0.0004495725,0.000214815,0.00001609734,0.0002179188,0.0002057434,0.0001346652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003952196,"about_ca_system_score_gemma":0.0004323936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001004627,"about_ca_topic_score_gemma":0.00001464066,"domain_scores_codex":[0.9978587,0.00004112235,0.0007223381,0.0001937619,0.0008394961,0.0003445969],"domain_scores_gemma":[0.9986301,0.00008460508,0.000177283,0.0004913068,0.0003062735,0.0003104459],"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":[0.008290402,0.0005236288,0.002985197,0.0003633372,0.0001146948,0.0000307981,0.002048903,0.00005961926,0.1385119,0.0009191257,0.2304411,0.6157113],"study_design_scores_gemma":[0.001922874,0.001574328,0.005775819,0.00007648967,0.000009799421,0.0000223429,0.0004293263,0.0001716571,0.3406263,0.00002546106,0.6490836,0.0002819858],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9056827,0.0003849659,0.08600736,0.001260483,0.000967199,0.0003141451,0.00005889535,0.00008189082,0.005242387],"genre_scores_gemma":[0.9953862,0.00005166898,0.002819026,0.0009773894,0.0002808393,0.000001818663,0.0002800938,0.00001280959,0.0001901599],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6154293,"threshold_uncertainty_score":0.6038679,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2032328503","doi":"10.1007/s10791-009-9108-x","title":"Document clustering of scientific texts using citation contexts","year":2009,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Information retrieval; Computer science; Document clustering; Citation; Vocabulary; Context (archaeology); Similarity (geometry); Representation (politics); Document retrieval; Natural language processing; Artificial intelligence; World Wide Web; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.0160256859248469,"gpt":0.2950436954188471,"spread":0.2790180094940002,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004991781,0.00008795421,0.0001313024,0.0004504971,0.0001252266,0.0002914423,0.0003874276,0.00004483317,0.000008330959],"category_scores_gemma":[0.0001120901,0.00008700669,0.00005907105,0.001012773,0.00004293321,0.004929793,0.00007694725,0.00006564358,0.00001839687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000102123,"about_ca_system_score_gemma":0.00005679828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003224357,"about_ca_topic_score_gemma":8.041845e-7,"domain_scores_codex":[0.9987367,0.00002385109,0.0004896937,0.0001185582,0.0004796878,0.0001514541],"domain_scores_gemma":[0.9988553,0.00002792194,0.0003641493,0.0003516878,0.0003563927,0.00004456832],"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":[0.00006801321,0.00006210744,0.0001788734,0.00005857395,0.00003056094,0.000002354211,0.005232785,0.01538972,0.04377983,0.08165631,0.0003050675,0.8532358],"study_design_scores_gemma":[0.0007095921,0.0002734871,0.004252001,0.0001070285,0.00001836316,0.000017211,0.00008620138,0.7957874,0.162362,0.03252544,0.003489282,0.0003719551],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07608683,0.00002104312,0.922473,0.0001017454,0.0001384385,0.0001526482,0.000001153878,0.0001453661,0.0008797561],"genre_scores_gemma":[0.8730282,0.000001792197,0.1267933,0.0001273347,0.000009851551,6.357538e-7,0.000008104314,0.000001526252,0.00002923284],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8528638,"threshold_uncertainty_score":0.3573981,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2033681837","doi":"10.1007/s10791-011-9163-y","title":"Improving document clustering using Okapi BM25 feature weighting","year":2011,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Weighting; Cluster analysis; Computer science; Artificial intelligence; Data mining; Feature (linguistics); Document clustering; Pattern recognition (psychology); Term (time)","retraction":null,"screen_n_in":null,"score":{"opus":0.02482047029488173,"gpt":0.2420373186875677,"spread":0.2172168483926859,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005130527,0.0001611199,0.0001367132,0.0002224043,0.000243293,0.0003748015,0.00061486,0.0001224578,0.00004676209],"category_scores_gemma":[0.0001045715,0.0001461635,0.00007572631,0.0005935211,0.00003402359,0.004979827,0.0003002153,0.0002161064,0.00008917789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001528695,"about_ca_system_score_gemma":0.0000953784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002720457,"about_ca_topic_score_gemma":4.717999e-7,"domain_scores_codex":[0.9986537,0.00003613325,0.00042941,0.0001772465,0.0004096886,0.0002937875],"domain_scores_gemma":[0.9988438,0.00002455741,0.0003633167,0.0004275315,0.0002471335,0.00009369713],"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":[0.0002738333,0.00011825,0.0008292533,0.0005347833,0.00009868265,0.00002612919,0.02204791,0.00005721625,0.05010868,0.06460754,0.001022965,0.8602747],"study_design_scores_gemma":[0.0007008398,0.0002074788,0.001522326,0.0001040015,0.00002065786,0.0001254055,0.0004016093,0.5432329,0.437895,0.002118879,0.0129606,0.0007104031],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004745881,0.00003619622,0.9876043,0.0001378365,0.0003831296,0.0002364359,0.000001983369,0.0005358714,0.006318327],"genre_scores_gemma":[0.6141777,0.00001445694,0.3847898,0.0006124816,0.0001029586,0.000006494244,0.00001039994,0.00001218457,0.0002735689],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8595644,"threshold_uncertainty_score":0.5960376,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2141520705","doi":"10.1023/a:1026028229881","title":"Applying Machine Learning to Text Segmentation for Information Retrieval","year":2003,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Topic Modeling","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Segmentation; Computer science; Text segmentation; Artificial intelligence; Pattern recognition (psychology); Natural language processing; Word (group