{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":465,"total_is_capped":false,"direct_labels_cover":3,"predictions_cover":465,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"4f2ab75c29b4","filters":{"topic":"Information Retrieval and Search Behavior"}},"results":[{"id":"W2069870183","doi":"10.1145/582415.582418","title":"Cumulated gain-based evaluation of IR techniques","year":2002,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":4634,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Tampereen Yliopisto; McGill University","keywords":"Relevance (law); Computer science; Information retrieval; Precision and recall; Recall; Data mining","authors":[{"name":"Kalervo Järvelin","is_ca":false},{"name":"Jaana Kekäläinen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05912903173965583,"gpt":0.3135213631932822,"spread":0.2543923314536263,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01577956,0.001550693,0.001341587,0.006118166,0.0005098194,0.002538706,0.001635801,0.001307046,0.002495575],"category_scores_gemma":[0.07454475,0.0002580684,0.000816701,0.003474753,0.001146181,0.003609414,0.001876878,0.001015519,0.001084225],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002323342,"about_ca_system_score_gemma":0.001054092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001627633,"about_ca_topic_score_gemma":0.002051967,"domain_scores_codex":[0.9740858,0.01019223,0.001208266,0.00166143,0.01231673,0.0005355356],"domain_scores_gemma":[0.9274374,0.05250627,0.004136703,0.006833653,0.008365315,0.0007206601],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003382952,0.0005307753,0.01205059,0.001419174,0.0007455303,0.000173,0.0004480548,0.2283435,0.02966649,0.0205612,0.006204493,0.6964742],"study_design_scores_gemma":[0.0001529937,0.001981454,0.01464161,0.00008702091,0.0002110465,0.0004728742,0.0001192023,0.9413317,0.02191063,0.01439871,0.004558822,0.0001339276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2771446,0.0100257,0.6793712,0.0005101059,0.00040927,0.0009312058,0.001172913,0.004688074,0.02574678],"genre_scores_gemma":[0.8209091,0.00110258,0.1721575,0.0001307703,0.0002772051,0.0004425558,0.001372672,0.0003870563,0.00322055],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01577956,"threshold_uncertainty_score":0.08345133,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2132314908","doi":"10.1145/1390334.1390446","title":"Novelty and diversity in information retrieval evaluation","year":2008,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":951,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Novelty; Computer science; Redundancy (engineering); Ranking (information retrieval); Information retrieval; Ambiguity; Learning to rank; Information gain; Data mining; Artificial intelligence; Machine learning","authors":[{"name":"Charles L. A. Clarke","is_ca":true},{"name":"Maheedhar Kolla","is_ca":true},{"name":"Gordon V. Cormack","is_ca":true},{"name":"Olga Vechtomova","is_ca":true},{"name":"Azin Ashkan","is_ca":true},{"name":"Stefan Büttcher","is_ca":true},{"name":"Ian MacKinnon","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0679627973098831,"gpt":0.2735590934351592,"spread":0.2055962961252761,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06834721,0.002364682,0.00333351,0.009538271,0.001767174,0.006254688,0.002078248,0.003686226,0.001183263],"category_scores_gemma":[0.1770916,0.0008234837,0.001593938,0.005154718,0.005884214,0.01164137,0.006614281,0.003743243,0.000356199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004350632,"about_ca_system_score_gemma":0.002010297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001130315,"about_ca_topic_score_gemma":0.001412207,"domain_scores_codex":[0.8959367,0.06570719,0.005090998,0.006158061,0.02553216,0.001574851],"domain_scores_gemma":[0.7930283,0.1662651,0.01121405,0.01091479,0.01550054,0.00307716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001929104,0.0005354147,0.03829167,0.001414913,0.001324444,0.0003026591,0.001076931,0.1476975,0.007681496,0.2743159,0.005170656,0.5202593],"study_design_scores_gemma":[0.0003771018,0.00281531,0.01890167,0.0004810068,0.0004459539,0.0008437143,0.0002497858,0.4565943,0.008950614,0.5018911,0.008015301,0.0004342504],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07982308,0.01073372,0.890636,0.002024294,0.0002501182,0.0006751702,0.0002813963,0.0008016846,0.01477457],"genre_scores_gemma":[0.7264948,0.001249706,0.2678781,0.0005311417,0.0006432043,0.0009073077,0.0003063684,0.0002584513,0.001730907],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.06834721,"threshold_uncertainty_score":0.3614589,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2045935559","doi":"10.1108/00220410310457993","title":"A model of information practices in accounts of everyday‐life information seeking","year":2003,"lang":"en","type":"article","venue":"Journal of Documentation","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":595,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Information seeking; Everyday life; Neglect; Focus (optics); Strict constructionism; Psychology; Sociology; Information needs; Information behavior; Cognition; Computer science; Knowledge management; Social psychology; Epistemology; World Wide Web; Information retrieval; Human–computer interaction","authors":[{"name":"Pamela J. McKenzie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03956720142467514,"gpt":0.3266791205103419,"spread":0.2871119190856667,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006238956,0.0009002872,0.0005670408,0.006149706,0.003940203,0.0116449,0.002429562,0.003661025,0.00448301],"category_scores_gemma":[0.0138607,0.0006970479,0.001327414,0.006341484,0.01890175,0.02312783,0.004144903,0.002844166,0.0009549987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008326387,"about_ca_system_score_gemma":0.005738819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01051079,"about_ca_topic_score_gemma":0.006511761,"domain_scores_codex":[0.9925969,0.004566742,0.0003746939,0.0006389477,0.001360845,0.0004618049],"domain_scores_gemma":[0.9840416,0.01191135,0.001016973,0.00158508,0.0009467835,0.0004982721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001703958,0.0000279017,0.0006891857,0.00007977958,0.000008778655,0.00009866102,0.04028999,0.0009362421,0.0001627069,0.9527856,0.0004267134,0.004477372],"study_design_scores_gemma":[0.00004146689,0.00004121614,0.001165254,0.0003659159,0.00002947788,0.000462483,0.01975797,0.01421895,0.0002296461,0.9276057,0.03604454,0.00003732268],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1341727,0.004187903,0.4219901,0.02903958,0.000187937,0.0004897063,0.0005202601,0.0005536698,0.4088582],"genre_scores_gemma":[0.9246871,0.001210965,0.06346607,0.0005808346,0.0000860973,0.0005948273,0.000233434,0.0001215888,0.009019082],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0116449,"threshold_uncertainty_score":0.06041241,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2120308175","doi":"10.1016/s0306-4573(00)00010-8","title":"Variations in relevance judgments and the measurement of retrieval effectiveness","year":2000,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":507,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute of Standards and Technology; University of Waterloo","keywords":"Relevance (law); Information retrieval; Computer science; NIST; Set (abstract data type); Test (biology); Reliability (semiconductor); Ranking (information retrieval); Document retrieval; Natural language processing","authors":[{"name":"Ellen M. Voorhees","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01358723951661481,"gpt":0.2439882889508641,"spread":0.2304010494342493,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02027675,0.0003902094,0.0008037236,0.003208354,0.000516544,0.002878197,0.0007765157,0.001811885,0.001334948],"category_scores_gemma":[0.3084425,0.0004411684,0.0004142646,0.002551426,0.001332262,0.002222596,0.00100395,0.001700244,0.0005639677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008852497,"about_ca_system_score_gemma":0.0004947886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001455787,"about_ca_topic_score_gemma":0.001216212,"domain_scores_codex":[0.9669511,0.0202517,0.002204835,0.002753044,0.007238827,0.0006004745],"domain_scores_gemma":[0.6498775,0.3022025,0.02286725,0.01484736,0.00797183,0.002233591],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.009852016,0.002030525,0.6785566,0.0008471128,0.001720816,0.0003162361,0.006507598,0.01066102,0.09339182,0.008429323,0.002665767,0.1850212],"study_design_scores_gemma":[0.0001086026,0.001155992,0.9737563,0.00004207894,0.0002059622,0.0004813164,0.0002902412,0.008780705,0.007849541,0.006406734,0.0008049486,0.0001176381],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9859698,0.001376231,0.007141199,0.0001545675,0.00004093683,0.0001107648,0.000202766,0.0001084405,0.004895355],"genre_scores_gemma":[0.9975782,0.00009921359,0.001760935,0.0000537457,0.0000328627,0.00004654071,0.0001412378,0.00004071946,0.0002466349],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02027675,"threshold_uncertainty_score":0.107235,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1992156462","doi":"10.1108/00220410510578023","title":"“Isms” in information science: constructivism, collectivism and constructionism","year":2005,"lang":"en","type":"article","venue":"Journal of Documentation","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":363,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Library of Parliament","funders":"","keywords":"Metatheory; Constructionism; Constructivism (international relations); Originality; Strict constructionism; Epistemology; Collectivism; Value (mathematics); Computer science; Objectivism; Sociology; Knowledge management; Social science; Philosophy; Politics; Individualism","authors":[{"name":"Sanna Talja","is_ca":false},{"name":"Kimmo Tuominen","is_ca":true},{"name":"Reijo Savolainen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.005605229972077005,"gpt":0.2681537019985687,"spread":0.2625484720264917,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.02402311,0.0007274044,0.0009830652,0.009069039,0.003883679,0.01252727,0.001571176,0.002166011,0.001829762],"category_scores_gemma":[0.01876547,0.0006200924,0.00110803,0.008326477,0.05682149,0.0177853,0.0049768,0.004577515,0.0002836158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008200582,"about_ca_system_score_gemma":0.00686465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002491153,"about_ca_topic_score_gemma":0.001603421,"domain_scores_codex":[0.9734134,0.02080607,0.001036991,0.001025567,0.003059104,0.0006587238],"domain_scores_gemma":[0.9730312,0.0197664,0.001704294,0.003362103,0.00155053,0.0005854673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000009195431,0.00001476239,0.0005950002,0.0001105664,0.00001400388,0.00002492008,0.007135078,0.0002395824,0.00004753576,0.9835597,0.0006263027,0.007623306],"study_design_scores_gemma":[0.000008897746,0.00001619619,0.0006136547,0.0002480807,0.00001121233,0.00004935747,0.003245481,0.0007058671,0.00009775091,0.9820307,0.0129633,0.000009407648],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1027163,0.06322034,0.3615232,0.1698962,0.001236579,0.0003830213,0.00027269,0.0004758002,0.3002759],"genre_scores_gemma":[0.9400694,0.01014381,0.04139924,0.003062596,0.0009351273,0.0006612948,0.0001222577,0.00008406916,0.003522108],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9961163,"threshold_uncertainty_score":0.1270479,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2740321901","doi":"10.1145/3077136.3080721","title":"Anserini","year":2017,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":323,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Scalability; Ranking (information retrieval); Information retrieval; Search engine indexing; World Wide Web; Database","authors":[{"name":"Peilin Yang","is_ca":false},{"name":"Hui Fang","is_ca":false},{"name":"Jimmy Lin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03590055928300059,"gpt":0.3085574560823229,"spread":0.2726568967993224,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003035212,0.001722615,0.001246716,0.003326435,0.00167828,0.004832644,0.002804007,0.001628622,0.1996145],"category_scores_gemma":[0.0114126,0.001188533,0.001467907,0.002446195,0.0008671345,0.007220777,0.005014215,0.002170104,0.2277051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001730875,"about_ca_system_score_gemma":0.002536446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004226551,"about_ca_topic_score_gemma":0.00464728,"domain_scores_codex":[0.9966182,0.0005523411,0.0002887806,0.0007440951,0.00149932,0.0002972],"domain_scores_gemma":[0.995297,0.001035278,0.0002410587,0.001576631,0.001414044,0.0004359721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004993593,0.0001490497,0.001358859,0.0007519377,0.00005608398,0.0002156348,0.000498173,0.001321568,0.009000601,0.03484727,0.5037453,0.4475561],"study_design_scores_gemma":[0.00005087497,0.00007966298,0.0009742782,0.0001201195,0.00002431092,0.0003400307,0.00006038194,0.007184939,0.007628292,0.01452192,0.9689315,0.00008356144],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"software","genre_scores_codex":[0.006902224,0.003170676,0.2734137,0.002720429,0.001332189,0.001017522,0.02176412,0.3391314,0.3505478],"genre_scores_gemma":[0.05103498,0.002620186,0.3165924,0.002587281,0.0007393798,0.001527313,0.0809017,0.04991461,0.4940822],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.1996145,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2899154813","doi":"10.1145/3239571","title":"Anserini","year":2018,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":230,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Information