{"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018713081,0.03735979,0.89232945,0.0068526375,0.001010235,0.001774134,0.0035509884,0.0028381285,0.0355716],"genre_scores_gemma":[0.10449985,0.0073017785,0.85457027,0.0020436007,0.0010365036,0.0021521251,0.0042212824,0.0005117679,0.023662828],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98360276,0.011269539,0.0007411248,0.0016530178,0.0023386753,0.00039481142],"domain_scores_gemma":[0.9389367,0.053080663,0.0019797764,0.0030764134,0.0021217985,0.00080466096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014690832,0.0018432199,0.002918023,0.015520417,0.0026414543,0.0074604745,0.003660403,0.005022048,0.02362129],"category_scores_gemma":[0.05330307,0.001121327,0.0019682755,0.0123816505,0.0028923317,0.013105141,0.004800465,0.0026239057,0.008235662],"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":[0.00041237008,0.0007340079,0.010136252,0.0032036358,0.0006105514,0.00028818464,0.002804995,0.0061011864,0.0020481914,0.10162462,0.05684399,0.81519204],"study_design_scores_gemma":[0.00040849185,0.0003256188,0.012074715,0.0012813129,0.00036311615,0.0014919572,0.0050764894,0.14037354,0.0043182415,0.6257686,0.2082094,0.00030856853],"about_ca_topic_score_codex":0.0030824183,"about_ca_topic_score_gemma":0.0069263177,"teacher_disagreement_score":0.02362129,"about_ca_system_score_codex":0.001788444,"about_ca_system_score_gemma":0.0021726494,"threshold_uncertainty_score":0.079021096},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97261727,0.0022498874,0.009712175,0.00072923914,0.00038888768,0.0008673828,0.0031922988,0.004077038,0.0061658733],"genre_scores_gemma":[0.93731666,0.00046641123,0.040339682,0.0004498585,0.00041174487,0.0007778126,0.014030347,0.0006252815,0.0055822595],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9843163,0.008304994,0.0013671031,0.002150874,0.0032294388,0.00063130556],"domain_scores_gemma":[0.9626464,0.028518025,0.001482786,0.002916577,0.0032748391,0.0011613291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0119051,0.0019263175,0.0022097435,0.0013375221,0.0020686362,0.0019956194,0.0022434997,0.0024166508,0.0038093368],"category_scores_gemma":[0.040022634,0.00073528895,0.0009949096,0.0024220021,0.0010840874,0.0028515118,0.0017639139,0.002137366,0.0016312313],"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":[0.032369025,0.02388874,0.038365487,0.008505081,0.00380754,0.0024054607,0.0058686202,0.1216327,0.16252884,0.0032088214,0.10051386,0.4969058],"study_design_scores_gemma":[0.008120317,0.03329992,0.117036976,0.0003721862,0.0019065274,0.0031567623,0.0037612566,0.5885445,0.18037146,0.004405428,0.058043182,0.0009815376],"about_ca_topic_score_codex":0.014327412,"about_ca_topic_score_gemma":0.014742744,"teacher_disagreement_score":0.014327412,"about_ca_system_score_codex":0.001887333,"about_ca_system_score_gemma":0.0015692704,"threshold_uncertainty_score":0.06296098},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.897703,0.010359552,0.055448927,0.0027151993,0.0011525551,0.004998323,0.0074133985,0.005371933,0.0148371775],"genre_scores_gemma":[0.82566875,0.0015730729,0.14220762,0.0014371523,0.000602637,0.0030954455,0.015439944,0.0009842828,0.008991082],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9774818,0.014171603,0.002023522,0.0016711794,0.0038148665,0.00083688844],"domain_scores_gemma":[0.8522637,0.12971237,0.002298871,0.008496322,0.004538774,0.0026899641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026072672,0.0023123887,0.0029715397,0.0026154423,0.0025587913,0.00318797,0.0038222496,0.0057508303,0.009843691],"category_scores_gemma":[0.11008709,0.0010825219,0.0016291032,0.0034346944,0.0019941658,0.008370861,0.0036976966,0.0050196825,0.0037226884],"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":[0.0617849,0.04685712,0.02785149,0.016223544,0.0044765305,0.0023694849,0.008600711,0.098679684,0.041934926,0.010081804,0.10548579,0.57565403],"study_design_scores_gemma":[0.01808015,0.04322507,0.03478437,0.000553309,0.0019644701,0.002539945,0.0046634614,0.79538757,0.04086543,0.028733382,0.028430022,0.00077286264],"about_ca_topic_score_codex":0.010601699,"about_ca_topic_score_gemma":0.009047964,"teacher_disagreement_score":0.026072672,"about_ca_system_score_codex":0.0017748887,"about_ca_system_score_gemma":0.0020058488,"threshold_uncertainty_score":0.13788706},"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":"software","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044980686,0.0041585546,0.20666394,0.0030587143,0.0032430512,0.0025570083,0.13598646,0.570745,0.0286066],"genre_scores_gemma":[0.103589185,0.001202684,0.3185437,0.0016583924,0.00093543495,0.0014847639,0.49911192,0.0129681565,0.060505785],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9957045,0.00078234,0.00031453988,0.0005543639,0.0022895762,0.00035469644],"domain_scores_gemma":[0.9926092,0.0013039632,0.00039314028,0.0018430982,0.0033762031,0.00047439206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045876163,0.0031984493,0.0036510953,0.008038163,0.0028387131,0.0042837695,0.0037465044,0.004015462,0.016776616],"category_scores_gemma":[0.012722408,0.0011492546,0.0009294952,0.00452114,0.00082537165,0.004198157,0.0023658706,0.0022226728,0.027681518],"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":[0.001319403,0.00064662466,0.00205862,0.0007262903,0.00028679133,0.00022924921,0.0001546966,0.0036526127,0.012919976,0.0013652962,0.8126759,0.16396444],"study_design_scores_gemma":[0.0011968997,0.0016632495,0.007841817,0.0001682527,0.00045750878,0.0007092048,0.00020857574,0.38268933,0.11705915,0.0073373234,0.48020995,0.0004586857],"about_ca_topic_score_codex":0.019576581,"about_ca_topic_score_gemma":0.02205114,"teacher_disagreement_score":0.019576581,"about_ca_system_score_codex":0.0014280541,"about_ca_system_score_gemma":0.0025334153,"threshold_uncertainty_score":0.056123376},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001226862,0.030035421,0.009792499,0.089246795,0.11280469,0.0016902037,0.0449144,0.0102738,0.70001537],"genre_scores_gemma":[0.005274868,0.03588816,0.013759162,0.024106102,0.024715863,0.0014886745,0.0541854,0.0040522306,0.83652955],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99708986,0.00042175953,0.00028341016,0.00036051995,0.0014472256,0.00039717942],"domain_scores_gemma":[0.9850134,0.001158469,0.00071278185,0.0008333559,0.00763557,0.0046464144],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00602668,0.0009615357,0.001038782,0.005878786,0.0024972563,0.0076836147,0.0033376939,0.0037769794,0.48294872],"category_scores_gemma":[0.01748159,0.00049418333,0.0011302475,0.0060588573,0.0007175971,0.005218913,0.0057065054,0.003392581,0.34474126],"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":[0.000034305198,0.000025730067,0.00017009981,0.00037593034,0.0000036657386,0.000034312627,0.000028566597,0.00004081648,0.0001297848,0.0017885824,0.9035607,0.093807615],"study_design_scores_gemma":[0.000002921957,0.00000907194,0.00019538433,0.00019070887,0.0000022083534,0.000024569901,0.000019350668,0.000013962655,0.000036509504,0.0002701392,0.9992304,0.000004870734],"about_ca_topic_score_codex":0.008686122,"about_ca_topic_score_gemma":0.018406708,"teacher_disagreement_score":0.48294872,"about_ca_system_score_codex":0.00287945,"about_ca_system_score_gemma":0.0136851845,"threshold_uncertainty_score":0.7375109},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19958167,0.014601297,0.070250966,0.015389925,0.005443461,0.010489898,0.27110282,0.104081154,0.3090588],"genre_scores_gemma":[0.2144273,0.0021698861,0.13442563,0.0021363366,0.0010654229,0.0058000116,0.40896642,0.003307949,0.22770102],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956963,0.0016294926,0.0004465065,0.00053153496,0.0012343517,0.0004618245],"domain_scores_gemma":[0.9891411,0.003109242,0.00047479666,0.0014408608,0.004506763,0.0013272048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0079503395,0.0016035959,0.0018686632,0.0056193597,0.0034808265,0.0029427106,0.0019064359,0.002129144,0.044942725],"category_scores_gemma":[0.015702758,0.00063610636,0.00065441965,0.0043267175,0.00054213614,0.0042011226,0.0017787386,0.002149923,0.025597218],"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":[0.00048726433,0.0006787258,0.0016007338,0.00078295387,0.00006155766,0.00010737915,0.0003409448,0.00195333,0.0050791716,0.0018241188,0.89139146,0.09569229],"study_design_scores_gemma":[0.0015704733,0.0012437627,0.030141897,0.0003644905,0.0002012783,0.00035387042,0.0011905703,0.062200237,0.03513097,0.0070488993,0.86004806,0.0005055028],"about_ca_topic_score_codex":0.053654708,"about_ca_topic_score_gemma":0.08222938,"teacher_disagreement_score":0.053654708,"about_ca_system_score_codex":0.0036058293,"about_ca_system_score_gemma":0.0035793418,"threshold_uncertainty_score":0.15034842},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20251517,0.013509169,0.10232138,0.017924191,0.01224547,0.029883651,0.37520462,0.11147013,0.13492623],"genre_scores_gemma":[0.13655259,0.0019431115,0.14213353,0.0033081283,0.0009143121,0.00908906,0.5800944,0.0033920314,0.1225728],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99099123,0.0031621882,0.0005628322,0.0011572134,0.0035008525,0.0006257686],"domain_scores_gemma":[0.9733786,0.004607114,0.00068762526,0.0039517456,0.015159009,0.0022158767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018954702,0.002167927,0.0024028097,0.003347807,0.004405282,0.002766868,0.0031202354,0.0025734187,0.02452498],"category_scores_gemma":[0.026548652,0.0010096851,0.00078451005,0.0029665807,0.0008509378,0.0043100975,0.0018531883,0.0044313325,0.024356905],"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":[0.0007287416,0.001454767,0.0014475173,0.00045324,0.000105495135,0.00007205534,0.00016477046,0.0023749436,0.008225492,0.0008841908,0.9236892,0.060399696],"study_design_scores_gemma":[0.0048240754,0.004532778,0.044734966,0.00030185928,0.00037346449,0.0004969133,0.000539904,0.092825204,0.06401194,0.005096456,0.7814369,0.00082556054],"about_ca_topic_score_codex":0.114738636,"about_ca_topic_score_gemma":0.16807868,"teacher_disagreement_score":0.114738636,"about_ca_system_score_codex":0.0044289096,"about_ca_system_score_gemma":0.0072543146,"threshold_uncertainty_score":0.2281416},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06318483,0.008305123,0.012526862,0.031609952,0.0054027913,0.0027140516,0.401353,0.01544599,0.45945746],"genre_scores_gemma":[0.08645991,0.0031636541,0.022779083,0.0024129474,0.000774231,0.0009803488,0.39273846,0.0016682595,0.4890231],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99709153,0.0004257826,0.0001238317,0.000495307,0.0015312867,0.0003321784],"domain_scores_gemma":[0.9902734,0.0008415773,0.00022078025,0.00056073535,0.0069873654,0.0011161343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003924493,0.00091375184,0.0010965926,0.0035153732,0.0039269566,0.004647271,0.0012181875,0.0008283218,0.06664876],"category_scores_gemma":[0.00715332,0.0005189852,0.00026742645,0.0032678563,0.00071255973,0.0029928903,0.0011178502,0.0011139951,0.026151825],"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":[0.00007921858,0.000101853315,0.001245736,0.00014421693,0.000008911351,0.000035235433,0.00012672295,0.00015820065,0.0016063503,0.0006836491,0.9637947,0.032015137],"study_design_scores_gemma":[0.00017495161,0.00015320693,0.019710366,0.00017511185,0.00003182698,0.000066844455,0.00070185994,0.0051787486,0.0053416416,0.0011242372,0.96724606,0.00009504301],"about_ca_topic_score_codex":0.47273383,"about_ca_topic_score_gemma":0.682788,"teacher_disagreement_score":0.47273383,"about_ca_system_score_codex":0.009687452,"about_ca_system_score_gemma":0.013019221,"threshold_uncertainty_score":0.9399644},"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":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016463615,0.015457493,0.011152468,0.0227003,0.008755158,0.0037275837,0.846627,0.02893306,0.0461833],"genre_scores_gemma":[0.0120920325,0.002769531,0.014241668,0.0023645887,0.0011882134,0.0016273463,0.9285212,0.0010026678,0.036192656],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9862541,0.0040778727,0.0012572231,0.0013995582,0.005976236,0.0010350011],"domain_scores_gemma":[0.96151483,0.0067528985,0.0021585855,0.005678092,0.01964117,0.004254486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02224003,0.004561493,0.0044159372,0.009036218,0.0040735663,0.0057571204,0.0045549246,0.004161833,0.05565176],"category_scores_gemma":[0.0326659,0.0011269234,0.0018670512,0.008430782,0.0011978677,0.0066741174,0.003105791,0.0047088126,0.046427347],"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":[0.00020643655,0.00016831017,0.00044234897,0.00050558033,0.000059704922,0.000034186556,0.000028849012,0.00039236728,0.0010605283,0.0002931753,0.98086697,0.015941504],"study_design_scores_gemma":[0.0016303954,0.0010416599,0.02624767,0.0006141818,0.00033559772