theory); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01664541220876287,"gpt":0.2556849407473694,"spread":0.2390395285386065,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00109138,0.0001641134,0.0001531945,0.0003972802,0.0003189477,0.0005628691,0.0003651689,0.000102621,0.00002280603],"category_scores_gemma":[0.00113483,0.0001702474,0.00006952147,0.0007744515,0.00001037037,0.00702247,0.0000847463,0.0001909804,0.0003310138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001815788,"about_ca_system_score_gemma":0.0001139314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009044008,"about_ca_topic_score_gemma":7.178546e-7,"domain_scores_codex":[0.9982131,0.0000547674,0.0006964821,0.0001489014,0.0005632973,0.0003234305],"domain_scores_gemma":[0.9987821,0.0001184678,0.0003035023,0.0003027005,0.0003604657,0.0001327614],"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":[0.0004527553,0.000045205,0.0009856811,0.0003584147,0.00006416906,9.814225e-7,0.02396457,0.1227017,0.003111723,0.2245377,0.001238539,0.6225386],"study_design_scores_gemma":[0.001439928,0.0002376027,0.0001668019,0.00002677819,0.000009425885,0.00001809367,0.0005584903,0.586629,0.01444473,0.0007945496,0.3953047,0.0003699399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01314583,0.00001491661,0.9808013,0.0002860309,0.0005810044,0.001337618,0.00000948932,0.0002662791,0.003557491],"genre_scores_gemma":[0.7399691,0.000009288218,0.2564479,0.002910964,0.00008605512,0.0001279367,0.0002022341,0.00001322499,0.0002332498],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7268233,"threshold_uncertainty_score":0.6942488,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1503824486","doi":"10.1023/a:1023936321956","title":"Query Expansion with Long-Span Collocates","year":2003,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Microsoft Research","keywords":"Collocation (remote sensing); Computer science; Window (computing); Information retrieval; Mathematics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.009880289279499396,"gpt":0.2239308871336277,"spread":0.2140505978541283,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005693992,0.0001714368,0.0001539137,0.0002843468,0.0002626609,0.0004917196,0.0004483455,0.00009944453,0.0001007315],"category_scores_gemma":[0.0001565168,0.000131152,0.00005450564,0.001132674,0.00006208379,0.006169804,0.00006504168,0.0001985593,0.0007388521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000921547,"about_ca_system_score_gemma":0.0003377448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009464384,"about_ca_topic_score_gemma":0.000001859468,"domain_scores_codex":[0.9981608,0.00006013302,0.0004603011,0.0001324086,0.0008290841,0.0003572848],"domain_scores_gemma":[0.9986442,0.00006251842,0.0001920389,0.0004332163,0.0004934813,0.0001745135],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001185887,0.0005615865,0.02854419,0.0005410814,0.0001848769,0.0001046682,0.03103234,0.007450412,0.001013661,0.6845196,0.01275044,0.2321112],"study_design_scores_gemma":[0.01129591,0.003960942,0.07571846,0.0003009606,0.00007388744,0.001205494,0.003431266,0.1154809,0.2728475,0.002278146,0.5098674,0.003539114],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1789887,0.00002441738,0.80165,0.0003841164,0.000410167,0.0005313431,0.000007018786,0.0003995154,0.01760468],"genre_scores_gemma":[0.9913939,0.00001206317,0.00714157,0.0008805265,0.00001788861,0.00001198678,0.00003398614,0.000006365418,0.0005017775],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8124051,"threshold_uncertainty_score":0.9496695,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3196754070","doi":"10.1007/s10791-022-09411-0","title":"Shallow pooling for sparse labels","year":2022,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Ranking (information retrieval); Mean reciprocal rank; Information retrieval; Pooling; Computer science; Relevance (law); Set (abstract data type); Rank (graph theory); Learning to rank; Preference; Artificial intelligence; Statistics; Mathematics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.02332481057054104,"gpt":0.2593679142488165,"spread":0.2360431036782755,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001051676,0.0001191742,0.0001312044,0.0003009828,0.0007185334,0.0003476872,0.0008470055,0.00004336391,0.0002137286],"category_scores_gemma":[0.0001713136,0.0001206884,0.0001088002,0.0007920345,0.00002139512,0.003685426,0.0003918732,0.0002256353,0.0001922615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001600988,"about_ca_system_score_gemma":0.0002050814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006186282,"about_ca_topic_score_gemma":2.831904e-7,"domain_scores_codex":[0.9981591,0.00004089025,0.0005264307,0.0001193601,0.0008040195,0.000350185],"domain_scores_gemma":[0.9989461,0.000100815,0.0002103754,0.0003312665,0.0003007505,0.0001107154],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000644945,0.0001925728,0.0006500225,0.0001751894,0.0000629955,0.0000100564,0.01452293,0.01145196,0.0007654493,0.73159,0.01750919,0.2224247],"study_design_scores_gemma":[0.002012526,0.0006285805,0.001442775,0.000006472383,0.00001038287,0.00006582828,0.0006074102,0.318732,0.002915881,0.002673634,0.6704598,0.0004447014],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07467826,0.00003426994,0.9095519,0.002393947,0.001901267,0.001462768,0.000213074,0.0006218875,0.009142665],"genre_scores_gemma":[0.9702983,0.0000048884,0.02342345,0.004593429,0.0001012856,0.0001654993,0.0002870214,0.00001159533,0.001114538],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.89562,"threshold_uncertainty_score":0.552645,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2967813257","doi":"10.1007/s10791-019-09361-0","title":"Evaluating sentence-level relevance feedback for high-recall information retrieval","year":2019,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Topic Modeling","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Relevance feedback; Relevance (law); Recall; Computer science; Sentence; Baseline (sea); Information retrieval; Precision and recall; Natural language processing; Artificial intelligence; Cognitive psychology; Psychology; Image retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.04688903707632153,"gpt":0.292025163440755,"spread":0.2451361263644335,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001657817,0.0002508897,0.0002852199,0.0002941217,0.0002080377,0.0006004287,0.0009571533,0.0002063052,0.00005302965],"category_scores_gemma":[0.001572526,0.0002481626,0.0001180916,0.0007286257,0.00003004411,0.01238474,0.0002618658,0.0002828366,0.001411036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002531035,"about_ca_system_score_gemma":0.0003034283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002212436,"about_ca_topic_score_gemma":8.695101e-7,"domain_scores_codex":[0.9968733,0.00005611903,0.001159055,0.0002631182,0.001142315,0.0005061578],"domain_scores_gemma":[0.9969814,0.0003514196,0.0006795368,0.0008184863,0.001038762,0.0001304048],"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":[0.001563148,0.00008240072,0.001056261,0.001158182,0.000130585,0.000001375229,0.01184533,0.06378419,0.003649749,0.2340185,0.004764323,0.677946],"study_design_scores_gemma":[0.002623551,0.0004065951,0.001867975,0.00009905322,0.00001260513,0.00001740322,0.0002236504,0.9673481,0.005361234,0.003641358,0.01793341,0.0004650866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2182396,0.0000160242,0.7757292,0.0009311115,0.001946559,0.001145741,0.00004261674,0.000292135,0.001656957],"genre_scores_gemma":[0.7672732,0.00001493538,0.2295872,0.002108195,0.000190516,0.00002071892,0.0001948523,0.00001396311,0.0005964512],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9035639,"threshold_uncertainty_score":0.9999971,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2556771250","doi":"10.1007/s10791-016-9290-6","title":"Efficient distributed selective search","year":2016,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Directorate for Computer and Information Science and Engineering; Australian Research Council; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Ranking (information retrieval); Resource (disambiguation); Index (typography); Mirroring; Data mining; Selection (genetic algorithm); Web search query; Query expansion; Search engine; Information retrieval; Distributed computing; Machine learning; Computer network; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.01353276958545393,"gpt":0.2529916586149543,"spread":0.2394588890295003,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006541641,0.0001374961,0.0001277978,0.0002787846,0.0002188693,0.0002628319,0.0006410485,0.00009235714,0.00009697556],"category_scores_gemma":[0.0002791901,0.00008811807,0.00007879559,0.001134931,0.00007072811,0.002081384,0.0002172076,0.0001435767,0.002337408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000237895,"about_ca_system_score_gemma":0.0002241363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005918697,"about_ca_topic_score_gemma":1.772788e-7,"domain_scores_codex":[0.9980074,0.00005773928,0.0004631723,0.0001362417,0.0009095062,0.0004259335],"domain_scores_gemma":[0.9984536,0.0001315059,0.0001217888,0.0003753768,0.0007326341,0.0001850757],"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":[0.0006422705,0.0002565342,0.002674649,0.00009638011,0.00009023469,0.00001842521,0.009266807,0.003188472,0.006046324,0.3808343,0.01086069,0.5860249],"study_design_scores_gemma":[0.009521821,0.001644298,0.1149794,0.0001826873,0.00002747513,0.0002257171,0.0006049169,0.4565658,0.2531801,0.001919992,0.1590282,0.002119535],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1215922,0.00000453937,0.871971,0.00157334,0.0003030552,0.0003331726,0.00007945806,0.0003459883,0.003797229],"genre_scores_gemma":[0.9975632,0.000003475308,0.00187029,0.000302092,0.00003232501,0.000006946047,0.00002560009,0.00000355342,0.0001924588],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.875971,"threshold_uncertainty_score":0.9984394,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2082055394","doi":"10.1007/s10791-012-9218-8","title":"Increasing evaluation sensitivity to diversity","year":2013,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"National Science Foundation","keywords":"Computer science; Diversity (politics); Context (archaeology); Information retrieval; Discriminative model; Measure (data warehouse); Data science; Data mining; Artificial intelligence; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.02380544427014461,"gpt":0.2593833951838307,"spread":0.2355779509136861,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002391295,0.0001236089,0.0001194852,0.0003300906,0.0004872083,0.0005975086,0.0003785559,0.00007857154,0.0002231839],"category_scores_gemma":[0.0008201572,0.0001161017,0.00005822012,0.0009015072,0.00002400565,0.0097673,0.0007756918,0.0001466503,0.004764339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002195849,"about_ca_system_score_gemma":0.0001279681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003487538,"about_ca_topic_score_gemma":0.00000251352,"domain_scores_codex":[0.9977418,0.0001789902,0.0003674117,0.0001246939,0.001288962,0.0002981759],"domain_scores_gemma":[0.9978443,0.0001146669,0.0001337514,0.0003573127,0.001313458,0.0002364445],"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":[0.0001720586,0.00009907965,0.01463191,0.00006030949,0.00003855972,0.000004711017,0.01948855,0.00214186,0.003466099,0.02143931,0.01012359,0.9283339],"study_design_scores_gemma":[0.00119771,0.0002337372,0.4264012,0.00002746946,0.00001751103,0.00008361277,0.0004474405,0.5546914,0.006403589,0.001120199,0.008793486,0.0005826814],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7435578,0.000001817908,0.2481371,0.001135417,0.0003213805,0.000871696,0.000006047756,0.0002102472,0.005758462],"genre_scores_gemma":[0.9894375,7.895794e-7,0.00860889,0.001836435,0.00003154971,0.00001103634,0.00002732648,0.000002289664,0.00004420911],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9277513,"threshold_uncertainty_score":0.9960105,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2850470857","doi":"10.1007/s10791-018-9337-y","title":"User interest prediction over future unobserved topics on social networks","year":2018,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Focus (optics); Work (physics); User modeling; Data science; Social network (sociolinguistics); World Wide Web; Social media; User