retrieval; World Wide Web; Ranking (information retrieval); Context (archaeology); Search engine indexing; Implementation; Data science; Software engineering","authors":[{"name":"Peilin Yang","is_ca":false},{"name":"Hui Fang","is_ca":false},{"name":"Jimmy Lin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1067568912519719,"gpt":0.3914247076637422,"spread":0.2846678164117703,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004391655,0.001382338,0.001320268,0.004665756,0.002545107,0.006867705,0.002537536,0.001988963,0.1391873],"category_scores_gemma":[0.01659606,0.000774427,0.001161966,0.003775898,0.001315966,0.007519593,0.005211914,0.002431556,0.1528894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002295859,"about_ca_system_score_gemma":0.003203284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004579382,"about_ca_topic_score_gemma":0.005225856,"domain_scores_codex":[0.9941661,0.001074485,0.0003905293,0.001403015,0.002542177,0.0004236937],"domain_scores_gemma":[0.9922965,0.002050696,0.0003985959,0.002452871,0.002163561,0.0006376668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003865675,0.0001824367,0.002591538,0.0006043327,0.0000581545,0.0002520788,0.0004523397,0.002013202,0.004741944,0.05996548,0.3109477,0.6178042],"study_design_scores_gemma":[0.00003409402,0.0001094384,0.001257177,0.0001531599,0.00002788227,0.0005490099,0.00009432207,0.008790037,0.005517837,0.01858827,0.9648036,0.00007508496],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.01584384,0.01171018,0.2932384,0.01258994,0.005840839,0.0009887861,0.0129375,0.06034621,0.5865043],"genre_scores_gemma":[0.1044367,0.007031924,0.2440297,0.005872109,0.002175173,0.001032389,0.0305411,0.008911609,0.5959693],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.1391873,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2108279663","doi":"10.1145/1935826.1935840","title":"Personalizing web search using long term browsing history","year":2011,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":202,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Personalization; Computer science; World Wide Web; Information retrieval; Personalized search; Term (time); Search engine; The Internet; Web navigation; Web page","authors":[{"name":"Nicolaas Matthijs","is_ca":false},{"name":"Filip Radlinski","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2027700771185297,"gpt":0.2961379762883247,"spread":0.09336789916979496,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001703965,0.0007296601,0.0009830279,0.002455544,0.0004383674,0.001338206,0.0007964548,0.0008108218,0.0008602373],"category_scores_gemma":[0.008321156,0.0004371798,0.0005660871,0.001894215,0.0003633214,0.00300914,0.0007496554,0.0007996876,0.0008003337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004991048,"about_ca_system_score_gemma":0.0005896051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003524681,"about_ca_topic_score_gemma":0.006462081,"domain_scores_codex":[0.9990456,0.0003183555,0.00007030637,0.0002180335,0.0002722307,0.00007551222],"domain_scores_gemma":[0.9949459,0.00250618,0.0005523527,0.001178344,0.0006266639,0.0001904274],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009483758,0.001174658,0.06212535,0.0002886753,0.0003857808,0.0002253121,0.0009451904,0.08823214,0.03096064,0.003295026,0.004824042,0.8065948],"study_design_scores_gemma":[0.00005738419,0.0005534567,0.02564757,0.00003282253,0.0002342697,0.0007515355,0.0002005032,0.9446262,0.01548415,0.008284634,0.004004071,0.0001234658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4846486,0.002298242,0.5024747,0.0003825342,0.00006068329,0.0002631614,0.0003915684,0.004002661,0.005477836],"genre_scores_gemma":[0.9087268,0.00061187,0.08697011,0.00006498577,0.0001211663,0.00006486169,0.0004712953,0.0001557663,0.00281308],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003524681,"threshold_uncertainty_score":0.009011507,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2029009258","doi":"10.1145/2348283.2348300","title":"Time-based calibration of effectiveness measures","year":2012,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":200,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"University of Waterloo","keywords":"Computer science; Measure (data warehouse); Process (computing); Quality (philosophy); Information retrieval; Calibration; Adaptation (eye); Data mining; Machine learning","authors":[{"name":"Mark D. Smucker","is_ca":true},{"name":"Charles L. A. Clarke","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02563785066914584,"gpt":0.2660673763852607,"spread":0.2404295257161148,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03200497,0.001284413,0.0008742473,0.004797782,0.0006308739,0.002321976,0.002352586,0.001884615,0.002867628],"category_scores_gemma":[0.3036897,0.000562711,0.0009430076,0.004493567,0.001479991,0.004468923,0.001878044,0.001663689,0.001291005],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002473348,"about_ca_system_score_gemma":0.0009465561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002536812,"about_ca_topic_score_gemma":0.001923103,"domain_scores_codex":[0.9519276,0.025659,0.003170342,0.004704596,0.01364213,0.0008961958],"domain_scores_gemma":[0.687858,0.2212814,0.01767446,0.04321877,0.02863112,0.001336238],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003300424,0.001850441,0.1190937,0.002258078,0.001137494,0.0002782678,0.003554696,0.2064402,0.0266499,0.05137167,0.01640589,0.5676592],"study_design_scores_gemma":[0.0004452246,0.005811258,0.2162781,0.0008344466,0.0006882705,0.001690671,0.001743121,0.5894116,0.07379001,0.06165162,0.04695525,0.000700498],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3315251,0.003774985,0.6272882,0.0006738813,0.0003910474,0.001648501,0.002825499,0.002776228,0.02909657],"genre_scores_gemma":[0.846961,0.0004377394,0.1458361,0.0002970345,0.0001169222,0.001587576,0.002380563,0.0006388359,0.001744143],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03200497,"threshold_uncertainty_score":0.1692604,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4236702116","doi":"10.1002/asi.20249","title":"Human information behavior: Integrating diverse approaches and information use","year":2005,"lang":"en","type":"article","venue":"Journal of the American Society for Information Science and Technology","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":179,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"CLARITY; Computer science; Information system; Perspective (graphical); Cognitive models of information retrieval; Cognitive science; Data science; Focus (optics); Process (computing); Information architecture; Management science; Artificial intelligence; Management information systems; Psychology","authors":[{"name":"Amanda Spink","is_ca":false},{"name":"Charles Cole","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03545342368456286,"gpt":0.2865945693561238,"spread":0.2511411456715609,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003161505,0.0003524255,0.0003704072,0.003052677,0.0009962849,0.007011291,0.0007776991,0.001771647,0.001226361],"category_scores_gemma":[0.01022999,0.0003339343,0.0004980877,0.002216149,0.007093791,0.00636074,0.002986721,0.001029072,0.000157318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001647231,"about_ca_system_score_gemma":0.0008065431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002805223,"about_ca_topic_score_gemma":0.002071542,"domain_scores_codex":[0.9968573,0.001768925,0.0001390598,0.0002758768,0.0008229174,0.0001359782],"domain_scores_gemma":[0.9936237,0.00363013,0.0009489924,0.0005414203,0.0009159207,0.0003398213],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001889774,0.0003558952,0.08676789,0.0007460478,0.0003185124,0.0004103707,0.04749974,0.01115334,0.005915081,0.6838717,0.002219808,0.1605525],"study_design_scores_gemma":[0.00004356262,0.0003339739,0.07616728,0.0005344074,0.0002190139,0.0009425626,0.02252565,0.07907163,0.002777191,0.7937851,0.02345271,0.0001468881],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7265561,0.01124003,0.1284899,0.01362189,0.00007446318,0.0001172983,0.0001190948,0.0001447743,0.1196364],"genre_scores_gemma":[0.9893311,0.0008827158,0.008781248,0.0002159612,0.00001967156,0.0000222847,0.00002260916,0.000006761758,0.0007175303],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007011291,"threshold_uncertainty_score":0.01671982,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2070507812","doi":"10.1145/1148170.1148285","title":"Term proximity scoring for ad-hoc retrieval on very large text collections","year":2006,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":162,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Information retrieval; Term (time); Term Discrimination; Artificial intelligence; Natural language processing; Search engine; Concept search; Web search query","authors":[{"name":"Stefan Büttcher","is_ca":true},{"name":"Charles L. A. Clarke","is_ca":true},{"name":"Brad Lushman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02238626999339941,"gpt":0.2708168976675244,"spread":0.248430627674125,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003938238,0.001669488,0.002402649,0.006628517,0.001847408,0.002268425,0.002526033,0.001462613,0.004204764],"category_scores_gemma":[0.01630929,0.0005090956,0.001019285,0.006845159,0.0007911081,0.003382941,0.001927836,0.001361929,0.005136847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008916894,"about_ca_system_score_gemma":0.00188833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004948084,"about_ca_topic_score_gemma":0.008248072,"domain_scores_codex":[0.9966312,0.001048723,0.0003062296,0.0005100026,0.001355898,0.0001478655],"domain_scores_gemma":[0.9943522,0.002508192,0.0004005027,0.001078378,0.001433149,0.0002275426],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003402031,0.000546916,0.002152586,0.0006662645,0.0002642459,0.0002063913,0.0002361366,0.02220717,0.03450051,0.003220544,0.01868981,0.9169692],"study_design_scores_gemma":[0.0002184449,0.001099594,0.008558518,0.0001143432,0.0003979893,0.00107384,0.0003721338,0.8942028,0.04293935,0.03187007,0.01893513,0.0002177284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03812081,0.002727755,0.9465234,0.0003299712,0.0002846963,0.0007223025,0.0005769706,0.007870689,0.002843411],"genre_scores_gemma":[0.2073316,0.001347596,0.7814657,0.000247898,0.0006686189,0.000872903,0.002601748,0.0004932196,0.004970776],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006628517,"threshold_uncertainty_score":0.02082765,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2015915702","doi":"10.5860/crl.62.4.355","title":"Usability of the Academic Library Web Site: Implications for Design","year":2001,"lang":"en","type":"article","venue":"College & Research Libraries","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":142,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Memorial University of Newfoundland","keywords":"World Wide Web; Usability; Web site; CLARITY; Computer science; Reading (process); Task (project management); Set (abstract data type); Academic library; Web usability; Web design; Web page; The Internet; Human–computer interaction; Library science; Engineering","authors":[{"name":"Louise McGillis","is_ca":false},{"name":"Elaine G. Toms","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1497566672809508,"gpt":0.3684894611330714,"spread":0.2187327938521206,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05161039,0.0007277656,0.000947638,0.001923188,0.002442759,0.009692797,0.002164712,0.00228999,0.004383381],"category_scores_gemma":[0.1574028,0.00077984,0.0007442402,0.001834209,0.004163404,0.007622926,0.001664246,0.001456442,0.001240304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004410446,"about_ca_system_score_gemma":0.005250527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005653774,"about_ca_topic_score_gemma":0.006304914,"domain_scores_codex":[0.9577577,0.03208981,0.00217258,0.0009942229,0.005889265,0.001096392],"domain_scores_gemma":[0.7950763,0.1769752,0.003165752,0.004656924,0.01707264,0.003053183],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001772998,0.004816735,0.1975887,0.006722723,0.0002974218,0.002038741,0.1729034,0.00480738,0.0096751,0.03701674,0.02262056,0.5397396],"study_design_scores_gemma":[0.001772131,0.01140855,0.4522457,0.008289445,0.001057418,0.00412653,0.2549762,0.04912323,0.01355567,0.0913164,0.11113,0.0009986944],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8346802,0.004641293,0.06806043,0.02558056,0.0003314931,0.005476318,0.0002819222,0.000904703,0.06004294],"genre_scores_gemma":[0.9368621,0.001234772,0.05411488,0.001693609,0.0000969267,0.002634729,0.0001277615,0.000205277,0.003029962],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05161039,"threshold_uncertainty_score":0.2729451,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1779866227","doi":"10.18438/b8ww3x","title":"Research Methods: Triangulation","year":2014,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":136,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Triangulation; Computer science; Information retrieval; Mathematics; Geometry","authors":[{"name":"Virginia