,0.00043964057,0.0003129735,0.018501543,0.009926459,0.0032305946,0.93732196,0.00039723577],"about_ca_topic_score_codex":0.10271128,"about_ca_topic_score_gemma":0.15404584,"teacher_disagreement_score":0.10271128,"about_ca_system_score_codex":0.0069420626,"about_ca_system_score_gemma":0.011715938,"threshold_uncertainty_score":0.20422691},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022839045,0.0027877616,0.93333066,0.00061656086,0.00023034067,0.0011976997,0.004581975,0.026819477,0.007596481],"genre_scores_gemma":[0.20104505,0.0017974123,0.7693122,0.0004087705,0.00043160978,0.0008591648,0.015932808,0.0015971481,0.008615846],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99597126,0.00061101577,0.0005147148,0.0005409865,0.0020567535,0.00030527677],"domain_scores_gemma":[0.99261546,0.0017394004,0.00049420935,0.0028723576,0.002026619,0.00025186306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025060042,0.0010287914,0.0022462842,0.007955873,0.0015783964,0.0035101438,0.0028930097,0.0012447924,0.004643549],"category_scores_gemma":[0.010185452,0.0006456714,0.0012040886,0.01168967,0.001344521,0.0066773486,0.0029018938,0.0012564025,0.0047821617],"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":[0.00037246008,0.0007020903,0.004344872,0.00086464774,0.00015114239,0.00022258631,0.0007940956,0.015694553,0.071589075,0.039746016,0.071065605,0.79445285],"study_design_scores_gemma":[0.0002465493,0.00078097987,0.006111533,0.00012765254,0.00023895441,0.0016671973,0.00071334455,0.596708,0.12889333,0.10967939,0.15453932,0.0002937441],"about_ca_topic_score_codex":0.0054097064,"about_ca_topic_score_gemma":0.0073990836,"teacher_disagreement_score":0.007955873,"about_ca_system_score_codex":0.0014854146,"about_ca_system_score_gemma":0.002561274,"threshold_uncertainty_score":0.015534282},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021564543,0.0011419544,0.70789266,0.0021198795,0.00059181533,0.0014779385,0.008540386,0.23761956,0.019051244],"genre_scores_gemma":[0.1391872,0.00066149567,0.7768408,0.0018601711,0.00030573749,0.000841115,0.027915915,0.0066673285,0.04572025],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972149,0.00057547033,0.0002944801,0.0008810735,0.00086407276,0.00016993731],"domain_scores_gemma":[0.9959078,0.0008428835,0.00020509765,0.0012992956,0.0015284701,0.00021648462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004331584,0.0012993452,0.0016603756,0.002724305,0.0011612981,0.0026325553,0.003740552,0.0023580359,0.021742456],"category_scores_gemma":[0.00815233,0.0009049403,0.0015033173,0.0012385584,0.0011274472,0.005056226,0.003380413,0.0031409469,0.016759612],"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":[0.0012449847,0.0007395202,0.003054888,0.0015461256,0.0003236627,0.000505943,0.0013110933,0.014273748,0.10934965,0.029407611,0.32714584,0.51109695],"study_design_scores_gemma":[0.0004850458,0.0008989056,0.0030641719,0.00014796031,0.00026245118,0.0011487528,0.0003465562,0.37211236,0.15032706,0.035016958,0.43579692,0.00039277677],"about_ca_topic_score_codex":0.012273865,"about_ca_topic_score_gemma":0.010109714,"teacher_disagreement_score":0.021742456,"about_ca_system_score_codex":0.0021492213,"about_ca_system_score_gemma":0.0029680212,"threshold_uncertainty_score":0.07273579},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50603604,0.014326471,0.2505009,0.008222388,0.0072657913,0.0087485425,0.05249018,0.06644563,0.08596397],"genre_scores_gemma":[0.64658755,0.0008632124,0.24010946,0.0013037252,0.0010527514,0.003308867,0.0809052,0.0019256015,0.023943648],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9804387,0.006965431,0.0011705604,0.0034551236,0.0068779257,0.0010923109],"domain_scores_gemma":[0.9806974,0.0046479544,0.0007798347,0.0048809214,0.007594686,0.001399185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02397801,0.0028022074,0.002992799,0.0045212945,0.0025705441,0.0029803808,0.0042262506,0.0025137784,0.0068952222],"category_scores_gemma":[0.03275941,0.0006501659,0.0013023484,0.003851366,0.0013574841,0.0041917614,0.0031447904,0.0039422954,0.0054177297],"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":[0.004258039,0.0037506174,0.007264738,0.0014127198,0.0007542355,0.00026164495,0.0004359516,0.06414228,0.020581966,0.0041170064,0.3172338,0.575787],"study_design_scores_gemma":[0.0042232675,0.0054255193,0.036562447,0.00021545905,0.0004951401,0.00054056273,0.0008396891,0.7540265,0.10816098,0.013087308,0.07574192,0.00068111904],"about_ca_topic_score_codex":0.024245862,"about_ca_topic_score_gemma":0.03495745,"teacher_disagreement_score":0.024245862,"about_ca_system_score_codex":0.0059259715,"about_ca_system_score_gemma":0.0040288274,"threshold_uncertainty_score":0.12680936},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9913037,0.00015882068,0.0008631539,0.000110983456,0.000020870046,0.00044683125,0.00047452303,0.0000810964,0.00653993],"genre_scores_gemma":[0.9938188,0.0001225275,0.0017082278,0.0000733509,0.000031115353,0.0011081605,0.0006381111,0.00010517679,0.0023944029],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98736763,0.006303018,0.0020224052,0.0009969643,0.002203785,0.0011063102],"domain_scores_gemma":[0.66171235,0.2984511,0.013466776,0.007973975,0.014791447,0.0036043483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020295415,0.0007963474,0.0009951589,0.0020867109,0.00098515,0.002720416,0.0010727288,0.0013196453,0.0077946],"category_scores_gemma":[0.13502982,0.00066153036,0.0013838916,0.0009927006,0.0015719307,0.0027769632,0.0019116846,0.0016487531,0.0014601758],"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":[0.02346682,0.005915126,0.6864419,0.0033435093,0.0010358839,0.0006009404,0.106474206,0.0017594079,0.021438245,0.001403093,0.0054903356,0.14263055],"study_design_scores_gemma":[0.00036161943,0.0068716602,0.94701046,0.00026115094,0.00062995777,0.00027301753,0.030402401,0.0029082985,0.006418208,0.0008036398,0.0038914555,0.0001682561],"about_ca_topic_score_codex":0.0019148672,"about_ca_topic_score_gemma":0.0021603464,"teacher_disagreement_score":0.020295415,"about_ca_system_score_codex":0.0007884593,"about_ca_system_score_gemma":0.0008801713,"threshold_uncertainty_score":0.10733366},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05558458,0.003463844,0.57046056,0.0030892123,0.0009544568,0.0023454223,0.01587123,0.30800667,0.040223982],"genre_scores_gemma":[0.27398852,0.0012416862,0.57071567,0.0022419137,0.00040752813,0.0010471623,0.08058278,0.012791768,0.05698301],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9944887,0.0021359182,0.00033993943,0.0013528571,0.001348785,0.00033379774],"domain_scores_gemma":[0.9940136,0.0021863894,0.00020036373,0.0017836149,0.0015725913,0.00024349625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050573153,0.0014108045,0.0016734877,0.001758084,0.0009932478,0.003024858,0.0035656083,0.0022874332,0.018586976],"category_scores_gemma":[0.010510463,0.000895262,0.0012459375,0.001162159,0.0010838478,0.004356581,0.002328982,0.003061239,0.011126745],"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":[0.0014841567,0.0009335515,0.0015840753,0.0019325733,0.00038149062,0.0007738547,0.0012717266,0.017940503,0.08060946,0.021937454,0.3731783,0.49797282],"study_design_scores_gemma":[0.0010704933,0.00079660176,0.003957591,0.0001442709,0.00025004422,0.0013886854,0.0005377437,0.2815157,0.1685955,0.026552418,0.5148561,0.0003349071],"about_ca_topic_score_codex":0.012521504,"about_ca_topic_score_gemma":0.011731834,"teacher_disagreement_score":0.018586976,"about_ca_system_score_codex":0.0020801795,"about_ca_system_score_gemma":0.0019075205,"threshold_uncertainty_score":0.062179565},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63642544,0.021661274,0.06466748,0.009958145,0.006254591,0.006907433,0.1079313,0.043009583,0.10318473],"genre_scores_gemma":[0.6806932,0.0025406163,0.08554547,0.0028753835,0.0009148879,0.0026696445,0.17021467,0.0020977734,0.05244831],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99447745,0.0028328872,0.00022920218,0.0009008114,0.0010575969,0.00050210726],"domain_scores_gemma":[0.9900803,0.0054629333,0.00032787028,0.0014801621,0.0015788117,0.0010698282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011960326,0.0026300538,0.0018965852,0.001385499,0.0027202985,0.002266593,0.003127241,0.0025691898,0.011051055],"category_scores_gemma":[0.020926608,0.00077662186,0.001473482,0.0020807132,0.0009778687,0.0040662447,0.0018403193,0.003653599,0.0057027917],"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":[0.005400076,0.011218584,0.009376397,0.0019056828,0.0012778353,0.00043381038,0.000850266,0.068797134,0.008614266,0.00544503,0.646936,0.23974499],"study_design_scores_gemma":[0.0052233357,0.0075320373,0.049938887,0.00040955056,0.0009850633,0.00042281713,0.0017648526,0.7205356,0.028671851,0.01795079,0.16576016,0.0008050893],"about_ca_topic_score_codex":0.291977,"about_ca_topic_score_gemma":0.38230178,"teacher_disagreement_score":0.291977,"about_ca_system_score_codex":0.0060455017,"about_ca_system_score_gemma":0.0050003836,"threshold_uncertainty_score":0.58055496},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029052304,0.009333902,0.022104999,0.014305613,0.006357309,0.0041176667,0.6694995,0.064375,0.18085365],"genre_scores_gemma":[0.0395139,0.0017978078,0.025016133,0.0017702611,0.0010349163,0.0018645441,0.68146086,0.0032912397,0.2442504],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99655247,0.00073851354,0.00022965415,0.0004685391,0.0016219951,0.0003888881],"domain_scores_gemma":[0.9870042,0.0015035962,0.0005097398,0.0014804885,0.0073649846,0.0021370288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069495947,0.0032313217,0.0019414168,0.004547769,0.0028905154,0.0038264696,0.0023509972,0.0019638287,0.092946626],"category_scores_gemma":[0.011226455,0.00088790176,0.0005008347,0.0042691543,0.0006743216,0.0038711815,0.0014379265,0.0026716131,0.08078127],"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":[0.00012637221,0.00017298832,0.00030356774,0.00018384312,0.00001666112,0.000022274113,0.000023725122,0.00034607694,0.0019912678,0.0002439517,0.97469044,0.021878773],"study_design_scores_gemma":[0.0010040097,0.0007837317,0.023384612,0.00025494397,0.00013149335,0.00023987965,0.00029118234,0.018685548,0.020273896,0.0027552096,0.9318774,0.00031817128],"about_ca_topic_score_codex":0.14813614,"about_ca_topic_score_gemma":0.26826215,"teacher_disagreement_score":0.14813614,"about_ca_system_score_codex":0.0035647848,"about_ca_system_score_gemma":0.005611433,"threshold_uncertainty_score":0.3109374},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022957312,0.03803134,0.038710423,0.01661871,0.009702956,0.012438736,0.4955842,0.03443097,0.33152533],"genre_scores_gemma":[0.036455646,0.014381539,0.059191037,0.004754162,0.0029500404,0.0065796524,0.7741999,0.0036463367,0.09784171],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9897261,0.0015170596,0.0009223312,0.001416161,0.005186392,0.0012319952],"domain_scores_gemma":[0.9841091,0.0011462452,0.00077176036,0.0015812586,0.010566116,0.0018254584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010845855,0.0021112785,0.0017983998,0.013765684,0.0036910744,0.005978091,0.0032870048,0.0025874218,0.035982363],"category_scores_gemma":[0.011145874,0.0010462023,0.0014022005,0.013236362,0.0006920851,0.00550031,0.0022309166,0.0024260506,0.044078525],"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":[0.00023128257,0.00028500924,0.0013238364,0.00073644373,0.0000347419,0.000047639816,0.000067854955,0.0010317311,0.0029354438,0.0014645862,0.8869195,0.10492187],"study_design_scores_gemma":[0.00010673401,0.0003522491,0.011203073,0.00040648447,0.00006408167,0.00015560571,0.00013147401,0.0029912791,0.0035826932,0.0014761813,0.97939795,0.00013219632],"about_ca_topic_score_codex":0.104434036,"about_ca_topic_score_gemma":0.12762916,"teacher_disagreement_score":0.104434036,"about_ca_system_score_codex":0.007895012,"about_ca_system_score_gemma":0.011946922,"threshold_uncertainty_score":0.20765233},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10564944,0.014168375,0.021209337,0.014621,0.017034084,0.006981912,0.665282,0.07146175,0.08359205],"genre_scores_gemma":[0.081927255,0.0026904528,0.041468475,0.0021497733,0.0020000604,0.0033739563,0.7520476,0.0023321419,0.11201039],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952023,0.0016081705,0.00024301517,0.00066723936,0.0017957914,0.00048356078],"domain_scores_gemma":[0.9892335,0.0024838143,0.00036847306,0.0015114022,0.0047454885,0.001657298],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0073954742,0.003923351,0.002864947,0.006008905,0.0039439905,0.0038228033,0.002702709,0.002966729,0.03237714],"category_scores_gemma":[0.014871695,0.0007151858,0.0011093096,0.0035324304,0.00065842504,0.006441104,0.002290321,0.0030527695,0.01968764],"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":[0.00034605231,0.00069485087