{"meta":{"query_hash":"d932170372cf","filters":{"venue":"Text REtrieval Conference"},"cohort_total":70,"direct_labels_cover":0,"predictions_cover":70,"exported":70,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/d932170372cf","api":"https://metacan.xera.ac/api/v1/cohort?venue=Text+REtrieval+Conference"},"results":[{"id":"W125929235","doi":"","title":"In Enterprise Search: Methods to Identify Argumentative Discussions and to Find Topical Experts.","year":2006,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Argumentative; Computer science; Ranking (information retrieval); Argument (complex analysis); Information retrieval; Rank (graph theory); World Wide Web; Topic model; Data science; Mathematics","score_opus":0.061267112044445654,"score_gpt":0.41117530078168313,"score_spread":0.3499081887372375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W125929235","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4497984,0.000090087124,0.5411358,0.00648426,0.0003680581,0.00038065633,0.000004835824,0.00006307259,0.0016748772],"genre_scores_gemma":[0.9454991,0.000005459924,0.049989726,0.0004644994,0.000072465176,0.000023193043,0.000001443493,0.0000080136615,0.003936089],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99790645,0.0003791001,0.00034404735,0.00061139354,0.00034698483,0.00041200884],"domain_scores_gemma":[0.9989056,0.00027802773,0.000041345465,0.00043222037,0.00007759659,0.00026519984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062869216,0.0001818145,0.0002914577,0.00024828917,0.000118726726,0.0003438849,0.0006407358,0.00008122911,0.00005780815],"category_scores_gemma":[0.00018786827,0.00014312612,0.000043062166,0.00064253603,0.00005412406,0.00032920152,0.00055776903,0.0001745335,0.00008074226],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003061886,0.0005534168,0.02330312,0.0000867686,0.000044207194,0.0002827744,0.106588334,0.00007149271,0.5290592,0.205779,0.018154368,0.11577114],"study_design_scores_gemma":[0.0034251765,0.0018904479,0.59325767,0.0012658314,0.000022026788,0.0001695713,0.006643512,0.018454561,0.30638564,0.01852496,0.047150742,0.0028098824],"about_ca_topic_score_codex":0.00062518567,"about_ca_topic_score_gemma":0.00007551685,"teacher_disagreement_score":0.5699545,"about_ca_system_score_codex":0.00009838646,"about_ca_system_score_gemma":0.00007016785,"threshold_uncertainty_score":0.58365136},"labels":[],"label_agreement":null},{"id":"W1503829033","doi":"","title":"Experiments with the Negotiated Boolean Queries of the TREC 2008 Legal Track","year":2008,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Open Text (Canada)","funders":"","keywords":"Relevance (law); Task (project management); Computer science; Relevance feedback; Information retrieval; Recall; Standard Boolean model; Rank (graph theory); Boolean expression; Learning to rank; Boolean network; And-inverter graph; Theoretical computer science; Boolean function; Data mining; Artificial intelligence; Algorithm; Mathematics; Ranking (information retrieval); Combinatorics; Psychology; Cognitive psychology","score_opus":0.04573418768938414,"score_gpt":0.24959330938408245,"score_spread":0.2038591216946983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1503829033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89479846,0.00023227665,0.09706339,0.001986193,0.00022374536,0.00029404278,0.000002964742,0.00010922263,0.005289692],"genre_scores_gemma":[0.9958075,0.000017466298,0.0016604421,0.0002308659,0.000032408923,0.0000041478447,5.4293344e-7,0.000008649295,0.0022379665],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984827,0.000121320154,0.00024721184,0.00033790313,0.00053855364,0.00027230298],"domain_scores_gemma":[0.998547,0.00007792337,0.00016676719,0.0009638192,0.00018453594,0.00005992593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016668552,0.00017150627,0.00019767006,0.00003203595,0.00027528717,0.00008105252,0.0015046583,0.00005734408,0.000058681297],"category_scores_gemma":[0.000056527322,0.00009000124,0.000064572436,0.00044131387,0.00038988853,0.00036490322,0.00024173335,0.00024053798,0.000015253346],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014558322,0.001126009,0.03629505,0.00017454808,0.0005630305,0.00037862835,0.12968093,0.002577599,0.09982333,0.6560469,0.014034887,0.057843227],"study_design_scores_gemma":[0.0044468082,0.001420549,0.11552779,0.00042216553,0.00008454494,0.0008854013,0.0027135385,0.13535208,0.7044419,0.0019854542,0.03082487,0.0018948984],"about_ca_topic_score_codex":0.00025167374,"about_ca_topic_score_gemma":0.000048918584,"teacher_disagreement_score":0.6540615,"about_ca_system_score_codex":0.000029379738,"about_ca_system_score_gemma":0.00036970296,"threshold_uncertainty_score":0.3670144},"labels":[],"label_agreement":null},{"id":"W161736330","doi":"","title":"Approaches to High Accuracy Retrieval: Phrase-Based Search Experiments in the HARD Track.","year":2004,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Focus (optics); Phrase; Selection (genetic algorithm); Natural language processing; Word (group theory); Artificial intelligence; Noun phrase; Noun; Information retrieval; Mathematics","score_opus":0.1651441880432227,"score_gpt":0.33111074693969944,"score_spread":0.16596655889647674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W161736330","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4219636,0.0010130819,0.5574816,0.016328277,0.00020815429,0.0014561147,0.000012110032,0.000897758,0.00063930626],"genre_scores_gemma":[0.85114664,0.000008469591,0.14726627,0.0014083895,0.000051904026,0.00002382485,0.000008491839,0.000018976789,0.00006704013],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9966598,0.00026337392,0.00042588485,0.00085718423,0.0011285845,0.00066517404],"domain_scores_gemma":[0.99797463,0.00029004965,0.00012212897,0.0012558547,0.00018112415,0.00017623529],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013806949,0.0003373413,0.00032580225,0.00030400982,0.00019198818,0.000778665,0.0035817432,0.0001809997,0.000040815998],"category_scores_gemma":[0.00072568376,0.0002478734,0.00008389514,0.0020561072,0.00014132189,0.000745538,0.00037887064,0.00072419486,0.00010785555],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014886009,0.0016321423,0.0006945869,0.00030806952,0.000056241042,0.00067186315,0.034754056,0.000609999,0.15370344,0.7007619,0.00080704945,0.104512036],"study_design_scores_gemma":[0.0015857719,0.0005805323,0.0023877705,0.00031288218,0.000010837614,0.000031055093,0.00035613865,0.0032197167,0.9441438,0.046156768,0.00041570637,0.0007990714],"about_ca_topic_score_codex":0.00022308917,"about_ca_topic_score_gemma":0.000013822144,"teacher_disagreement_score":0.7904403,"about_ca_system_score_codex":0.00025882077,"about_ca_system_score_gemma":0.0006165315,"threshold_uncertainty_score":0.9999974},"labels":[],"label_agreement":null},{"id":"W165780999","doi":"","title":"DalTREC 2005 Spam Track: Spam Filtering using N-gram-based Techniques","year":2005,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; n-gram; Track (disk drive); Spambot; Computer network; Spamming; World Wide Web; Artificial intelligence; Operating system; The Internet","score_opus":0.046815254187237254,"score_gpt":0.2834078574464462,"score_spread":0.23659260325920894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W165780999","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14748447,0.00017846175,0.8454019,0.0011173227,0.00051373336,0.0003192827,0.000006841769,0.0012038812,0.0037741126],"genre_scores_gemma":[0.9057441,0.000022497008,0.0931314,0.0003807597,0.00034422713,0.000005061671,0.0000037719437,0.000020677484,0.00034755404],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978703,0.00010072776,0.00037148083,0.0006254285,0.00047564105,0.0005563873],"domain_scores_gemma":[0.9985543,0.00011719544,0.00018263476,0.00077225047,0.0001801114,0.00019352848],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005912915,0.00028409017,0.00027338383,0.00022963235,0.00024858434,0.00054601574,0.0010139474,0.00018525466,0.00025180748],"category_scores_gemma":[0.00012975176,0.0002866797,0.00010863059,0.0005888816,0.000090356945,0.000933097,0.00016547527,0.0003947852,0.000118145355],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024006206,0.00036167065,0.001546158,0.00013997579,0.00005243057,0.000057957317,0.0011927802,0.0018925009,0.3957789,0.011833586,0.0017336042,0.5851704],"study_design_scores_gemma":[0.00033173608,0.00018506369,0.0007188177,0.00015398247,0.00001572205,0.00003836331,0.0000132076975,0.4902335,0.47555512,0.00069911714,0.03152976,0.00052559894],"about_ca_topic_score_codex":0.0001460092,"about_ca_topic_score_gemma":0.000062907704,"teacher_disagreement_score":0.7582596,"about_ca_system_score_codex":0.00019837849,"about_ca_system_score_gemma":0.00029093627,"threshold_uncertainty_score":0.9999585},"labels":[],"label_agreement":null},{"id":"W1878790362","doi":"10.3390/ijms232113127","title":"Overview of the TREC 2012 Contextual Suggestion Track.","year":2012,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Track (disk drive); Computer science; Context (archaeology); Information retrieval; Task (project management); Set (abstract data type); World Wide Web; Data science; Geography; Engineering","score_opus":0.09325439221598353,"score_gpt":0.3162031300342015,"score_spread":0.22294873781821795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1878790362","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8817296,0.0025904016,0.09075242,0.0024443734,0.0022787128,0.0011340478,0.00005518946,0.00030187448,0.018713392],"genre_scores_gemma":[0.9973133,0.00007584964,0.0005211904,0.00021536941,0.000057015597,0.0000038908415,0.0000035525254,0.0000054231505,0.0018043927],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99813306,0.00016736193,0.0004129577,0.00016792615,0.00069833524,0.00042036726],"domain_scores_gemma":[0.9984732,0.00014491208,0.00022714368,0.00061987777,0.0003701922,0.00016465018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084969006,0.00015843284,0.00022056526,0.00007530746,0.00014368151,0.000093040326,0.0010755901,0.00010610026,0.00043943134],"category_scores_gemma":[0.00023644912,0.00010498621,0.00013077784,0.0007089788,0.00016008508,0.0016568347,0.00027634623,0.00027439193,0.00023580773],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098079014,0.00029130108,0.010101892,0.000121039426,0.000025707579,0.0000013466644,0.0048011183,0.0000031945387,0.008761893,0.8103043,0.0020396556,0.16345046],"study_design_scores_gemma":[0.0020012413,0.0004963327,0.76842344,0.00032384973,0.0000746888,0.00009798446,0.00037287062,0.0067154057,0.1514352,0.0025587496,0.06652452,0.00097573217],"about_ca_topic_score_codex":0.000030977924,"about_ca_topic_score_gemma":0.000004949593,"teacher_disagreement_score":0.8077456,"about_ca_system_score_codex":0.000050992927,"about_ca_system_score_gemma":0.00020724896,"threshold_uncertainty_score":0.4811465},"labels":[],"label_agreement":null},{"id":"W2115057477","doi":"","title":"York University at TREC 2006: Enterprise Email Discussion Search","year":2006,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Information retrieval; Thread (computing); Ranking (information retrieval); Search engine; Word (group theory); Document retrieval; Rank (graph theory); Query expansion; World Wide Web","score_opus":0.025149645107489006,"score_gpt":0.24079465806604977,"score_spread":0.21564501295856076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115057477","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7569639,0.00008334635,0.18539183,0.0029520988,0.00055515673,0.0006971783,0.00009130452,0.00068593357,0.05257926],"genre_scores_gemma":[0.95159405,0.000019179859,0.0014993271,0.000071110764,0.00004823256,7.0295033e-7,0.000030556464,0.000007498299,0.04672931],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99772435,0.00015508934,0.00029803842,0.00043200445,0.000848763,0.00054175925],"domain_scores_gemma":[0.99870527,0.00007796547,0.00010536856,0.00060890964,0.00028115764,0.00022130302],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000432185,0.00021105997,0.00021778743,0.00021414063,0.00045100588,0.00026522437,0.0012189678,0.0001301932,0.0006314731],"category_scores_gemma":[0.000031966647,0.0001538929,0.00011914986,0.0009412284,0.000160035,0.0008333632,0.0006988372,0.00030273278,0.0011433773],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003032052,0.0016575324,0.1010874,0.00033904542,0.00009660204,0.0009077431,0.012855753,0.00027240373,0.06691819,0.52361417,0.057093978,0.2321251],"study_design_scores_gemma":[0.00804271,0.0017255496,0.38930014,0.0004269054,0.00009470054,0.00022324301,0.001715499,0.12369378,0.11418276,0.0032816029,0.35364363,0.00366947],"about_ca_topic_score_codex":0.00032990883,"about_ca_topic_score_gemma":0.000078769524,"teacher_disagreement_score":0.5203326,"about_ca_system_score_codex":0.0002869298,"about_ca_system_score_gemma":0.00026855143,"threshold_uncertainty_score":0.9996343},"labels":[],"label_agreement":null},{"id":"W2121587139","doi":"","title":"York University at TREC 2009: Relevance Feedback Track","year":2009,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Relevance feedback; Relevance (law); Computer science; Weighting; Task (project management); Track (disk drive); Domain (mathematical analysis); Information retrieval; Series (stratigraphy); Artificial intelligence; Mathematics; Engineering; Image retrieval","score_opus":0.03342038611951475,"score_gpt":0.24673428687266485,"score_spread":0.2133139007531501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121587139","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7222897,0.0003700492,0.14599767,0.0065185204,0.00083791773,0.0010010047,0.00007858378,0.0014336957,0.121472865],"genre_scores_gemma":[0.97175854,0.00011294419,0.0038179178,0.0005121716,0.000041874006,3.3315092e-7,0.000010945291,0.0000056381755,0.023739643],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978891,0.00009830341,0.00031200045,0.0004669753,0.00068284076,0.000550768],"domain_scores_gemma":[0.9983705,0.00012065081,0.00016373549,0.000708518,0.00033826876,0.0002983088],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00036454672,0.00023596312,0.0002610778,0.00015437466,0.0003659309,0.00022212134,0.0014542416,0.0001531299,0.00043833896],"category_scores_gemma":[0.00012725349,0.00022722324,0.00011945303,0.0011389841,0.0001227053,0.0011024754,0.00020871154,0.0003500649,0.0015008793],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014023851,0.0005125119,0.0013474484,0.000067644134,0.000042132837,0.00032047677,0.00705452,0.00007450154,0.023032745,0.44028485,0.025432067,0.50042874],"study_design_scores_gemma":[0.006594076,0.003220695,0.22269589,0.00029251003,0.000081194055,0.00028556556,0.0006660166,0.06114883,0.09923125,0.009851556,0.5924993,0.0034330948],"about_ca_topic_score_codex":0.000022459995,"about_ca_topic_score_gemma":0.000009981302,"teacher_disagreement_score":0.56706727,"about_ca_system_score_codex":0.00026226116,"about_ca_system_score_gemma":0.00029655732,"threshold_uncertainty_score":0.9992766},"labels":[],"label_agreement":null},{"id":"W2128027916","doi":"","title":"University of Waterloo at TREC 2008 Blog track","year":2008,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Lexicon; Divergence (linguistics); Information retrieval; Natural language processing; Matching (statistics); Track (disk drive); Artificial intelligence; Polarity (international relations); Linguistics; Statistics; Mathematics","score_opus":0.030359246017418007,"score_gpt":0.23594040493848395,"score_spread":0.20558115892106593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128027916","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68257105,0.0001644163,0.3077005,0.0003244411,0.0000662171,0.0001784209,0.000008178374,0.00050622865,0.008480538],"genre_scores_gemma":[0.96156996,0.0002946039,0.027450098,0.00003676345,0.00001263557,2.540736e-7,0.000004497569,0.00000753289,0.010623625],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985034,0.00008036894,0.00024218246,0.0004822871,0.00038691444,0.00030485942],"domain_scores_gemma":[0.9985029,0.000087117354,0.00019358678,0.0008049305,0.00028653748,0.00012492845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001675855,0.00017919378,0.0003451393,0.0001436591,0.00020434953,0.000016554191,0.0012956932,0.0001118573,0.00033241662],"category_scores_gemma":[0.00004183899,0.00017864237,0.00013585365,0.000658846,0.00034209827,0.0004514242,0.00042771947,0.0001713289,0.00016833509],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013537076,0.0017034105,0.05193028,0.00024164774,0.0006142288,0.002528308,0.035905957,0.00019946172,0.48913866,0.2366367,0.021762175,0.15798545],"study_design_scores_gemma":[0.0025257366,0.001105144,0.04415562,0.00013816499,0.00012320427,0.00041769465,0.0003632955,0.03444808,0.8655317,0.020745624,0.028525086,0.0019206916],"about_ca_topic_score_codex":0.00014396421,"about_ca_topic_score_gemma":0.00007897935,"teacher_disagreement_score":0.376393,"about_ca_system_score_codex":0.00010070804,"about_ca_system_score_gemma":0.00013936035,"threshold_uncertainty_score":0.7284825},"labels":[],"label_agreement":null},{"id":"W2132630274","doi":"","title":"York University at TREC 2012: Medical Records Track","year":2012,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Track (disk drive); Computer science; Information retrieval; Medical record; Work (physics); Artificial