interface; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02993305481423278,"gpt":0.2657125739616944,"spread":0.2357795191474616,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002523861,0.0001026474,0.00009966941,0.00009391858,0.000184497,0.0002959719,0.0003541292,0.000163565,0.00003117758],"category_scores_gemma":[0.0000150515,0.00008801559,0.0000554335,0.0002890206,0.00002347663,0.001748799,0.0001044865,0.000165592,0.00005960936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007324976,"about_ca_system_score_gemma":0.00002334372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009484728,"about_ca_topic_score_gemma":0.00000470562,"domain_scores_codex":[0.9991594,0.00003760323,0.0003200162,0.0001066127,0.0002152843,0.0001611113],"domain_scores_gemma":[0.9993788,0.00001399449,0.000159118,0.0002516738,0.0001538231,0.00004256438],"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":[0.0001406111,0.00006061142,0.001974823,0.00004282581,0.00005605679,0.0000018677,0.004332461,0.00002539295,0.00002988739,0.3346659,0.3609842,0.2976854],"study_design_scores_gemma":[0.0004816231,0.0003973085,0.04223178,0.00003167821,0.000003764766,0.000007133579,0.00008679782,0.05047197,0.0009123939,0.0005057956,0.9046782,0.0001915948],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05724481,0.00001355958,0.9171967,0.003228683,0.006323499,0.0004273863,0.00001287731,0.0009923772,0.01456008],"genre_scores_gemma":[0.9928478,0.000008196766,0.001775813,0.001935623,0.003091968,0.000006827901,0.00003037197,0.000005805956,0.0002976198],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.935603,"threshold_uncertainty_score":0.3589172,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3044191208","doi":"10.1007/s10791-020-09379-9","title":"Robust keyword search in large attributed graphs","year":2020,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":20,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"IBM (Canada); Toronto Metropolitan University; University of Waterloo; Ontario Tech University","funders":"","keywords":"Scalability; Computer science; SPARK (programming language); Theoretical computer science; Set (abstract data type); Graph; Keyword search; Data mining; Information retrieval; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.0316519411098354,"gpt":0.2600099557485858,"spread":0.2283580146387504,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002807771,0.0001024661,0.0001721506,0.0001460681,0.00006406277,0.00008397778,0.0001784701,0.00003056776,0.0009196281],"category_scores_gemma":[0.00001757921,0.0001045639,0.00009170584,0.001211732,0.00001688882,0.0006214853,0.00009380715,0.0002385276,0.0001961084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000258352,"about_ca_system_score_gemma":0.00003862363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005231302,"about_ca_topic_score_gemma":0.000003286784,"domain_scores_codex":[0.998993,0.00004124949,0.0003785297,0.00009519957,0.0002469243,0.0002450823],"domain_scores_gemma":[0.999545,0.00003231157,0.00008597859,0.0001383657,0.0001094953,0.00008889606],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005128373,0.0002535986,0.7076033,0.00008924984,0.0002695606,0.000006342319,0.006181812,0.01736832,0.000240269,0.1727745,0.03774374,0.05695643],"study_design_scores_gemma":[0.004276867,0.0002875272,0.08356037,0.00006498351,0.00006514331,0.000001397142,0.002301052,0.6729969,0.006315765,0.005333474,0.2237639,0.001032656],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6700756,0.00002373601,0.3058002,0.001735778,0.00007143352,0.0006127774,0.0001689673,0.0003322245,0.02117932],"genre_scores_gemma":[0.9984302,0.000001855208,0.000724249,0.0003525063,0.00006274371,0.000004680305,0.0003996193,0.000005377923,0.00001877698],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6556286,"threshold_uncertainty_score":0.9999937,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2056081579","doi":"10.1007/s10791-007-9042-8","title":"Hybrid index maintenance for contiguous inverted lists","year":2008,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"University of Waterloo","keywords":"Merge (version control); Computer science; Inverted index; Information retrieval; Data mining; Search engine indexing","retraction":null,"screen_n_in":null,"score":{"opus":0.01558255272543664,"gpt":0.2299373068822662,"spread":0.2143547541568295,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001782373,0.0001030684,0.0001249523,0.0001076629,0.0002164107,0.000121225,0.0005385965,0.00004955729,0.00001056428],"category_scores_gemma":[0.0001828183,0.00008869423,0.0000540481,0.0002074,0.00004367493,0.003224666,0.0001552298,0.0000933039,0.0001054275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004309748,"about_ca_system_score_gemma":0.0001065969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002036115,"about_ca_topic_score_gemma":3.329671e-7,"domain_scores_codex":[0.9990118,0.00001329992,0.0003221174,0.0001258655,0.0003037895,0.0002231967],"domain_scores_gemma":[0.9990357,0.00005406843,0.0001666286,0.0003688156,0.0002871103,0.00008769828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000638112,0.000150992,0.001587182,0.0001500778,0.00006786099,0.00005423145,0.003872472,0.0008092258,0.0003005463,0.05889479,0.5312862,0.4021884],"study_design_scores_gemma":[0.00137802,0.000115313,0.005220438,0.00002183824,0.000001814185,0.000130692,0.00001316407,0.7236498,0.001872719,0.001282118,0.2661092,0.0002048681],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01690527,0.0000205521,0.9805768,0.0002626763,0.0005469847,0.0002792024,0.00004310091,0.000186465,0.001178954],"genre_scores_gemma":[0.9693955,0.00003012367,0.02793687,0.001981889,0.00009538919,0.00001533187,0.0001453921,0.000006196335,0.0003932998],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9526399,"threshold_uncertainty_score":0.3616846,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2576646839","doi":"10.1007/s10791-016-9292-4","title":"Enhancing click models with mouse movement information","year":2017,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Relevance (law); Computer science; Information retrieval; Search engine; Process (computing); Movement (music); Artificial intelligence; World Wide Web; Human–computer