Wilson","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06874072354947192,"gpt":0.4074737545774705,"spread":0.3387330310279986,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.235897,0.003228185,0.007025025,0.02186522,0.005423012,0.006635855,0.007748451,0.005876312,0.08559464],"category_scores_gemma":[0.5685504,0.003580855,0.003677061,0.02530487,0.005630671,0.007430288,0.007929291,0.004871673,0.02122166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008486117,"about_ca_system_score_gemma":0.03287686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006082893,"about_ca_topic_score_gemma":0.00913666,"domain_scores_codex":[0.6609761,0.2186374,0.06244979,0.01441071,0.04109361,0.00243245],"domain_scores_gemma":[0.5709299,0.2057458,0.02845692,0.09050321,0.101889,0.002475242],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003123279,0.0004658914,0.003958353,0.2993565,0.002104835,0.0006952594,0.01314523,0.001172859,0.001474607,0.05234097,0.2108313,0.411331],"study_design_scores_gemma":[0.008865004,0.001402515,0.006773784,0.3137147,0.005371117,0.0009116805,0.01318516,0.002541817,0.004183548,0.09829565,0.5442417,0.0005133539],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"protocol","genre_gemma":"methods","genre_scores_codex":[0.009525894,0.06422146,0.2227075,0.01853201,0.01528358,0.5265608,0.05812011,0.001133846,0.08391483],"genre_scores_gemma":[0.05344163,0.02155049,0.1708031,0.007324718,0.0009844494,0.7219418,0.007864423,0.0007069393,0.01538245],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7641029,"threshold_uncertainty_score":0.942275,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4247619421","doi":"10.1007/978-3-319-68699-8","title":"Information Retrieval","year":2017,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":127,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Information retrieval","authors":[{"name":"Tieyun Qian","is_ca":false},{"name":"Yiqun Liu","is_ca":true},{"name":"Tong Ruan","is_ca":false},{"name":"Jian‐Yun Nie","is_ca":false},{"name":"Ji-Rong Wen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01808543326184723,"gpt":0.269928670917719,"spread":0.2518432376558718,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009412733,0.001640772,0.001792568,0.007666701,0.0009775283,0.004987641,0.001693039,0.001255822,0.1468862],"category_scores_gemma":[0.002544736,0.0006606171,0.0009211435,0.008423338,0.0008220773,0.005597508,0.001922822,0.001460585,0.2467496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001223861,"about_ca_system_score_gemma":0.001531963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009138872,"about_ca_topic_score_gemma":0.00153185,"domain_scores_codex":[0.9987907,0.0001210315,0.00008011406,0.0001828859,0.0007478722,0.00007744864],"domain_scores_gemma":[0.9989214,0.0002055594,0.00005038498,0.00039294,0.0003563627,0.00007339897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002516198,0.00005773955,0.0001071061,0.0006684929,0.00003441663,0.00004144198,0.00005931514,0.0003189866,0.002885427,0.0208076,0.3433107,0.6316836],"study_design_scores_gemma":[0.00001029658,0.00005169296,0.0004934038,0.0002912365,0.00003548501,0.0004360373,0.00005942689,0.001208715,0.00385294,0.02185917,0.9716763,0.00002529442],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.002460897,0.06144868,0.09741317,0.002980816,0.003296153,0.0004430871,0.004195207,0.007614242,0.8201478],"genre_scores_gemma":[0.01289044,0.03488645,0.03784736,0.001182348,0.001770172,0.0002003311,0.008417675,0.00112275,0.9016826],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.1468862,"threshold_uncertainty_score":0.4913831,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2062551457","doi":"10.1002/meet.1450410116","title":"“I still like Google”: University student perceptions of searching OPACs and the web","year":2004,"lang":"en","type":"article","venue":"Proceedings of the American Society for Information Science and Technology","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":124,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"World Wide Web; Computer science; Usability; Admiration; Web page; Web design; Interface (matter); Web presence; Information retrieval; The Internet; Psychology; Human–computer interaction","authors":[{"name":"Karl V. Fast","is_ca":true},{"name":"D. Grant Campbell","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.008036790569434455,"gpt":0.2562357019349353,"spread":0.2481989113655008,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003537979,0.0003475598,0.0005529243,0.001936378,0.00244031,0.007037723,0.000710559,0.001677812,0.003783469],"category_scores_gemma":[0.01768418,0.0003308002,0.0004320277,0.0011935,0.002433124,0.002418662,0.002394412,0.001586599,0.0006150913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008261395,"about_ca_system_score_gemma":0.001016157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00517906,"about_ca_topic_score_gemma":0.004708583,"domain_scores_codex":[0.9958943,0.002125503,0.0002443414,0.0001989854,0.0009471615,0.0005897578],"domain_scores_gemma":[0.9843741,0.006550194,0.002969088,0.0003971251,0.001981254,0.003728115],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0002663813,0.0006887049,0.2549396,0.0002584488,0.00006972579,0.001252923,0.7112259,0.0001363107,0.003476053,0.0009298394,0.002254053,0.02450209],"study_design_scores_gemma":[0.00001790475,0.0004706495,0.07582316,0.00009226362,0.00003137375,0.0006213649,0.9158965,0.0003467693,0.0004359154,0.0002210688,0.005988646,0.00005448394],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9978326,0.0001165146,0.00008923314,0.0002688127,0.000008716284,0.000007550643,0.000009688841,0.00001002789,0.001656883],"genre_scores_gemma":[0.9990707,0.0001331316,0.00006692005,0.0001602413,0.000006489316,0.000006093021,0.00001243488,0.000006366787,0.0005377106],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9929623,"threshold_uncertainty_score":0.01871085,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1743300701","doi":"10.1002/asi.23201","title":"Data mining from web search queries: A comparison of google trends and baidu index","year":2014,"lang":"en","type":"article","venue":"Journal of the Association for Information Science and Technology","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":124,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Social Sciences and Humanities Research Council of Canada; Huawei Technologies; Baidu","keywords":"Computer science; Information retrieval; Volume (thermodynamics); Search engine; Web search query; Index (typography); Disadvantage; Database; World Wide Web","authors":[{"name":"Liwen Vaughan","is_ca":true},{"name":"Yue Chen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03577363737151772,"gpt":0.3252905443616383,"spread":0.2895169069901206,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00577424,0.0006621355,0.001246259,0.02277209,0.0005006008,0.002675084,0.0009785243,0.0006064377,0.0006779039],"category_scores_gemma":[0.02508222,0.000243401,0.001138647,0.03285911,0.00042131,0.003325412,0.000938805,0.0006099264,0.0005576419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001626081,"about_ca_system_score_gemma":0.001558349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0345457,"about_ca_topic_score_gemma":0.03703145,"domain_scores_codex":[0.9945135,0.001314368,0.0009080571,0.0005658863,0.002420607,0.0002776231],"domain_scores_gemma":[0.9799383,0.01096491,0.002654883,0.001263452,0.004441221,0.0007371866],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001234343,0.0003462519,0.8031528,0.002041247,0.0009052662,0.0004338222,0.001627827,0.003205237,0.001834593,0.00269479,0.008593528,0.1739303],"study_design_scores_gemma":[0.00006356875,0.0005244277,0.9352677,0.0002992936,0.0003451193,0.0009336114,0.003320066,0.04006511,0.001900545,0.001282625,0.01592014,0.00007775915],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9537549,0.01016136,0.004302207,0.001332637,0.0001316606,0.0002783716,0.01877812,0.0008205582,0.01044016],"genre_scores_gemma":[0.9547973,0.003359163,0.009505707,0.0001692597,0.0001065785,0.0001517653,0.03104849,0.0001056608,0.000755957],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0345457,"threshold_uncertainty_score":0.06868923,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2145781566","doi":"10.1002/meet.14504301167","title":"What Can Searching Behavior Tell Us About the Difficulty of Information Tasks? A Study of Web Navigation","year":2006,"lang":"en","type":"article","venue":"Proceedings of the American Society for Information Science and Technology","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":123,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Ontario Centres of Excellence","keywords":"Task (project management); Affect (linguistics); Context (archaeology); Computer science; Information seeking; Information seeking behavior; Path (computing); Path analysis (statistics); Psychology; Cognitive psychology; Information retrieval; Machine learning; Communication; Engineering","authors":[{"name":"Jacek Gwizdka","is_ca":false},{"name":"Ian Spence","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01126035862586267,"gpt":0.2723364713887259,"spread":0.2610761127628632,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003515529,0.0002558039,0.0003583919,0.001120184,0.0003429505,0.00186149,0.0002552372,0.0007260844,0.001118462],"category_scores_gemma":[0.03575604,0.000413163,0.0003894989,0.0009313656,0.001053128,0.001816901,0.00047622,0.0008910113,0.0001858129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002766227,"about_ca_system_score_gemma":0.0002302418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001220272,"about_ca_topic_score_gemma":0.00228817,"domain_scores_codex":[0.9986902,0.0007819525,0.000119497,0.0001235412,0.0002114687,0.00007337198],"domain_scores_gemma":[0.9242547,0.05980617,0.01091192,0.001956924,0.001274819,0.001795576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00026774,0.0005346231,0.9877998,0.0000479412,0.0001290793,0.00005551145,0.005385496,0.0001899264,0.001273954,0.0001820196,0.00006753813,0.004066258],"study_design_scores_gemma":[0.00001322763,0.0004722775,0.9961331,0.00001128716,0.00002265785,0.0001033349,0.001549124,0.001108485,0.0001694815,0.0002555853,0.0001460791,0.00001546213],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9994445,0.00005002912,0.0001197087,0.00003430626,9.437791e-7,0.000004638578,0.00002694212,0.000001709322,0.0003171844],"genre_scores_gemma":[0.9996312,0.00004708782,0.0001691571,0.00001879046,0.00000336122,0.000009782487,0.00004917272,0.000002656853,0.0000688878],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003515529,"threshold_uncertainty_score":0.01859212,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4248112467","doi":"10.1002/asi.20590","title":"A field study characterizing Web‐based information‐seeking tasks","year":2007,"lang":"en","type":"article","venue":"Journal of the American Society for Information Science and Technology","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":123,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; World Wide Web; Task (project management); Web navigation; Information seeking; Session (web analytics); Web page; Information retrieval; Field (mathematics); Information seeking behavior","authors":[{"name":"Melanie Kellar","is_ca":true},{"name":"Carolyn Watters","is_ca":true},{"name":"Michael Shepherd","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01531358925920824,"gpt":0.2983754545638338,"spread":0.2830618653046256,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003718337,0.0004233907,0.0004348162,0.001392138,0.001785076,0.0008065039,0.0004593653,0.0008091434,0.001878558],"category_scores_gemma":[0.00834561,0.0004569754,0.0002696642,0.00066111,0.0008986536,0.0008244904,0.000560962,0.0008995343,0.0004407031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005547601,"about_ca_system_score_gemma":0.0007196876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00302557,"about_ca_topic_score_gemma":0.004851159,"domain_scores_codex":[0.9985428,0.0007658848,0.00009841816,0.0002660653,0.0001720571,0.0001548276],"domain_scores_gemma":[0.9801436,0.01276685,0.001478623,0.001410355,0.00283699,0.001363495],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003986979,0.02541184,0.6624413,0.0006852624,0.0001047264,0.001466947,0.1709394,0.0005031881,0.05468632,0.0009240079,0.002867742,0.07598238],"study_design_scores_gemma":[0.0005115573,0.02283602,0.8788272,0.0001444986,0.00007162237,0.001295672,0.07454719,0.002061534,0.01181204,0.0008629916,0.00687863,0.0001510908],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9990011,0.00002231103,0.0002955465,0.00001975855,0.000003489686,0.0001338324,0.00006710192,0.000005510505,0.0004515211],"genre_scores_gemma":[0.9974528,0.00005500939,0.001211995,0.00007340445,0.00001272923,0.000268318,0.0001506394,0.000004468618,0.0007706695],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003718337,"threshold_uncertainty_score":0.01966465,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1498594556","doi":"10.1007/978-3-642-04417-5_17","title":"An Effectiveness Measure for Ambiguous and Underspecified Queries","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":120,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Novelty; Simplicity; Measure (data warehouse); Simple (philosophy); Information retrieval; Data mining","authors":[{"name":"Charles L. A. Clarke","is_ca":true},{"name":"Maheedhar Kolla","is_ca":true},{"name":"Olga