intelligence; Medicine; Engineering","score_opus":0.03818721144490055,"score_gpt":0.2545070467609054,"score_spread":0.21631983531600485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132630274","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15535916,0.0014177737,0.78210515,0.0021867026,0.0031092218,0.00033787475,0.00005639029,0.00073677703,0.05469096],"genre_scores_gemma":[0.9782911,0.00017633168,0.00979845,0.00021139234,0.0002578208,4.5395043e-7,0.000018805908,0.000009243607,0.011236398],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980978,0.0001431028,0.00018857546,0.00039123854,0.0006884951,0.0004908069],"domain_scores_gemma":[0.99838454,0.00017970573,0.000102868806,0.000697599,0.0000923513,0.0005429208],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00056751794,0.00017281718,0.00021072259,0.00007451197,0.00024079246,0.0000756497,0.0014713628,0.00018710313,0.0025554218],"category_scores_gemma":[0.00012065149,0.0001517618,0.00006879496,0.00043005878,0.000116974945,0.001169322,0.0009346745,0.00029446924,0.0008982558],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041718554,0.0006599082,0.013484522,0.000057624016,0.000070163354,0.0001683086,0.0030086057,0.0000021604938,0.0014276187,0.20134278,0.13416587,0.64519525],"study_design_scores_gemma":[0.0013511026,0.00025025866,0.044729598,0.00014056974,0.000026348367,0.00015014944,0.00012407164,0.035170943,0.002965439,0.0008965302,0.9133415,0.00085345784],"about_ca_topic_score_codex":0.00009658392,"about_ca_topic_score_gemma":0.00002935853,"teacher_disagreement_score":0.82293195,"about_ca_system_score_codex":0.00011405443,"about_ca_system_score_gemma":0.00022009746,"threshold_uncertainty_score":0.99987966},"labels":[],"label_agreement":null},{"id":"W2135220386","doi":"","title":"Query-Structure Based Web Page Indexing","year":2012,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Search engine indexing; Computer science; Information retrieval; Web page; Index (typography); World Wide Web; Web search query; Set (abstract data type); Static web page; Search engine; Web navigation","score_opus":0.02983501488973424,"score_gpt":0.2575284238493121,"score_spread":0.22769340895957788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135220386","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5254001,0.00043945457,0.46156457,0.0013478018,0.0008526247,0.00017180303,0.000087468274,0.0006591912,0.009476984],"genre_scores_gemma":[0.98676157,0.000006626713,0.012114994,0.00045853955,0.00014987579,0.0000012494436,0.000023413593,0.000010023481,0.00047370148],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998266,0.000118607044,0.00024330651,0.0003938723,0.00044743388,0.0005308116],"domain_scores_gemma":[0.9984823,0.00014123706,0.0001277958,0.0008802031,0.00012455086,0.00024389956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047264446,0.00020545776,0.0002463058,0.0001632148,0.00016361047,0.00030009376,0.0011560862,0.00012524195,0.00042763603],"category_scores_gemma":[0.00024174913,0.00017754229,0.00008542009,0.0008196693,0.00007201338,0.0008473704,0.0002687557,0.0003166785,0.00018903098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014095906,0.000494983,0.17752604,0.00023800948,0.00031010393,0.00010957668,0.0054664975,0.00012689496,0.33675018,0.3039359,0.012336793,0.16256407],"study_design_scores_gemma":[0.0025039478,0.0003342171,0.049309812,0.00035756954,0.00019470284,0.00008734409,0.00035630906,0.744475,0.10854765,0.003665393,0.08726138,0.0029066978],"about_ca_topic_score_codex":0.000029803787,"about_ca_topic_score_gemma":0.000008939095,"teacher_disagreement_score":0.7443481,"about_ca_system_score_codex":0.000042418844,"about_ca_system_score_gemma":0.0002476768,"threshold_uncertainty_score":0.7239964},"labels":[],"label_agreement":null},{"id":"W2142018130","doi":"","title":"DalTREC 2006 QA System Jellyfish: Regular Expressions Mark-and-Match Approach to Question Answering","year":2006,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Question answering; Rewriting; Computer science; Jellyfish; Robustness (evolution); Regular expression; Artificial intelligence; Architecture; Natural language processing; Information retrieval; Programming language","score_opus":0.02211898084258234,"score_gpt":0.2386022074487429,"score_spread":0.21648322660616054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142018130","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10137213,0.00020558875,0.87850267,0.00034291908,0.0002681627,0.00036389127,0.0000062372374,0.00045291134,0.018485503],"genre_scores_gemma":[0.9194544,0.0000072202715,0.07863701,0.000060556897,0.00013874518,0.000017926874,0.0000068815034,0.000016034293,0.0016612216],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976109,0.00015455374,0.0004393385,0.00082189107,0.0005111584,0.00046210736],"domain_scores_gemma":[0.9984661,0.00008087745,0.0001265688,0.0009185041,0.00020394262,0.0002040503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065150234,0.0002547745,0.00030698034,0.0001569055,0.00022840277,0.0003975679,0.0008796937,0.00014558526,0.00000896307],"category_scores_gemma":[0.00007443455,0.00024294782,0.00005164683,0.00047933566,0.00004795579,0.00046801975,0.00045557562,0.0002377255,0.000049903647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076177814,0.00018222809,0.0029042447,0.0004997601,0.000027138716,0.000043328575,0.0017531505,0.0044115963,0.041241188,0.9222208,0.0019844344,0.024655936],"study_design_scores_gemma":[0.0009714282,0.00017398848,0.01279231,0.0011549642,0.000041658743,0.00017933952,0.00051283045,0.9509105,0.01932043,0.0056797382,0.006831346,0.0014314639],"about_ca_topic_score_codex":0.00054125127,"about_ca_topic_score_gemma":0.000014080718,"teacher_disagreement_score":0.94649893,"about_ca_system_score_codex":0.00011723482,"about_ca_system_score_gemma":0.00011050159,"threshold_uncertainty_score":0.99071246},"labels":[],"label_agreement":null},{"id":"W2142564378","doi":"","title":"Distributed EDLSI, BM25, and Power Norm at TREC 2008","year":2008,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Normalization (sociology); Weighting; Information retrieval; Search engine indexing; Vector space model; Data mining; Relevance feedback; Relevance (law); Artificial intelligence; Image retrieval","score_opus":0.03705805193682006,"score_gpt":0.24251510019953243,"score_spread":0.20545704826271238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142564378","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6383957,0.00040909284,0.3530188,0.0010343043,0.00031000059,0.0001838987,0.000020750764,0.00025804646,0.006369414],"genre_scores_gemma":[0.9928614,0.000113855174,0.0043918467,0.00020023949,0.00004200975,0.0000027073852,0.00000908904,0.000009147306,0.0023696905],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822265,0.000051846084,0.00028947127,0.0006125738,0.00040796105,0.0004154734],"domain_scores_gemma":[0.99866664,0.00010844202,0.00009931781,0.00073263206,0.00017318332,0.00021977261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018419014,0.0002114084,0.00025466154,0.00007186689,0.0002837119,0.00010299537,0.0007259413,0.000117234544,0.00022369341],"category_scores_gemma":[0.00014400005,0.00019498375,0.000051326464,0.00035934837,0.00016410263,0.00038928312,0.00057559024,0.00021491101,0.00017631751],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011903795,0.0011038432,0.22307515,0.00030778066,0.0004069713,0.002774865,0.032846246,0.0004026659,0.051000737,0.4734125,0.05661174,0.15686712],"study_design_scores_gemma":[0.0067130444,0.0013904172,0.38996708,0.00029117445,0.000066397944,0.003029998,0.00022221287,0.41930586,0.039303534,0.012954758,0.12249586,0.0042596585],"about_ca_topic_score_codex":0.000051028735,"about_ca_topic_score_gemma":0.00001831666,"teacher_disagreement_score":0.46045774,"about_ca_system_score_codex":0.00009295505,"about_ca_system_score_gemma":0.00017263062,"threshold_uncertainty_score":0.7951206},"labels":[],"label_agreement":null},{"id":"W2145841197","doi":"","title":"Selecting versus Describing: A Preliminary Analysis of the Efficacy of Categories in Exploring the Web","year":2001,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Task (project management); Session (web analytics); Directory; Computer science; Information retrieval; Point (geometry); Rating scale; Certainty; Scale (ratio); Process (computing); Psychology; World Wide Web; Mathematics","score_opus":0.14601003743330127,"score_gpt":0.3010006766775535,"score_spread":0.15499063924425222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145841197","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99315774,0.000042730444,0.0050111627,0.00028790312,0.00021042027,0.00021996288,0.0000025050085,0.00003182958,0.0010357576],"genre_scores_gemma":[0.99962157,0.000045524885,0.00020660285,0.000016620615,0.000011008302,0.0000061952533,0.0000015068139,0.000003649508,0.00008734552],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982901,0.00015019068,0.00048358113,0.000198868,0.00059400697,0.0002832037],"domain_scores_gemma":[0.9980803,0.00067794614,0.0002419192,0.000594897,0.000360373,0.000044568733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078310224,0.00012557166,0.00026253477,0.0002967358,0.00015177974,0.00008362657,0.0012777026,0.000045128963,0.00003122759],"category_scores_gemma":[0.00074372644,0.00007695201,0.00014970104,0.0053894734,0.00016745698,0.00051941804,0.0003752337,0.00028344992,0.0000040458817],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0064786496,0.00095032837,0.3636985,0.00021036605,0.0011787176,0.00004808719,0.12537684,0.009309434,0.03685044,0.23580578,0.00009687967,0.21999595],"study_design_scores_gemma":[0.0017727829,0.0005745453,0.7468692,0.00012740407,0.00029699368,0.000008982433,0.0023697705,0.1961692,0.05100362,0.00020217289,0.0002622785,0.00034305907],"about_ca_topic_score_codex":0.00017601524,"about_ca_topic_score_gemma":0.00008005533,"teacher_disagreement_score":0.38317066,"about_ca_system_score_codex":0.000058940455,"about_ca_system_score_gemma":0.00031113127,"threshold_uncertainty_score":0.3138012},"labels":[],"label_agreement":null},{"id":"W2166281503","doi":"","title":"DalTREC 2004: Question Answering using Regular Expression Rewriting","year":2004,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Rewriting; Regular expression; Computer science; Expression (computer science); Question answering; Search engine; Information retrieval; Track (disk drive); Programming language; Natural language processing; World Wide Web; Artificial intelligence; Operating system","score_opus":0.028250012493525753,"score_gpt":0.2986974757111274,"score_spread":0.27044746321760166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166281503","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09903895,0.0017511562,0.897034,0.00039842806,0.00017031413,0.00017522126,0.0000014616922,0.001084114,0.0003463882],"genre_scores_gemma":[0.6032013,0.000014412925,0.39657256,0.00007710383,0.000061868486,0.0000017476585,0.0000022961858,0.0000120352015,0.00005662906],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99803305,0.00009065986,0.00034065085,0.00060990144,0.00049793796,0.00042777488],"domain_scores_gemma":[0.9986324,0.000050467843,0.00021340692,0.0006679422,0.00030641616,0.00012938648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005870951,0.00023824371,0.00023107379,0.00017332289,0.00027477596,0.0004193625,0.0010386151,0.00017512336,0.000015714293],"category_scores_gemma":[0.00040042313,0.00022558913,0.000058604703,0.00066415744,0.00008455727,0.0013388264,0.0003850908,0.00040458018,0.000016527987],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029313134,0.000039454946,0.000119225246,0.00007390835,0.0000052175315,0.00008567797,0.000701083,0.00015433585,0.88765395,0.08617448,0.00002493309,0.02493841],"study_design_scores_gemma":[0.00034686908,0.00008439561,0.000089190304,0.0011679454,0.0000074075456,0.000109908855,0.00004479996,0.009985743,0.90548,0.082110815,0.0001519263,0.00042096837],"about_ca_topic_score_codex":0.00013688044,"about_ca_topic_score_gemma":0.0000051660127,"teacher_disagreement_score":0.50416243,"about_ca_system_score_codex":0.0002462956,"about_ca_system_score_gemma":0.0002672039,"threshold_uncertainty_score":0.9199258},"labels":[],"label_agreement":null},{"id":"W2182378606","doi":"","title":"Universite de Montreal at TREC 2013: Experiments with Quantum Language Models in the Web Track.","year":2013,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Robustness (evolution); Computer science; Language model; Artificial intelligence; Focus (optics); Information retrieval; Data mining","score_opus":0.031722842998086316,"score_gpt":0.24765294626240222,"score_spread":0.21593010326431591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2182378606","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89595145,0.0001823165,0.09435176,0.000891378,0.000042710464,0.00028217107,0.0000021233027,0.00008332227,0.0082127545],"genre_scores_gemma":[0.99540704,0.000035958386,0.002962142,0.0002242598,0.000019878165,0.000008177424,0.000002041397,0.0000074493723,0.0013330296],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985873,0.00013207934,0.00016326463,0.00038003636,0.00035528032,0.00038204013],"domain_scores_gemma":[0.9990407,0.000091269474,0.0000704307,0.00063308346,0.000070093614,0.00009438732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022954948,0.00016230192,0.00016051088,0.00008109822,0.00009287658,0.00017346266,0.0011344013,0.000071448754,0.00013198967],"category_scores_gemma":[0.000011083398,0.000112436304,0.000034354493,0.00028526157,0.000058874517,0.00070292456,0.00018599212,0.00019878695,0.00010798862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007749993,0.0010249489,0.012451574,0.00012828034,0.00017568671,0.0012444321,0.39412323,0.014244245,0.07769018,0.3898643,0.007547061,0.100731045],"study_design_scores_gemma":[0.0007276428,0.000106083055,0.0036398326,0.000036510915,0.0000056578283,0.000025225077,0.0017510246,0.98950267,0.0013737866,0.0025117411,0.000099686455,0.00022014332],"about_ca_topic_score_codex":0.0035119534,"about_ca_topic_score_gemma":0.00060909335,"teacher_disagreement_score":0.9752584,"about_ca_system_score_codex":0.00012924257,"about_ca_system_score_gemma":0.0001533815,"threshold_uncertainty_score":0.53090465},"labels":[],"label_agreement":null},{"id":"W218939381","doi":"","title":"York University at TREC 2012: Microblog Track.","year":2012,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Microblogging; Social media; Computer science; Track (disk drive); Task (project management); Information retrieval; Component (thermodynamics); World Wide Web; Engineering","score_opus":0.036784068514360425,"score_gpt":0.25995983062612626,"score_spread":0.22317576211176585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W218939381","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034392074,0.0017079248,0.9355472,0.00052065775,0.00044336964,0.00034565243,0.000020006475,0.0010532669,0.025969857],"genre_scores_gemma":[0.95205015,0.00028712442,0.03182779,0.00025392012,0.000104596955,8.286381e-7,0.000007254025,0.000016196182,0.015452155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99810165,0.00012765202,0.00023794861,0.0004901742,0.00033248158,0.0007101104],"domain_scores_gemma":[0.99834764,0.00016874324,0.00016457583,0.00081412325,0.00017524906,0.0003296465],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040944142,0.00027081103,0.00029290255,0.00014483366,0.0002753346,0.00009692466,0.0013108004,0.00017166455,0.00040752642],"category_scores_gemma":[0.000100637255,0.00026560252,0.00012575825,0.0008127768,0.00017585918,0.0019084143,0.0006148518,0.0003131983,0.0006533659],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076102355,0.00079911,0.010939635,0.00012935119,0.00013085893,0.00016153647,0.00475877,0.0000026250295,0.21998008,0.36095232,0.04931689,0.35206783],"study_design_scores_gemma":[0.00081963843,0.0003112134,0.011208555,0.000074104646,0.00003699061,0.00012807715,0.0001037086,0.00043423704,0.4328153,0.0032272493,0.54983544,0.0010054869],"about_ca_topic_score_codex":0.000022429644,"about_ca_topic_score_gemma":0.000007324833,"teacher_disagreement_score":0.91765803,"about_ca_system_score_codex":0.00022955281,"about_ca_system_score_gemma":0.00011433936,"threshold_uncertainty_score":0.9999796},"labels":[],"label_agreement":null},{"id":"W2294145134","doi":"","title":"Overview of the TREC 2009 Web Track","year":2009,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Information retrieval; Relevance (law); Task (project management); World Wide Web; Clef; Session (web analytics); Web page; Set (abstract data type); Search engine indexing; Query expansion","score_opus":0.07088538982854531,"score_gpt":0.3088896404462865,"score_spread":0.23800425061774116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2294145134","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8756815,0.0014414933,0.032746833,0.012119611,0.0011450902,0.0014092332,0.00007430393,0.00050710235,0.074874826],"genre_scores_gemma":[0.99660224,0.000121928075,0.0007620483,0.00071343774,0.000023374447,0.0000010532474,0.0000015263432,0.0000030183023,0.0017713598],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99826264,0.000095961994,0.00040669192,0.00022328156,0.0007059554,0.00030547197],"domain_scores_gemma":[0.9985422,0.00006436472,0.00018784065,0.0007459125,0.0003539263,0.000105765364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004543763,0.00015149525,0.0002217576,0.00008019483,0.00012595492,0.0001380988,0.0015857262,0.00008695435,0.00024862678],"category_scores_gemma":[0.00014982029,0.00009915593,0.0001428233,0.0010419396,0.00009826345,0.00059095625,0.00014982697,0.0002629655,0.00013665913],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010499736,0.00028184662,0.001012261,0.00007809139,0.000017302355,0.000009825684,0.0024254369,0.000011328354,0.026579129,0.5875516,0.0035716286,0.37835655],"study_design_scores_gemma":[0.003571992,0.002038413,0.5455216,0.0006108407,0.000076875265,0.00012509702,0.00020376984,0.06355919,0.26831296,0.031672202,0.08269104,0.0016160012],"about_ca_topic_score_codex":0.0000103656985,"about_ca_topic_score_gemma":0.0000031476497,"teacher_disagreement_score":0.5558794,"about_ca_system_score_codex":0.00003761409,"about_ca_system_score_gemma":0.000427779,"threshold_uncertainty_score":0.40434614},"labels":[],"label_agreement":null},{"id":"W2296709160","doi":"","title":"GUCAS at TREC 2011 Microblog Track.","year":2011,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Microblogging; Social