interaction; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01890283138193856,"gpt":0.2518378594100482,"spread":0.2329350280281096,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0007458297,0.000214725,0.0001920592,0.0003168007,0.00101654,0.002861231,0.001379327,0.0001177018,0.00003801582],"category_scores_gemma":[0.0001620892,0.0001730688,0.00007360365,0.0002505794,0.00008388788,0.04976904,0.0003818257,0.000259195,0.0007804157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000150508,"about_ca_system_score_gemma":0.0002404059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000732414,"about_ca_topic_score_gemma":0.000006542178,"domain_scores_codex":[0.9974905,0.00002383472,0.0007633201,0.0001202422,0.001173527,0.000428634],"domain_scores_gemma":[0.9971603,0.00002952202,0.0007533819,0.001108001,0.0007505952,0.0001981729],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008530401,0.0001461092,0.001358564,0.0003846477,0.00012487,0.00001042178,0.02686745,0.01035719,0.0009824913,0.7371527,0.002940977,0.2188216],"study_design_scores_gemma":[0.007303429,0.001382068,0.01478967,0.0001760845,0.00003768646,0.00006110244,0.001507163,0.7228205,0.1669962,0.004903662,0.07814456,0.001877862],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07459474,0.000003416257,0.8994113,0.0008834596,0.0003345208,0.0006300039,0.0000282648,0.0003213146,0.02379304],"genre_scores_gemma":[0.9702352,0.00002258956,0.0258885,0.003067777,0.00006222414,0.00003320225,0.0001163241,0.000008877815,0.0005652608],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8956405,"threshold_uncertainty_score":0.9999976,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4387453959","doi":"10.1007/s10791-023-09421-6","title":"Learning heterogeneous subgraph representations for team discovery","year":2023,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph; York University; Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Overfitting; Ranking (information retrieval); Machine learning; Set (abstract data type); Graph; Task (project management); Artificial intelligence; Baseline (sea); Representation (politics); Data science; Artificial neural network; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01446712919078797,"gpt":0.2738418785845982,"spread":0.2593747493938103,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002369998,0.0001027899,0.0001011972,0.0002775129,0.0002863486,0.0003397961,0.0003853274,0.00005695781,0.000002189165],"category_scores_gemma":[0.0002747815,0.000100838,0.0001105858,0.001460625,0.00003137578,0.004396531,0.0001381954,0.0001379154,0.0001200105],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002482876,"about_ca_system_score_gemma":0.000029264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002065455,"about_ca_topic_score_gemma":6.871988e-7,"domain_scores_codex":[0.9989251,0.00003057215,0.0003233648,0.0001568127,0.0002781244,0.0002860164],"domain_scores_gemma":[0.9990876,0.0002621983,0.000161355,0.0003017118,0.0001248418,0.00006233488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001528263,0.0000247795,0.002493137,0.00005979114,0.00006092834,0.00000802609,0.003578291,0.8198736,0.0006554859,0.04281274,0.01239689,0.1178835],"study_design_scores_gemma":[0.0008326068,0.0003055158,0.004346172,0.00001906635,0.000007823332,0.00003061024,0.0002125565,0.9289084,0.004234688,0.009526776,0.05121839,0.0003573806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1178128,0.00001496244,0.878769,0.0004765447,0.0007023332,0.0004714478,0.00001356019,0.0009456194,0.0007936924],"genre_scores_gemma":[0.9928805,0.00003795397,0.005806231,0.0003788746,0.00008167373,0.00002464279,0.0001629406,0.000009801276,0.0006173337],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8750677,"threshold_uncertainty_score":0.4112054,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121315872","doi":"10.1007/s10791-013-9230-7","title":"Discover hidden web properties by random walk on bipartite graph","year":2013,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; State Key Laboratory of Novel Software Technology; Nanjing University","keywords":"Zipf's law; Crawling; Simple random sample; Random walk; Sampling (signal processing); Bipartite graph; Statistics; Computer science; Sample size determination; Sample (material); Bernoulli's principle; Population; Mathematics; Graph; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.008604713258223986,"gpt":0.189222311925318,"spread":0.180617598667094,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002167648,0.000111514,0.0001025707,0.0001483567,0.0001447471,0.0007285004,0.0003425946,0.00006922973,0.00007060746],"category_scores_gemma":[0.0001031842,0.00008251806,0.00005745373,0.000405515,0.00003132957,0.005295907,0.0000597008,0.0001298966,0.001736952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003806556,"about_ca_system_score_gemma":0.00004039179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000705081,"about_ca_topic_score_gemma":0.000001174872,"domain_scores_codex":[0.9989814,0.00003815541,0.0002793106,0.0001108242,0.0004044168,0.0001859131],"domain_scores_gemma":[0.9993744,0.00003880611,0.0001189313,0.0002867522,0.0001094982,0.00007164221],"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":[0.001306336,0.0002586937,0.00205544,0.000215465,0.000177405,0.000002748483,0.01590895,0.001100304,0.03970342,0.02197419,0.5408679,0.3764291],"study_design_scores_gemma":[0.009899545,0.001587879,0.00938682,0.0002156077,0.00003084236,0.00004112798,0.0002840151,0.3420992,0.2272429,0.008431642,0.3991634,0.001617096],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9132439,0.0001035254,0.06682483,0.003290104,0.001845628,0.0008506338,0.000013309,0.0006033828,0.01322461],"genre_scores_gemma":[0.998154,0.00001487045,0.0002743995,0.001025725,0.00005567139,0.00001972156,0.00001204281,0.000004039427,0.000439483],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.374812,"threshold_uncertainty_score":0.9990403,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2074280490","doi":"10.1007/s10791-011-9168-6","title":"A study of the integration of passage-, document-, and cluster-based information for re-ranking search results","year":2011,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Israel Science Foundation; McGill University","keywords":"Ranking (information retrieval); Computer science; Information retrieval; Context (archaeology); Representation (politics); Query expansion; Task (project management); Cluster (spacecraft); Document retrieval; Data