,0.0006904686,0.0005582514,0.000089696536,0.00008174958,0.00006531863,0.0011132892,0.0021312684,0.00053423864,0.9588061,0.034888797],"study_design_scores_gemma":[0.0019282438,0.0015311657,0.021685459,0.00030478975,0.00041038904,0.0003830646,0.0010437481,0.096178755,0.03209002,0.0033285657,0.84071696,0.00039895065],"about_ca_topic_score_codex":0.17701058,"about_ca_topic_score_gemma":0.24732497,"teacher_disagreement_score":0.17701058,"about_ca_system_score_codex":0.006484662,"about_ca_system_score_gemma":0.0055450397,"threshold_uncertainty_score":0.35196054},"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":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014678959,0.009080539,0.012938594,0.011736397,0.0029357255,0.0024574022,0.7627143,0.028921807,0.15453632],"genre_scores_gemma":[0.026019836,0.002701474,0.020794334,0.001086059,0.00039969484,0.0009350247,0.84465086,0.0016208898,0.101791725],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957131,0.0008190097,0.00025934738,0.0009144402,0.0017987705,0.0004953261],"domain_scores_gemma":[0.9900215,0.0015181368,0.00033656452,0.001449693,0.0053407494,0.0013332699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056370446,0.00251254,0.0022712606,0.0057795094,0.0044925753,0.005784139,0.0025498038,0.0018693382,0.0838113],"category_scores_gemma":[0.012374561,0.0012277658,0.00071722997,0.005595828,0.0011084835,0.0066098045,0.0020530606,0.0024939314,0.058410294],"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":[0.000071269904,0.00008953497,0.0004119163,0.00025128457,0.000020771507,0.000027784852,0.000060829774,0.00039079197,0.00065102533,0.00077952864,0.97662896,0.020616442],"study_design_scores_gemma":[0.0003085034,0.00014359168,0.007259942,0.00028709645,0.00005167482,0.000075002936,0.00036453133,0.016177136,0.00377474,0.0034374958,0.9680072,0.00011300302],"about_ca_topic_score_codex":0.47363713,"about_ca_topic_score_gemma":0.6227235,"teacher_disagreement_score":0.47363713,"about_ca_system_score_codex":0.011152823,"about_ca_system_score_gemma":0.014058927,"threshold_uncertainty_score":0.94176054},"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":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007077255,0.011218451,0.024273997,0.009921955,0.0043352116,0.0055919713,0.73966277,0.023936193,0.1739822],"genre_scores_gemma":[0.018830797,0.0046528494,0.03859375,0.0021082857,0.0012469525,0.0037468162,0.82291776,0.002837213,0.10506553],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9934657,0.0016042899,0.0004904693,0.0007366166,0.0030650282,0.0006379708],"domain_scores_gemma":[0.98184574,0.0024783108,0.0008820911,0.0018958129,0.011193214,0.001704841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010583707,0.0017294128,0.0010844821,0.008979253,0.0020987,0.004006035,0.002149395,0.0016470733,0.107846335],"category_scores_gemma":[0.015358534,0.00085814187,0.0008404023,0.0095780855,0.00050122204,0.004801618,0.0016415234,0.0017674883,0.099614084],"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":[0.00007172587,0.00007410086,0.0003250593,0.00039578337,0.000013022003,0.000015889205,0.000040727675,0.0004922892,0.001152587,0.00073114986,0.95944524,0.03724253],"study_design_scores_gemma":[0.000111645146,0.00016315817,0.007964171,0.0002886725,0.000053314983,0.000109318484,0.00016347013,0.0024590387,0.0031381175,0.0019271815,0.9835012,0.000120743665],"about_ca_topic_score_codex":0.088469565,"about_ca_topic_score_gemma":0.115350276,"teacher_disagreement_score":0.107846335,"about_ca_system_score_codex":0.004322385,"about_ca_system_score_gemma":0.009431419,"threshold_uncertainty_score":0.3607819},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10931018,0.03715201,0.04969872,0.08597151,0.0227293,0.0022159358,0.41203952,0.039171446,0.24171138],"genre_scores_gemma":[0.13009557,0.010174849,0.06737836,0.00160501,0.0012487255,0.00040158862,0.2184267,0.0032584756,0.5674107],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9934769,0.00088965247,0.00030148996,0.00087781233,0.0034477073,0.0010064715],"domain_scores_gemma":[0.96078986,0.0029428916,0.00047303137,0.0028956009,0.028404629,0.0044940957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009206556,0.001996802,0.002186654,0.0073616435,0.0049867914,0.008567633,0.0029802052,0.001699443,0.04607755],"category_scores_gemma":[0.015572188,0.0013875022,0.0009926368,0.0074916384,0.001691746,0.005238658,0.0016671784,0.0025758224,0.0240755],"study_design_candidate":"simulation_or_modeling","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":[0.0004684631,0.00021171676,0.0024078775,0.00022219933,0.000055493656,0.00006542487,0.00016651789,0.0016724099,0.0026425784,0.0017912171,0.929446,0.060850132],"study_design_scores_gemma":[0.00051249715,0.0003809478,0.026948264,0.00042824273,0.00031366365,0.00017852493,0.0014574144,0.028034309,0.025043093,0.0046117073,0.9117294,0.00036192263],"about_ca_topic_score_codex":0.832477,"about_ca_topic_score_gemma":0.89487916,"teacher_disagreement_score":0.832477,"about_ca_system_score_codex":0.023484394,"about_ca_system_score_gemma":0.035178125,"threshold_uncertainty_score":0.33701915},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036991198,0.02212929,0.042891923,0.05238995,0.020047734,0.008931794,0.5930122,0.075806096,0.14779976],"genre_scores_gemma":[0.04441995,0.0046453476,0.06285783,0.006143179,0.0026195326,0.0057881656,0.70695835,0.004549431,0.16201816],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9909053,0.0024175807,0.00029217958,0.0009076816,0.004644443,0.00083283527],"domain_scores_gemma":[0.9765979,0.003679274,0.0006194194,0.0021807018,0.012544183,0.0043784166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012827426,0.004200568,0.0032479062,0.005026823,0.0058596637,0.0054679234,0.0045731585,0.0037334082,0.07703705],"category_scores_gemma":[0.022372866,0.001104575,0.0011095617,0.004929041,0.0013459846,0.0069460445,0.003086828,0.0057679634,0.04518236],"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":[0.00010743478,0.00018013349,0.00022148517,0.00013505317,0.000023262026,0.000024738056,0.00004332738,0.00032879214,0.00073996925,0.00027846935,0.98752767,0.010389735],"study_design_scores_gemma":[0.0011090081,0.00071459654,0.008320262,0.00035524197,0.00016386955,0.00019734705,0.0008805137,0.019506905,0.00868455,0.004468812,0.95517594,0.00042296146],"about_ca_topic_score_codex":0.2440349,"about_ca_topic_score_gemma":0.46932372,"teacher_disagreement_score":0.2440349,"about_ca_system_score_codex":0.0075954064,"about_ca_system_score_gemma":0.0144234095,"threshold_uncertainty_score":0.4852289},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03985818,0.01558799,0.10315083,0.03016127,0.008888322,0.0063272514,0.44194013,0.046640996,0.30744502],"genre_scores_gemma":[0.063940026,0.0038410083,0.12323491,0.0023358364,0.0009883603,0.001975217,0.47793424,0.0041650534,0.32158533],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9951149,0.0009784334,0.00020704263,0.0009220341,0.0023391545,0.00043833177],"domain_scores_gemma":[0.98774683,0.0012107833,0.00024280834,0.0009042881,0.008482391,0.0014128841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069671106,0.0015173727,0.001856497,0.0034285872,0.0030754341,0.004324626,0.0018556319,0.0010892142,0.057038125],"category_scores_gemma":[0.009219456,0.0006532292,0.00062054145,0.0045559816,0.00080117077,0.0031676574,0.0013888745,0.0017285576,0.020410767],"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":[0.0001906149,0.00013841936,0.0004905722,0.0003131988,0.000031581287,0.000047424186,0.00021086694,0.00062149536,0.0044311327,0.0014582963,0.9300441,0.062022284],"study_design_scores_gemma":[0.00025821905,0.00022907373,0.0053833723,0.00011776207,0.000059026966,0.0000548925,0.0004720347,0.011138193,0.012374453,0.0023820035,0.96742445,0.000106390085],"about_ca_topic_score_codex":0.45764893,"about_ca_topic_score_gemma":0.6083322,"teacher_disagreement_score":0.45764893,"about_ca_system_score_codex":0.009968801,"about_ca_system_score_gemma":0.014461805,"threshold_uncertainty_score":0.9099702},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.212673,0.01673969,0.6544166,0.002420217,0.00073563855,0.0020499197,0.022166776,0.021948617,0.06684953],"genre_scores_gemma":[0.63497293,0.0033536877,0.313951,0.00024725276,0.0006964006,0.00050181575,0.030667339,0.0006419564,0.014967623],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968514,0.0005423191,0.00022878204,0.00047844838,0.0016947594,0.00020423338],"domain_scores_gemma":[0.99248934,0.0027097627,0.0008930835,0.001777537,0.0016775366,0.00045282757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029273832,0.00110925,0.0017341346,0.023128038,0.0012879107,0.0043132356,0.0012254197,0.0010149837,0.0028735579],"category_scores_gemma":[0.013375169,0.00044651964,0.0011279656,0.014216083,0.0005735827,0.004948688,0.0019896738,0.00097449304,0.003321356],"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":[0.0002112216,0.0005819359,0.022251723,0.00082064717,0.00057943945,0.00021923539,0.0005069761,0.012425773,0.007846484,0.011128358,0.050875254,0.892553],"study_design_scores_gemma":[0.00019522994,0.0010659243,0.06435592,0.00057335786,0.0012640757,0.0018359494,0.0019111873,0.51135695,0.034045607,0.22630538,0.15669318,0.0003972744],"about_ca_topic_score_codex":0.004978637,"about_ca_topic_score_gemma":0.014357913,"teacher_disagreement_score":0.023128038,"about_ca_system_score_codex":0.0012513781,"about_ca_system_score_gemma":0.0014806822,"threshold_uncertainty_score":0.015481651},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036413785,0.029699324,0.029374493,0.05483222,0.00578544,0.008391572,0.737739,0.031545933,0.0662182],"genre_scores_gemma":[0.03816479,0.0046054334,0.044603344,0.004586429,0.0008665811,0.0021267696,0.8756398,0.001120256,0.028286653],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99337137,0.0020278313,0.000941037,0.00081918243,0.0023713582,0.00046917534],"domain_scores_gemma":[0.9685702,0.009968861,0.0018621355,0.002199364,0.014742782,0.002656629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015881011,0.0026891783,0.0023911097,0.0074915034,0.0023047873,0.004924522,0.003775383,0.0032494783,0.032339767],"category_scores_gemma":[0.033751845,0.0009227378,0.0012474112,0.0057223383,0.001085069,0.0045769764,0.0022177494,0.002943837,0.019928355],"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":[0.00030709655,0.00021051537,0.0009338949,0.0009810907,0.00010314845,0.00007845258,0.00005550222,0.00088606233,0.0013194153,0.0003740012,0.96546936,0.029281504],"study_design_scores_gemma":[0.0031988139,0.0010601465,0.026358034,0.0015543945,0.0005518914,0.0007390126,0.0005435813,0.048678894,0.01784947,0.006426466,0.8926049,0.0004343838],"about_ca_topic_score_codex":0.16449954,"about_ca_topic_score_gemma":0.27007198,"teacher_disagreement_score":0.16449954,"about_ca_system_score_codex":0.009992594,"about_ca_system_score_gemma":0.016980717,"threshold_uncertainty_score":0.32708406},"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":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040136553,0.01397053,0.10716579,0.016085982,0.004623603,0.0062982757,0.5410218,0.17676096,0.09393649],"genre_scores_gemma":[0.08519561,0.0023464514,0.176748,0.0039339196,0.0007517428,0.0022452206,0.63782805,0.0037105617,0.087240465],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965132,0.0010084471,0.00018467975,0.00060007937,0.0013512769,0.00034227822],"domain_scores_gemma":[0.9899858,0.0020037063,0.00034590985,0.0015812247,0.0053040623,0.00077930617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00598183,0.0015657643,0.0015876445,0.003481928,0.0029320354,0.0027243,0.0022843229,0.002067665,0.03226847],"category_scores_gemma":[0.0128882695,0.0006318673,0.0004598303,0.0034167643,0.0008555455,0.0037852202,0.001990313,0.0024317293,0.018020673],"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":[0.00028109577,0.0001900129,0.0009899621,0.00041955546,0.000046108275,0.000049804796,0.00016299589,0.00075638806,0.004781559,0.0009973402,0.9383735,0.052951667],"study_design_scores_gemma":[0.00039880638,0.00040521476,0.010059191,0.00019416846,0.0001088773,0.00013113361,0.0004644173,0.022019845,0.012793335,0.0022998496,0.95091003,0.00021504749],"about_ca_topic_score_codex":0.28022903,"about_ca_topic_score_gemma":0.54321015,"teacher_disagreement_score":0.28022903,"about_ca_system_score_codex":0.005777915,"about_ca_system_score_gemma":0.009137995,"threshold_uncertainty_score":0.55719584},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047295064,0.035588406,0.0710213,0.04083132,0.020504816,0.007762236,0.47670472,0.046159495,0.2541327],"genre_scores_gemma":[0.093282916,0.0054360544,0.04583829,0.004940753,0.0019363799,0.0023257644,0.5402797,0.0024350034,0.3035253],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99108607,0.0016283192,0.00044088837,0.0007808627,0.0052697654,0.0007940609],"domain_scores_gemma