media; Context (archaeology); Relevance (law); Track (disk drive); Probabilistic logic; Information retrieval; Baseline (sea); Natural language processing; Query expansion; Artificial intelligence; Language model; World Wide Web","score_opus":0.09059576231893875,"score_gpt":0.25523591573740934,"score_spread":0.1646401534184706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2296709160","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36556053,0.0004442319,0.5264538,0.00063154136,0.001027064,0.00033511617,0.0000071630457,0.00060722424,0.10493335],"genre_scores_gemma":[0.9614867,0.000033263885,0.029234637,0.00027357895,0.000059205442,0.0000034653306,0.0000019970169,0.000012800566,0.008894358],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981552,0.00007620593,0.000340454,0.0006622784,0.00029918988,0.00046670804],"domain_scores_gemma":[0.9984109,0.000064675616,0.00012795934,0.0010454622,0.00016504548,0.00018595983],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00033462455,0.00022172563,0.00024488702,0.00009796029,0.00014067897,0.00009687075,0.0015091274,0.00013924776,0.0018826049],"category_scores_gemma":[0.000058577232,0.00020622223,0.00009028442,0.00020739222,0.0000959749,0.00041827888,0.00051399786,0.00023582416,0.0020177178],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038233047,0.00055568386,0.01237687,0.00013351467,0.00013571359,0.00039453316,0.026476966,0.000014742556,0.09554705,0.587179,0.010341822,0.2664618],"study_design_scores_gemma":[0.0047932863,0.0016031726,0.08554494,0.00031435824,0.00013484678,0.0008875057,0.00032326241,0.1469687,0.5788514,0.10558511,0.07027108,0.0047223363],"about_ca_topic_score_codex":0.00015424343,"about_ca_topic_score_gemma":0.000044950364,"teacher_disagreement_score":0.59592617,"about_ca_system_score_codex":0.000085004634,"about_ca_system_score_gemma":0.00015634892,"threshold_uncertainty_score":0.9990298},"labels":[],"label_agreement":null},{"id":"W2395887233","doi":"","title":"University of Waterloo at TREC 2015 Microblog Track","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Microblogging; Exploit; Social media; Information retrieval; Relevance (law); Word (group theory); Query expansion; World Wide Web; Mathematics","score_opus":0.0386870167005127,"score_gpt":0.26424134556232476,"score_spread":0.22555432886181206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395887233","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32989463,0.00033767198,0.6574223,0.001091771,0.00015200877,0.00028226545,0.000014667981,0.0006629161,0.010141728],"genre_scores_gemma":[0.9489643,0.000048453738,0.041312058,0.00004073548,0.000013489461,2.1819689e-7,0.000006472258,0.00000784057,0.009606437],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985613,0.00010085822,0.0002323469,0.00045425913,0.0003647506,0.00028648946],"domain_scores_gemma":[0.99824816,0.00006069702,0.00020113186,0.0007948011,0.0004918354,0.00020336435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038107837,0.00017303386,0.0003282477,0.0001337738,0.00007255063,0.000039133873,0.0013815901,0.000112687456,0.000116562536],"category_scores_gemma":[0.000077982266,0.00017003858,0.00010151809,0.0005596566,0.00020590842,0.0005204067,0.0005719574,0.00015322697,0.00022337442],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013928054,0.0010467926,0.014063878,0.00017755834,0.00041575477,0.00050789566,0.031775944,0.00022836665,0.5589889,0.16311967,0.06698333,0.16129906],"study_design_scores_gemma":[0.0031688064,0.001276995,0.005170565,0.00015310204,0.00014805951,0.00010679607,0.00085600076,0.028741227,0.83347607,0.044568256,0.080632396,0.0017017171],"about_ca_topic_score_codex":0.00018490972,"about_ca_topic_score_gemma":0.00013264231,"teacher_disagreement_score":0.61906964,"about_ca_system_score_codex":0.00016968032,"about_ca_system_score_gemma":0.00020016303,"threshold_uncertainty_score":0.69339716},"labels":[],"label_agreement":null},{"id":"W2402510845","doi":"","title":"Overview of the TREC 2011 Legal Track.","year":2011,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Task (project management); Computer science; Track (disk drive); Rank (graph theory); Information retrieval; Natural language processing; Artificial intelligence","score_opus":0.1480039556696987,"score_gpt":0.28564236471141913,"score_spread":0.13763840904172042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2402510845","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41195112,0.001723096,0.4672304,0.0013599253,0.0017922726,0.00059746887,0.000010272003,0.0003043697,0.11503104],"genre_scores_gemma":[0.9921593,0.000048131435,0.0060787755,0.00016274811,0.000027372482,0.0000015967859,1.971367e-7,0.0000056512467,0.0015161936],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987166,0.000091617236,0.0002955726,0.00032307164,0.00034355393,0.00022960061],"domain_scores_gemma":[0.99855804,0.00004693034,0.00015273955,0.0010214593,0.00015428141,0.00006656743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003269789,0.00012863462,0.00019316433,0.000040061826,0.00006405603,0.000045928908,0.0017526795,0.00007045639,0.0005231067],"category_scores_gemma":[0.0000713617,0.0000894498,0.00010192043,0.0002487886,0.00009578756,0.0003545131,0.00035336116,0.00019558417,0.00010019722],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026435691,0.00008603968,0.0018380774,0.000054819036,0.000019772364,0.0000072963035,0.0026303323,0.0000030325164,0.002464341,0.92855287,0.00029668413,0.064020306],"study_design_scores_gemma":[0.0029176637,0.00093986985,0.29775316,0.0008338299,0.00014524565,0.00019834888,0.00033882685,0.13196439,0.3745921,0.15343037,0.03466652,0.0022196705],"about_ca_topic_score_codex":0.00029341804,"about_ca_topic_score_gemma":0.00002858648,"teacher_disagreement_score":0.77512246,"about_ca_system_score_codex":0.000020360863,"about_ca_system_score_gemma":0.00022264816,"threshold_uncertainty_score":0.5727652},"labels":[],"label_agreement":null},{"id":"W2403585915","doi":"","title":"University of Ottawa at TREC 2010 Web Track Ranking Web Documents Using Meta-Data","year":2010,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Track (disk drive); Ranking (information retrieval); Information retrieval; World Wide Web","score_opus":0.0936111074354567,"score_gpt":0.2862664339247185,"score_spread":0.1926553264892618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2403585915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94620085,0.00018436674,0.04754441,0.00056569633,0.00063453196,0.00015907947,0.0003378819,0.00018386327,0.0041893204],"genre_scores_gemma":[0.97475225,0.000042081265,0.02280725,0.000030077668,0.00003530802,9.788709e-8,0.000049112317,0.000008385542,0.0022754283],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979363,0.00013762756,0.0003107443,0.00075152674,0.00052755646,0.0003362331],"domain_scores_gemma":[0.99706787,0.0001733201,0.00032102515,0.00206836,0.00021435686,0.00015507401],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010372597,0.00021562641,0.00049138936,0.0001770195,0.0002503702,0.00016671364,0.0033181743,0.0001330705,0.0012464976],"category_scores_gemma":[0.00018954602,0.00020244594,0.0001619679,0.0007426015,0.00019844255,0.0012029022,0.0014644448,0.0003651234,0.00011594516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003003319,0.0006724467,0.029023606,0.00021412456,0.0043906686,0.00037983924,0.003047994,0.00016527997,0.83962303,0.031408403,0.018322244,0.072452016],"study_design_scores_gemma":[0.0019912415,0.00012803968,0.0043784054,0.000077121564,0.002111324,0.00007161857,0.00015995436,0.9235734,0.015489571,0.0005045937,0.050502833,0.0010119524],"about_ca_topic_score_codex":0.00048055383,"about_ca_topic_score_gemma":0.0009019474,"teacher_disagreement_score":0.9234081,"about_ca_system_score_codex":0.00003531476,"about_ca_system_score_gemma":0.00039934652,"threshold_uncertainty_score":0.9996665},"labels":[],"label_agreement":null},{"id":"W2403808737","doi":"","title":"York University at TREC 2013: Contextual Suggestion Track.","year":2013,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Geographic Information Systems Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Ontology; Information retrieval; Directory; Context (archaeology); User profile; World Wide Web; Track (disk drive); Construct (python library); User modeling; Human–computer interaction; User interface","score_opus":0.03865126584643107,"score_gpt":0.2564622964168803,"score_spread":0.2178110305704492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2403808737","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7486272,0.00013829138,0.00029376114,0.0029173407,0.0004708738,0.0006944227,0.000019063493,0.00027493702,0.24656415],"genre_scores_gemma":[0.9626764,0.00016889373,0.00005525533,0.000076672455,0.00007779369,0.0000027212545,0.00000902871,0.000004963802,0.03692827],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984448,0.00019548269,0.0002465224,0.00021310312,0.00051849295,0.00038163166],"domain_scores_gemma":[0.99860907,0.00021472794,0.00019088724,0.0001935089,0.00062084774,0.00017097822],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005737531,0.00014006336,0.00021447128,0.00012491588,0.0010086297,0.00012582197,0.00032778713,0.00016128311,0.0031957387],"category_scores_gemma":[0.00023429024,0.00013926259,0.00008116474,0.0005432576,0.00056934665,0.0005998573,0.0000883691,0.00015110546,0.0030451175],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035754175,0.00014842868,0.08944062,0.0000929934,0.00020796915,0.000014035736,0.1895996,0.000009725831,0.00095988286,0.56272334,0.12636027,0.030085605],"study_design_scores_gemma":[0.0013999541,0.00018534364,0.19159989,0.00010436859,0.000050914063,0.000006155597,0.11459103,0.00023878248,0.00022560856,0.0018896795,0.68894213,0.00076611777],"about_ca_topic_score_codex":0.015247654,"about_ca_topic_score_gemma":0.0061567957,"teacher_disagreement_score":0.5625819,"about_ca_system_score_codex":0.00021130471,"about_ca_system_score_gemma":0.00016254403,"threshold_uncertainty_score":0.99773115},"labels":[],"label_agreement":null},{"id":"W2403963403","doi":"","title":"University of Waterloo at the TREC 2013 Temporal Summarization Track.","year":2013,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Automatic summarization; Computer science; Cosine similarity; Ranking (information retrieval); Relevance (law); Information retrieval; Similarity (geometry); Metric (unit); Latency (audio); Set (abstract data type); Task (project management); Relevance feedback; Artificial intelligence; Natural language processing; Data mining; Pattern recognition (psychology); Image retrieval","score_opus":0.027573731347673866,"score_gpt":0.21319151961247845,"score_spread":0.18561778826480457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2403963403","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7155336,0.00006126202,0.27864617,0.0029258193,0.00016919548,0.00027198307,0.0000033039776,0.000090299895,0.0022983586],"genre_scores_gemma":[0.98566586,0.000029465797,0.002889748,0.000050653332,0.000017274238,3.8400606e-7,0.000005133591,0.0000037934512,0.011337687],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903893,0.000086194275,0.00016270977,0.00027447613,0.0002516594,0.00018603622],"domain_scores_gemma":[0.9989803,0.00007018517,0.000114145434,0.00055368093,0.0002192514,0.0000624352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020587248,0.000097784214,0.00013040064,0.000038784656,0.0001343774,0.0000754197,0.00086986943,0.00006653543,0.0007182094],"category_scores_gemma":[0.00002800289,0.000073598356,0.000046096255,0.00022001134,0.000106377905,0.00045294088,0.0003094277,0.00011027106,0.0002962813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026807035,0.00041259167,0.07044587,0.0002450254,0.00018577739,0.00004590785,0.042809647,0.0017843429,0.10038775,0.20952699,0.02848265,0.5454054],"study_design_scores_gemma":[0.0014822478,0.00030741593,0.05541895,0.00009984506,0.00003915047,0.000021568532,0.0009818118,0.8801074,0.030269139,0.013392909,0.017092302,0.0007872606],"about_ca_topic_score_codex":0.0026710664,"about_ca_topic_score_gemma":0.00031880554,"teacher_disagreement_score":0.8783231,"about_ca_system_score_codex":0.000045181183,"about_ca_system_score_gemma":0.00009218318,"threshold_uncertainty_score":0.786389},"labels":[],"label_agreement":null},{"id":"W2407544020","doi":"","title":"Ranking Web Pages Using Collective Knowledge.","year":2011,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Search engine indexing; Information retrieval; Web page; Ranking (information retrieval); World Wide Web; Static web page; Index (typography); Web navigation","score_opus":0.1401130716483935,"score_gpt":0.29170747471099256,"score_spread":0.15159440306259905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2407544020","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23776428,0.0006309304,0.63535446,0.00010584574,0.00055871287,0.00020633875,0.000016111704,0.0005124961,0.12485083],"genre_scores_gemma":[0.97800183,0.000034133114,0.020352172,0.0000452331,0.000053012824,0.0000017027926,0.0000023458322,0.000009852025,0.0014997226],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844676,0.00014603007,0.00025462094,0.0005358812,0.00025562907,0.00036109868],"domain_scores_gemma":[0.99866194,0.00012366855,0.0001333753,0.0006550879,0.0003026153,0.00012333455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004823178,0.0001923658,0.000279748,0.00022335841,0.0002596869,0.00022712549,0.0011775108,0.00008677175,0.00022507782],"category_scores_gemma":[0.00020491664,0.00017655775,0.00009237131,0.001313099,0.00010892242,0.0005508113,0.0004238445,0.00021103739,0.00018698108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005701548,0.0016466336,0.03598341,0.00028083424,0.001395381,0.0005598151,0.111236975,0.000052650375,0.15822,0.34375632,0.0094360635,0.33686176],"study_design_scores_gemma":[0.0020789593,0.00058509223,0.017834881,0.00050415774,0.00027042313,0.000116608615,0.0011308774,0.8660879,0.085644595,0.018318502,0.0053692716,0.002058732],"about_ca_topic_score_codex":0.000055231852,"about_ca_topic_score_gemma":0.00002352523,"teacher_disagreement_score":0.8660352,"about_ca_system_score_codex":0.000084276464,"about_ca_system_score_gemma":0.00067261874,"threshold_uncertainty_score":0.71998155},"labels":[],"label_agreement":null},{"id":"W2546705495","doi":"","title":"WaterlooClarke: TREC 2015 Clinical Decision Support Track","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Information retrieval; Mean reciprocal rank; Search engine; Reciprocal; Clinical decision support system; Test (biology); Rank (graph theory); Decision support system; Data mining","score_opus":0.08993383767107038,"score_gpt":0.3806690461193441,"score_spread":0.2907352084482737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2546705495","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98043096,0.000770298,0.009614192,0.0008402051,0.0010753536,0.0001774797,0.000029111125,0.00009718892,0.0069652377],"genre_scores_gemma":[0.9880388,0.00023721709,0.004533532,0.00041238597,0.00038349183,0.0000034871186,0.00012651614,0.000019454386,0.006245146],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99805546,0.000152638,0.0004936268,0.0005558094,0.00036376942,0.00037871054],"domain_scores_gemma":[0.9985568,0.00007738434,0.00011306876,0.00052932044,0.00029730028,0.0004261573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012855014,0.0002098141,0.00031235124,0.000041047282,0.000052938638,0.00005517461,0.0004592543,0.00050731556,0.00026769761],"category_scores_gemma":[0.0018935329,0.000163062,0.0001341475,0.00012792551,0.00039283407,0.0000057146767,0.0002063209,0.00026926817,0.00037736056],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030617665,0.00036172703,0.014129652,0.000021572387,0.00011228637,0.00008343084,0.00030904106,0.0000023964317,0.020661231,0.00020444096,0.33162758,0.62942487],"study_design_scores_gemma":[0.0029684121,0.0035271044,0.012133456,0.000041043342,0.000048213493,0.000091777976,0.00035800217,0.00021170254,0.024892619,0.0012248923,0.9539291,0.00057366095],"about_ca_topic_score_codex":0.00001609878,"about_ca_topic_score_gemma":0.000028215369,"teacher_disagreement_score":0.62885123,"about_ca_system_score_codex":0.000017131904,"about_ca_system_score_gemma":0.00048479863,"threshold_uncertainty_score":0.6649475},"labels":[],"label_agreement":null},{"id":"W2554197048","doi":"","title":"WaterlooClarke: TREC 2015 Contextual Suggestion Track","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Task (project management); Track (disk drive); Point of interest; Point (geometry); Contextual design; Information retrieval; Human–computer interaction; Artificial intelligence; Machine learning","score_opus":0.0765092666209366,"score_gpt":0.29243765734721133,"score_spread":0.21592839072627473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2554197048","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22531989,0.0003694523,0.75684136,0.0034000222,0.0011320228,0.0003260137,0.0000063307466,0.0006162168,0.011988716],"genre_scores_gemma":[0.9862878,0.000013516327,0.0090560075,0.00023742083,0.00013937398,0.000004592266,0.000007504444,0.000012330642,0.004241493],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777657,0.00015935216,0.00037725878,0.000609761,0.00062868564,0.00044836084],"domain_scores_gemma":[0.998103,0.0000927095,0.00011952628,0.0008241447,0.00050233875,0.00035828096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008646448,0.00022805954,0.0002765622,0.00010603218,0.0000815113,0.00032435206,0.0011462894,0.00015885508,0.000087776934],"category_scores_gemma":[0.00037838385,0.00020353962,0.000063888765,0.00033226414,0.00008950586,0.00080261694,0.00025620472,0.0003100569,0.0006006799],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005309596,0.0003878621,0.0031831947,0.000078828,0.00009355727,0.00024799668,0.018699795,0.0005844976,0.011268677,0.4987576,0.022147583,0.44401944],"study_design_scores_gemma":[0.006457575,0.0015752532,0.006000344,0.0002473948,0.0000638961,0.00033447187,0.0010554583,0.8202107,0.03397452,0.056015566,0.071681805,0.002383039],"about_ca_topic_score_codex":0.00014177801,"about_ca_topic_score_gemma":0.000029223365,"teacher_disagreement_score":0.81962615,"about_ca_system_score_codex":0.00011830848,"about_ca_system_score_gemma":0.00046022044,"threshold_uncertainty_score":0.8300105},"labels":[],"label_agreement":null},{"id":"W2572043595","doi":"","title":"WaterlooClarke: TREC 2015 Total Recall Track","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Recall; Track (disk drive); Cluster analysis; Selection (genetic algorithm); Process (computing); Precision and recall; Information retrieval; Data mining; Artificial intelligence","score_opus":0.0752741043559129,"score_gpt":0.2872297986682088,"score_spread":0.21195569431229588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2572043595","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32266265,0.00040622748,0.6412211,0.00429307,0.0016026078,0.0003518386,0.0000061926066,0.0007148474,0.028741498],"genre_scores_gemma":[0.9722361,0.000011036516,0.01923305,0.00021544902,0.00015499305,0.0000039000097,0.000004108494,0.00001334709,0.008128],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977333,0.0001307326,0.00036852353,0.0006455101,0.00063065055,0.00049129647],"domain_scores_gemma":[0.99809146,0.00007080256,0.00010137101,0.0009588466,0.00037685983,0.00040067342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007651807,0.00022848755,0.00027702824,0.0000942977,0.00007102723,0.00032839936,0.0012288224,0.00015419055,0.00011281979],"category_scores_gemma":[0.00025941766,0.0002009253,0.00007348024,0.0003532619,0.0000723877,0.00071674254,0.00036543273,0.0003249949,0.0006678387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061628164,0.0005992707,0.0029879736,0.00013145898,0.00015455809,0.0005397448,0.024510954,0.0010590748,0.016367286,0.32354882,0.03753409,0.5919505],"study_design_scores_gemma":[0.0045843394,0.0013320853,0.004254844,0.00019736229,0.00005218302,0.000511394,0.00053750334,0.84488225,0.029975675,0.053709954,0.057541993,0.0024203882],"about_ca_topic_score_codex":0.00010212102,"about_ca_topic_score_gemma":0.000013608339,"teacher_disagreement_score":0.8438232,"about_ca_system_score_codex":0.00010603801,"about_ca_system_score_gemma":0.00045389752,"threshold_uncertainty_score":0.85839385},"labels":[],"label_agreement":null},{"id":"W2572785564","doi":"","title":"WaterlooClarke: TREC 2015 Temporal Summarization Track.","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Automatic summarization; Computer science; Track (disk drive); Multi-document summarization; Information retrieval","score_opus":0.04169239849904795,"score_gpt":0.2977835804427729,"score_spread":0.256091181943725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2572785564","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015106204,0.0017988381,0.97243834,0.0029840828,0.0005824909,0.0003733395,0.000008000023,0.002114836,0.0045939037],"genre_scores_gemma":[0.86303383,0.000012218188,0.1340907,0.00022073477,0.0000769584,0.000004760771,0.000025997693,0.000014605979,0.002520176],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980454,0.00013043126,0.00032155987,0.0005235602,0.0006050779,0.00037395817],"domain_scores_gemma":[0.9982645,0.000049552316,0.00016147444,0.00065790355,0.0006148509,0.0002516983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007414333,0.00022998762,0.0002427977,0.00015476547,0.00008914051,0.00049478735,0.0013907094,0.00018203212,0.000045779234],"category_scores_gemma":[0.00039409846,0.00019155038,0.000051441082,0.0006960058,0.000093657356,0.0012441044,0.00031615037,0.00032086277,0.00014203959],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063138036,0.00051761797,0.008983675,0.0002145832,0.00008960922,0.00044103805,0.012558848,0.000016563696,0.041966885,0.46787542,0.06603497,0.40066943],"study_design_scores_gemma":[0.0030796689,0.0015107085,0.0012838747,0.000374547,0.000060471095,0.00026853764,0.00031233093,0.08562172,0.42503002,0.4309247,0.04877533,0.0027580624],"about_ca_topic_score_codex":0.00012980352,"about_ca_topic_score_gemma":0.00002258141,"teacher_disagreement_score":0.84792763,"about_ca_system_score_codex":0.000115536495,"about_ca_system_score_gemma":0.00045877803,"threshold_uncertainty_score":0.7811198},"labels":[],"label_agreement":null},{"id":"W2572992153","doi":"","title":"WaterlooClarke: TREC 2015 Microblog Track.","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Optimization and Search Problems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Victoria","funders":"","keywords":"Microblogging; Social media; Track (disk drive); Computer science; World Wide Web; Information retrieval; Narrative","score_opus":0.06991052720693956,"score_gpt":0.2990576984579198,"score_spread":0.22914717125098022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2572992153","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020317713,0.00050537824,0.9034838,0.011245201,0.0010724852,0.0006813299,0.000014374704,0.0009908454,0.061688837],"genre_scores_gemma":[0.95369095,0.00006009225,0.030225508,0.00062387454,0.0000687896,0.0000061131896,0.000015570695,0.000016445281,0.015292638],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805623,0.00017466191,0.00030425072,0.0004889179,0.0005127612,0.00046319552],"domain_scores_gemma":[0.9981612,0.000060410934,0.00008799377,0.0006570306,0.0006023486,0.00043103695],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008226698,0.00019182239,0.00022387893,0.00013098706,0.00009432688,0.00045386146,0.0012447285,0.00012229338,0.00024476307],"category_scores_gemma":[0.00020471778,0.0001640426,0.000058272737,0.0005731337,0.00011105966,0.0007170181,0.00029213456,0.00027197483,0.0010490133],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063879794,0.0011865771,0.003013134,0.00017534653,0.00019337426,0.0003539272,0.029496666,0.0018603557,0.040930074,0.4714353,0.25327837,0.19743808],"study_design_scores_gemma":[0.007696406,0.0020752132,0.002312421,0.00018920425,0.000039901017,0.00029247245,0.00062103657,0.49925277,0.061577316,0.047596134,0.37568432,0.0026628077],"about_ca_topic_score_codex":0.000043882832,"about_ca_topic_score_gemma":0.000012365859,"teacher_disagreement_score":0.9333733,"about_ca_system_score_codex":0.000072266805,"about_ca_system_score_gemma":0.000523178,"threshold_uncertainty_score":0.9997288},"labels":[],"label_agreement":null},{"id":"W2573384236","doi":"","title":"Waterloo (Cormack) Participation in the TREC 2015 Total Recall Track.","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Library Science and Information Systems","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Recall; Track (disk drive); Computer science; Information retrieval; Artificial intelligence; Cognitive psychology; Psychology","score_opus":0.08988319202190065,"score_gpt":0.3078099765277643,"score_spread":0.21792678450586367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2573384236","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94346493,0.00006489739,0.02013088,0.005078149,0.001077455,0.00044410306,0.0000039496535,0.00016528642,0.029570343],"genre_scores_gemma":[0.997087,0.0000057424586,0.0003255256,0.00065388886,0.00006741061,0.000011200985,0.000007156991,0.0000030492577,0.0018390516],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798197,0.00028374497,0.00045153525,0.00025936085,0.0006785815,0.0003448139],"domain_scores_gemma":[0.9988872,0.00010416513,0.00013397181,0.0005485825,0.00017015712,0.00015593531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018528757,0.00013352753,0.00015901598,0.00011042475,0.00009050675,0.00069162325,0.0013432605,0.00007106613,0.00004758321],"category_scores_gemma":[0.00016975182,0.000084622065,0.00003965146,0.00088028325,0.00007417764,0.005145048,0.00012802622,0.00021634965,0.0007564578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039020102,0.0007777305,0.025559459,0.00009180238,0.000033226806,0.0001023511,0.5528194,0.0011363825,0.0021550502,0.18855882,0.077751696,0.15062393],"study_design_scores_gemma":[0.0042631826,0.0024548115,0.12335933,0.00017477208,0.000011311188,0.00026835853,0.013897956,0.71374327,0.01495326,0.016259423,0.1089168,0.0016975532],"about_ca_topic_score_codex":0.000089222536,"about_ca_topic_score_gemma":0.000014632999,"teacher_disagreement_score":0.71260685,"about_ca_system_score_codex":0.000041396594,"about_ca_system_score_gemma":0.0002901509,"threshold_uncertainty_score":0.9722987},"labels":[],"label_agreement":null},{"id":"W2576107865","doi":"","title":"WaterlooClarke: TREC 2015 LiveQA Track","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Question answering; Computer science; NIST; Track (disk drive); Task (project management); Questions and answers; Information retrieval; World Wide Web; Natural language processing; Artificial intelligence","score_opus":0.07404688050771699,"score_gpt":0.29366238254542576,"score_spread":0.21961550203770877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2576107865","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5073421,0.0031473364,0.32384622,0.009884744,0.0077612293,0.0012467102,0.000028930699,0.0029471398,0.14379555],"genre_scores_gemma":[0.9833311,0.000022323102,0.0027059275,0.00019776136,0.00020608542,0.0000066700236,0.0000056342765,0.000016199145,0.013508303],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997572,0.00020548233,0.0003830396,0.0006271611,0.00068060466,0.0005317181],"domain_scores_gemma":[0.9979772,0.00010306735,0.00013845254,0.0009258086,0.00040920838,0.00044627517],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00096425257,0.00026297465,0.0003445182,0.00013211707,0.00011834679,0.00045858737,0.0014919777,0.00017895528,0.00007235672],"category_scores_gemma":[0.0002396754,0.00021643835,0.00008826743,0.0005092427,0.00009630847,0.00063235365,0.00026052693,0.00029099564,0.0015710117],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071721553,0.0010636338,0.010951618,0.00025839955,0.00030322812,0.0008573324,0.103951335,0.000090775466,0.03420467,0.3353814,0.37282893,0.13939147],"study_design_scores_gemma":[0.00833809,0.00399003,0.007896209,0.0008093908,0.000080431615,0.001029466,0.0033236472,0.14363976,0.13407512,0.025339954,0.6665015,0.00497641],"about_ca_topic_score_codex":0.00020996414,"about_ca_topic_score_gemma":0.000025866,"teacher_disagreement_score":0.47598895,"about_ca_system_score_codex":0.00010874195,"about_ca_system_score_gemma":0.0004197662,"threshold_uncertainty_score":0.99920636},"labels":[],"label_agreement":null},{"id":"W2576853603","doi":"","title":"Laval University and Lakehead University at TREC Dynamic Domain 2015: Combination of Techniques for Subtopics Coverage.","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Lakehead University; Université Laval","funders":"","keywords":"Computer science; Domain (mathematical analysis); Information retrieval; Library science; Mathematics","score_opus":0.02569653499890819,"score_gpt":0.25028060544675074,"score_spread":0.22458407044784254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2576853603","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5410211,0.00003653487,0.4565053,0.00066077465,0.000050459184,0.00013693157,0.00009617647,0.00009338166,0.001399316],"genre_scores_gemma":[0.9886207,0.000047673147,0.0085674,0.000009116409,0.000005594367,9.645875e-8,0.000036079677,0.0000030571334,0.0027102556],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992026,0.000090731264,0.000105470615,0.00027844252,0.00018494957,0.00013777746],"domain_scores_gemma":[0.9990995,0.00010355967,0.00012136122,0.00029860646,0.0002776688,0.000099328965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038373686,0.0000958835,0.00018932023,0.0001253105,0.000102686354,0.000035292214,0.00046073124,0.00007893367,0.000005073739],"category_scores_gemma":[0.000067059234,0.00010352752,0.000043820844,0.00033797437,0.00011707848,0.0003608103,0.00028817475,0.000071827235,0.0000030996978],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001766293,0.000605471,0.041305784,0.00030350036,0.00028503855,0.00012068325,0.0074729454,0.000020565676,0.01950956,0.78674775,0.010672971,0.13118944],"study_design_scores_gemma":[0.019548882,0.0067738355,0.10384155,0.00059794233,0.0006904013,0.00011343488,0.0049903034,0.32842967,0.060777213,0.08623298,0.38429448,0.0037092871],"about_ca_topic_score_codex":0.00013658461,"about_ca_topic_score_gemma":0.00028315483,"teacher_disagreement_score":0.7005148,"about_ca_system_score_codex":0.00013580493,"about_ca_system_score_gemma":0.000183851,"threshold_uncertainty_score":0.42217296},"labels":[],"label_agreement":null},{"id":"W2577984450","doi":"","title":"Laval University and Lakehead University Experiments at TREC 2015 Contextual Suggestion Track","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Lakehead University; Université Laval","funders":"","keywords":"Ranking (information retrieval); Track (disk drive); Computer science; Construct (python library); Rank (graph theory); Learning to rank; Information retrieval; Artificial intelligence; Search engine; Machine learning; Programming language; Mathematics","score_opus":0.06872451868132005,"score_gpt":0.27741124033577474,"score_spread":0.20868672165445468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2577984450","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9735859,0.000068965004,0.017173324,0.00074552663,0.00022401758,0.00025861128,0.000035264824,0.0002117176,0.007696647],"genre_scores_gemma":[0.9875912,0.00003022585,0.0006440199,0.00003764218,0.000018260705,1.3806651e-7,0.00001706916,0.0000043759155,0.011657053],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984865,0.00016613262,0.0001620861,0.00034810373,0.0005205019,0.0003166636],"domain_scores_gemma":[0.9986237,0.000071548515,0.00010331517,0.0003212847,0.00044715687,0.000432975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000412359,0.0001702378,0.00019893664,0.00014090599,0.00023984518,0.00012139233,0.0005906677,0.00012723113,0.00008492922],"category_scores_gemma":[0.00008448738,0.00017463064,0.000046302077,0.0004362804,0.00021096242,0.0012286927,0.00045770075,0.00019883858,0.00023843745],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009953924,0.001268633,0.066829816,0.00017197721,0.00022736445,0.0014334403,0.075847015,0.0000622807,0.030791385,0.611181,0.052100614,0.15013252],"study_design_scores_gemma":[0.025343949,0.0046749273,0.2550485,0.00023348261,0.00016407663,0.00045047328,0.0133861,0.07075951,0.074215196,0.0013336085,0.5506396,0.0037504956],"about_ca_topic_score_codex":0.00019230596,"about_ca_topic_score_gemma":0.00010336629,"teacher_disagreement_score":0.6098474,"about_ca_system_score_codex":0.00030744,"about_ca_system_score_gemma":0.00038611027,"threshold_uncertainty_score":0.71212304},"labels":[],"label_agreement":null},{"id":"W2578945560","doi":"","title":"Real Time Filtering of Tweets Using Wikipedia Concepts and Google Tri-gram Semantic Relatedness","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Information retrieval; n-gram; Semantic similarity; Word (group theory); Social media; World Wide Web; Natural language processing; Language model","score_opus":0.07837344284233229,"score_gpt":0.3094833050650553,"score_spread":0.231109862222723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2578945560","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8783889,0.00013983926,0.11798114,0.00008330756,0.0003374529,0.000172115,0.0000033383478,0.00014297204,0.002750959],"genre_scores_gemma":[0.9834204,0.000025658965,0.016017327,0.000017268847,0.00006705023,9.483891e-7,0.0000019010228,0.000012302136,0.0004371857],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826163,0.00010859865,0.00041081462,0.0004727895,0.00041738886,0.00032878932],"domain_scores_gemma":[0.9986024,0.00012468288,0.00020685939,0.0005581833,0.0002881838,0.00021968345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005453297,0.00019116115,0.00036207357,0.00010424438,0.00006559748,0.00013138833,0.00059910415,0.00013501303,0.00002243183],"category_scores_gemma":[0.00022008075,0.00018799113,0.000040751824,0.00036385897,0.00014392116,0.0005037197,0.00043516542,0.00019534887,0.000027707862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073756627,0.00047470236,0.02176086,0.0008686349,0.00031297703,0.00049482594,0.051487423,0.0042635826,0.7154399,0.09467457,0.0008466554,0.10863826],"study_design_scores_gemma":[0.0013762624,0.00027957477,0.0019128302,0.00028681714,0.00003945873,0.00009211886,0.000159065,0.9754195,0.015257446,0.00441224,0.00024887733,0.00051578437],"about_ca_topic_score_codex":0.00024369065,"about_ca_topic_score_gemma":0.000003385014,"teacher_disagreement_score":0.97115594,"about_ca_system_score_codex":0.000061761486,"about_ca_system_score_gemma":0.00033707268,"threshold_uncertainty_score":0.76660556},"labels":[],"label_agreement":null},{"id":"W2604217576","doi":"","title":"Word embeddings and Global Preference for Contextual Suggestion.","year":2016,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University; Université Laval","funders":"","keywords":"Preference; Computer science; Word (group theory); Natural language processing; Artificial intelligence; Speech