Vechtomova","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02946664520315483,"gpt":0.2797366614465977,"spread":0.2502700162434429,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01194643,0.001348968,0.002297814,0.01530508,0.0008617612,0.003258857,0.001661568,0.002284055,0.003474425],"category_scores_gemma":[0.04885605,0.0003416497,0.001660455,0.004271138,0.002177828,0.006522688,0.001305618,0.001150348,0.0006995822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001945454,"about_ca_system_score_gemma":0.0009899394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009479097,"about_ca_topic_score_gemma":0.0008889202,"domain_scores_codex":[0.9849627,0.004975811,0.001396401,0.001366955,0.006520392,0.0007777052],"domain_scores_gemma":[0.9292246,0.0583075,0.003171842,0.003214359,0.004936317,0.001145373],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00504113,0.001593314,0.07121214,0.002293557,0.001655071,0.0004468563,0.0009342498,0.0556711,0.03050585,0.04481538,0.01402321,0.7718081],"study_design_scores_gemma":[0.0003889641,0.008168902,0.1345209,0.0004972227,0.003296922,0.005249318,0.001844358,0.7038426,0.05348054,0.07295512,0.01523028,0.0005247994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4029488,0.01988897,0.5261522,0.001536545,0.0006266498,0.001039998,0.004143836,0.002606682,0.04105633],"genre_scores_gemma":[0.9152746,0.001011346,0.07867659,0.0001921474,0.0005280057,0.0003454356,0.001907023,0.0001930645,0.001871809],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01530508,"threshold_uncertainty_score":0.06317949,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2083141524","doi":"10.1016/s0740-8188(01)00102-5","title":"The academic and the everyday: Investigating the overlap in mature undergraduates' information–seeking behaviors","year":2002,"lang":"en","type":"article","venue":"Library & Information Science Research","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Everyday life; Information seeking; Psychology; Information behavior; Qualitative research; Information seeking behavior; Social psychology; Sociology; Social science; Library science; Computer science; Epistemology","authors":[{"name":"Lisa M. Given","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05281244775290806,"gpt":0.3248792240559549,"spread":0.2720667763030469,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001963018,0.0002050786,0.0004847664,0.001488149,0.001230793,0.003318923,0.0004028854,0.0009392702,0.001875774],"category_scores_gemma":[0.01304741,0.0005576172,0.0002455614,0.0009657182,0.001293444,0.001492178,0.001792751,0.001375006,0.0003853163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006829001,"about_ca_system_score_gemma":0.0009079198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005988247,"about_ca_topic_score_gemma":0.01435686,"domain_scores_codex":[0.9990346,0.0002912961,0.00009442437,0.0001054863,0.000313755,0.0001602854],"domain_scores_gemma":[0.9883967,0.003414133,0.002647108,0.0006059919,0.001197481,0.003738573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004596248,0.001564405,0.9550512,0.00002528501,0.00004757802,0.00009605059,0.02893145,0.00003098326,0.003182348,0.0002774498,0.0001860278,0.01014753],"study_design_scores_gemma":[0.00001114989,0.0003689044,0.9875528,0.000005471357,0.00001073639,0.00006367247,0.01120899,0.0001439536,0.0002137322,0.0001018829,0.0003103387,0.000008400883],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.999681,0.00003274438,0.00001517913,0.0000298376,0.000001327347,0.000002859187,0.000008921996,8.298724e-7,0.0002273628],"genre_scores_gemma":[0.9995945,0.00003837971,0.00005600824,0.00004402098,0.000003980826,0.00000613545,0.00003540659,0.000001334128,0.0002203],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9966811,"threshold_uncertainty_score":0.01190674,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159545104","doi":"10.1145/1553374.1553513","title":"BoltzRank","year":2009,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Pairwise comparison; Ranking (information retrieval); Computer science; Set (abstract data type); Rank (graph theory); Relevance (law); ENCODE; Function (biology); Information retrieval; Learning to rank; Measure (data warehouse); Data mining; Artificial intelligence; Machine learning; Mathematics","authors":[{"name":"Maksims Volkovs","is_ca":true},{"name":"Richard S. Zemel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01179954817276005,"gpt":0.254509222366211,"spread":0.242709674193451,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002622215,0.002125426,0.002513894,0.006775951,0.002147106,0.005667411,0.003217677,0.002450071,0.07612832],"category_scores_gemma":[0.01379138,0.0008572698,0.001240368,0.007178618,0.001063875,0.006421829,0.002913062,0.002006327,0.07392827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001508411,"about_ca_system_score_gemma":0.002988152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004040662,"about_ca_topic_score_gemma":0.008270034,"domain_scores_codex":[0.995156,0.001105966,0.0003909344,0.0006486676,0.00220587,0.0004926382],"domain_scores_gemma":[0.9959091,0.001210808,0.0003183883,0.001430248,0.0009431607,0.0001883059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002940732,0.0001996815,0.001481042,0.0008173725,0.0001699498,0.0001225397,0.0001243063,0.02469266,0.0016709,0.1304036,0.2643049,0.5757188],"study_design_scores_gemma":[0.0003249419,0.0002291531,0.0006854646,0.0002591496,0.0001177279,0.0005965888,0.0001587265,0.1548984,0.00744129,0.3607417,0.4744104,0.0001364481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008501618,0.006935749,0.775121,0.002248282,0.001603121,0.001357588,0.01403976,0.04767355,0.1425193],"genre_scores_gemma":[0.1428652,0.005425909,0.6347102,0.001451419,0.001265889,0.00164918,0.03866259,0.006787437,0.1671822],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.07612832,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2041328912","doi":"10.1108/00220410510585214","title":"Scholarly journal usage: the results of deep log analysis","year":2005,"lang":"en","type":"article","venue":"Journal of Documentation","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Visitor pattern; Originality; Computer science; Information seeking; Value (mathematics); Digital library; World Wide Web; Quarter (Canadian coin); Information behavior; Data science; Information retrieval; Library science; Sociology; Social science","authors":[{"name":"David Nicholas","is_ca":false},{"name":"Paul Huntington","is_ca":false},{"name":"Anthony Watkinson","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01784896142118223,"gpt":0.3123404645847844,"spread":0.2944915031636021,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0056098,0.0003882209,0.0006559398,0.005697133,0.0006250473,0.003228282,0.0005753751,0.0005396293,0.002277566],"category_scores_gemma":[0.06268199,0.0002176623,0.0005248364,0.007550896,0.0008260235,0.003513999,0.001953902,0.0009871611,0.001413342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005569184,"about_ca_system_score_gemma":0.000658883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002999605,"about_ca_topic_score_gemma":0.003334177,"domain_scores_codex":[0.9901839,0.004613747,0.0008049065,0.000652503,0.003324861,0.0004201514],"domain_scores_gemma":[0.8363069,0.1246853,0.01113237,0.01023374,0.01596919,0.00167241],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001936415,0.0008685577,0.6999175,0.0008347188,0.000239243,0.0002099451,0.01445859,0.002622921,0.005455601,0.002026354,0.00741586,0.2640142],"study_design_scores_gemma":[0.00003837598,0.001064717,0.9118108,0.0001610247,0.0001642726,0.0007288536,0.01806119,0.04388081,0.00707633,0.005282863,0.01154033,0.0001905087],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9827473,0.000434133,0.00659962,0.0005274108,0.00002583007,0.0001115065,0.002989717,0.0005016556,0.006063035],"genre_scores_gemma":[0.9916415,0.0001675666,0.004109312,0.00008044606,0.000033714,0.00007701537,0.00185641,0.0001375524,0.001896461],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9967717,"threshold_uncertainty_score":0.02966779,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1982584634","doi":"10.1145/1367497.1367533","title":"Deciphering mobile search patterns","year":2008,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":104,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Web search query; Information retrieval; Sample (material); World Wide Web; Search engine","authors":[{"name":"Jeonghee Yi","is_ca":false},{"name":"Farzin Maghoul","is_ca":false},{"name":"Jan Pedersen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03997268411406353,"gpt":0.2752666123975869,"spread":0.2352939282835234,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001143295,0.0003234097,0.0005802435,0.006289631,0.0004329492,0.001810924,0.0004552215,0.0004819623,0.001419379],"category_scores_gemma":[0.01262932,0.0002212069,0.0003432786,0.005998802,0.0003428312,0.002454855,0.0007177349,0.0004510857,0.001097993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003767591,"about_ca_system_score_gemma":0.0003405011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004632668,"about_ca_topic_score_gemma":0.007611479,"domain_scores_codex":[0.9982168,0.0003123483,0.0002640163,0.0003601605,0.0006302759,0.0002162899],"domain_scores_gemma":[0.9871162,0.006862868,0.002707354,0.0009064045,0.002096093,0.0003111742],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005759223,0.0001092877,0.8541673,0.0004812778,0.0001753687,0.0006866945,0.003690111,0.001692764,0.01444826,0.001188077,0.002726035,0.1200589],"study_design_scores_gemma":[0.00001772931,0.0002037591,0.956449,0.00007335313,0.00009990744,0.002572159,0.00584248,0.01907442,0.005985613,0.001583335,0.00803763,0.00006050246],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9893624,0.000897661,0.004164844,0.0002989163,0.00001673293,0.00005709119,0.002250197,0.0001863843,0.002765695],"genre_scores_gemma":[0.9927679,0.0003594841,0.003146777,0.00004969596,0.00003381532,0.00003640067,0.002679292,0.00006010746,0.0008663646],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006289631,"threshold_uncertainty_score":0.009211421,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4236647746","doi":"10.1007/978-1-4614-6170-8_100122","title":"Information Retrieval","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Information retrieval; Computer science","authors":[{"name":"Reda Alhajj","is_ca":true},{"name":"Jon Rokne","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01740005744966362,"gpt":0.2307709918713209,"spread":0.2133709344216572,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007175284,0.001419317,0.001248769,0.00506397,0.001030904,0.004849916,0.001514116,0.001375915,0.1128538],"category_scores_gemma":[0.00197643,0.0005175953,0.0005401246,0.006276781,0.001259637,0.006262343,0.001992546,0.001565198,0.163403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001531214,"about_ca_system_score_gemma":0.001471648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001260897,"about_ca_topic_score_gemma":0.00228069,"domain_scores_codex":[0.99907,0.0001107841,0.00005332103,0.000145563,0.0005649475,0.00005534721],"domain_scores_gemma":[0.9994202,0.0001546805,0.00002671276,0.0001757538,0.0001812699,0.00004148551],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001273183,0.00004500654,0.00008240869,0.000603092,0.00001620357,0.00003270008,0.0001514981,0.0002639787,0.001578521,0.05717321,0.307114,0.6329266],"study_design_scores_gemma":[0.000003026079,0.00001632238,0.0002148041,0.0002587101,0.00001042388,0.0001971629,0.00005995853,0.0004157111,0.0009525769,0.02682048,0.971039,0.00001181903],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"review","genre_scores_codex":[0.0009604501,0.04412363,0.0431761,0.002053556,0.001369223,0.0001594022,0.000815548,0.001877784,0.9054644],"genre_scores_gemma":[0.007174911,0.03245075,0.01766867,0.00118114,0.0009874289,0.0001196543,0.001792792,0.0004673142,0.9381573],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.1128538,"threshold_uncertainty_score":0.3775336,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Charles L. A. Clarke","is_ca":true},{"name":"Nick Craswell","is_ca":false},{"name":"Ellen M. Voorhees","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07088538982854531,"gpt":0.3088896404462865,"spread":0.2380042506177412,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01084585,0.002111278,0.0017984,0.01376568,0.003691074,0.005978091,0.003287005,0.002587422,0.03598236],"category_scores_gemma":[0.01114587,0.001046202,0.001402201,0.01323636,0.0006920851,0.00550031,0.002230917,0.002426051,0.04407853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007895012,"about_ca_system_score_gemma":0.01194692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.104434,"about_ca_topic_score_gemma":0.1276292,"domain_scores_codex":[0.9897261,0.00151706,0.0009223312,0.001416161,0.005186392,0.001231995],"domain_scores_gemma":[0.9841091,0.001146245,0.0007717604,0.001581259,0.01056612,0.001825458],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002312826,0.0002850092,0.001323836,0.0007364437,0.0000347419,0.00004763982,0.00006785495,0.001031731,0.002935444,0.001464586,0.8869195,0.1049219],"study_design_scores_gemma":[0.000106734,0.0003522491,0.01120307,0.0004064845,0.00006408167,0.0001556057,0.000131474,0.002991279,0.003582693,0.001476181,0.979398,0.0001321963],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.02295731,0.03803134,0.03871042,0.01661871,0.009702956,0.01243874,0.4955842,0.03443097,0.3315253],"genre_scores_gemma":[0.03645565,0.01438154,0.05919104,0.004754162,0.00295004,0.006579652,0.7741999,0.003646337,0.09784171],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.104434,"threshold_uncertainty_score":0.2076523,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2338216121","doi":"10.1145/2911451.2911507","title":"When