":[0.97139955,0.0022663872,0.000967263,0.0022530563,0.02098079,0.0021328924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014485605,0.002032948,0.002095816,0.0073560355,0.0036163724,0.0069205547,0.0034002734,0.0024039415,0.023699872],"category_scores_gemma":[0.0205852,0.0007930917,0.0009092933,0.0040832716,0.001361721,0.004411845,0.002564009,0.0033809717,0.015864044],"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":[0.00018453778,0.00013713787,0.0007162642,0.0003116088,0.000061445426,0.000033907316,0.000041664687,0.0009562999,0.002010691,0.00095225335,0.9629249,0.031669267],"study_design_scores_gemma":[0.0005675825,0.0007032862,0.021620112,0.0003693745,0.00020898979,0.00025027167,0.00026135036,0.025407037,0.019674994,0.0045824065,0.9260593,0.00029543872],"about_ca_topic_score_codex":0.27196303,"about_ca_topic_score_gemma":0.5217234,"teacher_disagreement_score":0.27196303,"about_ca_system_score_codex":0.012003957,"about_ca_system_score_gemma":0.016343264,"threshold_uncertainty_score":0.54076004},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009614935,0.018729996,0.06440945,0.012817989,0.007839403,0.0025856982,0.7714569,0.041998766,0.070546925],"genre_scores_gemma":[0.009979734,0.003177332,0.050174832,0.0014094426,0.00078336836,0.00086255866,0.84698814,0.002317729,0.08430685],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978922,0.00054559537,0.00022190271,0.0003373482,0.00079961005,0.0002033503],"domain_scores_gemma":[0.99140036,0.0010731226,0.00038889045,0.0008902984,0.0056531397,0.00059424504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004229312,0.0023390015,0.0019035372,0.0059315814,0.0024660842,0.0039560874,0.0032895803,0.0015338631,0.05565622],"category_scores_gemma":[0.008653516,0.00068179757,0.0009297352,0.0054818555,0.00085570576,0.005237808,0.0018525064,0.002205516,0.038103264],"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":[0.0000897623,0.00004223484,0.00009397145,0.00033925514,0.00003131018,0.000021955238,0.000030912724,0.00025531228,0.0021225663,0.00045038894,0.97238535,0.024136864],"study_design_scores_gemma":[0.00028360524,0.00016300156,0.0043053,0.0002951408,0.00019463334,0.00013565016,0.0003338899,0.0083240755,0.0143377045,0.0035921119,0.9679184,0.000116412775],"about_ca_topic_score_codex":0.2007812,"about_ca_topic_score_gemma":0.39428198,"teacher_disagreement_score":0.2007812,"about_ca_system_score_codex":0.004214403,"about_ca_system_score_gemma":0.010208433,"threshold_uncertainty_score":0.39922506},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011156387,0.014497669,0.009045472,0.020298978,0.008709198,0.003763945,0.7637238,0.03639557,0.13240899],"genre_scores_gemma":[0.015452468,0.0022649067,0.010816544,0.0022349008,0.0010488129,0.0011999257,0.82101303,0.002182941,0.14378646],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958507,0.00070485676,0.0002694079,0.0006292471,0.0020443632,0.00050142437],"domain_scores_gemma":[0.9856163,0.0015132027,0.00048468728,0.0013185964,0.008560801,0.0025064382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007988935,0.004885445,0.0034770225,0.0077460385,0.005613895,0.008823962,0.0051492997,0.0031881763,0.11962767],"category_scores_gemma":[0.012368054,0.0017817765,0.0010185111,0.006711323,0.0016678355,0.00921065,0.002552829,0.004829469,0.09634684],"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":[0.00006063212,0.000087638255,0.00011790295,0.000121920726,0.000017017732,0.00001699073,0.000016486256,0.00015840857,0.00035042866,0.00015831432,0.99229735,0.006596931],"study_design_scores_gemma":[0.0010393327,0.00033989098,0.01294559,0.00037627437,0.0001363901,0.00012805112,0.00033932552,0.011275042,0.0061328965,0.0033639888,0.9636944,0.00022873454],"about_ca_topic_score_codex":0.4552945,"about_ca_topic_score_gemma":0.70593566,"teacher_disagreement_score":0.4552945,"about_ca_system_score_codex":0.012972352,"about_ca_system_score_gemma":0.014169215,"threshold_uncertainty_score":0.90528876},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029221976,0.016321372,0.03222805,0.039303318,0.015312396,0.004886643,0.35605684,0.014005869,0.49266356],"genre_scores_gemma":[0.036269624,0.0022940093,0.020238062,0.0045728674,0.0011129074,0.001067812,0.18579234,0.0019566028,0.7466957],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99275255,0.0015690242,0.00031429122,0.0011700275,0.0032382738,0.000955828],"domain_scores_gemma":[0.97651845,0.0013930502,0.0003783196,0.00172975,0.017018344,0.002962084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0152765205,0.0015742142,0.0019853455,0.005138173,0.004013502,0.0054059695,0.0030050226,0.0015581449,0.1158521],"category_scores_gemma":[0.014514829,0.000574408,0.0008288709,0.004713631,0.0013744503,0.002719883,0.003308538,0.0015509924,0.04376391],"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":[0.00017307127,0.00007674229,0.00041228425,0.00021365233,0.000019822906,0.000025175968,0.000108957385,0.00017809082,0.0017519206,0.00085119146,0.95882976,0.03735934],"study_design_scores_gemma":[0.00013246226,0.000118841606,0.0059519694,0.0001352615,0.00004841395,0.000051357645,0.00040132253,0.0014438755,0.004504443,0.0013616075,0.9857976,0.000052827058],"about_ca_topic_score_codex":0.48720607,"about_ca_topic_score_gemma":0.7099874,"teacher_disagreement_score":0.48720607,"about_ca_system_score_codex":0.013143853,"about_ca_system_score_gemma":0.021123832,"threshold_uncertainty_score":0.96874046},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05063422,0.008167766,0.039707784,0.0155958645,0.0071816626,0.010095814,0.64299846,0.07643976,0.14917864],"genre_scores_gemma":[0.04870628,0.00061948167,0.02694652,0.0026734583,0.00061462447,0.0023417799,0.83484536,0.003932325,0.07932016],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9894713,0.003032071,0.00066424976,0.002043856,0.0037115556,0.0010769989],"domain_scores_gemma":[0.9723566,0.004154014,0.0006544957,0.0035001861,0.01643583,0.00289891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01767681,0.0032755318,0.0022399758,0.0056010606,0.0057558217,0.006211665,0.0044629723,0.004319162,0.062294874],"category_scores_gemma":[0.02038388,0.0013407066,0.0012590411,0.0034998877,0.0020436193,0.0068345508,0.004203525,0.0045200842,0.047797848],"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":[0.000244418,0.00029024528,0.00036956876,0.0003773441,0.000048198122,0.00004651442,0.00017079458,0.0004100239,0.002821389,0.0005639988,0.97957015,0.015087225],"study_design_scores_gemma":[0.0013121876,0.0006230748,0.014396555,0.00032221925,0.00011358891,0.0002899723,0.0008670827,0.016629532,0.017620701,0.00388512,0.9436982,0.00024169545],"about_ca_topic_score_codex":0.27291724,"about_ca_topic_score_gemma":0.4138702,"teacher_disagreement_score":0.27291724,"about_ca_system_score_codex":0.0118497815,"about_ca_system_score_gemma":0.012154021,"threshold_uncertainty_score":0.5426574},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17292416,0.022459364,0.37592927,0.011731887,0.0038517532,0.0022926691,0.17987332,0.13524316,0.095694445],"genre_scores_gemma":[0.23006018,0.003026803,0.44501102,0.0010104065,0.0009927576,0.0012622413,0.24386168,0.007998213,0.066776715],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9922167,0.0019328629,0.00040837404,0.0014372821,0.0032353841,0.0007693003],"domain_scores_gemma":[0.9856039,0.0038136635,0.00051843096,0.0025913506,0.005955839,0.0015168845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055801766,0.0019357669,0.001460173,0.012680181,0.0016489233,0.0031611654,0.0023052962,0.0017364227,0.017197683],"category_scores_gemma":[0.02187644,0.0008030303,0.0012188578,0.0072277114,0.0006933728,0.005870084,0.0035208229,0.00220693,0.013038678],"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":[0.0008685585,0.0005761759,0.008367204,0.00048233327,0.00016467198,0.0001213156,0.00039471572,0.003370088,0.02119266,0.0023970727,0.38671637,0.57534885],"study_design_scores_gemma":[0.0007435952,0.0011962168,0.06814034,0.0004058972,0.00045944162,0.000935797,0.0020498675,0.2730742,0.12267448,0.016062895,0.51376355,0.0004937129],"about_ca_topic_score_codex":0.04595241,"about_ca_topic_score_gemma":0.11152819,"teacher_disagreement_score":0.04595241,"about_ca_system_score_codex":0.0020722738,"about_ca_system_score_gemma":0.004106578,"threshold_uncertainty_score":0.09136987},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8479025,0.0033990033,0.010790252,0.0034901104,0.0014373659,0.0025221817,0.049825933,0.022414155,0.05821853],"genre_scores_gemma":[0.7525941,0.000728783,0.05021447,0.0012061386,0.00060066,0.0014536909,0.14567399,0.0014567442,0.04607138],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9913119,0.003800559,0.0006270549,0.0014010019,0.0021269713,0.00073252135],"domain_scores_gemma":[0.9807164,0.007972623,0.00067566853,0.0034556966,0.0051032547,0.002076399],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008557481,0.0012770705,0.0012036407,0.0015847574,0.0029115858,0.0016701141,0.0016777456,0.0020005752,0.01139431],"category_scores_gemma":[0.021563476,0.0005680759,0.00078573485,0.0028638085,0.0007670625,0.003159761,0.0016698438,0.0019860694,0.0060862675],"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":[0.009902696,0.015952894,0.02413046,0.0018885608,0.0007383427,0.0005264518,0.001783923,0.029739672,0.02924761,0.00227178,0.6141018,0.2697158],"study_design_scores_gemma":[0.008594944,0.017026078,0.22083174,0.00031625605,0.00093804335,0.0007829484,0.0036588912,0.3159275,0.081598856,0.004580432,0.34469438,0.0010498652],"about_ca_topic_score_codex":0.10958245,"about_ca_topic_score_gemma":0.20298794,"teacher_disagreement_score":0.10958245,"about_ca_system_score_codex":0.0027704241,"about_ca_system_score_gemma":0.002959712,"threshold_uncertainty_score":0.21788925},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5646859,0.003639693,0.3740354,0.001137115,0.0009863785,0.001555434,0.01720816,0.023228139,0.013523793],"genre_scores_gemma":[0.6769998,0.0007001322,0.29394427,0.00016042205,0.00034456604,0.0005274453,0.023347905,0.00042399607,0.0035514778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986695,0.00026598995,0.00013766621,0.00036812975,0.0004247991,0.0001339713],"domain_scores_gemma":[0.9982017,0.00056246243,0.00020369564,0.0001599977,0.0007584417,0.00011357433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010199769,0.0014644064,0.0010455328,0.011258868,0.001144069,0.0014291485,0.00064288307,0.00089624006,0.0016948178],"category_scores_gemma":[0.0051731835,0.00026930476,0.0010270072,0.0051656477,0.00030107467,0.002671326,0.0009942116,0.0007721198,0.002620385],"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":[0.0023627854,0.0014235604,0.027475985,0.0017098903,0.0005965793,0.0014304534,0.0020940176,0.016955722,0.10253004,0.0054495474,0.0458358,0.7921356],"study_design_scores_gemma":[0.00013487572,0.0009880048,0.046345927,0.00018294965,0.0003468475,0.0011772952,0.0024557095,0.84491026,0.053524908,0.012338354,0.037339747,0.00025504464],"about_ca_topic_score_codex":0.010838072,"about_ca_topic_score_gemma":0.016243283,"teacher_disagreement_score":0.011258868,"about_ca_system_score_codex":0.0007016975,"about_ca_system_score_gemma":0.0009506127,"threshold_uncertainty_score":0.02154994},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9280536,0.0023116018,0.038851954,0.0010681188,0.00024839788,0.00011360441,0.00052969443,0.0004464721,0.02837654],"genre_scores_gemma":[0.9925956,0.00023142538,0.005284213,0.000084537605,0.000047925547,0.000024004185,0.00036151547,0.00008828781,0.0012825303],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987527,0.0005923565,0.00009228885,0.0002463471,0.00020911454,0.0001072775],"domain_scores_gemma":[0.9878649,0.0074581564,0.0015284823,0.001092431,0.0013855372,0.0006705104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017243688,0.00034529218,0.00029710238,0.00091232074,0.00038880206,0.0023821907,0.00044265034,0.0008560479,0.008598678],"category_scores_gemma":[0.032251447,0.00024361022,0.00026566966,0.00090332504,0.0006479841,0.004293395,0.0010654645,0.0012036052,0.0009996092],"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":[0.007291966,0.001182257,0.13602503,0.0021962326,0.00071173976,0.0008367235,0.0073271203,0.008990762,0.16422163,0.08844464,0.018043064,0.564729],"study_design_scores_gemma":[0.0009900099,0.003413072,0.43086052,0.00064980815,0.0014961567,0.0035489963,0.010167973,0.17766862,0.04474949,0.2978743,0.027950391,0.0006307028],"about_ca_topic_score_codex":0.0007498011,"about_ca_topic_score_gemma":0.0010113679,"teacher_disagreement_score":0.008598678,"about_ca_system_score_codex":0.0004091698,"about_ca_system_score_gemma":0.00035644422,"threshold_uncertainty_score":0.02876544},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009767732,0.045663886,0.01829249,0.0064011756,0.0114260735,0.0024870532,0.81385666,0.036996864,0.055108033],"genre_scores_gemma":[0.008311318,