recognition; Linguistics; Mathematics; Statistics; Philosophy","score_opus":0.05459598172282607,"score_gpt":0.32174729225759735,"score_spread":0.26715131053477126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604217576","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92896557,0.0006872459,0.044508927,0.00071367365,0.0006486309,0.00065474486,0.00033792152,0.00019498412,0.023288311],"genre_scores_gemma":[0.99157727,0.00005426123,0.00030836478,0.000262411,0.0001533283,0.000048158905,0.000018690851,0.000014907293,0.007562633],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984852,0.00009605531,0.00027646567,0.0005316982,0.0001993748,0.00041122784],"domain_scores_gemma":[0.99873745,0.00036318536,0.00013010115,0.0002895107,0.0003181139,0.0001616464],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00030932578,0.00021634999,0.00026498424,0.000047743273,0.00010972473,0.00007541234,0.00021901223,0.0001938349,0.0023247458],"category_scores_gemma":[0.00050471554,0.00015124731,0.000067017725,0.00016882556,0.00024247619,0.0001776775,0.00005632173,0.00010137751,0.0003352393],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025002132,0.00013943686,0.0058521223,0.000046748526,0.00012490588,0.000016550155,0.002090433,2.3336037e-8,0.006983558,0.4334794,0.004113077,0.54465353],"study_design_scores_gemma":[0.02696589,0.0043693096,0.53877354,0.0012061001,0.0007624545,0.00047204265,0.00692087,0.00014845647,0.014891096,0.31188318,0.090058796,0.0035482806],"about_ca_topic_score_codex":0.00006508469,"about_ca_topic_score_gemma":0.000043390573,"teacher_disagreement_score":0.5411053,"about_ca_system_score_codex":0.000050924165,"about_ca_system_score_gemma":0.00008036113,"threshold_uncertainty_score":0.99858725},"labels":[],"label_agreement":null},{"id":"W2604321711","doi":"","title":"TREC 2016 Total Recall Track Overview.","year":2016,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Public Relations and Crisis Communication","field":"Social Sciences","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Track (disk drive); Recall; Information retrieval; Psychology","score_opus":0.07651398741119439,"score_gpt":0.3523979570630005,"score_spread":0.27588396965180606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604321711","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2871326,0.0013076069,0.0043315063,0.030694855,0.00047351548,0.0004247489,0.000026651624,0.0003050701,0.67530346],"genre_scores_gemma":[0.95725656,0.0025159349,0.00020580801,0.00009209392,0.000111215755,0.0000057952902,0.000003898775,0.0000075485345,0.039801147],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985151,0.00032933333,0.00024748023,0.00022741704,0.00038709247,0.00029353666],"domain_scores_gemma":[0.9986402,0.00032718354,0.00011979615,0.00048201045,0.00027842948,0.00015237315],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000921414,0.000101737096,0.00014410946,0.00006500313,0.00037016056,0.00013218947,0.00050547754,0.00014884982,0.003725546],"category_scores_gemma":[0.00076561223,0.00007118943,0.00007515045,0.0003639326,0.00028288714,0.00056356995,0.00007296406,0.00012324167,0.0008301816],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004634085,0.00007946353,0.001534657,0.00000383947,0.000018114402,0.0000010877941,0.0027842922,1.9542519e-7,0.0023211446,0.59747744,0.009072029,0.38666138],"study_design_scores_gemma":[0.00076403376,0.00011061478,0.042666625,0.00015329802,0.000025321733,0.0000028347079,0.0012831151,0.00007870929,0.0006582298,0.03195355,0.92186916,0.0004345],"about_ca_topic_score_codex":0.0004383838,"about_ca_topic_score_gemma":0.00025590067,"teacher_disagreement_score":0.91279715,"about_ca_system_score_codex":0.00012994341,"about_ca_system_score_gemma":0.00045895268,"threshold_uncertainty_score":0.9999478},"labels":[],"label_agreement":null},{"id":"W2604796591","doi":"","title":"\"When to Stop\" Waterloo (Cormack) Participation in the TREC 2016 Total Recall Track.","year":2016,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Border Security and International Relations","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Recall; Track (disk drive); Computer science; Information retrieval; Natural language processing; Psychology; Operating system; Cognitive psychology","score_opus":0.06282087771289732,"score_gpt":0.35408237521879915,"score_spread":0.2912614975059018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604796591","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9069056,0.00003303539,0.0017983372,0.03704466,0.00028131343,0.00037692086,0.000022241786,0.00004819014,0.053489733],"genre_scores_gemma":[0.9849629,0.000058552865,0.000071449394,0.00040034638,0.00013491021,0.00001959502,0.000003903677,0.0000048745746,0.014343479],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984064,0.00037250694,0.000241814,0.00020921874,0.00048069627,0.0002893747],"domain_scores_gemma":[0.99895835,0.00052118325,0.000058709065,0.00016712805,0.0001899684,0.00010466892],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010488078,0.000089825204,0.00010157299,0.00007221542,0.00025128436,0.000119611446,0.00037842614,0.00009590458,0.0018305182],"category_scores_gemma":[0.0011696485,0.00005430197,0.000044251043,0.00024877742,0.00015646672,0.00042546936,0.000031784417,0.00015797604,0.0007206117],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003194236,0.00036697026,0.0063959127,0.000006648546,0.000025120898,0.000008516703,0.21455051,0.000008807984,0.0025203198,0.6368074,0.007258243,0.13173217],"study_design_scores_gemma":[0.0019571565,0.00077324366,0.28663465,0.00038950657,0.00005339662,0.000004468933,0.008296279,0.00042235284,0.0026457098,0.11131714,0.5866189,0.0008871796],"about_ca_topic_score_codex":0.0018660283,"about_ca_topic_score_gemma":0.0055078384,"teacher_disagreement_score":0.57936066,"about_ca_system_score_codex":0.00010809849,"about_ca_system_score_gemma":0.00024094046,"threshold_uncertainty_score":0.99908197},"labels":[],"label_agreement":null},{"id":"W2605327093","doi":"","title":"Laval University at TREC Dynamic Domain 2016: Subtopic extraction focused on Named Entities.","year":2016,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval; Lakehead University","funders":"","keywords":"Computer science; Domain (mathematical analysis); Extraction (chemistry); Information extraction; Named-entity recognition; Artificial intelligence; Engineering; Systems engineering; Chemistry; Mathematics; Chromatography","score_opus":0.014616333478574932,"score_gpt":0.25083006232655075,"score_spread":0.2362137288479758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605327093","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24300139,0.000041948966,0.7491952,0.001091679,0.00019977483,0.00021673054,0.000011988861,0.0006456585,0.005595607],"genre_scores_gemma":[0.96712935,0.00025052333,0.0101763485,0.000059592276,0.000026787568,0.0000018987945,0.000004463973,0.0000137430625,0.022337321],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99793196,0.0001835838,0.0002566145,0.0007109216,0.0004985273,0.0004184163],"domain_scores_gemma":[0.9982097,0.00028698103,0.00023521112,0.0009259339,0.00018935358,0.00015279184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029636206,0.000257487,0.0002990914,0.00027946377,0.00022813694,0.00008320731,0.0010766358,0.00015639591,0.00032334772],"category_scores_gemma":[0.000102072234,0.00020602187,0.00014532471,0.00053361355,0.0001934676,0.00088663114,0.00032923243,0.0001950574,0.00039974536],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009363952,0.0003102421,0.0019871462,0.000034405493,0.00014271907,0.00025503783,0.0008759425,0.000005183613,0.33119053,0.32028866,0.002429631,0.3415441],"study_design_scores_gemma":[0.009006059,0.0027146447,0.07055749,0.0009908323,0.00019901914,0.00011639533,0.00030041044,0.012700791,0.5190481,0.18096638,0.19916394,0.004235967],"about_ca_topic_score_codex":0.000052232663,"about_ca_topic_score_gemma":0.0001864591,"teacher_disagreement_score":0.73901886,"about_ca_system_score_codex":0.0007857753,"about_ca_system_score_gemma":0.00018208154,"threshold_uncertainty_score":0.84013283},"labels":[],"label_agreement":null},{"id":"W26866788","doi":"10.1088/0957-4484/27/10/105204","title":"Experiments for HARD and Enterprise Tracks.","year":2005,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Cohesion (chemistry); Computer science; Natural language processing; Lexical database; Social connectedness; Artificial intelligence; Information retrieval; Selection (genetic algorithm); Lexical item; Schema (genetic algorithms); Linguistics; Psychology; WordNet","score_opus":0.034836813912769604,"score_gpt":0.3130115114656667,"score_spread":0.2781746975528971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W26866788","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046581488,0.004038824,0.9460503,0.0015445807,0.000116778996,0.0003759512,0.0000062910244,0.0005982102,0.00068759447],"genre_scores_gemma":[0.66640586,0.00003261138,0.33264765,0.00031753126,0.000043825607,0.000010911015,0.000001498993,0.0000063290436,0.00053378195],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989548,0.000022572336,0.00017920812,0.0003980689,0.00019511869,0.00025025095],"domain_scores_gemma":[0.99929,0.00007056762,0.00007761231,0.00034375308,0.00012031546,0.00009778582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020447941,0.00014537064,0.00015616874,0.00006992207,0.000095521515,0.00028438744,0.00067461625,0.000078393205,0.000029867204],"category_scores_gemma":[0.0001092946,0.00012804009,0.00003801786,0.00011401514,0.00006167245,0.00062714674,0.00019666312,0.0001253736,0.000015965035],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015252414,0.00012095855,0.00023005351,0.000067880734,0.00002337916,0.000012994925,0.0038111578,3.9811925e-7,0.106847025,0.12004796,0.0026898012,0.76599586],"study_design_scores_gemma":[0.0010443556,0.0003617904,0.0003921321,0.00013401869,0.000010749318,0.000053077514,0.000058946298,0.023900522,0.91535527,0.035167452,0.02290309,0.0006186206],"about_ca_topic_score_codex":0.000005169138,"about_ca_topic_score_gemma":0.0000014793095,"teacher_disagreement_score":0.8085082,"about_ca_system_score_codex":0.000039163206,"about_ca_system_score_gemma":0.00006143623,"threshold_uncertainty_score":0.52213234},"labels":[],"label_agreement":null},{"id":"W2885556514","doi":"","title":"UWaterlooMDS at the TREC 2017 Common Core Track.","year":2017,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Track (disk drive); Computer science; Core (optical fiber); Telecommunications; Operating system","score_opus":0.06543898827919384,"score_gpt":0.3335348181136187,"score_spread":0.2680958298344248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885556514","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7607842,0.0077460734,0.12034782,0.028581781,0.0026622969,0.0017702258,0.00006915955,0.0037817264,0.07425673],"genre_scores_gemma":[0.9812773,0.00005644591,0.0095037455,0.0003639218,0.00008121693,0.000007230039,0.0000053921326,0.000013286694,0.008691492],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99822944,0.00007024825,0.00025949065,0.00053940585,0.00048194866,0.00041947162],"domain_scores_gemma":[0.99656796,0.0001384764,0.00034926133,0.0026092972,0.00021839852,0.00011662991],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00059036724,0.00024579442,0.0002685511,0.000051103158,0.0013384332,0.0013883864,0.005323424,0.00015717762,0.00013324548],"category_scores_gemma":[0.000258854,0.00015710005,0.00009141899,0.0001243115,0.000455833,0.00087728107,0.0014561204,0.00045556593,0.00021767097],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002755586,0.0001457527,0.008218133,0.00010983471,0.0000693737,0.00041696578,0.004599126,0.0000010483162,0.057583407,0.30038157,0.027498169,0.60070103],"study_design_scores_gemma":[0.0015292695,0.0006630735,0.03532819,0.0004856684,0.00007417305,0.0005342589,0.00008174439,0.012629108,0.7038386,0.20627429,0.03663706,0.0019245902],"about_ca_topic_score_codex":0.00023231244,"about_ca_topic_score_gemma":0.00022061288,"teacher_disagreement_score":0.6462552,"about_ca_system_score_codex":0.000086887645,"about_ca_system_score_gemma":0.00012049129,"threshold_uncertainty_score":0.9999617},"labels":[],"label_agreement":null},{"id":"W2885586573","doi":"","title":"MRG_UWaterloo and WaterlooCormack Participation in the TREC 2017 Common Core Track.","year":2017,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Track (disk drive); Core (optical fiber); Telecommunications; Operating system","score_opus":0.354013297376704,"score_gpt":0.5097599940313238,"score_spread":0.15574669665461977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885586573","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99248147,0.000074855874,0.0010052786,0.0022308484,0.00017993384,0.0005004735,0.000022255972,0.000023085953,0.003481803],"genre_scores_gemma":[0.99702984,0.000078169316,0.00010544232,0.00008975925,0.00008057982,0.000019580528,0.00000677194,0.00000952735,0.0025803056],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9964394,0.00032818367,0.00058565335,0.0005757079,0.0015589204,0.00051214197],"domain_scores_gemma":[0.99647766,0.0011408412,0.0003286458,0.0015585962,0.00035084639,0.00014342337],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0039143334,0.00019835425,0.0003588877,0.00016722722,0.00073771545,0.0015758822,0.0021925105,0.00011821954,0.00033199505],"category_scores_gemma":[0.0026996247,0.00011375236,0.0000551833,0.00025208388,0.0007304106,0.0010509748,0.00033116553,0.00046944237,0.00037513333],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012929424,0.00036864876,0.20076455,0.00003432153,0.000027123624,0.0003570848,0.020049268,0.00009467639,0.004368275,0.005300851,0.002603775,0.7647385],"study_design_scores_gemma":[0.0013251159,0.00032048183,0.9216443,0.000044733715,0.000011770802,0.00003339603,0.0011437368,0.018129148,0.0053748097,0.045671783,0.0059843864,0.0003163752],"about_ca_topic_score_codex":0.000293035,"about_ca_topic_score_gemma":0.0009712568,"teacher_disagreement_score":0.7644221,"about_ca_system_score_codex":0.000037852657,"about_ca_system_score_gemma":0.000088532826,"threshold_uncertainty_score":0.9994606},"labels":[],"label_agreement":null},{"id":"W2887055502","doi":"","title":"Overview of the TREC 2016 Real-Time Summarization Track.","year":2016,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Automatic summarization; Computer science; Track (disk drive); Information retrieval; Multi-document summarization; Natural language processing; Operating system","score_opus":0.0542293694693188,"score_gpt":0.2754098846886667,"score_spread":0.22118051521934787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887055502","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17081273,0.00036338952,0.7969151,0.005248847,0.0007137062,0.0005178058,0.000020821211,0.00029232935,0.025115285],"genre_scores_gemma":[0.99046713,0.00034749016,0.002437786,0.000073171956,0.000041641033,0.0000018550578,6.127306e-7,0.0000073045394,0.0066230027],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998648,0.00012892621,0.00030934502,0.0003327839,0.00037080166,0.00021018411],"domain_scores_gemma":[0.99844563,0.00018081018,0.00018943915,0.0009199085,0.00020582556,0.000058374204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003716943,0.000121422934,0.00018531429,0.00004374917,0.000062751205,0.000049497376,0.0011685224,0.0000769495,0.0002518416],"category_scores_gemma":[0.00021845278,0.000065977256,0.00007610533,0.0003502814,0.00008368021,0.00036335725,0.00027327996,0.00007072802,0.0001295279],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003689671,0.00006656813,0.0021280448,0.00006361952,0.000024505687,0.000002606212,0.00069129263,0.000009570589,0.23112449,0.39168537,0.0010117757,0.37315527],"study_design_scores_gemma":[0.0049917996,0.00068998773,0.13200936,0.0040825084,0.00012813119,0.000053300348,0.000053273732,0.17112252,0.50544673,0.15233877,0.026810005,0.0022735926],"about_ca_topic_score_codex":0.000057487297,"about_ca_topic_score_gemma":0.000006734777,"teacher_disagreement_score":0.8196544,"about_ca_system_score_codex":0.00004504829,"about_ca_system_score_gemma":0.0002779569,"threshold_uncertainty_score":0.27574888},"labels":[],"label_agreement":null},{"id":"W2946940318","doi":"","title":"UWaterlooMDS at the TREC 2018 Common Core Track.","year":2018,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Track (disk drive); Computer science; Core (optical fiber); Information retrieval; Artificial intelligence; Telecommunications; Operating system","score_opus":0.03971195414912118,"score_gpt":0.29323575829561693,"score_spread":0.2535238041464958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946940318","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8853215,0.0002904475,0.055812016,0.007936896,0.0020555444,0.00039501794,0.000016719887,0.00076259306,0.04740925],"genre_scores_gemma":[0.97466314,0.000017039007,0.001379508,0.000665968,0.00033917668,0.0000033440472,0.0000068920763,0.0000131801535,0.022911724],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981428,0.00015617709,0.0002688945,0.0005216885,0.00046239546,0.0004480839],"domain_scores_gemma":[0.998285,0.00019759224,0.00013398066,0.0010634924,0.00018236291,0.00013755157],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005938451,0.00022354182,0.00023041051,0.00005512299,0.000570781,0.00032419505,0.0016957547,0.00010056689,0.0009021085],"category_scores_gemma":[0.00010995025,0.00014419445,0.00007641687,0.00046600896,0.0004246698,0.00023540122,0.0005533242,0.00038431992,0.0018022597],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002786864,0.00022723727,0.013532897,0.00004910559,0.000098218974,0.00008978786,0.011515748,0.000019736659,0.011361272,0.07513656,0.055038642,0.8326521],"study_design_scores_gemma":[0.0027720553,0.003623999,0.08579616,0.00023919824,0.00007995877,0.0005006305,0.00025641287,0.34969345,0.07394654,0.024199026,0.45668066,0.0022119272],"about_ca_topic_score_codex":0.00024658904,"about_ca_topic_score_gemma":0.00015360762,"teacher_disagreement_score":0.83044016,"about_ca_system_score_codex":0.000056891487,"about_ca_system_score_gemma":0.00009666785,"threshold_uncertainty_score":0.998975},"labels":[],"label_agreement":null},{"id":"W2947119606","doi":"","title":"H2oloo at TREC 2018: Cross-Collection Relevance Transfer for the Common Core Track.","year":2018,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Track (disk drive); Relevance (law); Core (optical fiber); Transfer (computing); Information retrieval; Telecommunications; Parallel