mining; Information integration; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.05817615587411926,"gpt":0.295348948589657,"spread":0.2371727927155378,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001807044,0.0001283612,0.0001801297,0.0003734755,0.0001873044,0.0001484741,0.0005667522,0.00008700838,0.000005719955],"category_scores_gemma":[0.0004808842,0.00009047459,0.00007620132,0.0007912647,0.0000742207,0.005608257,0.0001869612,0.0001565704,0.000005988559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005099894,"about_ca_system_score_gemma":0.0001564089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008231913,"about_ca_topic_score_gemma":0.00001029007,"domain_scores_codex":[0.9976307,0.0001102158,0.001164085,0.00008942556,0.0008115132,0.0001940871],"domain_scores_gemma":[0.9976883,0.0001743264,0.0006812881,0.0004503651,0.0009500984,0.0000556261],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00754975,0.0008110072,0.006681907,0.001113765,0.0001474654,7.999395e-7,0.606445,0.002772077,0.0008060521,0.07019144,0.001072391,0.3024084],"study_design_scores_gemma":[0.03303875,0.01050457,0.1795054,0.0005112298,0.0001542792,0.00002050705,0.04589498,0.4565667,0.2663996,0.002409868,0.003853405,0.001140723],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6980612,0.000002916091,0.2969633,0.0002759153,0.0002780402,0.002272602,0.00004351714,0.00005881267,0.002043716],"genre_scores_gemma":[0.9947947,0.000001673323,0.004958039,0.00016268,0.000008283591,0.00002226932,0.00003302937,0.000002625961,0.00001670363],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.56055,"threshold_uncertainty_score":0.4065851,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2976855657","doi":"10.1007/s10791-019-09364-x","title":"ReBoost: a retrieval-boosted sequence-to-sequence model for neural response generation","year":2019,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Topic Modeling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Computer science; Benchmark (surveying); Conversation; Sequence (biology); Process (computing); Artificial intelligence; Natural language generation; Artificial neural network; Language model; Natural language processing; Recurrent neural network; Machine learning; Natural language; Programming language; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.06926171490965688,"gpt":0.2995985784680832,"spread":0.2303368635584264,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001450704,0.0002161703,0.0002216691,0.0003561389,0.0001814812,0.0004467911,0.0008575641,0.0001681538,0.00001466723],"category_scores_gemma":[0.0008624003,0.0002170535,0.0001017879,0.0007054896,0.00002418436,0.004090133,0.000158905,0.0001911788,0.0003587093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002853267,"about_ca_system_score_gemma":0.0003951143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006716341,"about_ca_topic_score_gemma":0.000001007991,"domain_scores_codex":[0.9976791,0.00009269248,0.0007370894,0.0003689482,0.0006877419,0.0004344753],"domain_scores_gemma":[0.9978774,0.0001736581,0.0002702385,0.0009075433,0.0005895459,0.0001815843],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003132684,0.00003063073,0.0001263696,0.0001189673,0.00002785051,0.000004178572,0.0109792,0.6805344,0.2461183,0.03273423,0.001555016,0.0246382],"study_design_scores_gemma":[0.0007968033,0.0002418384,0.00005211249,0.00002119904,0.000004531062,0.00001968601,0.0000295893,0.9821163,0.01371604,0.00053965,0.002188241,0.0002740068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4081828,0.000006275698,0.5883753,0.001513113,0.0005336319,0.0009094819,0.00003032443,0.0001999773,0.000249058],"genre_scores_gemma":[0.9350578,0.000002122336,0.06088006,0.002997816,0.00009069626,0.00002005989,0.00005538219,0.00001238719,0.0008836364],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5274953,"threshold_uncertainty_score":0.8851187,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2008283248","doi":"10.1007/s10791-013-9220-9","title":"Latent word context model for information retrieval","year":2013,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Ministry of Education, Culture, Sports, Science and Technology","keywords":"Computer science; Latent Dirichlet allocation; Word (group theory); Context (archaeology); Information retrieval; Natural language processing; Latent semantic analysis; Search engine indexing; Topic model; Relevance (law); Artificial intelligence; Probabilistic latent semantic analysis; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02483661079381079,"gpt":0.2376980274101974,"spread":0.2128614166163866,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004929929,0.0001741893,0.0001805844,0.0002603876,0.0001766102,0.0007607176,0.0006563172,0.0001544858,0.0000315356],"category_scores_gemma":[0.0003303098,0.0001635917,0.0001045703,0.0003827318,0.00002617917,0.01487401,0.0001682219,0.0001679377,0.0008800389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000137684,"about_ca_system_score_gemma":0.0001651602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002440699,"about_ca_topic_score_gemma":8.899866e-7,"domain_scores_codex":[0.9981062,0.00001809506,0.0008292467,0.0001351397,0.0005474159,0.0003638866],"domain_scores_gemma":[0.9981827,0.00008106513,0.0003414582,0.0005047977,0.0007487138,0.0001412892],"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":[0.0002635034,0.00004591195,0.0001830645,0.0002365516,0.00006164689,3.685764e-7,0.01754322,0.07628082,0.0002113027,0.2332588,0.01714627,0.6547686],"study_design_scores_gemma":[0.0008563441,0.00005526953,0.0002700482,0.00001529104,0.000004474485,0.000004925474,0.0001034131,0.9815409,0.000651005,0.003883029,0.01240925,0.0002060887],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03142921,0.00001392181,0.9636255,0.001416529,0.0005613189,0.0009803092,0.00001504289,0.0002906279,0.00166753],"genre_scores_gemma":[0.9453468,0.000007021092,0.05118074,0.002989806,0.00006534528,0.00003491534,0.00007345893,0.000006231357,0.0002956708],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9139176,"threshold_uncertainty_score":0.9998979,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2062626555","doi":"10.1007/s10791-009-9105-0","title":"Swapping documents and terms","year":2009,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Agricultural Research Development Agency","keywords":"Relevance feedback; Computer science; Information retrieval; Relevance (law); Query expansion; Data mining; Artificial intelligence; Image retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.009581800700385145,"gpt":0.2530781925278839,"spread":0.2434963918274988,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003266942,0.000100472,0.00009594345,0.0002060283,0.0001717687,0.000580398,0.0003307436,0.00006089912,0.00003480637],"category_scores_gemma":[0.00007188461,0.00008678935,0.00003260349,0.0004189861,0.00002384374,0.007054247,0.00008570192,0.0001263357,0.0003540281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003918214,"about_ca_system_score_gemma":0.00003747901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003828765,"about_ca_topic_score_gemma":8.597794e-8,"domain_scores_codex":[0.9988753,0.00001611579,0.0003515054,0.00008516246,0.000444609,0.000227294],"domain_scores_gemma":[0.9994001,0.00002095394,0.0001149208,0.0002208034,0.0001221484,0.0001210679],"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":[0.00005036402,0.00002758667,0.0003807906,0.00002176549,0.000008630208,0.000004383724,0.003886712,0.00001423846,0.0004600986,0.1039124,0.002026084,0.8892069],"study_design_scores_gemma":[0.006019909,0.001964118,0.3720127,0.000140274,0.00002548816,0.0003751983,0.0005129598,0.1287145,0.02334466,0.02200111,0.4430757,0.001813409],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3445991,0.00006302138,0.5440471,0.005452713,0.0008328023,0.0009229107,0.00001250702,0.0009065008,0.1031634],"genre_scores_gemma":[0.9906166,0.00002315594,0.005911984,0.00304917,0.00002972157,0.000001818746,0.00001671843,0.000001698918,0.0003490875],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8873935,"threshold_uncertainty_score":0.5596791,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2069744915","doi":"10.1007/s10791-012-9192-1","title":"Extended structural relevance framework: a framework for evaluating structured document retrieval","year":2012,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":3,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Relevance (law); Information retrieval; Redundancy (engineering); Probabilistic logic; Task (project management); Tree (set theory); Data mining; Range (aeronautics); Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03216634289591799,"gpt":0.3490464434591703,"spread":0.3168801005632523,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002230343,0.000434599,0.0004158978,0.0003853019,0.0007229766,0.0009118169,0.001257803,0.0004721436,0.0002822595],"category_scores_gemma":[0.005255644,0.0003838698,0.0002686558,0.001384317,0.0001058509,0.011237,0.0003647286,0.0008066576,0.0002679526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003894376,"about_ca_system_score_gemma":0.000295776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004061358,"about_ca_topic_score_gemma":1.446623e-7,"domain_scores_codex":[0.9950216,0.0001375364,0.00135124,0.0003063147,0.001914777,0.001268535],"domain_scores_gemma":[0.9957963,0.0009475234,0.0007894472,0.0009595088,0.001024024,0.0004832326],"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":[0.001003433,0.00003879215,0.0004622402,0.0002072594,0.00007269971,0.000001100411,0.01151523,0.0002696196,0.0004482938,0.8474795,0.0005248997,0.1379769],"study_design_scores_gemma":[0.008313396,0.003479715,0.06419552,0.0006424112,0.000233714,0.0003519274,0.002557546,0.2720647,0.09141935,0.4913899,0.06072437,0.004627453],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1229336,0.0001503898,0.8706788,0.00067144,0.003095519,0.001556578,0.0000651526,0.0004642099,0.0003842298],"genre_scores_gemma":[0.6544176,0.00001383399,0.3438435,0.001148151,0.0003648122,0.00003290896,0.00007571754,0.00001771093,0.00008573438],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5314841,"threshold_uncertainty_score":0.9998613,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3133365413","doi":"10.1007/s10791-021-09398-0","title":"Neural ranking models for document retrieval","year":2021,"lang":"en","type":"preprint","venue":"Information Retrieval","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; National Institute of Standards and Technology; Institute for Catastrophic Loss Reduction; National Science Foundation","keywords":"Ranking (information retrieval); Computer science; Artificial intelligence; Machine learning; Set (abstract data type); Variety (cybernetics); Information retrieval; Artificial neural network; Deep learning; Learning to rank; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.02256006568427007,"gpt":0.2916584035119547,"spread":0.2690983378276846,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000976382,0.0003757549,0.0004195159,0.0003287749,0.0003086005,0.001874109,0.001695591,0.0003958014,0.00002584736],"category_scores_gemma":[0.0004730223,0.0004025093,0.0003272566,0.0005527239,0.00003975575,0.002980573,0.001680011,0.0009526065,0.00004781018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000288609,"about_ca_system_score_gemma":0.0004656279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001035654,"about_ca_topic_score_gemma":0.000001368526,"domain_scores_codex":[0.9970396,0.0001041552,0.001003964,0.0005231541,0.000882239,0.0004468695],"domain_scores_gemma":[0.9965968,0.0002739785,0.0007667113,0.001382972,0.000819331,0.0001602602],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001891297,0.00005924394,0.00007008817,0.000616852,0.0001318132,0.000003048625,0.006593277,0.8637565,0.0001314774,0.07432712,0.0006576356,0.05346381],"study_design_scores_gemma":[0.0007125494,0.00005218892,0.0005041033,0.00007367885,0.00002539051,0.00001282545,0.00004869489,0.9826886,0.0006501641,0.01232996,0.002477426,0.0004244148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04124403,0.0001131043,0.951335,0.002535166,0.001394367,0.001463559,0.00004483762,0.0005711074,0.001298793],"genre_scores_gemma":[0.8614902,0.00002028115,0.1365261,0.0008894645,0.0001994449,0.00009800235,0.0006880732,0.00002163317,0.00006673157],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8202462,"threshold_uncertainty_score":0.9998427,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2584295907","doi":"10.1007/s10791-017-9294-x","title":"Constructing