does Relevance Mean Usefulness and User Satisfaction in Web Search?","year":2016,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Relevance (law); Computer science; Information retrieval; Context (archaeology); Set (abstract data type); User satisfaction; Computer user satisfaction; Quality (philosophy); Search engine; World Wide Web; Human–computer interaction; User experience design; User interface design","authors":[{"name":"Jiaxin Mao","is_ca":false},{"name":"Yiqun Liu","is_ca":false},{"name":"Ke Zhou","is_ca":false},{"name":"Jian‐Yun Nie","is_ca":true},{"name":"Jingtao Song","is_ca":false},{"name":"Min Zhang","is_ca":false},{"name":"Shaoping Ma","is_ca":false},{"name":"Jiashen Sun","is_ca":false},{"name":"Hengliang Luo","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02073580549311979,"gpt":0.2519200293944052,"spread":0.2311842239012854,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006875014,0.0003471859,0.000631976,0.002031661,0.0005024162,0.00253898,0.00031752,0.001024144,0.0015915],"category_scores_gemma":[0.06473295,0.0002464954,0.0005185978,0.002237715,0.001008435,0.002699685,0.0009957099,0.0008259498,0.0003858818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005929306,"about_ca_system_score_gemma":0.0003380479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001091779,"about_ca_topic_score_gemma":0.001390864,"domain_scores_codex":[0.9913164,0.005508332,0.0004700501,0.0005028124,0.001824398,0.0003778991],"domain_scores_gemma":[0.9241199,0.05664584,0.009374728,0.001879538,0.005429411,0.002550567],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001711586,0.0005448936,0.8779155,0.0005242344,0.0002777089,0.0002032954,0.006255889,0.001303745,0.005694023,0.001892928,0.001325878,0.1023504],"study_design_scores_gemma":[0.00003365829,0.001071438,0.9822798,0.00007596914,0.0001188713,0.0002409905,0.002514193,0.008711372,0.001637351,0.002436829,0.0008228606,0.00005667189],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9885678,0.0008715834,0.004251416,0.0004386858,0.00002428585,0.00004805133,0.0001256706,0.00006055124,0.005611965],"genre_scores_gemma":[0.9989792,0.00006517147,0.0006470801,0.00004225145,0.00001866541,0.00001977121,0.00004717119,0.00001149865,0.0001690653],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006875014,"threshold_uncertainty_score":0.03635895,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2097443371","doi":"10.1145/1571941.1572003","title":"Smoothing clickthrough data for web search ranking","year":2009,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Ranking (information retrieval); Information retrieval; Smoothing; Estimator; Cluster analysis; Data mining; Machine learning; Artificial intelligence; Mathematics; Statistics","authors":[{"name":"Jianfeng Gao","is_ca":false},{"name":"Wei Yuan","is_ca":true},{"name":"Xiao Li","is_ca":false},{"name":"Kefeng Deng","is_ca":false},{"name":"Jian‐Yun Nie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1244217204774397,"gpt":0.3708430013819626,"spread":0.2464212809045229,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003800493,0.0006980431,0.001040655,0.002303827,0.000316293,0.0007191806,0.0007142036,0.0009950456,0.0005105019],"category_scores_gemma":[0.01777351,0.0004789389,0.0006923652,0.001902574,0.0004417201,0.001935527,0.0004463213,0.001246041,0.0004879216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007729609,"about_ca_system_score_gemma":0.0006158733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006876971,"about_ca_topic_score_gemma":0.01036391,"domain_scores_codex":[0.9988092,0.0005652748,0.00008729099,0.0002093069,0.0002540881,0.00007487086],"domain_scores_gemma":[0.9885347,0.007546515,0.001186657,0.001730024,0.000809022,0.0001930078],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008492909,0.0004895899,0.03965262,0.0003730744,0.0003277127,0.0001668409,0.0002947812,0.5047116,0.01343519,0.007683794,0.004764408,0.4272511],"study_design_scores_gemma":[0.00001872487,0.0001140918,0.008015414,0.00001185364,0.00003188603,0.00006994376,0.00001401659,0.9840803,0.002786786,0.00376402,0.001056721,0.00003635194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3199829,0.002279395,0.6719897,0.0003527758,0.00007573691,0.0001184563,0.0008907409,0.003404033,0.0009063004],"genre_scores_gemma":[0.9305933,0.0004308037,0.0662705,0.00005467279,0.00008345706,0.00005749989,0.001445321,0.0001012711,0.0009632622],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006876971,"threshold_uncertainty_score":0.02009916,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2307814545","doi":"10.1007/978-3-319-30671-1_30","title":"Toward Reproducible Baselines: The Open-Source IR Reproducibility Challenge","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Open source; Information retrieval; World Wide Web; Source code; Data science; Software; Programming language","authors":[{"name":"Jimmy Lin","is_ca":true},{"name":"Matt Crane","is_ca":true},{"name":"Andrew Trotman","is_ca":false},{"name":"Jamie Callan","is_ca":false},{"name":"Ishan Chattopadhyaya","is_ca":false},{"name":"John F. Foley","is_ca":false},{"name":"Grant Ingersoll","is_ca":false},{"name":"Craig Macdonald","is_ca":false},{"name":"Sebastiano Vigna","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06459347854591166,"gpt":0.2974063553987016,"spread":0.23281287685279,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1063875,0.003584481,0.004279277,0.005385949,0.003785686,0.01397727,0.01257727,0.007196176,0.007318506],"category_scores_gemma":[0.3187569,0.002293064,0.003192501,0.006255355,0.004920019,0.01725592,0.01613441,0.01039723,0.01302155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002132603,"about_ca_system_score_gemma":0.005993261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002856187,"about_ca_topic_score_gemma":0.003897526,"domain_scores_codex":[0.8577686,0.07060713,0.01021457,0.01765573,0.04077088,0.002983083],"domain_scores_gemma":[0.6427979,0.1269802,0.0109349,0.1719242,0.04350978,0.003853039],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002173782,0.001195657,0.0075527,0.005294164,0.001561289,0.0004989238,0.00173495,0.01397282,0.03391204,0.03841288,0.2119023,0.6817885],"study_design_scores_gemma":[0.00142699,0.001618303,0.01309377,0.001742296,0.001116278,0.002924457,0.001861702,0.2908488,0.09789767,0.36045,0.2263255,0.0006942771],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04566764,0.02140775,0.7979408,0.01204104,0.005706161,0.001135703,0.01307855,0.08376784,0.01925453],"genre_scores_gemma":[0.2331636,0.00399811,0.6690294,0.005533408,0.003308087,0.001466864,0.04603302,0.02549885,0.01196867],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8936125,"threshold_uncertainty_score":0.5626375,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2048476252","doi":"10.1016/j.ins.2011.03.007","title":"Modeling term proximity for probabilistic information retrieval models","year":2011,"lang":"en","type":"article","venue":"Information Sciences","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Term (time); Divergence-from-randomness model; Computer science; Probabilistic logic; Term Discrimination; Probabilistic relevance model; Information retrieval; Data mining; Artificial intelligence; Probabilistic analysis of algorithms; Search engine; Concept search","authors":[{"name":"Ben He","is_ca":true},{"name":"Jimmy Xiangji Huang","is_ca":true},{"name":"Xiaofeng Zhou","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1286481222828739,"gpt":0.2964142241644975,"spread":0.1677661018816236,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005898091,0.001027026,0.002293184,0.003303752,0.001147287,0.00320889,0.002998248,0.00384017,0.004164561],"category_scores_gemma":[0.03849712,0.001445169,0.002332366,0.004070184,0.001351964,0.007560414,0.00218837,0.002864847,0.001634522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002292605,"about_ca_system_score_gemma":0.001358061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01044759,"about_ca_topic_score_gemma":0.009870564,"domain_scores_codex":[0.9963197,0.001810089,0.0002326552,0.0008022539,0.0005636772,0.0002716021],"domain_scores_gemma":[0.9819687,0.01517652,0.001105151,0.0008263593,0.0006730899,0.0002501177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004184147,0.0002523196,0.004332437,0.0003724401,0.0002645561,0.0002250525,0.0006084892,0.7971791,0.001694063,0.1360554,0.0026961,0.05590159],"study_design_scores_gemma":[0.00002311183,0.00003325273,0.0003261711,0.00001324776,0.00004668949,0.00006147779,0.00002030906,0.9468389,0.0001738649,0.05201257,0.0004318588,0.00001854816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08041908,0.002102051,0.9119908,0.001415859,0.0001097001,0.0001543004,0.0005250617,0.0005987241,0.002684362],"genre_scores_gemma":[0.8712137,0.002251678,0.1140756,0.0002974476,0.000397913,0.0005608755,0.001025803,0.0002084648,0.00996851],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01044759,"threshold_uncertainty_score":0.03119242,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135290016","doi":"10.1145/1183614.1183644","title":"A document-centric approach to static index pruning in text retrieval systems","year":2006,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Pruning; Index (typography); Information retrieval; Divergence (linguistics); Document retrieval; Term (time); Language model; Artificial intelligence; Inverted index; Natural language processing; Search engine indexing; World Wide Web","authors":[{"name":"Stefan Büttcher","is_ca":true},{"name":"Charles L. A. Clarke","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01364077173481446,"gpt":0.2435377339678875,"spread":0.229896962233073,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002815365,0.0009695852,0.001774536,0.003885181,0.001842325,0.002865553,0.00271664,0.00141042,0.001658016],"category_scores_gemma":[0.01278267,0.0008320152,0.0008690779,0.004778752,0.001357984,0.004756206,0.001949407,0.001743752,0.001355169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001075645,"about_ca_system_score_gemma":0.001731645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002183187,"about_ca_topic_score_gemma":0.003832059,"domain_scores_codex":[0.9966876,0.0008433207,0.0003547373,0.0004239787,0.00151047,0.0001798309],"domain_scores_gemma":[0.9912121,0.003351066,0.0006340862,0.002636355,0.001956139,0.0002102512],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003842384,0.0003273659,0.002754325,0.0005539028,0.0001399678,0.0004384342,0.0008155603,0.032418,0.07409833,0.02683641,0.01301129,0.8482222],"study_design_scores_gemma":[0.0001736978,0.0006919863,0.003735792,0.0001725408,0.000405806,0.002152455,0.0003003472,0.7402562,0.1253235,0.07211211,0.05444859,0.000227053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02154746,0.002089771,0.9682657,0.0004204111,0.00008796555,0.0002766831,0.0001945363,0.004208006,0.002909519],"genre_scores_gemma":[0.1562488,0.0009960176,0.8369401,0.0003063719,0.0002829506,0.0003504014,0.0007143657,0.0004750119,0.00368612],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003885181,"threshold_uncertainty_score":0.01488924,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2059516109","doi":"10.1108/jd-03-2014-0056","title":"Untangling search task complexity and difficulty in the context of interactive information retrieval studies","year":2014,"lang":"en","type":"article","venue":"Journal of Documentation","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Task (project management); Context (archaeology); Information retrieval","authors":[{"name":"Barbara M. Wildemuth","is_ca":false},{"name":"Luanne Freund","is_ca":true},{"name":"Elaine G. Toms","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04345031035981671,"gpt":0.349304838060599,"spread":0.3058545277007823,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07435977,0.0006001493,0.001185387,0.005348768,0.002077891,0.007341645,0.001805932,0.0009855349,0.003663115],"category_scores_gemma":[0.2687298,0.0009138031,0.0007042288,0.004883375,0.006669525,0.008466586,0.005525511,0.002304937,0.0003352945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002980667,"about_ca_system_score_gemma":0.002464949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001324213,"about_ca_topic_score_gemma":0.002491433,"domain_scores_codex":[0.9167393,0.06273767,0.006648849,0.003064875,0.009905307,0.0009040688],"domain_scores_gemma":[0.4074827,0.5353017,0.0285535,0.01891491,0.008302759,0.001444289],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002232261,0.003035838,0.2370489,0.01539723,0.001038929,0.0004718837,0.209354,0.003459073,0.01692799,0.09855006,0.001542993,0.4109409],"study_design_scores_gemma":[0.0009189192,0.005091862,0.6498102,0.008564318,0.001463344,0.001472671,0.09335601,0.01746321,0.02185474,0.1652361,0.03405774,0.0007109347],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8761698,0.008084268,0.08590657,0.001525133,0.00007619194,0.001894674,0.0001662272,0.0001176193,0.02605961],"genre_scores_gemma":[0.9577488,0.00111313,0.03794556,0.0003636631,0.00005585188,0.002038505,0.00008935529,0.00005626282,0.0005889219],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07435977,"threshold_uncertainty_score":0.3932568,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1665115054","doi":"10.48550/arxiv.1106.1925","title":"Ranking