0.0076043825,0.015164043,0.0013371013,0.0016124268,0.0018772288,0.8990116,0.0025393262,0.06254254],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99080724,0.0015005915,0.0011095142,0.0013249494,0.0041735466,0.0010841613],"domain_scores_gemma":[0.9704561,0.003350082,0.0021392824,0.0032635343,0.018514594,0.002276417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015935797,0.0075584142,0.0046822047,0.026312556,0.0049378145,0.0087470375,0.008016528,0.0042019025,0.049533777],"category_scores_gemma":[0.023517122,0.0020600578,0.003360318,0.016510328,0.001282488,0.008481686,0.0047723907,0.0041781254,0.067215785],"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":[0.00022304412,0.00008068767,0.00059710647,0.0013080989,0.00011323167,0.00003364811,0.000029644158,0.00050770293,0.0015931088,0.0002664422,0.96374834,0.031498924],"study_design_scores_gemma":[0.0006211232,0.0007913409,0.014934292,0.0018279189,0.0008913481,0.00052552443,0.0002799914,0.007679473,0.02003321,0.0035325808,0.9483554,0.000527849],"about_ca_topic_score_codex":0.12861072,"about_ca_topic_score_gemma":0.16926117,"teacher_disagreement_score":0.12861072,"about_ca_system_score_codex":0.0063812085,"about_ca_system_score_gemma":0.0154467495,"threshold_uncertainty_score":0.25572425},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.084496066,0.020208515,0.033047546,0.20447855,0.023027789,0.004432297,0.19680692,0.013569983,0.41993234],"genre_scores_gemma":[0.103092395,0.004435987,0.02578557,0.021080146,0.0016221395,0.0009755804,0.12689295,0.0026113125,0.71350396],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99536186,0.0015888998,0.00029029412,0.00062731997,0.0015372405,0.0005944304],"domain_scores_gemma":[0.989551,0.0014864979,0.00033123317,0.00065620017,0.006639223,0.001335793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009419212,0.0009098294,0.0010060429,0.0018265785,0.004479566,0.0044055725,0.002445646,0.0024073585,0.051245335],"category_scores_gemma":[0.014927426,0.00030655914,0.0004994993,0.0016962547,0.0012386605,0.0033962235,0.0024316055,0.0022903942,0.020800993],"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":[0.00015012412,0.0000522453,0.00077553914,0.00015979273,0.000009814786,0.000022368611,0.00035437403,0.00009595444,0.0012514986,0.00048348206,0.9594476,0.037197202],"study_design_scores_gemma":[0.0000803477,0.00011117758,0.0063706394,0.00026612493,0.00004032345,0.00006289206,0.0019044519,0.0011444477,0.0058073923,0.0015584956,0.9825912,0.00006249005],"about_ca_topic_score_codex":0.3191621,"about_ca_topic_score_gemma":0.6500387,"teacher_disagreement_score":0.3191621,"about_ca_system_score_codex":0.005832062,"about_ca_system_score_gemma":0.015195691,"threshold_uncertainty_score":0.63460875},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.087178074,0.011527807,0.0915122,0.0073640333,0.004534156,0.0030719526,0.6601518,0.06850435,0.06615562],"genre_scores_gemma":[0.058257923,0.0013106929,0.10929217,0.0007768828,0.00046453674,0.001026219,0.78111124,0.0034292343,0.044331104],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99623495,0.0010907311,0.00030297638,0.00089316384,0.0010694314,0.000408721],"domain_scores_gemma":[0.99272835,0.0015700292,0.00020563391,0.0012978442,0.003460687,0.00073744985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037793792,0.0025887217,0.0015469326,0.0066690166,0.0025399872,0.0030404415,0.0024149248,0.0022443293,0.023103498],"category_scores_gemma":[0.010994697,0.0007518034,0.0010777885,0.0034243523,0.0007530657,0.0054537184,0.0034584699,0.0025796182,0.022780355],"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":[0.0006122097,0.00045828367,0.0015447895,0.0010642731,0.00009556577,0.0002579203,0.00034322194,0.0013091075,0.035213552,0.0017954136,0.79675835,0.1605473],"study_design_scores_gemma":[0.0007216169,0.0004221651,0.016853888,0.00047548432,0.00022813691,0.0009621403,0.0012679925,0.032701135,0.08925302,0.0046480875,0.852206,0.00026038382],"about_ca_topic_score_codex":0.06180754,"about_ca_topic_score_gemma":0.087615386,"teacher_disagreement_score":0.06180754,"about_ca_system_score_codex":0.0023041537,"about_ca_system_score_gemma":0.006504895,"threshold_uncertainty_score":0.12289554},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24833947,0.0026586056,0.071541,0.0041103824,0.0028633245,0.0017370501,0.020257149,0.004861486,0.6436316],"genre_scores_gemma":[0.4012441,0.00140186,0.054445487,0.0018165715,0.00013577624,0.0011330479,0.013788679,0.0005466238,0.52548784],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99860185,0.00015467677,0.00006078235,0.0004987445,0.00047670113,0.00020724388],"domain_scores_gemma":[0.9985348,0.00018451219,0.000093671515,0.0004250526,0.0004840334,0.000278014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010964929,0.00046042638,0.00032137067,0.00073641277,0.0018929753,0.002027692,0.0008902908,0.0013052505,0.10026174],"category_scores_gemma":[0.0020425587,0.00026721953,0.00031592717,0.0012389248,0.0004859813,0.0020799292,0.0014434445,0.0010459552,0.03216751],"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":[0.0038063251,0.0019848002,0.016645005,0.0012259298,0.00014708085,0.0013921518,0.0035004034,0.0014712538,0.28721002,0.1077391,0.20186695,0.37301105],"study_design_scores_gemma":[0.0002561547,0.0012704212,0.010447539,0.00012746923,0.000066863955,0.0008813381,0.0019023834,0.0025605836,0.15892836,0.014852965,0.8086368,0.00006919235],"about_ca_topic_score_codex":0.0033070398,"about_ca_topic_score_gemma":0.0052233906,"teacher_disagreement_score":0.10026174,"about_ca_system_score_codex":0.00094163354,"about_ca_system_score_gemma":0.0010094013,"threshold_uncertainty_score":0.335409},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003226726,0.006974822,0.012671283,0.016958805,0.014799087,0.0010111484,0.34813547,0.025094725,0.5711279],"genre_scores_gemma":[0.005177018,0.0025692913,0.008296989,0.0018929766,0.0015685314,0.00027174337,0.17785403,0.004037347,0.79833204],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826103,0.00024714498,0.00008696298,0.00032591453,0.00085013115,0.00022877651],"domain_scores_gemma":[0.9948584,0.0004360389,0.00012546932,0.0005615867,0.0024787583,0.0015397941],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002813818,0.0016668878,0.0027072951,0.0050477246,0.0026080355,0.006534286,0.0024186037,0.0017054431,0.636452],"category_scores_gemma":[0.0058711413,0.0008303203,0.00072121905,0.007028039,0.00068377634,0.0063693896,0.0034119033,0.0020137986,0.45084074],"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":[0.000025665613,0.000028292874,0.000043327433,0.00004876966,0.000003015682,0.000009653846,0.0000101977685,0.000031853244,0.00026661594,0.00042439453,0.9867306,0.012377694],"study_design_scores_gemma":[0.000043703483,0.000026089223,0.0008075878,0.00007192578,0.000007761277,0.000024632936,0.00008208418,0.0005169187,0.0006108429,0.0024516813,0.9953354,0.00002139208],"about_ca_topic_score_codex":0.07814548,"about_ca_topic_score_gemma":0.21512763,"teacher_disagreement_score":0.636452,"about_ca_system_score_codex":0.00351377,"about_ca_system_score_gemma":0.005592791,"threshold_uncertainty_score":0.5185571},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016787477,0.008997363,0.019325377,0.17298892,0.07243968,0.0044178437,0.143698,0.01088666,0.5504586],"genre_scores_gemma":[0.021117322,0.00094166846,0.0093009,0.0071869153,0.0033437784,0.00046926845,0.048586708,0.0015856111,0.90746784],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9900663,0.0013192487,0.00021962664,0.001231911,0.004837827,0.0023250342],"domain_scores_gemma":[0.9700944,0.0011322276,0.00038823942,0.0015996415,0.016583864,0.010201625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010414007,0.002055707,0.0033712843,0.0049538137,0.0064205695,0.0055835014,0.0031141036,0.0037382606,0.24904913],"category_scores_gemma":[0.014557877,0.00073358056,0.0010069904,0.0049235197,0.0014440962,0.0039081634,0.0052282265,0.002663233,0.10711842],"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":[0.00014292657,0.000062894804,0.00021804469,0.000039755076,0.000007518736,0.00005030178,0.000065823035,0.00007563177,0.0010095278,0.0010183644,0.9819577,0.015351561],"study_design_scores_gemma":[0.00009848219,0.00005607997,0.0013250036,0.00003136766,0.000013501385,0.00003487731,0.00029066106,0.0010116273,0.0014886308,0.0010851907,0.99453026,0.000034242443],"about_ca_topic_score_codex":0.28343266,"about_ca_topic_score_gemma":0.5706774,"teacher_disagreement_score":0.28343266,"about_ca_system_score_codex":0.013200108,"about_ca_system_score_gemma":0.021515965,"threshold_uncertainty_score":0.8331523},"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":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022111543,0.11276645,0.23669279,0.01815191,0.017561253,0.007845086,0.34723586,0.1305811,0.10705406],"genre_scores_gemma":[0.026057877,0.022158554,0.18193594,0.0024723755,0.003704,0.0032939583,0.66582483,0.0059162835,0.08863618],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962171,0.00087844214,0.00044557973,0.00063834625,0.0014156309,0.0004049813],"domain_scores_gemma":[0.9875771,0.0014040495,0.00068935886,0.0012224755,0.00797109,0.0011360004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009083415,0.003022748,0.0023126658,0.010674464,0.002199662,0.004712859,0.0036104373,0.001891015,0.029882034],"category_scores_gemma":[0.009235329,0.0011102845,0.0016611749,0.009430257,0.0004582205,0.0054616393,0.0019398162,0.002588303,0.038880385],"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":[0.0002795532,0.00023671256,0.0006854751,0.0018037214,0.00014742625,0.00008256924,0.00012024494,0.0017480401,0.0134508135,0.00083270745,0.79114455,0.18946818],"study_design_scores_gemma":[0.00023846346,0.0008618749,0.008956989,0.00071170356,0.00041108282,0.0003490705,0.00026991524,0.01500544,0.028222684,0.0032633268,0.94142467,0.00028475147],"about_ca_topic_score_codex":0.041821178,"about_ca_topic_score_gemma":0.07434688,"teacher_disagreement_score":0.041821178,"about_ca_system_score_codex":0.0028850988,"about_ca_system_score_gemma":0.0074805953,"threshold_uncertainty_score":0.09996539},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024558,0.0046088737,0.007300077,0.015586602,0.012676315,0.0007554541,0.28601736,0.016450701,0.6541489],"genre_scores_gemma":[0.0041277204,0.0016564835,0.0046886387,0.0015216513,0.0012741195,0.00017739208,0.108339004,0.0027018925,0.8755131],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851674,0.00017960308,0.000071557915,0.00028978192,0.00073394016,0.00020842113],"domain_scores_gemma":[0.99539953,0.00034728457,0.00010543062,0.0004909902,0.002269926,0.001386722],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023142793,0.0014604415,0.002659148,0.004353568,0.0026155505,0.0062806164,0.0021616442,0.0016249424,0.71701384],"category_scores_gemma":[0.005034408,0.0007373211,0.0006103997,0.0066761407,0.0006332745,0.0053154896,0.0031231453,0.0019503819,0.51205015],"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":[0.000022565302,0.00002420315,0.00004463292,0.000034379704,0.0000019592542,0.000008275456,0.000008047572,0.000026804628,0.00016871556,0.0003989428,0.9888188,0.010442662],"study_design_scores_gemma":[0.000029230783,0.000018290395,0.0007514722,0.000052827734,0.0000043147033,0.000016153337,0.00006021081,0.00034161555,0.00036244543,0.001705245,0.9966434,0.000014716282],"about_ca_topic_score_codex":0.07756723,"about_ca_topic_score_gemma":0.23054245,"teacher_disagreement_score":0.71701384,"about_ca_system_score_codex":0.0035981678,"about_ca_system_score_gemma":0.00492426,"threshold_uncertainty_score":0.4036454},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15944344,0.018958833,0.16079547,0.008221842,0.019098647,0.009272477,0.41740757,0.14498474,0.06181698],"genre_scores_gemma":[0.1284813,0.0011410926,0.121823244,0.0015776983,0.0017248151,0.0032318395,0.68185186,0.0053853206,0.05478282],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99356365,0.002311767,0.0003134765,0.0013181904,0.0016082273,0.00088463764],"domain_scores_gemma":[0.9891642,0.0022777407,0.00024757642,0.002822126,0.004147489,0.0013407879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011126602,0.0032375613,0.0022974887,0.004455529,0.0037785694,0.0032995248,0.0038958848,0.0030023055,0.021720802],"category_scores_gemma":[0.022782473,0.0009350904,0.0016886436,0.0034944874,0.0010516014,0.005731988,0.0059572835,0.004136692,0.016870053],"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":[0.0014773731,0.0007355039,0.002120504,0.0008959327,0.00032425422,0.0001077829,0.00030691785,0.0030472507,0.010279685,0.00089205184,0.86599815,0.11381455],"study_design_scores_gemma":[0.0061199656,0.0032509,0.041057084,0.0005776383,0.0013599327,0.0006725965,0.002023429,0.16256784,0.0746528,0.013746621,0.69312406,0.00084706995],"about_ca_topic_score_codex":0.07219913,"about_ca_topic_score_gemma":0