computing","score_opus":0.0819327481816418,"score_gpt":0.3220630675340519,"score_spread":0.24013031935241008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947119606","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31016695,0.0002006231,0.6844872,0.0012136868,0.001124186,0.00057939626,0.000010704571,0.00021001024,0.0020072313],"genre_scores_gemma":[0.9878695,0.000066506334,0.0037309288,0.00040497206,0.00028456972,0.000030180641,0.0000031794802,0.00001725627,0.0075929267],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805564,0.000053867192,0.00038929607,0.00064782833,0.00038724416,0.00046615102],"domain_scores_gemma":[0.9978097,0.00062735967,0.00008472426,0.0009855228,0.00039457684,0.00009809475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059484586,0.00022675257,0.00025074507,0.000059942016,0.00078567164,0.00029956704,0.0013255528,0.00015953615,0.00014964475],"category_scores_gemma":[0.00021815699,0.00017055114,0.00011413984,0.00046371596,0.0003398022,0.00042261407,0.00015528144,0.00024626116,0.00013387443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034303602,0.00037772694,0.00985256,0.0002544604,0.00024142998,0.000024308358,0.01849632,0.0004856175,0.067392856,0.37275413,0.017301893,0.5093883],"study_design_scores_gemma":[0.0023529679,0.001209364,0.014611266,0.000101107784,0.000054586824,0.00007585607,0.000060991846,0.81618273,0.089069255,0.01970493,0.055761524,0.00081542257],"about_ca_topic_score_codex":0.0000851788,"about_ca_topic_score_gemma":0.00035449918,"teacher_disagreement_score":0.81569713,"about_ca_system_score_codex":0.00014827063,"about_ca_system_score_gemma":0.00017080859,"threshold_uncertainty_score":0.6954873},"labels":[],"label_agreement":null},{"id":"W2947684374","doi":"","title":"MRG_UWaterloo Participation in the TREC 2018 Common Core Track.","year":2018,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Track (disk drive); Core (optical fiber); Computer science; Artificial intelligence; Telecommunications","score_opus":0.05982771642909706,"score_gpt":0.3453437846347422,"score_spread":0.2855160682056451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947684374","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8615221,0.00060669245,0.12754263,0.0036318875,0.00042415122,0.0006072155,0.0000055093305,0.00081110845,0.00484871],"genre_scores_gemma":[0.983168,0.000009479027,0.015779104,0.0007044812,0.00009244358,0.0000115230705,0.000004645247,0.000007350582,0.00022294509],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984377,0.0001550948,0.0002905701,0.0003739353,0.0003972276,0.0003454572],"domain_scores_gemma":[0.9987734,0.00015635588,0.00012407817,0.000711489,0.00018166857,0.000053008862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076232577,0.00016319459,0.00017720276,0.00010268553,0.00014565108,0.00032246322,0.0016623662,0.00011093052,0.00006506918],"category_scores_gemma":[0.00018324368,0.00010865918,0.00003353656,0.00075085287,0.00021629514,0.00055113103,0.00017043733,0.0003090003,0.00012002516],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002706346,0.00046120075,0.007559801,0.00008115914,0.000020983562,0.00013075615,0.035540305,0.0000011819353,0.035693966,0.43812257,0.006071641,0.47604582],"study_design_scores_gemma":[0.0014878875,0.0023314573,0.05042926,0.00046346537,0.00004318402,0.00012698995,0.0004018034,0.05576924,0.41321722,0.46716192,0.007087865,0.001479701],"about_ca_topic_score_codex":0.00016626183,"about_ca_topic_score_gemma":0.0002668243,"teacher_disagreement_score":0.4745661,"about_ca_system_score_codex":0.000051784897,"about_ca_system_score_gemma":0.00008787799,"threshold_uncertainty_score":0.4430993},"labels":[],"label_agreement":null},{"id":"W2947689917","doi":"","title":"KlickLabs at TREC 2018 Precision Medicine track.","year":2018,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Track (disk drive); Precision medicine; Information retrieval; Artificial intelligence; Medicine","score_opus":0.04302524158150629,"score_gpt":0.3146855815370476,"score_spread":0.27166033995554134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947689917","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9674541,0.001355243,0.0035262888,0.0015323556,0.00073766074,0.00017605095,0.0000199683,0.00008702403,0.025111318],"genre_scores_gemma":[0.9821305,0.00030294675,0.00073992123,0.0004500852,0.00085270713,0.0000035563203,0.00006434168,0.00001728988,0.015438619],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984437,0.000081836246,0.00029107908,0.000528914,0.00030171056,0.00035274433],"domain_scores_gemma":[0.99891424,0.000060553153,0.00010854312,0.00052513665,0.00021635272,0.00017516964],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038998426,0.00021012452,0.00024726667,0.00004839081,0.00016208229,0.000019413432,0.0003976635,0.0003340114,0.0013968906],"category_scores_gemma":[0.00094205997,0.00015633783,0.00005765753,0.00018433659,0.0011041503,0.0000034716793,0.0002335012,0.00013393171,0.00036418953],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001049243,0.00006164181,0.0013585204,0.00002160658,0.000052018582,0.000008524553,0.0004011469,1.2133938e-7,0.7493186,0.00025263283,0.09598885,0.15148713],"study_design_scores_gemma":[0.0013026166,0.0035806336,0.010659413,0.00009904224,0.000035848036,0.00005494713,0.0001531246,0.00010838225,0.36003214,0.0005778201,0.6229948,0.00040127797],"about_ca_topic_score_codex":0.00003117627,"about_ca_topic_score_gemma":0.000074068135,"teacher_disagreement_score":0.5270059,"about_ca_system_score_codex":0.00002824224,"about_ca_system_score_gemma":0.00009629839,"threshold_uncertainty_score":0.99951595},"labels":[],"label_agreement":null},{"id":"W3013067086","doi":"","title":"TREC-CHEM 2010.","year":2010,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Sarcoma Diagnosis and Treatment","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Information retrieval; Data science; Natural language processing","score_opus":0.04269585095493014,"score_gpt":0.3006716943740552,"score_spread":0.25797584341912505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013067086","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9633458,0.00023832903,0.00003174912,0.0024680104,0.00044505092,0.00026265244,0.000008837354,0.00010851359,0.033091012],"genre_scores_gemma":[0.9937863,0.00007574696,0.0007138436,0.00037433958,0.00016028923,0.000010289255,0.000021487895,0.000016300362,0.0048414273],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990202,0.000013570222,0.00017774753,0.00028031378,0.00026170322,0.00024641838],"domain_scores_gemma":[0.99902457,0.00010264482,0.0000525737,0.00044488374,0.00015957377,0.00021572637],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00011919145,0.00015738572,0.000257042,0.0000599011,0.000058663387,0.000037344314,0.000104856066,0.00012816439,0.004793619],"category_scores_gemma":[0.00021207271,0.00011999011,0.000096420736,0.00016458651,0.00009958118,0.000054338972,0.00003835571,0.00034377252,0.0010414963],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009205438,0.0020067529,0.5126883,0.000092698996,0.00026598718,0.0006427594,0.0006252706,1.1126499e-7,0.21291825,0.027749078,0.01781258,0.2242777],"study_design_scores_gemma":[0.0027965698,0.00042009808,0.7773194,0.000074948606,0.00019081673,0.00023500068,0.000072203555,0.00012962986,0.16310728,0.00090105546,0.05445335,0.0002996997],"about_ca_topic_score_codex":0.000068294445,"about_ca_topic_score_gemma":0.0000349668,"teacher_disagreement_score":0.2646311,"about_ca_system_score_codex":0.000027004078,"about_ca_system_score_gemma":0.00015401546,"threshold_uncertainty_score":0.9997363},"labels":[],"label_agreement":null},{"id":"W3013135062","doi":"","title":"Overview of the TREC 2018 Real-Time Summarization Track.","year":2018,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Automatic summarization; Computer science; Track (disk drive); Multi-document summarization; Information retrieval; World Wide Web; Operating system","score_opus":0.06766606094889346,"score_gpt":0.2918718006947948,"score_spread":0.22420573974590133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013135062","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4211119,0.00029498612,0.50823236,0.002283662,0.0014702522,0.0006689873,0.000015156428,0.00037100262,0.06555173],"genre_scores_gemma":[0.9923829,0.00008772193,0.0048228344,0.00012539387,0.0001029122,0.0000012649849,0.000001398941,0.0000071896784,0.0024683955],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986296,0.00011963682,0.0003065937,0.0003413227,0.00038964272,0.00021317735],"domain_scores_gemma":[0.9983989,0.0000841157,0.00018683908,0.0009721224,0.0003030272,0.000055000688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038829693,0.00012295473,0.0001847483,0.000045688757,0.00010850737,0.00008051544,0.0012400679,0.00008234408,0.00027794618],"category_scores_gemma":[0.00016787898,0.00008991322,0.000061198065,0.0005567477,0.00015994668,0.00029752663,0.0003100834,0.00010608768,0.00015491825],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008708482,0.00017135334,0.0036874344,0.00016362789,0.000056818248,0.0000040813266,0.0047833775,0.00003107975,0.14096338,0.64150506,0.0034636103,0.2050831],"study_design_scores_gemma":[0.0015451182,0.0007604424,0.067575894,0.00077882427,0.00007795088,0.000032110904,0.0000636272,0.6136886,0.24876136,0.05235922,0.01323874,0.0011181252],"about_ca_topic_score_codex":0.00012193303,"about_ca_topic_score_gemma":0.000021849113,"teacher_disagreement_score":0.61365753,"about_ca_system_score_codex":0.000037676615,"about_ca_system_score_gemma":0.0002345983,"threshold_uncertainty_score":0.3666555},"labels":[],"label_agreement":null},{"id":"W3013164143","doi":"","title":"TREC 2015 Total Recall Track Overview.","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Library Science and Information Systems","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Track (disk drive); Computer science; Recall; Information retrieval; Artificial intelligence; Cognitive psychology; Psychology; Operating system","score_opus":0.10649699156009955,"score_gpt":0.3029353534591744,"score_spread":0.19643836189907482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013164143","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29470178,0.0016294745,0.26558915,0.011607323,0.0057480778,0.001113358,0.00003177564,0.0016258756,0.4179532],"genre_scores_gemma":[0.9881002,0.000028365974,0.0023783618,0.0008566907,0.00012321424,0.0000036334113,0.0000069385364,0.0000060443535,0.0084966095],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978684,0.00010831165,0.00045637475,0.00037547652,0.00081023935,0.00038118765],"domain_scores_gemma":[0.99829197,0.00005820989,0.00018094578,0.0007320019,0.00032614882,0.00041069888],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00089012354,0.00018075347,0.00024342592,0.00012315085,0.000089589485,0.0007537273,0.0015337096,0.000101913254,0.00016694206],"category_scores_gemma":[0.00016204611,0.00014733797,0.00007203789,0.00091873796,0.00008775269,0.006476577,0.00030964563,0.00017750205,0.002601524],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018135014,0.00023671442,0.004240414,0.0001015333,0.000050726794,0.00006785192,0.03913847,0.0001689645,0.0019660054,0.47993448,0.3113755,0.162538],"study_design_scores_gemma":[0.0034245485,0.0017760434,0.017990952,0.0002231475,0.000009628997,0.00048613877,0.0026631728,0.27189198,0.01637867,0.022378162,0.6606503,0.0021272143],"about_ca_topic_score_codex":0.00003359531,"about_ca_topic_score_gemma":0.0000018540602,"teacher_disagreement_score":0.69339836,"about_ca_system_score_codex":0.00005624232,"about_ca_system_score_gemma":0.0006222773,"threshold_uncertainty_score":0.9981751},"labels":[],"label_agreement":null},{"id":"W3013426078","doi":"","title":"Overview of the TREC 2010 Legal Track.","year":2010,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Law, logistics, and international trade","field":"Business, Management and Accounting","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Track (disk drive); Information retrieval; Data science","score_opus":0.07474354518727247,"score_gpt":0.2791428321533284,"score_spread":0.20439928696605594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013426078","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.726491,0.00012372756,0.00038058058,0.0045450013,0.0047044693,0.00030171653,0.000024391331,0.000099775854,0.26332936],"genre_scores_gemma":[0.99347085,0.000022225093,0.00005255751,0.0008672493,0.00076434854,0.0000014811062,0.000007200632,0.000010867063,0.004803222],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.999038,0.00000797709,0.00025663627,0.00018670734,0.0003435114,0.0001671685],"domain_scores_gemma":[0.9991072,0.00005741299,0.00021235927,0.00030679372,0.00030483515,0.00001140416],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00024502163,0.00012252537,0.00016436429,0.00005257642,0.000088343426,0.00017092872,0.00059089,0.00008153382,0.0023314394],"category_scores_gemma":[0.00052881695,0.000085262385,0.00010493595,0.00021968412,0.00030703258,0.00046906734,0.00012768203,0.00029837867,0.00020325954],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003811616,0.00006413259,0.0053369785,0.0000858937,0.000015220793,0.0000017674842,0.000022631966,0.0000010842821,0.008414043,0.97915924,0.0040921085,0.0027687747],"study_design_scores_gemma":[0.0010023282,0.00003126108,0.28724542,0.00015630465,0.000113433765,0.00000899733,0.00007923501,0.0033416664,0.0091016395,0.04621165,0.652216,0.0004920565],"about_ca_topic_score_codex":0.0005212506,"about_ca_topic_score_gemma":0.0003373127,"teacher_disagreement_score":0.9329476,"about_ca_system_score_codex":0.000008366252,"about_ca_system_score_gemma":0.00006208769,"threshold_uncertainty_score":0.9985806},"labels":[],"label_agreement":null},{"id":"W3013632243","doi":"","title":"UWaterlooMDS at the TREC 2019 Decision Track.","year":2019,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Track (disk drive); Artificial intelligence","score_opus":0.016105505773538545,"score_gpt":0.23424234446721587,"score_spread":0.21813683869367734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013632243","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9232996,0.0004508178,0.055141576,0.0012991544,0.00065001793,0.00029247007,0.000008099782,0.00016625994,0.018692007],"genre_scores_gemma":[0.96839345,0.000047811474,0.001755039,0.00019948657,0.000051542564,0.0000014950674,0.0000059270506,0.000010434725,0.029534807],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998111,0.0000734774,0.00033720897,0.0005546141,0.0005285937,0.00039510292],"domain_scores_gemma":[0.9981803,0.00028593472,0.00015254994,0.0011005044,0.00017700154,0.0001036979],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005964246,0.00019649277,0.00026940714,0.00006787943,0.00024020308,0.00041975116,0.0014263467,0.00008978948,0.0022357411],"category_scores_gemma":[0.0000872416,0.00012136311,0.00015704488,0.0006038009,0.00008014351,0.00047701842,0.00062728254,0.0002161484,0.0032546625],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033566155,0.00010767304,0.008981648,0.000030862404,0.000116615054,0.00003082908,0.0031688076,0.0004098923,0.020665111,0.063558325,0.011752992,0.8908416],"study_design_scores_gemma":[0.0031970078,0.0017167075,0.09242983,0.00036484873,0.00014711889,0.0002625136,0.00059292483,0.4983011,0.054358065,0.0173784,0.32872412,0.002527392],"about_ca_topic_score_codex":0.00008053838,"about_ca_topic_score_gemma":0.00005365583,"teacher_disagreement_score":0.8883142,"about_ca_system_score_codex":0.000062733445,"about_ca_system_score_gemma":0.000080966405,"threshold_uncertainty_score":0.99867636},"labels":[],"label_agreement":null},{"id":"W3013646476","doi":"","title":"WaterlooClarke at the TREC 2019 Conversational Assistant Track.","year":2019,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Track (disk drive); Artificial intelligence; Natural language processing; World Wide Web; Multimedia; Operating system","score_opus":0.015280036519228327,"score_gpt":0.25267818070601816,"score_spread":0.23739814418678984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013646476","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67249244,0.0066366345,0.26535907,0.02354282,0.002543878,0.0021687492,0.00009349308,0.0029893212,0.024173595],"genre_scores_gemma":[0.96586347,0.000023591621,0.013487799,0.00062801613,0.00004147689,0.0000047320527,0.000017222832,0.000011697044,0.019921994],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981271,0.00011599555,0.0002640739,0.00052772125,0.0006180558,0.00034703143],"domain_scores_gemma":[0.9984084,0.00023965482,0.00016038948,0.0008455554,0.00026323673,0.000082794584],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005942879,0.00020384685,0.00020452843,0.00007034636,0.00017054463,0.0003480388,0.0015884754,0.00012691822,0.001066134],"category_scores_gemma":[0.00010569498,0.00012929481,0.00008369771,0.00037477125,0.00013298973,0.0005487673,0.00046633682,0.000340288,0.0010123587],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054238405,0.00017688259,0.0060756304,0.00016395611,0.00013250728,0.00009404372,0.0058480212,0.000009616446,0.22946545,0.6223268,0.030231953,0.10493278],"study_design_scores_gemma":[0.0026771054,0.00086257054,0.018678183,0.00036476448,0.00006950647,0.00033448194,0.00022353808,0.038270235,0.7318508,0.107097656,0.09723498,0.0023361826],"about_ca_topic_score_codex":0.000050564828,"about_ca_topic_score_gemma":0.000015935097,"teacher_disagreement_score":0.5152291,"about_ca_system_score_codex":0.00015661663,"about_ca_system_score_gemma":0.00023619777,"threshold_uncertainty_score":0.99984705},"labels":[],"label_agreement":null},{"id":"W3013805123","doi":"","title":"Query and Answer Expansion from Conversation History.","year":2019,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Conversation; Computer science; Query expansion; Information