via Sinkhorn Propagation","year":2011,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Normalization (sociology); Ranking (information retrieval); Operator (biology); Rank (graph theory); Learning to rank; Range (aeronautics); Projection (relational algebra); Mathematical optimization; Permutation (music); Artificial intelligence; Algorithm; Mathematics; Combinatorics","authors":[{"name":"Ryan P. Adams","is_ca":true},{"name":"Richard S. Zemel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.100974059935494,"gpt":0.1895552633344075,"spread":0.08858120339891352,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002703062,0.001173401,0.001217337,0.001792608,0.0007800147,0.00168318,0.00153365,0.001541261,0.004554872],"category_scores_gemma":[0.01055158,0.0006064103,0.0007707506,0.001745611,0.001208122,0.00355086,0.001583262,0.001421321,0.001812857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00101337,"about_ca_system_score_gemma":0.001186081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002385073,"about_ca_topic_score_gemma":0.004679208,"domain_scores_codex":[0.9986349,0.0004226746,0.00007490078,0.000245682,0.0005007869,0.0001210558],"domain_scores_gemma":[0.9950868,0.002689159,0.000408674,0.00059373,0.00108924,0.0001324608],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000240716,0.000209644,0.002408221,0.0002518696,0.0001064484,0.0001590644,0.0002136718,0.4812985,0.00945775,0.08538656,0.0125273,0.4077403],"study_design_scores_gemma":[0.00001441344,0.00005551085,0.0002229093,0.00001525125,0.00001075727,0.00004025753,0.00001670412,0.9533708,0.003058711,0.04161457,0.001566617,0.00001336258],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01227298,0.0001808336,0.9837672,0.0002379628,0.00004324822,0.00007284094,0.0001411971,0.0009628742,0.002320888],"genre_scores_gemma":[0.3863737,0.0004939122,0.5963202,0.0005669674,0.0001523231,0.0003794141,0.0010029,0.0005161554,0.01419447],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004554872,"threshold_uncertainty_score":0.01523757,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2049653588","doi":"10.1145/2348283.2348356","title":"Proximity-based rocchio's model for pseudo relevance","year":2012,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":81,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Relevance feedback; Computer science; Query expansion; Relevance (law); Boosting (machine learning); Information retrieval; Data mining; Term (time); Artificial intelligence; Image retrieval","authors":[{"name":"Jun Miao","is_ca":true},{"name":"Jimmy Xiangji Huang","is_ca":true},{"name":"Ye Zheng","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04683063451606024,"gpt":0.2939340319662767,"spread":0.2471033974502165,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004239107,0.001679289,0.002156637,0.003973363,0.0009775744,0.002179573,0.003980158,0.00290368,0.004614305],"category_scores_gemma":[0.01697931,0.0007176272,0.002454723,0.004065849,0.002080462,0.006982666,0.001521048,0.002199554,0.002920885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002594859,"about_ca_system_score_gemma":0.001435725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006784879,"about_ca_topic_score_gemma":0.005131864,"domain_scores_codex":[0.9954199,0.001525654,0.0002597313,0.001127843,0.001297656,0.0003692098],"domain_scores_gemma":[0.9928255,0.004003107,0.00063293,0.001120716,0.001230743,0.0001869345],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007175244,0.0003361792,0.005984422,0.0008533748,0.000278459,0.0008785167,0.001341198,0.3639133,0.01053649,0.3524279,0.01720476,0.2455278],"study_design_scores_gemma":[0.00004596499,0.0001626795,0.001115331,0.00003563843,0.00008231019,0.0005575691,0.00004471744,0.9318948,0.001216725,0.05870912,0.006060124,0.00007495464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03500282,0.003801932,0.9447551,0.001502791,0.0002060887,0.0004188236,0.0006996773,0.001236047,0.01237671],"genre_scores_gemma":[0.8034685,0.002917161,0.1664657,0.0005332726,0.0006383345,0.001355747,0.0009150082,0.0002537676,0.02345247],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006784879,"threshold_uncertainty_score":0.02241886,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2060816264","doi":"10.1145/1571941.1571995","title":"A bayesian learning approach to promoting diversity in ranking for biomedical information retrieval","year":2009,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Ranking (information retrieval); Computer science; Bayesian probability; Artificial intelligence; Biomedicine; Learning to rank; Machine learning; Domain (mathematical analysis); Information retrieval; Bayesian inference; Mathematics; Bioinformatics","authors":[{"name":"Qinmin Hu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02502986172271912,"gpt":0.2657594338881005,"spread":0.2407295721653814,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007994296,0.00102818,0.001885528,0.00326938,0.001463764,0.001637599,0.00272525,0.002085187,0.00266951],"category_scores_gemma":[0.02848031,0.0008129757,0.001284968,0.00262641,0.001442806,0.004363323,0.001423861,0.002763892,0.001333967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002044084,"about_ca_system_score_gemma":0.002300212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005795665,"about_ca_topic_score_gemma":0.00855901,"domain_scores_codex":[0.9927753,0.003764963,0.0003237908,0.0008311548,0.002038338,0.0002664675],"domain_scores_gemma":[0.9847347,0.01085804,0.0007990042,0.0010123,0.002300104,0.0002959419],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004457899,0.0007054218,0.004260858,0.0004451953,0.0003154245,0.0001662274,0.0005262797,0.3246345,0.01002815,0.06143587,0.008772257,0.588264],"study_design_scores_gemma":[0.00009901643,0.0002330585,0.000877955,0.0000389253,0.000077864,0.0001417921,0.00004104874,0.9351597,0.002760403,0.05697856,0.00350022,0.00009141389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005008432,0.0004788614,0.9924157,0.0004480417,0.00003232149,0.00009103634,0.00005723822,0.0002998914,0.001168465],"genre_scores_gemma":[0.3329645,0.0009717467,0.6591423,0.0007913188,0.0005320723,0.000586424,0.0004341767,0.0001472747,0.004430134],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007994296,"threshold_uncertainty_score":0.04227835,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2099048704","doi":"10.1145/1924475.1924484","title":"Report on the SIGIR 2010 workshop on the simulation of interaction","year":2011,"lang":"en","type":"article","venue":"ACM SIGIR Forum","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Field (mathematics); Embodied cognition; Human–computer interaction; Interface (matter); User interface; Data science; Information retrieval; Artificial intelligence","authors":[{"name":"Leif Azzopardi","is_ca":false},{"name":"Kalervo Järvelin","is_ca":false},{"name":"Jaap Kamps","is_ca":false},{"name":"Mark D. Smucker","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09104068326569431,"gpt":0.3145987307240725,"spread":0.2235580474583782,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01090277,0.001700346,0.001762341,0.0009115913,0.001900537,0.006213284,0.002846171,0.003189516,0.05109366],"category_scores_gemma":[0.02265959,0.0009635566,0.002228273,0.0009296015,0.001368069,0.008103962,0.00512161,0.00461762,0.01119997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003797636,"about_ca_system_score_gemma":0.004330947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02062173,"about_ca_topic_score_gemma":0.02210644,"domain_scores_codex":[0.9953094,0.002508522,0.0001972751,0.0005832642,0.001080644,0.0003208497],"domain_scores_gemma":[0.9830906,0.00918206,0.0002413413,0.00202783,0.003684303,0.001773879],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002162531,0.001002129,0.004234959,0.000976578,0.0002771987,0.0003853324,0.002164046,0.05446146,0.004451424,0.06882991,0.6610861,0.1999683],"study_design_scores_gemma":[0.0004455246,0.000412017,0.002410863,0.0006416983,0.0001705217,0.0002379072,0.001310699,0.08144066,0.005271042,0.05158067,0.8558619,0.00021644],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"commentary","genre_scores_codex":[0.07191424,0.04403067,0.430105,0.1227213,0.02918643,0.002396948,0.01320568,0.006597527,0.2798421],"genre_scores_gemma":[0.3368284,0.03523459,0.2396774,0.01139105,0.004949537,0.003174975,0.04547672,0.003547065,0.3197203],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.05109366,"threshold_uncertainty_score":0.1709253,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2039190550","doi":"10.1007/s10506-010-9093-9","title":"Evaluation of information retrieval for E-discovery","year":2010,"lang":"en","type":"article","venue":"Artificial Intelligence and Law","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Open Text (Canada)","funders":"","keywords":"Computer science; Information retrieval; Data science; Context (archaeology); Precision and recall; Question answering","authors":[{"name":"Douglas W. Oard","is_ca":false},{"name":"Jason R. Baron","is_ca":false},{"name":"Bruce Hedin","is_ca":false},{"name":"David Lewis","is_ca":false},{"name":"Stephen Tomlinson","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07755438895016285,"gpt":0.3380923055011545,"spread":0.2605379165509917,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03003398,0.001063006,0.001550501,0.005431361,0.001097296,0.004077092,0.001464743,0.002377948,0.005622379],"category_scores_gemma":[0.1194391,0.0002069449,0.0008657842,0.002725965,0.001126582,0.004574735,0.001239507,0.0008129923,0.001181469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003577279,"about_ca_system_score_gemma":0.002810545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006032267,"about_ca_topic_score_gemma":0.004284828,"domain_scores_codex":[0.9756103,0.0156387,0.001432548,0.0008812856,0.005825684,0.0006115506],"domain_scores_gemma":[0.8070284,0.1676114,0.004110135,0.006838935,0.01222089,0.002190211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.04271667,0.007204709,0.09572834,0.004125441,0.001828814,0.0003707525,0.0008644294,0.1140649,0.01011908,0.02838163,0.01302477,0.6815703],"study_design_scores_gemma":[0.001845247,0.01261032,0.04366994,0.0002867541,0.001422049,0.0004533156,0.0007242751,0.8944385,0.02114914,0.01533352,0.007879605,0.000187183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8978879,0.01137949,0.04439991,0.002831808,0.0002730156,0.001106579,0.001496337,0.001894689,0.03873021],"genre_scores_gemma":[0.9830014,0.0005231996,0.01364977,0.0001003126,0.00006401454,0.0001058316,0.0006939746,0.00006069393,0.001800837],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03003398,"threshold_uncertainty_score":0.1588368,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2076498890","doi":"10.1016/s0740-8188(01)00090-1","title":"Introduction to the special issue: Everyday life information-seeking research","year":2001,"lang":"en","type":"article","venue":"Library & Information Science Research","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Normative; Coping (psychology); Psychology; Interview; Everyday life; Grounded theory; Sociocultural evolution; Social psychology; Qualitative research; Developmental psychology; Sociology; Social science; Clinical psychology; Epistemology; Anthropology","authors":[{"name":"Amanda Spink","is_ca":false},{"name":"Charles Cole","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06281860241191674,"gpt":0.3663045366475856,"spread":0.3034859342356689,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003680643,0.003760946,0.006149159,0.0109599,0.003316988,0.01145464,0.003298473,0.008734143,0.1099535],"category_scores_gemma":[0.009567692,0.001102497,0.002869882,0.007001458,0.001445847,0.007131284,0.004875295,0.009451465,0.06777781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001705062,"about_ca_system_score_gemma":0.002641058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001304325,"about_ca_topic_score_gemma":0.003947564,"domain_scores_codex":[0.9980444,0.0003436024,0.0003404586,0.0003399144,0.000687276,0.0002442194],"domain_scores_gemma":[0.9801491,0.006860573,0.0009745708,0.0008733331,0.004898151,0.006244231],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002461495,0.00006298497,0.0001552667,0.0003360981,0.000009954411,0.00004567411,0.00002410054,0.000023649,0.0001195132,0.000347801,0.981719,0.01713125],"study_design_scores_gemma":[0.00003027441,0.0001277402,0.002527344,0.000712756,0.00003705193,0.0003121245,0.0001340489,0.0001269809,0.00006728122,0.001785155,0.9941075,0.00003171343],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.0003526235,0.04431254,0.001086566,0.0347143,0.9064901,0.0001367375,0.0007556566,0.0002485065,0.01190289],"genre_scores_gemma":[0.0008793212,0.02586767,0.0006772496,0.02031589,0.9147695,0.0002067465,0.001249878,0.0002792104,0.03575455],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.9885454,"threshold_uncertainty_score":0.3678311,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2034707531","doi":"10.1145/2009916.2009941","title":"CRTER","year":2011,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Term (time); Computer science; Term Discrimination; Information retrieval; Weighting; Intersection (aeronautics); Boosting (machine learning); Query expansion; Probabilistic logic; Ranking (information retrieval); Divergence-from-randomness model; Data mining; Artificial intelligence; Search engine; Web search query; Concept search; Geography","authors":[{"name":"Jiashu Zhao","is_ca":true},{"name":"Jimmy Xiangji Huang","is_ca":true},{"name":"Ben He","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07215051758748364,"gpt":0.2336056618730842,"spread":0.1614551442856006,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001602752,0.0007827926,0.0009716104,0.002370279,0.0006422529,0.001823142,0.001843991,0.001411153,0.01717475],"category_scores_gemma":[0.005889555,0.0002589648,0.0007456768,0.002915987,0.0005137327,0.00347461,0.001479595,0.0009393159,0.01404571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00104263,"about_ca_system_score_gemma":0.00108847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002819436,"about_ca_topic_score_gemma":0.004026631,"domain_scores_codex":[0.9982621,0.0003165247,0.000100727,0.0004388756,0.0007320479,0.0001497603],"domain_scores_gemma":[0.9977004,0.0004883154,0.0001884653,0.0009232486,0.0006138349,0.00008566953],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004967991,0.0003652504,0.003128601,0.0006282427,0.0001298381,0.000249077,0.0001910222,0.04215095,0.0361,0.09048936,0.0818833,0.7441875],"study_design_scores_gemma":[0.0001361466,0.0006123383,0.005029314,0.00009360577,0.0001733214,0.001699964,0.0001413842,0.6345516,0.04314195,0.08934874,0.2248807,0.0001909215],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.04093836,0.004693088,0.8531859,0.001602089,0.000574297,0.0008841961,0.006100317,0.0164406,0.07558117],"genre_scores_gemma":[0.4053974,0.002716409,0.4673917,0.001168624,0.0005626392,0.0006656891,0.01144971,0.001391773,0.109256],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9828252,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W74613997","doi":"10.29173/cais16","title":"Source Selection Among Information Seekers: Ideals and Realities","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Political science; Humanities; Library science; Art; Computer science","authors":[{"name":"Heidi Julien","is_ca":true},{"name":"David Michels","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01379897580461034,"gpt":0.2237250607144082,"spread":0.2099260849097978,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01569993,0.0003338273,0.0004083684,0.004094942,0.00337689,0.005278186,0.0008875106,0.001207051,0.001025581],"category_scores_gemma":[0.05086847,0.000532866,0.0004387657,0.001359143,0.006005585,0.004077356,0.00391702,0.001412884,0.0001927395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009221564,"about_ca_system_score_gemma":0.0009913457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001437751,"about_ca_topic_score_gemma":0.001509201,"domain_scores_codex":[0.988726,0.007072533,0.0006338073,0.0005890204,0.002409401,0.0005693132],"domain_scores_gemma":[0.94863,0.03391688,0.008522005,0.002385948,0.004541716,0.002003389],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0006547772,0.0003536583,0.3980433,0.0002503219,0.00009581856,0.001008416,0.5334501,0.000289026,0.003818386,0.01875886,0.0006425161,0.04263485],"study_design_scores_gemma":[0.0001313536,0.0007084183,0.2409514,0.0003723079,0.0001287258,0.004091743,0.6909465,0.005378838,0.003344354,0.04140078,0.01230979,0.0002358591],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9913788,0.0003175311,0.002714738,0.0009548668,0.000009170934,0.00001719457,0.00001495387,0.00001257319,0.004580209],"genre_scores_gemma":[0.9987747,0.0001012906,0.0008260201,0.00004932466,0.000007715822,0.000009473732,0.00001795335,0.000004100923,0.0002093907],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9947218,"threshold_uncertainty_score":0.0830301,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121854496","doi":"10.1145/1099554.1099645","title":"Indexing time vs. query time","year":2005,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Search engine indexing; Query expansion; Query optimization; Information retrieval; Response time; Sargable; Focus (optics); Query language; Web query classification; Web search query; Index (typography); Data mining; Database; Search engine; World Wide Web; Operating system","authors":[{"name":"Stefan Büttcher","is_ca":true},{"name":"Charles L. A. Clarke","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.008066757964557575,"gpt":0.2286195290006048,"spread":0.2205527710360472,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008766425,0.001019254,0.001743258,0.001646136,0.001192703,0.006369893,0.002890719,0.00180166,0.0109115],"category_scores_gemma":[0.04069377,0.0008513579,0.0007034041,0.004188992,0.0009791258,0.01286796,0.001838018,0.001703828,0.003659407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001912323,"about_ca_system_score_gemma":0.001572218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001211761,"about_ca_topic_score_gemma":0.001365829,"domain_scores_codex":[0.9918259,0.001947007,0.0005619488,0.001085679,0.003238884,0.001340451],"domain_scores_gemma":[0.9543161,0.03493407,0.002236024,0.004534654,0.003057224,0.0009219837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003167314,0.000605124,0.006003842,0.002043003,0.0001666675,0.000342838,0.001130753,0.07237516,0.2320325,0.1439666,0.008057055,0.5301092],"study_design_scores_gemma":[0.0005216432,0.004137984,0.00819047,0.0002383572,0.0008993244,0.002463986,0.0008862691,0.4913008,0.3041802,0.1377917,0.04905495,0.0003342648],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2281201,0.02298144,0.6829016,0.005764125,0.0006917203,0.0005062158,0.0009238577,0.006702248,0.05140868],"genre_scores_gemma":[0.8034153,0.006298222,0.1768903,0.0005968923,0.0005940316,0.0002805598,0.0006766244,0.001755184,0.009492924],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0109115,"threshold_uncertainty_score":0.04636186,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1991678929","doi":"10.1177/0165551506065787","title":"A study of the effect of term proximity on query expansion","year":2006,"lang":"en","type":"article","venue":"Journal of Information Science","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Query expansion; Computer science; Term (time); Information retrieval; Query optimization; Web query classification; Mutual information; Sargable; Web search query; Measure (data warehouse); Query language; Data mining; Search engine; Artificial intelligence","authors":[{"name":"Olga Vechtomova","is_ca":true},{"name":"Ying Wang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01217584193266941,"gpt":0.2799131262771092,"spread":0.2677372843444398,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009054122,0.0007323397,0.001110793,0.001711413,0.0007637332,0.001197957,0.0007488778,0.001058365,0.001918909],"category_scores_gemma":[0.1079358,0.0003632341,0.0006999389,0.00257697,0.0009062678,0.003988829,0.000969382,0.001079481,0.0003461046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006476306,"about_ca_system_score_gemma":0.0004394013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001290609,"about_ca_topic_score_gemma":0.00107392,"domain_scores_codex":[0.9911106,0.005321261,0.0005689351,0.0009015664,0.001781919,0.0003157477],"domain_scores_gemma":[0.668739,0.3168043,0.005124398,0.00439521,0.004103846,0.0008332529],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01318519,0.002657944,0.05703649,0.003866207,0.001027102,0.001088339,0.002782265,0.134447,0.231373,0.007332365,0.002194028,0.5430101],"study_design_scores_gemma":[0.0007360341,0.0218692,0.1444899,0.0001892308,0.002088314,0.003922824,0.001051537,0.6382636,0.1714876,0.009210175,0.006381566,0.0003099787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9316301,0.00419658,0.05770668,0.0002341075,0.00006162903,0.0003588429,0.0002213373,0.0004047734,0.005185932],"genre_scores_gemma":[0.9732503,0.0006622006,0.024856,0.0000581275,0.0000607295,0.000130334,0.0001969275,0.00008757452,0.000697906],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009054122,"threshold_uncertainty_score":0.04788333,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2792655782","doi":"10.1016/j.nedt.2018.01.004","title":"Relationship between information-seeking behavior and innovative behavior in Chinese nursing students","year":2018,"lang":"en","type":"article","venue":"Nurse Education Today","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Education Department of Hunan Province; University of Ottawa","keywords":"Information literacy; Information seeking; Information seeking behavior; Information behavior; Psychology; Scale (ratio); Nursing; Medical education; Nurse education; Medicine; Pedagogy; Computer science","authors":[{"name":"Zhuqing Zhong","is_ca":false},{"name":"Dehua Hu","is_ca":false},{"name":"Feng Zheng","is_ca":false},{"name":"Siqing Ding","is_ca":false},{"name":"Aijing Luo","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02745912243916376,"gpt":0.3726971580352288,"spread":0.3452380355960651,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006612958,0.0002570449,0.0003555162,0.00178295,0.0008449805,0.001104979,0.0003242605,0.0007331829,0.002782634],"category_scores_gemma":[0.002738357,0.0002477922,0.0005250486,0.001401223,0.0004161524,0.0005446611,0.0003715444,0.0008109404,0.0003776028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008011918,"about_ca_system_score_gemma":0.001584885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02219172,"about_ca_topic_score_gemma":0.02923725,"domain_scores_codex":[0.999527,0.00006732402,0.00009500096,0.00006170298,0.0001490247,0.0001000036],"domain_scores_gemma":[0.9961752,0.001301758,0.001060341,0.00009597815,0.0003814621,0.0009852968],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004649484,0.0003844566,0.9966006,0.00001893849,0.00002753963,0.00005346717,0.0009332995,0.00002299358,0.0002674777,0.000033245,0.00005842162,0.001553007],"study_design_scores_gemma":[0.000004546072,0.00009498672,0.9980152,0.000007407248,0.00003397389,0.00005349361,0.001332827,0.0002511008,0.0000835538,0.00003206066,0.00008506738,0.000005824626],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9994723,0.00007833344,0.000009084451,0.00004723297,0.000002329582,0.000004372902,0.00003335339,7.261058e-7,0.0003521923],"genre_scores_gemma":[0.9991572,0.0001113217,0.00002728614,0.00003979625,0.000005526998,0.000005641574,0.00007353759,9.880675e-7,0.0005789073],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02219172,"threshold_uncertainty_score":0.04412508,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2145664829","doi":"10.1145/1963405.1963459","title":"Learning to rank with multiple objective functions","year":2011,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Learning to rank; Measure (data warehouse); Computer science; Ranking (information retrieval); Relevance (law); Rank (graph theory); Function (biology); Perspective (graphical); Artificial intelligence; Machine learning; Information retrieval; Data mining; Mathematics","authors":[{"name":"Krysta M. Svore","is_ca":false},{"name":"Maksims Volkovs","is_ca":true},{"name":"Christopher J. C. Burges","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02798282266224064,"gpt":0.2342720804439619,"spread":0.2062892577817213,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01347819,0.002170392,0.003309538,0.003093488,0.0008777174,0.002688062,0.00301935,0.002761672,0.002677571],"category_scores_gemma":[0.02714192,0.000626453,0.001280589,0.003831224,0.00175701,0.004994807,0.002048972,0.003304935,0.001181472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001997791,"about_ca_system_score_gemma":0.001323677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002272929,"about_ca_topic_score_gemma":0.002473655,"domain_scores_codex":[0.9947034,0.002734942,0.0002351472,0.0008096955,0.001152671,0.0003641061],"domain_scores_gemma":[0.9792891,0.01484287,0.001691307,0.001795863,0.001882806,0.0004980122],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002361262,0.0004727478,0.003374011,0.0003136015,0.0002573008,0.0001168127,0.0001126568,0.663256,0.001621159,0.03843839,0.004281118,0.28752],"study_design_scores_gemma":[0.00001985624,0.0001385634,0.0003097672,0.000009373592,0.00001976755,0.00003716276,0.00001137747,0.9766223,0.0009863308,0.02124649,0.0005833813,0.00001554376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.020518,0.0008286887,0.9755988,0.0006220678,0.00005361789,0.00007520136,0.00008221257,0.0005351838,0.001686226],"genre_scores_gemma":[0.3893605,0.0008711499,0.6004012,0.0005033852,0.000531413,0.0003206101,0.0004931049,0.0003417485,0.00717695],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01347819,"threshold_uncertainty_score":0.07128036,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1503824486","doi":"10.1023/a:1023936321956","title":"Query Expansion with Long-Span Collocates","year":2003,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Microsoft Research","keywords":"Collocation (remote sensing); Computer science; Window (computing); Information retrieval; Mathematics; Machine learning","authors":[{"name":"Olga Vechtomova","is_ca":true},{"name":"Stephen Robertson","is_ca":false},{"name":"Susan