.15303023,"teacher_disagreement_score":0.07219913,"about_ca_system_score_codex":0.0027739517,"about_ca_system_score_gemma":0.008280939,"threshold_uncertainty_score":0.14355779},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023023982,0.010369802,0.026930664,0.088229455,0.04369895,0.006032956,0.32329115,0.016033303,0.46238974],"genre_scores_gemma":[0.025256116,0.0015643587,0.01768599,0.007899152,0.004423045,0.0013983299,0.16101788,0.0022941763,0.7784609],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99408543,0.0013152816,0.00015628838,0.0009038065,0.0024494152,0.0010898152],"domain_scores_gemma":[0.98279285,0.0008798252,0.00029601195,0.0010071706,0.009616914,0.005407167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009450942,0.0019130756,0.0029234777,0.0035478869,0.004633829,0.00504433,0.0031975126,0.0027150204,0.1578649],"category_scores_gemma":[0.010087335,0.000532568,0.00079963007,0.0033580384,0.0011785137,0.0044510053,0.0045098206,0.0020051568,0.087831736],"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":[0.00011348235,0.00009309315,0.00014939225,0.00007708998,0.000008310027,0.00002335787,0.00006105366,0.00007658349,0.0009973526,0.0005171809,0.98388827,0.013994716],"study_design_scores_gemma":[0.00014040062,0.000101703794,0.0016921221,0.00005126684,0.000021126849,0.000031951837,0.0003382834,0.0011581855,0.002017072,0.0012794435,0.9931356,0.000032803204],"about_ca_topic_score_codex":0.20594339,"about_ca_topic_score_gemma":0.39558187,"teacher_disagreement_score":0.20594339,"about_ca_system_score_codex":0.008546774,"about_ca_system_score_gemma":0.015822342,"threshold_uncertainty_score":0.5281107},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042078914,0.010719389,0.013708896,0.024400113,0.0117534315,0.0010478322,0.8263688,0.04214679,0.06564679],"genre_scores_gemma":[0.005906092,0.0021198003,0.014939035,0.0021801032,0.0012106627,0.0005395524,0.90350807,0.0022176176,0.06737916],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941239,0.0012004739,0.00045471673,0.001026046,0.0024815663,0.00071326894],"domain_scores_gemma":[0.98046976,0.0035418293,0.0007079813,0.0024602234,0.010314412,0.0025058095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009426671,0.004717301,0.0037186334,0.011090413,0.0034558927,0.0088870125,0.0053260303,0.0034761967,0.18356618],"category_scores_gemma":[0.022717811,0.0010756422,0.001986421,0.008555487,0.0010773224,0.0111951735,0.0048800493,0.003768427,0.18293713],"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":[0.000056383833,0.00004581788,0.00008601863,0.00017431875,0.000016081056,0.000018451552,0.00001116886,0.00011755513,0.00029780914,0.00029779464,0.9896768,0.009201858],"study_design_scores_gemma":[0.00041397213,0.00015400692,0.0030309055,0.0003752885,0.0001276161,0.00017025162,0.0002420317,0.005810654,0.0044294796,0.006621255,0.97850966,0.00011494044],"about_ca_topic_score_codex":0.07185958,"about_ca_topic_score_gemma":0.112798765,"teacher_disagreement_score":0.18356618,"about_ca_system_score_codex":0.006463628,"about_ca_system_score_gemma":0.008451271,"threshold_uncertainty_score":0.6140901},"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":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008169764,0.019157974,0.009443777,0.00673215,0.009748132,0.0018988891,0.84089476,0.05074744,0.053207118],"genre_scores_gemma":[0.0065867105,0.0027151247,0.01352451,0.0021087998,0.0008362682,0.0009147171,0.9048208,0.0030813697,0.0654118],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950604,0.0015893853,0.00045665985,0.0007801466,0.0016035094,0.0005098833],"domain_scores_gemma":[0.98956925,0.0029346622,0.0006708015,0.0013082913,0.0041265185,0.001390511],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006989842,0.010376429,0.006530145,0.006935353,0.0025587196,0.007781762,0.006693989,0.0056128646,0.090305045],"category_scores_gemma":[0.012170078,0.0025741092,0.0026197808,0.00468499,0.0020868946,0.0070660063,0.0029354137,0.0061974814,0.11355818],"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":[0.00017679385,0.000096896845,0.00007945926,0.00065151654,0.00007547305,0.000029300481,0.000012340605,0.0006518105,0.0013119893,0.00016899011,0.9865131,0.010232365],"study_design_scores_gemma":[0.0028607058,0.0010022647,0.008438311,0.0015849522,0.00083749625,0.00067379547,0.0003225161,0.025028512,0.026679464,0.0069703623,0.92494214,0.0006595549],"about_ca_topic_score_codex":0.10393873,"about_ca_topic_score_gemma":0.16875714,"teacher_disagreement_score":0.90969497,"about_ca_system_score_codex":0.0058802823,"about_ca_system_score_gemma":0.0063539175,"threshold_uncertainty_score":0.30210048},"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":"dataset","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021928681,0.10356001,0.2530893,0.016071685,0.015439098,0.0070267185,0.3362373,0.1493195,0.097327694],"genre_scores_gemma":[0.02725723,0.01996502,0.19007891,0.002338879,0.0036069793,0.0032519875,0.66820234,0.0064044106,0.07889424],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99648947,0.000830996,0.0004042947,0.0006320597,0.0012544177,0.00038872374],"domain_scores_gemma":[0.9880441,0.0014883612,0.0006590751,0.0012436185,0.0075012664,0.0010635437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008136649,0.002860575,0.0021968433,0.010019727,0.0020991056,0.004659898,0.0035702393,0.0018087599,0.031926934],"category_scores_gemma":[0.008990457,0.0010983705,0.0015798842,0.008820096,0.0004307086,0.005370573,0.0018798698,0.0026328657,0.04008277],"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":[0.0003056645,0.00024784292,0.0007240107,0.0018233804,0.00015522665,0.000088128814,0.00012412378,0.0017661419,0.013844005,0.00093072816,0.78211516,0.19787565],"study_design_scores_gemma":[0.00024625252,0.0008998708,0.008732851,0.0006598209,0.00043328851,0.0003638337,0.0002658882,0.01651647,0.029307734,0.0032058463,0.93910015,0.0002680014],"about_ca_topic_score_codex":0.0356416,"about_ca_topic_score_gemma":0.06005153,"teacher_disagreement_score":0.0356416,"about_ca_system_score_codex":0.002617656,"about_ca_system_score_gemma":0.0066367043,"threshold_uncertainty_score":0.10680622},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0119774,0.07126279,0.033159237,0.009422527,0.015291396,0.0028598483,0.7102184,0.041994266,0.10381411],"genre_scores_gemma":[0.02007108,0.016470186,0.027332233,0.0029174548,0.0027488202,0.0022344661,0.81599736,0.003530289,0.10869808],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99063885,0.0014655939,0.0010113952,0.001094683,0.004820417,0.00096908363],"domain_scores_gemma":[0.95871264,0.0031490135,0.0026002924,0.0034356576,0.029584382,0.0025181444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017901393,0.00523095,0.0034780605,0.028611466,0.004191015,0.0072955503,0.008120014,0.0027519227,0.040642317],"category_scores_gemma":[0.024781281,0.0015586569,0.0028095024,0.01641832,0.0012338983,0.0073975152,0.0041720783,0.00304176,0.046776626],"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":[0.0001531379,0.00005926038,0.0008892295,0.00090382696,0.000104472914,0.000019779498,0.000026616022,0.00051355496,0.00097204244,0.00040782697,0.9574878,0.038462427],"study_design_scores_gemma":[0.0002942349,0.0006786833,0.018196149,0.0017179108,0.00085424096,0.00036837,0.00021889046,0.0054257917,0.015628224,0.0033656093,0.9528572,0.0003946651],"about_ca_topic_score_codex":0.1635305,"about_ca_topic_score_gemma":0.202266,"teacher_disagreement_score":0.1635305,"about_ca_system_score_codex":0.0074790195,"about_ca_system_score_gemma":0.01651502,"threshold_uncertainty_score":0.32515728},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005964506,0.08825539,0.02989885,0.04914515,0.029056022,0.0059319334,0.34262398,0.024331829,0.42479238],"genre_scores_gemma":[0.014957669,0.047992367,0.054081146,0.010520666,0.008909477,0.004095544,0.4894317,0.0052879993,0.36472344],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99426574,0.0009594034,0.00043676211,0.00048056597,0.0032257135,0.0006319186],"domain_scores_gemma":[0.97537744,0.0019804703,0.0013471507,0.0013381408,0.01700047,0.0029563652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011076437,0.0018986226,0.0017210764,0.025408786,0.0035548797,0.008770743,0.00397326,0.002588564,0.09720081],"category_scores_gemma":[0.01424522,0.0009123529,0.0011258557,0.019212358,0.0010464574,0.0084283855,0.0028662265,0.0027708614,0.0850139],"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":[0.00002642836,0.000048302492,0.00011945977,0.00037322566,0.000008352518,0.00001692496,0.000020473462,0.00015903192,0.0006462284,0.0007913513,0.9579852,0.039805103],"study_design_scores_gemma":[0.000046835412,0.00007045326,0.0029009802,0.0005582118,0.000036924535,0.00008240231,0.00009615595,0.0009215798,0.0016408219,0.0023628986,0.99120903,0.00007371049],"about_ca_topic_score_codex":0.11758999,"about_ca_topic_score_gemma":0.20548947,"teacher_disagreement_score":0.11758999,"about_ca_system_score_codex":0.0071644434,"about_ca_system_score_gemma":0.018131973,"threshold_uncertainty_score":0.3251691},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021373853,0.0040927837,0.005358819,0.025794744,0.014694843,0.0010170318,0.2314681,0.007935452,0.7075009],"genre_scores_gemma":[0.004835698,0.0021179905,0.0040199985,0.0034352683,0.0016195574,0.00026075548,0.08882046,0.0013314094,0.8935589],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809355,0.00027749894,0.00011065274,0.0002623131,0.0009911127,0.00026489262],"domain_scores_gemma":[0.9952194,0.00049339264,0.00014029234,0.00035333456,0.0025476892,0.0012458413],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00271695,0.0014553755,0.0020071263,0.0035008108,0.0029991483,0.0073014363,0.0019898487,0.0025978978,0.6294483],"category_scores_gemma":[0.0066622756,0.00065805396,0.00057833537,0.004444374,0.0006195971,0.0045408043,0.0020323659,0.002317276,0.45280865],"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":[0.000021544813,0.000021576148,0.000047533147,0.000028710765,0.000002240025,0.000007714562,0.0000039062784,0.000035426463,0.0001054404,0.00034432966,0.9906855,0.008696085],"study_design_scores_gemma":[0.00003749433,0.000024533001,0.0007188795,0.00006733081,0.0000065768804,0.000013256984,0.000052222345,0.00056170183,0.00034310512,0.001501626,0.9966503,0.000022877284],"about_ca_topic_score_codex":0.13899593,"about_ca_topic_score_gemma":0.34693897,"teacher_disagreement_score":0.6294483,"about_ca_system_score_codex":0.0043005473,"about_ca_system_score_gemma":0.007201465,"threshold_uncertainty_score":0.52854705},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011779571,0.014904829,0.056634862,0.0600019,0.045535445,0.0031936592,0.21026652,0.028680753,0.5690025],"genre_scores_gemma":[0.011703557,0.0024916222,0.015876776,0.003845547,0.0026078639,0.00053721195,0.08272737,0.0016751642,0.8785349],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818295,0.00043208702,0.00006721081,0.00036034427,0.0006767044,0.00028067172],"domain_scores_gemma":[0.99604875,0.00053420727,0.00007979164,0.00026031633,0.0018217997,0.0012551951],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004510692,0.0015325506,0.0019389053,0.0019700432,0.003663611,0.005401331,0.0017093371,0.001901205,0.31464654],"category_scores_gemma":[0.0053135455,0.0006013637,0.0005520565,0.0020709895,0.0006956467,0.0049832505,0.0024227088,0.0024812273,0.15327705],"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":[0.00007305862,0.00005271658,0.00006307087,0.00006269767,0.000007070028,0.000020246129,0.000032727377,0.000040118433,0.00087110786,0.0005153955,0.9858078,0.012454148],"study_design_scores_gemma":[0.00009765957,0.00007961549,0.0012433855,0.00007472182,0.000021362803,0.000042721553,0.00024853577,0.0013824549,0.0019676406,0.0020024115,0.99279845,0.000041037456],"about_ca_topic_score_codex":0.124098636,"about_ca_topic_score_gemma":0.39462975,"teacher_disagreement_score":0.31464654,"about_ca_system_score_codex":0.004086189,"about_ca_system_score_gemma":0.00661627,"threshold_uncertainty_score":0.9775735},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14684497,0.0142875,0.7514319,0.0047807954,0.0014245132,0.00197897,0.027303755,0.019752037,0.032195628],"genre_scores_gemma":[0.69078827,0.0022752918,0.23974381,0.0004901854,0.0013838747,0.0010013246,0.043292414,0.000900784,0.02012403],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99749446,0.0011488323,0.00014317199,0.0005213657,0.00047030818,0.00022189085],"domain_scores_gemma":[0.9942871,0.0039800145,0.00017224786,0.0004300662,0.0009028879,0.00022781343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025920924,0.001085039,0.0010572593,0.0043377457,0.00084223936,0.0015518123,0.0012575621,0.0011460982,0.010880921],"category_scores_gemma":[0.012922151,0.00048485532,0.0008092202,0.0023020555,0.0003488438,0.0036010854,0.0017744149,0.0013714476,0.0060400283],"