click models for search users","year":2017,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; World Wide Web; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.05359408056046548,"gpt":0.3126871301685992,"spread":0.2590930496081337,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006205535,0.00009512767,0.0001149274,0.0001126883,0.0006293505,0.00117237,0.001095952,0.00008586996,0.000006866044],"category_scores_gemma":[0.0003170047,0.00008933809,0.00007500972,0.0001172988,0.0001035341,0.006956673,0.000193882,0.0001156049,0.00005324483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007630504,"about_ca_system_score_gemma":0.000117926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001216876,"about_ca_topic_score_gemma":4.367829e-7,"domain_scores_codex":[0.9989709,0.00001618834,0.0003280046,0.0001314543,0.0003255624,0.0002278555],"domain_scores_gemma":[0.9984071,0.00007325532,0.0002878394,0.0007009074,0.0004553317,0.0000756256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004301227,0.000009681312,0.000236124,0.00004906723,0.00001220241,4.001907e-7,0.0006245333,0.00002188119,0.0002137804,0.6774265,0.0006016318,0.3207612],"study_design_scores_gemma":[0.0008813962,0.0001298972,0.0006798824,0.0000307584,0.000006494103,0.00002117404,0.0003421254,0.8454003,0.1157181,0.01943032,0.0170392,0.0003203222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002189076,0.000006000443,0.9805351,0.001524999,0.0002572984,0.0003600296,0.00001673726,0.0002699179,0.01484085],"genre_scores_gemma":[0.8895741,0.00001354942,0.1096337,0.0003460507,0.00006788102,0.0000160475,0.00002178638,0.000006122719,0.0003206956],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8873851,"threshold_uncertainty_score":0.9998645,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2803782109","doi":"10.1007/s10791-018-9332-3","title":"(CF)2 architecture: contextual collaborative filtering","year":2018,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Oakville-Trafalgar Memorial Hospital; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Collaborative filtering; Computer science; Recommender system; Context (archaeology); Architecture; The Internet; Selection (genetic algorithm); Fraction (chemistry); Machine learning; Scale (ratio); Artificial intelligence; Contextual design; Filter (signal processing); Information retrieval; Data science; World Wide Web; Human–computer interaction","retraction":null,"screen_n_in":null,"score":{"opus":0.01103614124488447,"gpt":0.2479555254115812,"spread":0.2369193841666967,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002917208,0.0001008674,0.0001146189,0.0001404244,0.0001422685,0.0003434375,0.0004318013,0.0000617633,0.00003299108],"category_scores_gemma":[0.00007161121,0.0000858862,0.00003260127,0.000501385,0.00005006672,0.001780584,0.000148298,0.00009592235,0.0002163107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004030928,"about_ca_system_score_gemma":0.00006809886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001259881,"about_ca_topic_score_gemma":0.000004886374,"domain_scores_codex":[0.999128,0.00004046856,0.0003115129,0.0001032489,0.0002434885,0.0001733191],"domain_scores_gemma":[0.9991351,0.00004205893,0.000154798,0.0003025818,0.0003036635,0.00006178449],"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":[0.0001540137,0.00004381876,0.0003142883,0.00007599805,0.00009018445,0.000005344052,0.03522752,0.00001831054,0.002790363,0.2796016,0.05645462,0.6252239],"study_design_scores_gemma":[0.0006616793,0.000732184,0.0008712409,0.00004955779,0.000002952451,0.00006345531,0.0003094287,0.009323559,0.1025864,0.00323473,0.8818018,0.0003630052],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00581958,0.00001270129,0.9598922,0.0006531852,0.0006009172,0.000235338,0.000008559334,0.0003860067,0.0323915],"genre_scores_gemma":[0.9643563,0.000003070033,0.03435906,0.000993046,0.00016344,0.00000846122,0.000007479706,0.000003849068,0.0001052965],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9585367,"threshold_uncertainty_score":0.3502337,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2000952055","doi":"10.1007/s10791-006-9397-2","title":"Introduction to the special issue on the 27th European Conference on Information Retrieval Research","year":2006,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"University of Waterloo","keywords":"Information retrieval; Political science; Library science; Data science; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.03850458048473922,"gpt":0.2941051982642033,"spread":0.2556006177794641,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006372033,0.0002794393,0.0001851687,0.0007383103,0.001413521,0.002414212,0.001934026,0.0001237123,0.0006059597],"category_scores_gemma":[0.001399937,0.000170062,0.0001100042,0.002874594,0.0001798838,0.005404626,0.0004121944,0.001075944,0.0271589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000332579,"about_ca_system_score_gemma":0.0002300834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004172732,"about_ca_topic_score_gemma":0.000004564107,"domain_scores_codex":[0.994451,0.0006231013,0.001032171,0.0002455096,0.00295847,0.0006897327],"domain_scores_gemma":[0.9962813,0.0003486354,0.0003338312,0.001203275,0.001668413,0.0001645591],"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":[0.0005496198,0.00005321003,0.000011047,0.00001671329,0.000009044934,0.000001897927,0.004800342,0.001469427,0.00006672664,0.3691554,0.5704607,0.05340579],"study_design_scores_gemma":[0.000459438,0.000684443,0.004220283,0.00002570261,0.000004086228,0.00001469264,0.00068055,0.007979034,0.004325734,0.0006853837,0.9806615,0.0002591215],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.06710988,0.000007129245,0.05775145,0.2747535,0.007272895,0.004937622,0.0001462372,0.0007929472,0.5872284],"genre_scores_gemma":[0.9448259,0.00003299089,0.001164397,0.01694354,0.02966301,0.00006288366,0.0005183354,0.00003723094,0.006751745],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.877716,"threshold_uncertainty_score":0.9998865,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}