retrieval; Linguistics; Philosophy","score_opus":0.029768301305714517,"score_gpt":0.22192630470486654,"score_spread":0.19215800339915204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013805123","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68203974,0.00032260962,0.31452817,0.00038532552,0.00073802687,0.00012528394,0.0000012324365,0.00010678942,0.0017528591],"genre_scores_gemma":[0.99144274,0.00003289763,0.0073462776,0.00032450358,0.000043854223,0.0000010324841,0.0000038186713,0.000005436986,0.0007994672],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892294,0.00005027606,0.000166186,0.00044133927,0.00025866137,0.00016056637],"domain_scores_gemma":[0.99913806,0.00009539872,0.00007749221,0.00051181926,0.00010030585,0.00007689723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016825002,0.000111747206,0.00014854631,0.00005498488,0.000026954007,0.00007165025,0.0003594314,0.00008504043,0.0004101348],"category_scores_gemma":[0.000046757024,0.00010889912,0.000023887076,0.00007701765,0.000037856425,0.0005160287,0.00016364446,0.00013928094,0.00022327583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021937121,0.00011049836,0.045440454,0.00012054726,0.00006441742,0.00003368938,0.024591379,0.00007304914,0.27212992,0.4620789,0.0015841586,0.1935536],"study_design_scores_gemma":[0.0020820694,0.00029773053,0.0551051,0.00019484034,0.000023845258,0.000014048881,0.00043029277,0.86728674,0.012832682,0.024064194,0.036645237,0.0010232059],"about_ca_topic_score_codex":0.00023564609,"about_ca_topic_score_gemma":0.0000072916223,"teacher_disagreement_score":0.8672137,"about_ca_system_score_codex":0.00011203287,"about_ca_system_score_gemma":0.0001638641,"threshold_uncertainty_score":0.44906884},"labels":[],"label_agreement":null},{"id":"W305879088","doi":"","title":"Domain-specific synonym expansion and validation for biomedical information retrieval (multitext experiments for trec 2004)","year":2004,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Synonym (taxonomy); Information retrieval; Domain (mathematical analysis); Natural language processing; Artificial intelligence; Biology; Mathematics","score_opus":0.03568668182173386,"score_gpt":0.3012554734088946,"score_spread":0.26556879158716074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W305879088","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65543795,0.0008336888,0.34177575,0.00058397074,0.0003610666,0.00070069556,0.000120827,0.000048598944,0.00013746413],"genre_scores_gemma":[0.97017115,0.00030771305,0.027800394,0.00017370717,0.00024375138,0.00004742343,0.0010164409,0.00001907193,0.00022034094],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99860626,0.00003161269,0.00038653458,0.0003805999,0.0002554094,0.00033958172],"domain_scores_gemma":[0.999116,0.0000680079,0.00015058223,0.0002555595,0.00024474465,0.00016507541],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038779862,0.00021385722,0.00022743903,0.000090612986,0.00018602422,0.00009080678,0.00019166344,0.00039389334,0.000029753974],"category_scores_gemma":[0.00030314134,0.0001889045,0.000087095956,0.00014078432,0.00030034487,0.000026462814,0.000077850724,0.00009768,0.000011729861],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033310594,0.00016882262,0.00006358968,0.00014066749,0.000066053915,0.0000014354459,0.0010943669,0.0000050804542,0.8786006,0.002981175,0.0034223206,0.11012484],"study_design_scores_gemma":[0.004860142,0.001845624,0.0003802074,0.00008061715,0.000020933565,0.00001697799,0.0007533231,0.000076382945,0.45298433,0.0013504764,0.5372643,0.0003666911],"about_ca_topic_score_codex":0.00000651369,"about_ca_topic_score_gemma":0.0000012607507,"teacher_disagreement_score":0.53384197,"about_ca_system_score_codex":0.00005549481,"about_ca_system_score_gemma":0.00019807306,"threshold_uncertainty_score":0.77033013},"labels":[],"label_agreement":null},{"id":"W3173145038","doi":"","title":"Spotify at TREC 2020: Genre-Aware Abstractive Podcast Summarization.","year":2020,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Automatic summarization; Computer science; Information retrieval; Baseline (sea); Natural language processing; Task (project management); Key (lock); Granularity; Artificial intelligence; Aggregate (composite); World Wide Web","score_opus":0.029913480157860085,"score_gpt":0.26937939221752977,"score_spread":0.2394659120596697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173145038","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032380518,0.0017709937,0.9431062,0.011397633,0.00041110002,0.0006779219,0.00006856304,0.0027534948,0.0074335947],"genre_scores_gemma":[0.96093535,0.000047055513,0.036561172,0.0011414044,0.00013171084,0.000004930707,0.000031124826,0.000020999667,0.001126259],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978932,0.00008156053,0.00033368924,0.000764023,0.00053832796,0.0003891982],"domain_scores_gemma":[0.9984562,0.00013557229,0.0002290083,0.0005110022,0.00039669263,0.00027153583],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018241745,0.00028137703,0.00029048612,0.00006810493,0.00020496483,0.00036413723,0.0015212427,0.00018355004,0.0004480553],"category_scores_gemma":[0.000399877,0.00025855878,0.00008244612,0.000921272,0.0001032283,0.0008024022,0.0007458455,0.00046216368,0.00040134764],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013507747,0.0004288708,0.0075227,0.00071046624,0.0002591722,0.0019620068,0.022331402,0.00007826212,0.16320431,0.30766737,0.038396876,0.4560878],"study_design_scores_gemma":[0.002639315,0.0015660357,0.015501169,0.0005064323,0.00012145653,0.0003688715,0.00054589874,0.3063624,0.6065407,0.033686608,0.02787075,0.004290371],"about_ca_topic_score_codex":0.000034263467,"about_ca_topic_score_gemma":0.000008073048,"teacher_disagreement_score":0.92855483,"about_ca_system_score_codex":0.00014517145,"about_ca_system_score_gemma":0.0002522674,"threshold_uncertainty_score":0.99998665},"labels":[],"label_agreement":null},{"id":"W3173187978","doi":"","title":"The CLaC System at the TREC 2020 News Track.","year":2020,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Track (disk drive); Computer science; Operating system","score_opus":0.02671213014052321,"score_gpt":0.2636659143570772,"score_spread":0.236953784216554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173187978","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02392247,0.028734643,0.7162219,0.19794215,0.0015483827,0.0021399837,0.00003289929,0.006402558,0.023054993],"genre_scores_gemma":[0.98914236,0.000102672966,0.0073855845,0.0016662666,0.00018676968,0.000011368684,0.0000023159137,0.000015076978,0.001487579],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99796325,0.00021473835,0.00033133355,0.0005398661,0.00056039443,0.00039041176],"domain_scores_gemma":[0.9981389,0.00041501567,0.00020423876,0.0008732941,0.00020630892,0.00016223182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047897155,0.0002256964,0.00021891129,0.000017908902,0.00061528344,0.0007487366,0.0030257057,0.000110922156,0.000043977416],"category_scores_gemma":[0.00044467745,0.00011740638,0.00009879937,0.00076376856,0.00019652757,0.00032103312,0.000606041,0.0004994454,0.00028854032],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037787337,0.00003221944,0.0002941018,0.000213763,0.00006851269,0.00017833606,0.0065372535,0.000004607917,0.029847324,0.5173872,0.06689504,0.37816378],"study_design_scores_gemma":[0.0018466292,0.0013676031,0.001007971,0.00057797163,0.00013561599,0.00055281585,0.0025219496,0.15295553,0.4306833,0.029264277,0.37646613,0.0026202088],"about_ca_topic_score_codex":0.000045854158,"about_ca_topic_score_gemma":0.0000453008,"teacher_disagreement_score":0.9652199,"about_ca_system_score_codex":0.000121020224,"about_ca_system_score_gemma":0.00020017564,"threshold_uncertainty_score":0.7220084},"labels":[],"label_agreement":null},{"id":"W3173373527","doi":"","title":"TREC 2020 Notebook: CAsT Track.","year":2020,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Track (disk drive); Computer science; Operating system","score_opus":0.06551698452288615,"score_gpt":0.26444549199311357,"score_spread":0.19892850747022742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173373527","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046971828,0.00017003505,0.923755,0.0114143705,0.00035933696,0.00023096215,0.0000062884665,0.0005051065,0.016587097],"genre_scores_gemma":[0.98299634,0.000020522577,0.014348483,0.00175255,0.0002135488,0.0000023321602,0.0000019098047,0.000011548843,0.0006527884],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815065,0.000067823756,0.00031412064,0.00067145715,0.00042839505,0.00036754852],"domain_scores_gemma":[0.9987811,0.0000889667,0.00009526215,0.0005798022,0.00014349486,0.0003113618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018005334,0.00019956377,0.00025479426,0.000034520617,0.00009815679,0.00025943448,0.0013514155,0.000098656994,0.00034790635],"category_scores_gemma":[0.0002338918,0.00019313364,0.00008048396,0.00042958633,0.00005602679,0.00040313648,0.00034150723,0.00033526818,0.0007193108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023956936,0.00014213513,0.0014064146,0.0001904962,0.00008450519,0.00065503956,0.019505678,0.00047133808,0.047623683,0.33473304,0.007475096,0.587473],"study_design_scores_gemma":[0.0012302591,0.00046401907,0.0018265576,0.00006820163,0.000023107023,0.00007198882,0.0001559528,0.9271718,0.02473984,0.004991821,0.038272645,0.0009837901],"about_ca_topic_score_codex":0.000029464152,"about_ca_topic_score_gemma":0.000006982217,"teacher_disagreement_score":0.9360245,"about_ca_system_score_codex":0.00003680499,"about_ca_system_score_gemma":0.00024823236,"threshold_uncertainty_score":0.9245525},"labels":[],"label_agreement":null},{"id":"W3173838993","doi":"","title":"Overview of the TREC 2020 Health Misinformation Track.","year":2020,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Misinformation; Track (disk drive); Computer science; Information retrieval; Data science; Computer security","score_opus":0.15562876757196292,"score_gpt":0.3753961097522171,"score_spread":0.21976734218025418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173838993","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37478417,0.0013493134,0.0021533112,0.1984375,0.00078691315,0.0017520261,0.00010710885,0.00028868587,0.42034099],"genre_scores_gemma":[0.9935406,0.000696509,0.0000565255,0.0050420044,0.000066552595,2.3231533e-7,0.0000048260113,0.000003239728,0.00058952445],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99859595,0.00015924059,0.00037812025,0.000084897285,0.0005736178,0.00020818862],"domain_scores_gemma":[0.9990787,0.000059790756,0.00032392557,0.00015038966,0.00016700059,0.00022022625],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00062297046,0.00008044404,0.00017159274,0.00001897445,0.0002614271,0.000081020204,0.00035810025,0.000060443195,0.0015878587],"category_scores_gemma":[0.0010189055,0.000058563845,0.000072131974,0.0006569742,0.00014996857,0.0004923598,0.000037804126,0.0001422476,0.00013652393],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015708523,0.000051110048,0.0005081973,0.00042066775,0.000024276073,4.0316934e-7,0.54102546,0.00001770913,0.00031504445,0.20485353,0.05372569,0.1989008],"study_design_scores_gemma":[0.00177916,0.00053120224,0.066174254,0.00045945673,0.000033525354,0.0000035308217,0.05818657,0.004275978,0.004513449,0.0021618064,0.8612672,0.00061387056],"about_ca_topic_score_codex":0.0002975235,"about_ca_topic_score_gemma":0.00011311077,"teacher_disagreement_score":0.8075415,"about_ca_system_score_codex":0.0000587908,"about_ca_system_score_gemma":0.0009839912,"threshold_uncertainty_score":0.9993248},"labels":[],"label_agreement":null},{"id":"W3175228675","doi":"","title":"Abstract Podcast Summarization using BART with Longformer Attention.","year":2020,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Automatic summarization; Computer science; Information retrieval; Bartok; Multi-document summarization; Natural language processing; Literature; Art","score_opus":0.059727043961456026,"score_gpt":0.25761752029275026,"score_spread":0.19789047633129422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175228675","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22743966,0.000030147756,0.7692777,0.0011009533,0.000055239794,0.0000767385,0.000012997455,0.00015436285,0.0018521964],"genre_scores_gemma":[0.98515135,0.000008270454,0.014300971,0.000300373,0.00006721322,6.2726826e-7,0.000035604113,0.000009009534,0.00012656896],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986485,0.000030058754,0.00022739652,0.00045498728,0.00039493295,0.00024411826],"domain_scores_gemma":[0.99907196,0.000036205885,0.00013793104,0.00037039447,0.00021182986,0.00017170706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015832268,0.00015525993,0.00018934227,0.000070758164,0.00014928106,0.0004069658,0.0006181849,0.00005572169,0.00018436146],"category_scores_gemma":[0.00008730559,0.00012888182,0.00005178137,0.0008689453,0.000060612645,0.00089586305,0.0001534042,0.00016813727,0.0001770538],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009213933,0.00071476353,0.24071987,0.0007053051,0.0010800387,0.0007398482,0.009073413,0.0047293487,0.3980481,0.12958764,0.005499098,0.20818119],"study_design_scores_gemma":[0.0012663798,0.0004649824,0.10446168,0.00025562625,0.00014506244,0.000049984817,0.00037684353,0.87983286,0.007955703,0.0003335483,0.0037057754,0.001151567],"about_ca_topic_score_codex":0.000051396775,"about_ca_topic_score_gemma":0.000006690941,"teacher_disagreement_score":0.87510353,"about_ca_system_score_codex":0.000024862813,"about_ca_system_score_gemma":0.00018911526,"threshold_uncertainty_score":0.5255648},"labels":[],"label_agreement":null},{"id":"W3175902990","doi":"","title":"H2oloo at TREC 2020: When all you got is a hammer... Deep Learning, Health Misinformation, and Precision Medicine.","year":2020,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Misinformation; Hammer; Computer science; Artificial intelligence; Deep learning; Data science; Engineering; Computer security; Mechanical engineering","score_opus":0.056946370647176676,"score_gpt":0.28683623493138527,"score_spread":0.2298898642842086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175902990","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041666992,0.0021954868,0.86802214,0.08236996,0.0003023971,0.00048270065,0.0000043547716,0.00035743823,0.004598543],"genre_scores_gemma":[0.9720333,0.000884134,0.014445996,0.010211411,0.00017011825,0.0000038081737,0.000018520006,0.000016282913,0.0022163822],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975805,0.00014518749,0.0005921987,0.0006357064,0.0006332751,0.00041307975],"domain_scores_gemma":[0.9984088,0.00015662806,0.00030945474,0.00046455357,0.00020445118,0.0004561273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006319039,0.0002389876,0.0003788315,0.0000699812,0.00023428317,0.0001718861,0.00078919536,0.00011149086,0.0006057622],"category_scores_gemma":[0.0005409115,0.00020716037,0.00004489314,0.00031511707,0.00009984105,0.0005652618,0.0005577766,0.00037178007,0.00019451202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022985181,0.000036757494,0.0025190539,0.0002807409,0.00006180203,0.00002196357,0.16737315,0.00020505788,0.001037271,0.01267351,0.0334364,0.78212446],"study_design_scores_gemma":[0.0012136262,0.0008684453,0.0019347934,0.00014404888,0.000014660278,0.000045957655,0.00038673618,0.86116356,0.00051228044,0.0023728104,0.13093553,0.00040755808],"about_ca_topic_score_codex":0.0001697681,"about_ca_topic_score_gemma":0.000026252908,"teacher_disagreement_score":0.93036634,"about_ca_system_score_codex":0.000102072845,"about_ca_system_score_gemma":0.0001796909,"threshold_uncertainty_score":0.84477544},"labels":[],"label_agreement":null},{"id":"W3176031132","doi":"","title":"WaterlooClarke at the Trec 2020 Conversational Assistant Track.","year":2020,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Toronto Metropolitan University","funders":"","keywords":"Computer science; Track (disk drive); Natural language processing; Information retrieval; Artificial intelligence; World Wide Web; Operating system","score_opus":0.028489320889820827,"score_gpt":0.25937814739525294,"score_spread":0.23088882650543213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176031132","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07645247,0.0046914,0.7492498,0.15755695,0.000704942,0.0010580188,0.000076136894,0.0030197022,0.007190541],"genre_scores_gemma":[0.97343993,0.000028310913,0.022021921,0.0030706557,0.00010348082,0.000005840418,0.000013715965,0.000011327832,0.0013047904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981703,0.00012246742,0.00027547253,0.0005437655,0.0005849024,0.00030310283],"domain_scores_gemma":[0.9988093,0.0001829272,0.00014477417,0.00046986208,0.00022935212,0.00016381752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033962508,0.00020152645,0.00019848149,0.000027453649,0.00023533951,0.00036167176,0.0016067715,0.00010448757,0.00063261436],"category_scores_gemma":[0.00032145294,0.00013175339,0.000082229126,0.0005286945,0.00017249546,0.00043895384,0.00053016207,0.000373385,0.00026562373],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010985169,0.0001767809,0.0021357478,0.00029208304,0.00019853392,0.0005841198,0.024656285,0.000013294133,0.28111577,0.4125749,0.086461335,0.19069266],"study_design_scores_gemma":[0.0019163294,0.00087371044,0.0040125665,0.00016648817,0.000080769736,0.00022377905,0.00031191186,0.09378064,0.73473644,0.05226417,0.10975396,0.0018792349],"about_ca_topic_score_codex":0.000018907476,"about_ca_topic_score_gemma":0.000010594131,"teacher_disagreement_score":0.8969875,"about_ca_system_score_codex":0.000096666925,"about_ca_system_score_gemma":0.0002242679,"threshold_uncertainty_score":0.6926684},"labels":[],"label_agreement":null},{"id":"W3176527752","doi":"","title":"Spotify at the TREC 2020 Podcasts Track: Segment Retrieval.","year":2020,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Track (disk drive); Computer science; Information retrieval; World Wide Web; Operating