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":[0.0024245817,0.0005346725,0.006180443,0.0009994353,0.00027468384,0.00035764952,0.0012739568,0.016933454,0.030787759,0.008126564,0.094253264,0.8378536],"study_design_scores_gemma":[0.00018163219,0.00035645705,0.008406175,0.00019031059,0.00036355222,0.00035919508,0.0008223002,0.8933335,0.020641578,0.02211376,0.05314454,0.0000869801],"about_ca_topic_score_codex":0.008273984,"about_ca_topic_score_gemma":0.011961036,"teacher_disagreement_score":0.010880921,"about_ca_system_score_codex":0.00081057346,"about_ca_system_score_gemma":0.0014943179,"threshold_uncertainty_score":0.03640032},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87501395,0.0036027723,0.063949175,0.0031722076,0.001272297,0.001874725,0.032941703,0.009107155,0.00906605],"genre_scores_gemma":[0.6908451,0.0009051308,0.19384436,0.0007658031,0.0002264772,0.0015258394,0.099846795,0.0013761182,0.010664391],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98125756,0.01281798,0.0015011033,0.0013980997,0.002475138,0.0005500527],"domain_scores_gemma":[0.95280796,0.030280583,0.0013469429,0.006546598,0.007842772,0.0011751325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020955298,0.0015426236,0.0012532808,0.0033305413,0.0028157977,0.0015981689,0.0017416253,0.0021405416,0.004920068],"category_scores_gemma":[0.0456827,0.0007402484,0.001496863,0.0028136882,0.0013576741,0.005033787,0.0027395138,0.0024524166,0.0033244702],"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":[0.0097623635,0.0075160367,0.023827126,0.0029530644,0.0013877233,0.0011006376,0.003097933,0.02118467,0.14367022,0.0044240323,0.2849147,0.4961614],"study_design_scores_gemma":[0.005341374,0.0072809975,0.11539855,0.00035216022,0.002494431,0.0029110687,0.0036915636,0.3371896,0.42836654,0.00904293,0.08718477,0.00074595417],"about_ca_topic_score_codex":0.017707776,"about_ca_topic_score_gemma":0.018397914,"teacher_disagreement_score":0.020955298,"about_ca_system_score_codex":0.0016404197,"about_ca_system_score_gemma":0.0030354476,"threshold_uncertainty_score":0.11082351},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09852849,0.009335737,0.52466875,0.010455195,0.0128307855,0.008292456,0.17299177,0.11295652,0.049940277],"genre_scores_gemma":[0.17414032,0.001882046,0.36970568,0.001489445,0.002365349,0.0029453547,0.372997,0.004139656,0.07033512],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99624133,0.0017472742,0.00026464902,0.00056148606,0.00097092404,0.00021443196],"domain_scores_gemma":[0.99038494,0.0029381865,0.0004960323,0.0011597665,0.0040930277,0.0009280529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062857396,0.001841992,0.0010972511,0.002453057,0.0011401817,0.0025258474,0.0017745441,0.0018847253,0.011799369],"category_scores_gemma":[0.016034435,0.00038536533,0.0008702049,0.0012450265,0.00046911224,0.0027201483,0.001973068,0.0022864302,0.008495258],"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":[0.00079004234,0.0004504893,0.0011548286,0.0016918685,0.00019041491,0.00024475562,0.0009326867,0.0068576573,0.044119842,0.002203325,0.6724333,0.26893085],"study_design_scores_gemma":[0.0009184164,0.0024617133,0.013926578,0.00037915978,0.00032820084,0.0006366537,0.0019303355,0.15759172,0.08545105,0.010471565,0.72557765,0.00032701564],"about_ca_topic_score_codex":0.008469019,"about_ca_topic_score_gemma":0.017800663,"teacher_disagreement_score":0.011799369,"about_ca_system_score_codex":0.0015506978,"about_ca_system_score_gemma":0.0019582552,"threshold_uncertainty_score":0.03947282},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014510235,0.009369059,0.05614618,0.009746712,0.0092373965,0.0029052265,0.5695041,0.17696846,0.15161268],"genre_scores_gemma":[0.020112308,0.0011465113,0.05871778,0.0020796505,0.0010616939,0.00092872285,0.8103909,0.0048173266,0.10074518],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997074,0.0010091739,0.00017699657,0.00042744706,0.0009783035,0.0003340032],"domain_scores_gemma":[0.99513346,0.00057109003,0.00013166272,0.0008228168,0.00260257,0.00073829235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004110232,0.0023868175,0.0018109625,0.005277916,0.0021047646,0.0040321676,0.0033944373,0.0029307003,0.07925594],"category_scores_gemma":[0.0080679,0.00064958923,0.0008869894,0.0035606257,0.0005143775,0.0051593664,0.002965828,0.0020164386,0.107140936],"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":[0.00014096285,0.00006762381,0.00016709001,0.00014804809,0.00001882504,0.000023026852,0.000015296593,0.00014336305,0.0011334799,0.00054325967,0.9760424,0.02155667],"study_design_scores_gemma":[0.0008040276,0.0003930037,0.004171336,0.0002820597,0.00019015456,0.0003588063,0.00022009673,0.021141862,0.013841458,0.0063356035,0.9520629,0.00019863404],"about_ca_topic_score_codex":0.042861998,"about_ca_topic_score_gemma":0.071131915,"teacher_disagreement_score":0.07925594,"about_ca_system_score_codex":0.002128896,"about_ca_system_score_gemma":0.0051517403,"threshold_uncertainty_score":0.26513755},"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":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020497588,0.013639513,0.009974361,0.0070614917,0.020928705,0.0017334512,0.72682226,0.020553326,0.1972371],"genre_scores_gemma":[0.005310373,0.0051755463,0.010279756,0.0022997712,0.0043809623,0.0011491418,0.6500084,0.004168643,0.31722742],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99712014,0.0005336733,0.0001765314,0.00028451718,0.0015009204,0.00038425848],"domain_scores_gemma":[0.98296183,0.0015955978,0.0007039419,0.0011857081,0.010203678,0.0033493892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0066589573,0.004504459,0.00308029,0.009631332,0.0024312714,0.00719639,0.005421328,0.0023559448,0.26791924],"category_scores_gemma":[0.011002514,0.0013136587,0.0014383333,0.010259045,0.00087799306,0.0061250767,0.0025363849,0.0029561159,0.28209016],"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":[0.000030264131,0.000013667625,0.000019958325,0.00013920518,0.000005262087,0.0000034373434,0.0000020904267,0.00008060235,0.00021406796,0.000121716614,0.9926087,0.006760996],"study_design_scores_gemma":[0.00022707015,0.00017962075,0.0024549435,0.00028850685,0.00006573498,0.000073169474,0.000047826634,0.0016364877,0.0023195746,0.0020724721,0.99052715,0.00010734794],"about_ca_topic_score_codex":0.16751295,"about_ca_topic_score_gemma":0.21497685,"teacher_disagreement_score":0.26791924,"about_ca_system_score_codex":0.004675356,"about_ca_system_score_gemma":0.012770094,"threshold_uncertainty_score":0.89627916},"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":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0084671695,0.19250658,0.025233563,0.100215256,0.03140583,0.005513674,0.30158362,0.01791935,0.31715485],"genre_scores_gemma":[0.029911943,0.10510568,0.06758911,0.02325463,0.015038083,0.0034712153,0.45630708,0.003302035,0.29602024],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938671,0.0012691782,0.00041368924,0.0003670145,0.0034464851,0.0006364513],"domain_scores_gemma":[0.9700852,0.003965015,0.0017251408,0.0011850072,0.018731179,0.0043084845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015938243,0.0019404248,0.0014044497,0.02173156,0.0026964815,0.0086955335,0.0028800622,0.0024784305,0.054037116],"category_scores_gemma":[0.013268861,0.00069403363,0.001190364,0.014972557,0.0008488221,0.0071791587,0.0026610165,0.002513537,0.039126664],"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":[0.000059025562,0.00006111777,0.00034310325,0.000977296,0.000026555805,0.000022571065,0.000046987174,0.00029620974,0.0009723405,0.0007745069,0.92526203,0.07115819],"study_design_scores_gemma":[0.000049435956,0.00015408694,0.0041346042,0.0009695716,0.00009366894,0.00009494867,0.00017518563,0.0013145654,0.00227573,0.0017762253,0.988865,0.00009704526],"about_ca_topic_score_codex":0.1078189,"about_ca_topic_score_gemma":0.21657813,"teacher_disagreement_score":0.1078189,"about_ca_system_score_codex":0.007022777,"about_ca_system_score_gemma":0.01817399,"threshold_uncertainty_score":0.21438265},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045153964,0.004560372,0.9017177,0.0012647854,0.0036348628,0.00056418433,0.004816881,0.026451245,0.011836024],"genre_scores_gemma":[0.5331414,0.0015930879,0.39766186,0.0007625823,0.0037786204,0.00041183448,0.016962564,0.0016116793,0.04407635],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992656,0.00012949262,0.000065175416,0.00017820034,0.00025022155,0.000111199195],"domain_scores_gemma":[0.9976566,0.0005678583,0.0001373334,0.0004382987,0.0009879549,0.00021192052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009880287,0.0011888943,0.0015567029,0.0030791175,0.0011313532,0.0021896826,0.0012668883,0.0011741868,0.017863858],"category_scores_gemma":[0.004906649,0.00031765108,0.00072577305,0.002821326,0.00041253673,0.0023560736,0.0016281588,0.0012452708,0.006409601],"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":[0.001663616,0.00028613425,0.0011329409,0.0003821042,0.00013199716,0.00022978312,0.00018192794,0.01262534,0.027719375,0.002966675,0.056443617,0.8962366],"study_design_scores_gemma":[0.0002745067,0.0009269057,0.0054987436,0.00009988905,0.00045058804,0.00035887733,0.00068830233,0.86170053,0.048216872,0.017840115,0.063831165,0.000113457994],"about_ca_topic_score_codex":0.0050418894,"about_ca_topic_score_gemma":0.0111743845,"teacher_disagreement_score":0.017863858,"about_ca_system_score_codex":0.0005375932,"about_ca_system_score_gemma":0.0013659657,"threshold_uncertainty_score":0.05976057},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017278662,0.036881328,0.019241523,0.17164502,0.06058912,0.0014931319,0.5981041,0.0111066755,0.08366036],"genre_scores_gemma":[0.08486571,0.007941765,0.029418724,0.04291128,0.015510723,0.0011276633,0.6851285,0.0029143235,0.13018134],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969049,0.001304041,0.000121543955,0.0002847994,0.001006792,0.0003778348],"domain_scores_gemma":[0.9836233,0.006292259,0.0006661137,0.0010091203,0.0048691765,0.003539946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0114950575,0.0023484242,0.0013452793,0.0026670913,0.0020323028,0.0050025433,0.0025201712,0.004764943,0.046827268],"category_scores_gemma":[0.017502062,0.00048533388,0.0010121892,0.0017601597,0.0017939064,0.0045013507,0.0030821783,0.0042768237,0.018636195],"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":[0.00012028656,0.000027326958,0.00026387352,0.00022146778,0.000029315896,0.000012092934,0.000016130103,0.00040368608,0.00022455072,0.00028453165,0.9913121,0.007084661],"study_design_scores_gemma":[0.001433197,0.00051513966,0.011870504,0.0012007034,0.00029002898,0.00015748719,0.00061670406,0.016127871,0.0051880353,0.021747675,0.9405427,0.00030999462],"about_ca_topic_score_codex":0.0801805,"about_ca_topic_score_gemma":0.20271587,"teacher_disagreement_score":0.0801805,"about_ca_system_score_codex":0.004015107,"about_ca_system_score_gemma":0.0076537393,"threshold_uncertainty_score":0.15942758},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009586497,0.014989157,0.049352422,0.051440634,0.036844406,0.0025930055,0.1813039,0.026069231,0.6278208],"genre_scores_gemma":[0.010336866,0.0024153448,0.0136814015,0.0035945608,0.0023620748,0.00045453265,0.064809516,0.0014924844,0.9008533],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985025,0.00032466266,0.00004972158,0.00030778686,0.0005746954,0.00024060383],"domain_scores_gemma":[0.99679834,0.00038134074,0.000062637344,0.00018895639,0.0014511629,0.0011176522],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0040170853,0.001444672,0.0017685362,0.0017395017,0.0031710607,0.005168783,0.0015665762,0.0018300671,0.32473767],"category_scores_gemma":[0.004308164,0.0005669957,0.00050925236,0.001915611,0.0006377894,0.0044029737,0.0022043316,0.0022221177,0.16095291],"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":[0.00006128644,0.000045177203,0.000059023474,0.000053491392,0.000005339952,0.000016058042,0.000026315718,0.00003722656,0.00073348446,0.00051236514,0.98523116,0.01321903],"study_design_scores_gemma":[0.00008190572,0.00006477211,0.0010873207,0.00006058541,0.00001641769,0.000032087864,0.00018255664,0.0010747551,0.0014577488,0.0016981247,0.9942146,0.000029199231],"about_ca_topic_score_codex":0.1185358,"about_ca_topic_score_gemma":0.36352664,"teacher_disagreement_score":0.32473767,"about_ca_system_score_codex":0.003471375,"about_ca_system_score_gemma":0.0061473493,"threshold_uncertainty_score":0.96317977},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034919076,0.015380205,0.07520244,0.0288929,0.03860525,0.003982918,0.56377023,0.09874078,0.14050621],"genre_scores_gemma":[0.03192368,0.0025518541,0.04111877,0.0035616904,0.005238068,0.0009285126,0.675215,0.0056847143,0.23377772],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997855,0.00047744752,0.000081100654,0.00031481875,0.00092077826,0.00035078224],"domain_scores_gemma":[0.99247736,0.001319226,0.00018120407,0.00084283756,0.0033450776,0.0018342716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046977256,0.0026059018,0.0022001823,0.003562521,0.0026171284,0.005394547,0.0024253225,0.0027788312,0.091113925],"category_scores_gemma":[0.007243303,0.0005641526,0.0009149056,0.0033326454,0.0006609594,0.0052162865,0.0025776238,0.0031588087,0.06771435],"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":[0.00014283705,0.00007740664,0.00014546225,0.00014337394,0.00001658794,0.000021466798,0.000035711782,0.00017814066,0.0027204596,0.0002875172,0.9815672,0.014663797],"study_design_scores_gemma":[0.0006848253,0.0008269942,0.0078263115,0.00017543275,0.0001547846,0.00019691243,0.0006182693,0.017224012,0.021025648,0.0044549797,0.9466633,0.00014853018],"about_ca_topic_score_codex":0.06878214,"about_ca_topic_score_gemma":0.1561614,"teacher_disagreement_score":0.091113925,"about_ca_system_score_codex":0.0021971222,"about_ca_system_score_gemma":0.0046306215,"threshold_uncertainty_score":0.30480647},"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":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004341382,0.024673682,0.024273464,0.014994732,0.0485831,0.00419523,0.63831353,0.048343476,0.19228138],"genre_scores_gemma":[0.006311336,0.007253632,0.018531969,0.0032397024,0.008082471,0.0021956535,0.6154247,0.0050389213,0.33392158],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951609,0.00079144456,0.00024062836,0.00037775966,0.0027003703,0.0007290249],"domain_scores_gemma":[0.9749223,0.0020292988,0.0012171979,0.0016046065,0.0146441525,0.0055823955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0118053965,0.0042334264,0.002574337,0.01184147,0.0032286076,0.009065449,0.0059378454,0.0029471486,0.16026507],"category_scores_gemma":[0.014582235,0.0014381435,0.0017970599,0.009026304,0.00094726885,0.0069361217,0.004330505,0.0035045694,0.20752099],"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":[0.000067346315,0.000028084592,0.000054173408,0.00023309237,0.000009677364,0.000009274662,0.000007197609,0.000100453144,0.0005116216,0.0001541133,0.9872155,0.01160951],"study_design_scores_gemma":[0.00021232638,0.00020004435,0.002180599,0.00031013362,0.00007259021,0.000080075864,0.00007686051,0.001422332,0.0029015045,0.0013469792,0.9911097,0.00008689659],"about_ca_topic_score_codex":0.11912479,"about_ca_topic_score_gemma":0.18345468,"teacher_disagreement_score":0.16026507,"about_ca_system_score_codex":0.0045192153,"about_ca_system_score_gemma":0.017015368,"threshold_uncertainty_score":0.5361401},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010629021,0.014963763,0.011796116,0.12680486,0.053975817,0.00357807,0.22884062,0.0077627627,0.541649],"genre_scores_gemma":[0.017933946,0.0021898006,0.008404245,0.017398112,0.0057924087,0.00067827635,0.09822963,0.00088495604,0.8484887],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99303174,0.001323031,0.00016762674,0.00078729895,0.0034748062,0.0012155331],"domain_scores_gemma":[0.9872224,0.0007900037,0.00025908832,0.00057176023,0.007226313,0.003930469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011753537,0.0015828868,0.0020667876,0.0029668207,0.0041537597,0.005982981,0.0026656853,0.004052326,0.16110636],"category_scores_gemma":[0.009002735,0.0005190745,0.0009007745,0.002704711,0.0011002545,0.0028512839,0.003604298,0.0021021243,0.10036899],"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":[0.00006614546,0.000041786865,0.0001325768,0.000052214204,0.0000067946767,0.000012465447,0.000016986021,0.00005358145,0.00040255958,0.0003319098,0.9890485,0.009834483],"study_design_scores_gemma":[0.00010395175,0.00009703416,0.0018626632,0.000061154744,0.000018378907,0.00003010146,0.000121347766,0.0007042689,0.0012766673,0.00086413213,0.99483645,0.000023902405],"about_ca_topic_score_codex":0.19976693,"about_ca_topic_score_gemma":0.43666995,"teacher_disagreement_score":0.19976693,"about_ca_system_score_codex":0.00810436,"about_ca_system_score_gemma":0.018749632,"threshold_uncertainty_score":0.5389545},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95566833,0.004107628,0.022563687,0.00041039928,0.00032843385,0.00061980146,0.0056866067,0.00480454,0.005810445],"genre_scores_gemma":[0.9719864,0.00030079458,0.021199884,0.00011599928,0.0001623967,0.00021731682,0.004707912,0.00024226525,0.001067089],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96925473,0.011266278,0.0037144537,0.0035091257,0.011331032,0.0009243749],"domain_scores_gemma":[0.8357006,0.10867377,0.018057164,0.018949203,0.016109373,0.0025099386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019076522,0.0016192278,0.0016693065,0.0053947233,0.0009047722,0.002386232,0.0014851961,0.0024759586,0.0010430615],"category_scores_gemma":[0.111374974,0.0004722254,0.0012916527,0.0038821765,0.0010892801,0.0029471363,0.0012120595,0.0018440483,0.0011497659],"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":[0.022667913,0.0060357153,0.22866409,0.005635448,0.007240327,0.0006787422,0.0012933586,0.10090745,0.15253995,0.0020363342,0.025301175,0.4469995],"study_design_scores_gemma":[0.00082783814,0.019763395,0.46477774,0.00021984994,0.0017314387,0.00204945,0.00065036595,0.24178314,0.25620428,0.0024276192,0.008666447,0.0008983365],"about_ca_topic_score_codex":0.0047841296,"about_ca_topic_score_gemma":0.004627989,"teacher_disagreement_score":0.019076522,"about_ca_system_score_codex":0.0013087677,"about_ca_system_score_gemma":0.0012038512,"threshold_uncertainty_score":0.10088754},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008757146,0.017000046,0.021639023,0.036264643,0.01773245,0.0051228893,0.6697195,0.03786725,0.18589701],"genre_scores_gemma":[0.020873265,0.0041060494,0.025609976,0.0032933918,0.002023505,0.0034104246,0.72304225,0.0036833726,0.21395786],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9878335,0.0035979734,0.0006569964,0.0013234734,0.0055059623,0.0010821501],"domain_scores_gemma":[0.9703686,0.0035993303,0.001033894,0.004514141,0.014976251,0.005507737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019876845,0.007234418,0.0044574398,0.009414261,0.009248908,0.009217993,0.0059301835,0.004843805,0.08711207],"category_scores_gemma":[0.022643147,0.001461212,0.0013489319,0.008401699,0.002214527,0.008890569,0.0049351533,0.006895278,0.085722655],"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":[0.000048277416,0.000060080725,0.000093863426,0.00013894807,0.000010291548,0.000010221405,0.000020344993,0.0003505086,0.00021134243,0.00028126567,0.99105716,0.0077177486],"study_design_scores_gemma":[0.00037841153,0.00015163333,0.0049260384,0.00042513647,0.00004860865,0.00006172384,0.00034348958,0.009215571,0.0028349743,0.0050974335,0.9762915,0.00022557777],"about_ca_topic_score_codex":0.34578037,"about_ca_topic_score_gemma":0.4783251,"teacher_disagreement_score":0.34578037,"about_ca_system_score_codex":0.012561103,"about_ca_system_score_gemma":0.01893056,"threshold_uncertainty_score":0.6875354},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6925686,0.0021491856,0.2960187,0.0008883944,0.00015468987,0.00064536044,0.0019856845,0.0035742268,0.0020151576],"genre_scores_gemma":[0.79441774,0.00025102656,0.20299293,0.000085780695,0.000068240355,0.00014734015,0.0014555568,0.000040688956,0.0005406972],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982621,0.00058932934,0.0002468042,0.00026010204,0.0005069486,0.0001347468],"domain_scores_gemma":[0.99162066,0.0057381615,0.00062379264,0.0005853488,0.0011601065,0.00027190603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028712007,0.00065485074,0.0015095889,0.0042690127,0.00078669644,0.0010717047,0.0013899541,0.00074116397,0.0011569153],"category_scores_gemma":[0.010088167,0.00037270482,0.000727421,0.004361131,0.00030560757,0.0015050784,0.0006418093,0.0008002723,0.0006831712],"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":[0.002434334,0.0016113681,0.059366167,0.0007651269,0.00052536424,0.001032846,0.0005840472,0.10366636,0.028064843,0.003543699,0.010149271,0.78825665],"study_design_scores_gemma":[0.000058428657,0.00023759078,0.0057917405,0.000018434113,0.00006174045,0.00037293287,0.00020316501,0.9815336,0.008045097,0.0026519885,0.0010056606,0.000019555067],"about_ca_topic_score_codex":0.005292965,"about_ca_topic_score_gemma":0.004566489,"teacher_disagreement_score":0.005292965,"about_ca_system_score_codex":0.00077110843,"about_ca_system_score_gemma":0.0010558038,"threshold_uncertainty_score":0.015184522},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00502526,0.002362251,0.9868326,0.00045305802,0.00033531204,0.00021103422,0.0005454954,0.0016922068,0.0025427986],"genre_scores_gemma":[0.2612721,0.0071674017,0.6777792,0.0011566331,0.002324821,0.0022741489,0.0074949544,0.0023464411,0.038184308],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960006,0.0021824064,0.00021631761,0.0007439905,0.0006266758,0.00023001165],"domain_scores_gemma":[0.98751324,0.009126886,0.00054205954,0.0015580406,0.0010059774,0.00025375962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0093001705,0.0018604704,0.0024990244,0.0034483317,0.0009514055,0.0024076402,0.002700091,0.0018553956,0.008803787],"category_scores_gemma":[0.03729002,0.001320247,0.003052324,0.0029266193,0.0016688402,0.005749535,0.0027975633,0.003694678,0.008370481],"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":[0.000777949,0.00033658298,0.0020211714,0.0009978095,0.00056372257,0.00050028425,0.0007464394,0.27592093,0.006187542,0.24987532,0.0380997,0.42397264],"study_design_scores_gemma":[0.0000723843,0.00011464274,0.00043996953,0.00005797728,0.00012877145,0.00021175339,0.000043867472,0.8614446,0.0019811692,0.12348616,0.011959539,0.000059049788],"about_ca_topic_score_codex":0.0060057305,"about_ca_topic_score_gemma":0.006388693,"teacher_disagreement_score":0.0093001705,"about_ca_system_score_codex":0.0014604882,"about_ca_system_score_gemma":0.0015913282,"threshold_uncertainty_score":0.04918462},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8498437,0.009122601,0.018169438,0.0052189543,0.0015937181,0.0035681578,0.027655846,0.0283323,0.05649526],"genre_scores_gemma":[0.8015736,0.0020512326,0.09807819,0.0016253596,0.0005813411,0.0017092366,0.06631204,0.0015769263,0.026492052],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98984677,0.00541449,0.00058424263,0.0015490097,0.0021276614,0.0004779139],"domain_scores_gemma":[0.96407396,0.023628952,0.00089454214,0.0039149947,0.0053250124,0.0021624872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008740128,0.0016074046,0.0018304938,0.0017439008,0.003640552,0.0020924788,0.0030729554,0.0025182085,0.012655079],"category_scores_gemma":[0.0350465,0.00077034306,0.0007640295,0.0037198332,0.0011076708,0.0038697512,0.0016076466,0.0026187159,0.005004578],"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":[0.010977005,0.014391465,0.019856961,0.003895808,0.00093206123,0.0006633989,0.002856076,0.03945339,0.019371066,0.00246331,0.48171222,0.40342727],"study_design_scores_gemma":[0.009393843,0.008971638,0.096434325,0.000846573,0.0011508681,0.000775324,0.0063138525,0.6733085,0.04019113,0.006049659,0.15564002,0.00092426053],"about_ca_topic_score_codex":0.18286334,"about_ca_topic_score_gemma":0.20865199,"teacher_disagreement_score":0.18286334,"about_ca_system_score_codex":0.004432694,"about_ca_system_score_gemma":0.0045464463,"threshold_uncertainty_score":0.36359793},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020568717,0.0019851525,0.9645828,0.00033935695,0.00025238236,0.0007570464,0.00064776954,0.0069979136,0.0038689112],"genre_scores_gemma":[0.110476315,0.00065534306,0.88060045,0.0003231873,0.00022671843,0.00042634655,0.0025158406,0.00035018308,0.0044255173],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958961,0.001704541,0.00025276517,0.00060632377,0.0013168644,0.0002234168],"domain_scores_gemma":[0.99586296,0.0012840399,0.00031416182,0.00086569303,0.0015126924,0.00016051173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005392751,0.00117083,0.0018086787,0.0070267385,0.0010401411,0.0014569007,0.0018941008,0.0011594048,0.0029867794],"category_scores_gemma":[0.009490428,0.0005584182,0.0011778836,0.0051608398,0.0005774494,0.0026875571,0.0017724633,0.0011827106,0.004304155],"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":[0.00037447255,0.0004446272,0.0027035302,0.00044761598,0.00021301955,0.0002111561,0.0004088,0.009178377,0.05300895,0.005177511,0.020609353,0.90722257],"study_design_scores_gemma":[0.00029836592,0.0012384828,0.016729902,0.00015802663,0.00057219015,0.0022932221,0.0006190575,0.69964385,0.117107995,0.04860067,0.11232475,0.00041357768],"about_ca_topic_score_codex":0.0019374285,"about_ca_topic_score_gemma":0.0046644583,"teacher_disagreement_score":0.0070267385,"about_ca_system_score_codex":0.0006187105,"about_ca_system_score_gemma":0.0013053512,"threshold_uncertainty_score":0.028519928},"labels":[],"label_agreement":null}]}