system","score_opus":0.054511271836274806,"score_gpt":0.2668095807724929,"score_spread":0.2122983089362181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176527752","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4373351,0.0012067859,0.4708723,0.07490225,0.0014193568,0.0011103465,0.00003202316,0.0008980934,0.012223746],"genre_scores_gemma":[0.9904486,0.00009128574,0.0035782093,0.0030156132,0.00032241395,0.0000034908953,0.000006069328,0.000020941883,0.0025133684],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967576,0.00019610903,0.00051714334,0.0010071291,0.0009348269,0.0005871675],"domain_scores_gemma":[0.9977999,0.0002495801,0.00020325163,0.0011537547,0.00021736432,0.0003761772],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00059063436,0.00033167878,0.000356995,0.000039911683,0.00030509618,0.00037475783,0.0021964712,0.00014944465,0.00083843665],"category_scores_gemma":[0.00043084793,0.00024908068,0.00015310761,0.00089046574,0.00013818203,0.00039548517,0.0010323725,0.00054656604,0.0010544875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021679557,0.00044584728,0.0039901836,0.00044145083,0.00039261612,0.0010279693,0.040121738,0.0019498477,0.13974653,0.16603185,0.04566588,0.5980181],"study_design_scores_gemma":[0.0032797463,0.0012073545,0.012681178,0.00019534795,0.00011171804,0.00024100984,0.0005572198,0.73652923,0.12512311,0.0051037185,0.11271456,0.0022557862],"about_ca_topic_score_codex":0.000033704633,"about_ca_topic_score_gemma":0.000015018949,"teacher_disagreement_score":0.7345794,"about_ca_system_score_codex":0.00015978116,"about_ca_system_score_gemma":0.00031264275,"threshold_uncertainty_score":0.9999961},"labels":[],"label_agreement":null},{"id":"W3176967269","doi":"","title":"TREC 2020 Podcasts Track Overview.","year":2020,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Track (disk drive); Computer science; Information retrieval; Operating system","score_opus":0.06050055887350622,"score_gpt":0.310150801677166,"score_spread":0.2496502428036598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176967269","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012936906,0.0007891304,0.9662435,0.008811666,0.00013102769,0.00031389293,0.000009229618,0.0015228736,0.0092417635],"genre_scores_gemma":[0.9545207,0.00027510215,0.04237547,0.002239589,0.00013254101,0.0000054161133,0.0000061676224,0.000019574016,0.00042544087],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975493,0.00011426064,0.0004415426,0.0008632253,0.0005900356,0.00044164658],"domain_scores_gemma":[0.99823606,0.00011633833,0.00020597476,0.00082771044,0.00025721383,0.00035671052],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022632009,0.00030336838,0.00044696248,0.000075407195,0.00011026242,0.00026424875,0.0019538992,0.00012374706,0.00040979675],"category_scores_gemma":[0.00034797407,0.00028815726,0.00017787145,0.0015355616,0.00009898301,0.0009223288,0.00051467225,0.00039192932,0.00065645785],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001976266,0.00023921632,0.0016485781,0.00014718957,0.00015384538,0.00040391993,0.0041794544,0.000054576696,0.068325475,0.40194783,0.017554604,0.5051477],"study_design_scores_gemma":[0.002590619,0.0022321648,0.013919223,0.00025908396,0.00017141829,0.000135353,0.00022947023,0.33514,0.30776224,0.09944484,0.23420131,0.00391429],"about_ca_topic_score_codex":0.000012358436,"about_ca_topic_score_gemma":0.0000066837633,"teacher_disagreement_score":0.9415838,"about_ca_system_score_codex":0.0000614885,"about_ca_system_score_gemma":0.0001693409,"threshold_uncertainty_score":0.9999571},"labels":[],"label_agreement":null},{"id":"W3177257816","doi":"","title":"MRG_UWaterloo Participation in the TREC 2020 Precision Medicine Track.","year":2020,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Waterloo","funders":"","keywords":"Track (disk drive); Computer science; Precision medicine; Artificial intelligence; Information retrieval; Medicine","score_opus":0.0453331524621173,"score_gpt":0.31571176415762026,"score_spread":0.270378611695503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177257816","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43755227,0.0003775249,0.4069273,0.14196704,0.0005498421,0.00066150265,0.000003647696,0.0004178246,0.011543059],"genre_scores_gemma":[0.99678916,0.000032204538,0.0011431768,0.0016047619,0.00020503034,0.0000057765533,0.0000058704372,0.000005724205,0.0002082803],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813294,0.00034858924,0.00032444997,0.0004210444,0.00051404134,0.00025891865],"domain_scores_gemma":[0.9990192,0.00031019383,0.00010074477,0.00037460588,0.00007896854,0.00011628777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000791165,0.00014875173,0.00020686453,0.000044094108,0.00009122969,0.00014071897,0.001086178,0.000059853082,0.00021068814],"category_scores_gemma":[0.0007276601,0.00009153779,0.00003644849,0.0008422554,0.00006808299,0.00026649336,0.0001124401,0.00040220076,0.00015942052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023105758,0.00020166172,0.0051019713,0.000071738104,0.000018403878,0.00015928359,0.07650328,0.0005158891,0.005677591,0.037000727,0.005747601,0.8687708],"study_design_scores_gemma":[0.0015348069,0.0014150143,0.0756369,0.0001253677,0.000018271578,0.000019850397,0.00041165404,0.89504117,0.0021463456,0.0052274363,0.018009089,0.00041410807],"about_ca_topic_score_codex":0.00008643723,"about_ca_topic_score_gemma":0.000012743818,"teacher_disagreement_score":0.8945253,"about_ca_system_score_codex":0.000015653515,"about_ca_system_score_gemma":0.000057802878,"threshold_uncertainty_score":0.3732803},"labels":[],"label_agreement":null},{"id":"W335269702","doi":"","title":"Measuring Robustness with First Relevant Score in the TREC 2012 Microblog Track","year":2012,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Open Text (Canada)","funders":"","keywords":"Microblogging; Robustness (evolution); Computer science; Social media; Rank (graph theory); Measure (data warehouse); Context (archaeology); Post hoc; Artificial intelligence; Information retrieval; Data mining; Mathematics; World Wide Web; Medicine","score_opus":0.08410569437123029,"score_gpt":0.2573694548114804,"score_spread":0.1732637604402501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W335269702","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87836176,0.00040131217,0.11265698,0.0023952574,0.00033396517,0.0007858247,0.000008254341,0.00017657943,0.004880047],"genre_scores_gemma":[0.99677986,0.000047358044,0.0024185593,0.00020588859,0.000066645196,0.000015957587,0.0000053859803,0.000009909062,0.00045043815],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9976224,0.00015435934,0.00038651182,0.00028788857,0.00079644105,0.00075243594],"domain_scores_gemma":[0.99848014,0.00026517842,0.0001427108,0.0006830406,0.00025632363,0.00017262813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014597164,0.00024103283,0.00023967479,0.00016967292,0.0002610804,0.00036136893,0.0014702537,0.0001086997,0.000120565295],"category_scores_gemma":[0.00013841777,0.00014787809,0.000061741666,0.0010776086,0.000144849,0.002160625,0.00016704231,0.0005120191,0.00018128385],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025493768,0.0038884,0.24770872,0.0014404036,0.00019287215,0.00049090444,0.14649488,0.002201287,0.011892628,0.3735753,0.008539576,0.20102565],"study_design_scores_gemma":[0.005131407,0.0012532156,0.89332277,0.0010689571,0.00009031172,0.0010746794,0.0022739677,0.031122463,0.029693551,0.0005412903,0.031756394,0.002670999],"about_ca_topic_score_codex":0.000049624698,"about_ca_topic_score_gemma":0.00013629465,"teacher_disagreement_score":0.645614,"about_ca_system_score_codex":0.000089088506,"about_ca_system_score_gemma":0.00024199957,"threshold_uncertainty_score":0.6030294},"labels":[],"label_agreement":null},{"id":"W342589544","doi":"","title":"York University at TREC 2012: CrowdSourcing Track.","year":2012,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Crowdsourcing; Computer science; Quality (philosophy); Work (physics); Crowdsourcing software development; Data science; Control (management); Information retrieval; World Wide Web; Artificial intelligence; Engineering","score_opus":0.04766109456374461,"score_gpt":0.2510287572091137,"score_spread":0.2033676626453691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W342589544","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77113825,0.00030442126,0.17067009,0.0008446156,0.00094366545,0.0004260537,0.000025208104,0.00064000045,0.0550077],"genre_scores_gemma":[0.9802427,0.000023412038,0.0023899043,0.00014364091,0.00007623508,5.352064e-7,0.000007601637,0.0000070608653,0.017108854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981668,0.000113911956,0.00023931536,0.00026238494,0.0005579417,0.00065962155],"domain_scores_gemma":[0.9986211,0.00012658413,0.00013026039,0.0005256203,0.00020137413,0.00039503112],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006179572,0.00018922404,0.00020196501,0.00015968943,0.00039830327,0.00016516712,0.0010045337,0.00013067559,0.00095994456],"category_scores_gemma":[0.0000739869,0.00017835548,0.0001029241,0.00075326714,0.00011117545,0.002084857,0.0004398398,0.00028459972,0.0016846885],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009014531,0.0007410526,0.049825717,0.00018211664,0.00011217477,0.000103357415,0.034410406,0.000036451278,0.027771972,0.658189,0.02264289,0.20508341],"study_design_scores_gemma":[0.0032518927,0.000587743,0.26638803,0.00013835687,0.000087959284,0.00023646653,0.0013450627,0.020749962,0.08391462,0.00064805173,0.6203349,0.0023169585],"about_ca_topic_score_codex":0.00003806946,"about_ca_topic_score_gemma":0.000007871033,"teacher_disagreement_score":0.6575409,"about_ca_system_score_codex":0.00022446275,"about_ca_system_score_gemma":0.00015821136,"threshold_uncertainty_score":0.9999533},"labels":[],"label_agreement":null},{"id":"W413120383","doi":"","title":"Frequent Itemset Mining for Query Expansion in Microblog Ad-hoc Search","year":2012,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Microblogging; Computer science; Social media; Data mining; Information retrieval; Process (computing); Volume (thermodynamics); World Wide Web","score_opus":0.07056403817857194,"score_gpt":0.31730981864514873,"score_spread":0.2467457804665768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W413120383","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45678708,0.0011065203,0.5389504,0.0011415351,0.00037749895,0.000604018,0.00009665192,0.00017273365,0.0007635816],"genre_scores_gemma":[0.86359024,0.000078680394,0.13558958,0.0001744244,0.000076386925,0.000043684955,0.000051502437,0.000012567542,0.00038290757],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840605,0.0000588222,0.00030539648,0.0004232639,0.0002426919,0.0005637589],"domain_scores_gemma":[0.9987223,0.00026967714,0.00007781356,0.0006186032,0.00014313437,0.0001684392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085575023,0.00015824096,0.00019853424,0.00014076984,0.00013093498,0.00017657116,0.0008644817,0.000096446005,0.000032615586],"category_scores_gemma":[0.00011633495,0.00015190628,0.00004824858,0.0005081991,0.000063213876,0.0006446952,0.0002926381,0.00018403925,0.00008816061],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009661803,0.0005929152,0.0061218394,0.00014339798,0.000030301682,0.000009866859,0.012123277,0.000016691465,0.0938437,0.09269581,0.006333132,0.7879925],"study_design_scores_gemma":[0.006385418,0.0016610643,0.11110391,0.0013310879,0.00006699095,0.00018755585,0.0039345846,0.42838588,0.16034603,0.0070513687,0.27553114,0.004014991],"about_ca_topic_score_codex":0.00004435785,"about_ca_topic_score_gemma":0.000015891068,"teacher_disagreement_score":0.78397745,"about_ca_system_score_codex":0.000075343065,"about_ca_system_score_gemma":0.00018559324,"threshold_uncertainty_score":0.6194559},"labels":[],"label_agreement":null},{"id":"W60608539","doi":"","title":"Passage Retrieval by Shrinkage of Language Models.","year":2006,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Information retrieval; Scope (computer science); Search engine; World Wide Web; The Internet; Process (computing); Human–computer information retrieval","score_opus":0.02283974409388151,"score_gpt":0.2468398962509053,"score_spread":0.2240001521570238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W60608539","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24603724,0.00068654725,0.72660106,0.0003207804,0.00018424094,0.00019358075,0.000025360909,0.00025276167,0.025698435],"genre_scores_gemma":[0.98664653,0.000022589607,0.010165585,0.00009147651,0.00007027639,0.0000015120556,0.000013492337,0.000016011996,0.0029725463],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976327,0.000093286755,0.0005193313,0.00060232385,0.00070281816,0.00044956923],"domain_scores_gemma":[0.9983163,0.00012133937,0.00021865987,0.0010233067,0.00021028775,0.000110132285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047555065,0.00024075147,0.00035054964,0.00011383349,0.00007850795,0.00014387126,0.001395929,0.00015930904,0.00010770336],"category_scores_gemma":[0.00008278672,0.00023386999,0.00010282581,0.0005616378,0.000106529405,0.0006011307,0.0003695229,0.00029420835,0.000043376884],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001280554,0.00028046183,0.00065527024,0.00013671673,0.000039608236,0.00009255898,0.0024356195,0.0009868373,0.2201825,0.7536514,0.004261122,0.017149864],"study_design_scores_gemma":[0.0015053663,0.0002597771,0.00092693674,0.000129492,0.00002896097,0.000028859393,0.00018143392,0.6853189,0.2453852,0.063521534,0.0017528923,0.00096062943],"about_ca_topic_score_codex":0.00037143988,"about_ca_topic_score_gemma":0.000012524812,"teacher_disagreement_score":0.7406093,"about_ca_system_score_codex":0.000059424863,"about_ca_system_score_gemma":0.00016200016,"threshold_uncertainty_score":0.95369416},"labels":[],"label_agreement":null},{"id":"W923756419","doi":"","title":"University of Waterloo at TREC 2014 Contextual Suggestion: Experiments with suggestion clustering","year":2014,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Point of interest; Task (project management); Point (geometry); Similarity (geometry); Cluster analysis; Information retrieval; World Wide Web; Special Interest Group; Artificial intelligence; Mathematics","score_opus":0.01781061543086193,"score_gpt":0.24038491729818853,"score_spread":0.2225743018673266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W923756419","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26303977,0.000038117676,0.73461235,0.00016652484,0.000048892554,0.0001563924,0.0000025617278,0.0002773454,0.001658067],"genre_scores_gemma":[0.96947986,0.00002705749,0.028015839,0.00003211186,0.000019714229,0.000001014999,0.000009070095,0.000011158564,0.0024041461],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983216,0.000156059,0.00024599314,0.0005483609,0.0004311122,0.00029690244],"domain_scores_gemma":[0.9984159,0.0001187243,0.00026320375,0.00073556096,0.00033547185,0.00013112815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003266698,0.00022248544,0.00035823463,0.00013717994,0.0001730044,0.00005506869,0.0008748384,0.00010653495,0.00015825884],"category_scores_gemma":[0.000053468797,0.00020462816,0.00007064814,0.00034379077,0.00023197492,0.00043252896,0.00043671433,0.00015328657,0.0000785789],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004294624,0.0009669009,0.032602195,0.00035660816,0.0005350962,0.00019204365,0.020991009,0.0023870585,0.47332367,0.12494903,0.004742731,0.334659],"study_design_scores_gemma":[0.0050357766,0.0035358048,0.025307402,0.0006443459,0.00017078845,0.00012629628,0.0007715307,0.32701156,0.6203047,0.002460223,0.012501664,0.0021299017],"about_ca_topic_score_codex":0.00020604781,"about_ca_topic_score_gemma":0.00022738003,"teacher_disagreement_score":0.7065965,"about_ca_system_score_codex":0.00014771103,"about_ca_system_score_gemma":0.000067148765,"threshold_uncertainty_score":0.8344494},"labels":[],"label_agreement":null},{"id":"W94318738","doi":"","title":"Synonym-Based Expansion and Boosting-Based Re-Ranking: A Two-phase Approach for Genomic Information Retrieval.","year":2005,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Boosting (machine learning); WordNet; Information retrieval; Artificial intelligence; Ranking (information retrieval); Machine learning","score_opus":0.028944597508011552,"score_gpt":0.29892116513885053,"score_spread":0.269976567630839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W94318738","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030784588,0.0007144722,0.9651731,0.0009766364,0.00007379136,0.00093451655,0.000021446418,0.0008787909,0.00044266094],"genre_scores_gemma":[0.6012512,0.000004227714,0.3976868,0.0008909154,0.00005283218,0.000016215301,0.000052470976,0.000012938964,0.000032442396],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99773467,0.00009130008,0.0005655849,0.0005871018,0.00052813394,0.00049323053],"domain_scores_gemma":[0.9978603,0.00030973114,0.00039585686,0.00070070854,0.0005558196,0.00017755941],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010993854,0.00034195313,0.00035111237,0.00033848677,0.00031645535,0.0006914739,0.001004195,0.00020555315,0.000023365485],"category_scores_gemma":[0.00076809974,0.00031593928,0.00009078829,0.0006357682,0.0001364913,0.0015526232,0.00019452111,0.00036822917,0.000011040596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040681954,0.00070302887,0.00020769374,0.0014419946,0.000057786267,0.000019304505,0.0037561487,0.001416461,0.17823605,0.049575046,0.0014843578,0.7590339],"study_design_scores_gemma":[0.0030931605,0.00044924382,0.000038137263,0.00013286242,0.000020471844,0.000011881591,0.000025231351,0.85143995,0.14058362,0.0016372168,0.0020815837,0.00048664413],"about_ca_topic_score_codex":0.000017540653,"about_ca_topic_score_gemma":0.0000029078342,"teacher_disagreement_score":0.8500235,"about_ca_system_score_codex":0.00017251585,"about_ca_system_score_gemma":0.0005397989,"threshold_uncertainty_score":0.99992925},"labels":[],"label_agreement":null}]}