Jones","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.009880289279499396,"gpt":0.2239308871336277,"spread":0.2140505978541283,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00156122,0.0007202252,0.00101458,0.002013361,0.0008203689,0.0008628581,0.001007551,0.0009309647,0.008164558],"category_scores_gemma":[0.01240056,0.0004386032,0.0005324911,0.003224327,0.0005407943,0.004916726,0.001688348,0.000855206,0.00231876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000580765,"about_ca_system_score_gemma":0.0009312957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00505371,"about_ca_topic_score_gemma":0.007730771,"domain_scores_codex":[0.9982452,0.0006771127,0.0001270224,0.0003484123,0.0004503863,0.0001519191],"domain_scores_gemma":[0.9938959,0.003472231,0.0002398094,0.001261187,0.0009695214,0.0001612446],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003545396,0.001580514,0.009916513,0.001009787,0.0002884629,0.001171203,0.001534068,0.08860492,0.09957104,0.02613287,0.04911566,0.7175297],"study_design_scores_gemma":[0.0002158767,0.0005539703,0.004741539,0.00004920645,0.0001997677,0.0009767666,0.0005398252,0.9217857,0.0285642,0.02473149,0.01754844,0.00009317265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3972259,0.004419899,0.5721728,0.001287634,0.0003545566,0.0005837611,0.002123321,0.006577665,0.01525451],"genre_scores_gemma":[0.8546096,0.000704416,0.1340604,0.0002469746,0.0001758083,0.0002239484,0.002663836,0.0003816099,0.006933384],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008164558,"threshold_uncertainty_score":0.02731317,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2058749523","doi":"10.1006/ijhc.2000.0392","title":"World Wide Web navigation aid","year":2000,"lang":"en","type":"article","venue":"International Journal of Human-Computer Studies","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"World Wide Web; Computer science; Web navigation; Context (archaeology); Web design; Web Accessibility Initiative; Key (lock); Web modeling; Web development; User interface; Web page; Web standards; Web intelligence; Information retrieval; Multimedia","authors":[{"name":"Milena Head","is_ca":true},{"name":"Norm Archer","is_ca":true},{"name":"Yufei Yuan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03851633204836335,"gpt":0.3473049196187083,"spread":0.3087885875703449,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004309961,0.0004115441,0.0003073982,0.0007464446,0.0004860418,0.0009257768,0.0003597816,0.0006443678,0.06477316],"category_scores_gemma":[0.003177603,0.0001000069,0.0002092333,0.0003498177,0.0001046383,0.001110207,0.000558797,0.0003601599,0.02317352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001812998,"about_ca_system_score_gemma":0.0005261805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002079728,"about_ca_topic_score_gemma":0.004887068,"domain_scores_codex":[0.9997557,0.00007733266,0.00001379129,0.00002841515,0.00008827153,0.00003645857],"domain_scores_gemma":[0.9988691,0.000564133,0.00004529171,0.0001137251,0.0002782914,0.0001295013],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002588154,0.004425136,0.02260539,0.0006276135,0.0001038744,0.0005521168,0.0004432774,0.0004772672,0.009142036,0.002565261,0.1489751,0.8074947],"study_design_scores_gemma":[0.00159099,0.007955589,0.1300303,0.0010928,0.001231868,0.00688684,0.003412727,0.02518502,0.04582709,0.005804563,0.7707493,0.0002328744],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4979548,0.003789165,0.01363064,0.002620356,0.001259744,0.0005616951,0.003213278,0.01093745,0.4660329],"genre_scores_gemma":[0.7486205,0.001935608,0.01427808,0.00101032,0.0002022142,0.0001587697,0.002276419,0.0002163242,0.2313018],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06477316,"threshold_uncertainty_score":0.2166878,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1984070542","doi":"10.1145/2505515.2505526","title":"Effective measures for inter-document similarity","year":2013,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Cosine similarity; Computer science; Cluster analysis; Similarity (geometry); Document clustering; Artificial intelligence; Rank (graph theory); Randomness; Divergence (linguistics); Language model; Document retrieval; Data mining; Natural language processing; Machine learning; Information retrieval; Mathematics; Statistics","authors":[{"name":"John S. Whissell","is_ca":true},{"name":"Charles L. A. Clarke","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01948026662985459,"gpt":0.2824767624413327,"spread":0.2629964958114781,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01181776,0.001520508,0.00201595,0.01514918,0.001302612,0.004550758,0.002516186,0.002275821,0.00181802],"category_scores_gemma":[0.06204601,0.0004110615,0.001251028,0.01121291,0.001977267,0.009582537,0.002328455,0.002248283,0.001106559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002340693,"about_ca_system_score_gemma":0.001413115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001551425,"about_ca_topic_score_gemma":0.002108336,"domain_scores_codex":[0.9782748,0.006054016,0.002687359,0.002535837,0.009924557,0.000523404],"domain_scores_gemma":[0.9585243,0.02087866,0.004863075,0.008155928,0.006811406,0.0007665309],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008887691,0.000731484,0.03118486,0.001679177,0.001325903,0.0002292856,0.0009878119,0.09447375,0.01835704,0.1237637,0.01205871,0.7143195],"study_design_scores_gemma":[0.0001573523,0.001618555,0.03797292,0.0004156984,0.0004311977,0.00170804,0.0009006496,0.6835573,0.03227807,0.2217016,0.0187167,0.0005419613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0619015,0.006917102,0.9221278,0.0004672009,0.0002646778,0.0005218129,0.001470148,0.001085258,0.005244419],"genre_scores_gemma":[0.5487729,0.001307346,0.4449064,0.0002251896,0.0003109952,0.0006463759,0.002092561,0.000237357,0.001500812],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01514918,"threshold_uncertainty_score":0.06249911,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2052842594","doi":"10.1145/2590988","title":"Modeling Term Associations for Probabilistic Information Retrieval","year":2014,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; International Business Machines Corporation","keywords":"Term Discrimination; Computer science; Term (time); Bigram; Divergence-from-randomness model; Probabilistic logic; Ranking (information retrieval); Query expansion; Information retrieval; Data mining; Artificial intelligence; Web search query; Search engine; Concept search; Trigram","authors":[{"name":"Jiashu Zhao","is_ca":true},{"name":"Jimmy Xiangji Huang","is_ca":true},{"name":"Ye Zheng","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03054072446624775,"gpt":0.267857013344392,"spread":0.2373162888781443,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004333611,0.001486326,0.00192702,0.003842405,0.0009274848,0.002524682,0.003274251,0.002701929,0.002743546],"category_scores_gemma":[0.01983828,0.0009725412,0.002314277,0.006262755,0.001449513,0.007917346,0.002072444,0.002196685,0.002253713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002035314,"about_ca_system_score_gemma":0.001486177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007621221,"about_ca_topic_score_gemma":0.007163209,"domain_scores_codex":[0.9954612,0.001514216,0.0003651852,0.0009759381,0.001329714,0.0003538473],"domain_scores_gemma":[0.9926813,0.004638723,0.0009394166,0.0008443351,0.0007646119,0.0001316315],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002366491,0.0001323733,0.002965892,0.0003922682,0.0001976537,0.0003128555,0.0004096749,0.6860224,0.00564169,0.15638,0.004194378,0.1431141],"study_design_scores_gemma":[0.00001199592,0.00004251246,0.0002737198,0.00001112723,0.00003313255,0.0001126681,0.00001852565,0.9534232,0.0004575095,0.04411577,0.001472638,0.00002716037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01150598,0.001416278,0.9841663,0.0003388581,0.00005689228,0.00009500788,0.0002578175,0.0006733853,0.001489493],"genre_scores_gemma":[0.6159866,0.003796335,0.3650089,0.0004725867,0.0005371277,0.0009243336,0.002049478,0.0003684755,0.01085615],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007621221,"threshold_uncertainty_score":0.02291864,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2056260089","doi":"10.1016/s0740-8188(03)00005-7","title":"Knowledge organization in research: A conceptual model for organizing data","year":2003,"lang":"en","type":"article","venue":"Library & Information Science Research","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Transferability; Computer science; Relevance (law); Data science; Consistency (knowledge bases); Coding (social sciences); Recall; Knowledge management; Management science; Information retrieval; Psychology; Sociology; Artificial intelligence; Social science","authors":[{"name":"Lisa M. Given","is_ca":true},{"name":"Hope A. Olson","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4916944307815487,"gpt":0.471232263735003,"spread":0.02046216704654569,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00683953,0.0007866083,0.0008225062,0.01058576,0.003036411,0.01408081,0.003239649,0.003219548,0.005082539],"category_scores_gemma":[0.01871454,0.0008650832,0.002275013,0.01293759,0.01003167,0.02206852,0.003450222,0.001863132,0.001099282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004006246,"about_ca_system_score_gemma":0.006399369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00960086,"about_ca_topic_score_gemma":0.005836435,"domain_scores_codex":[0.9949436,0.002384692,0.0005227042,0.0008898497,0.0008479352,0.0004112685],"domain_scores_gemma":[0.9856728,0.007474014,0.001903373,0.00199222,0.001681798,0.001275797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000303643,0.00008845962,0.004475893,0.0002270864,0.00008222336,0.0001346143,0.005881074,0.003919369,0.0005421621,0.9508362,0.002125417,0.03165716],"study_design_scores_gemma":[0.00005041084,0.00006373669,0.002260174,0.0002511302,0.0001276613,0.0004101545,0.003624729,0.02757662,0.0004735807,0.9448394,0.02027459,0.00004784688],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0500499,0.002923787,0.8793134,0.01325178,0.0001298373,0.0006799791,0.0008278092,0.000510373,0.0523131],"genre_scores_gemma":[0.4884727,0.001683138,0.5021756,0.0006928009,0.0001681388,0.001108142,0.001135195,0.0001022827,0.004461944],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01408081,"threshold_uncertainty_score":0.03617132,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2087859840","doi":"10.1007/s10844-009-0096-5","title":"Evaluating information retrieval system performance based on user preference","year":2009,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Relevance (law); Information retrieval; Preference; Rank (graph theory); Precision and recall; Measure (data warehouse); Relevance feedback; Document retrieval; Data mining; Artificial intelligence; Image retrieval; Statistics","authors":[{"name":"Bing Zhou","is_ca":true},{"name":"Yiyu Yao","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07183585331902738,"gpt":0.3096554805127487,"spread":0.2378196271937213,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00439729,0.0004529562,0.0006554505,0.001687248,0.0003880383,0.001324401,0.0002804422,0.0008868991,0.001732357],"category_scores_gemma":[0.02918341,0.000164888,0.0006145542,0.001056226,0.0002206238,0.001458719,0.0003296096,0.0003624563,0.0006676685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004118551,"about_ca_system_score_gemma":0.0003644148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002019558,"about_ca_topic_score_gemma":0.002394897,"domain_scores_codex":[0.9968977,0.001508201,0.0003936879,0.0001888235,0.0008006527,0.0002109832],"domain_scores_gemma":[0.9566723,0.0360355,0.001836147,0.001006465,0.003564788,0.0008847522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.02355006,0.0027289,0.6423898,0.0007342655,0.001621492,0.0003177202,0.000896187,0.01721783,0.06221827,0.0006039595,0.002331186,0.2453902],"study_design_scores_gemma":[0.0006456163,0.01851963,0.6232491,0.00004643995,0.00169492,0.0008141388,0.001039023,0.3064464,0.04573683,0.0006757414,0.0008721117,0.0002599691],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9954938,0.0002315208,0.002980398,0.00004721873,0.00001459521,0.00003192725,0.0000769563,0.00009124496,0.001032348],"genre_scores_gemma":[0.9975552,0.00005438249,0.001977703,0.00001615745,0.00001246623,0.00001236203,0.0001157366,0.00001186234,0.0002441216],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00439729,"threshold_uncertainty_score":0.02325535,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2096249996","doi":"10.1145/1141753.1141818","title":"Using controlled query generation to evaluate blind relevance feedback algorithms","year":2006,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Query expansion; Query optimization; Web query classification; Relevance (law); Information retrieval; Sargable; Relevance feedback; Set (abstract data type); Query language; Process (computing); Web search query; Online aggregation; Data mining; Result set; Query by Example; Term (time); Algorithm; Search engine; Artificial intelligence","authors":[{"name":"Chris Jordan","is_ca":true},{"name":"Carolyn Watters","is_ca":true},{"name":"Qigang Gao","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08124939581230618,"gpt":0.3355957155963968,"spread":0.2543463197840906,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02257276,0.001167115,0.001059566,0.002340357,0.0006740199,0.001680803,0.001678164,0.001596488,0.0007806635],"category_scores_gemma":[0.1029676,0.0004461159,0.0006185466,0.001454328,0.002784177,0.002711017,0.001480136,0.001043109,0.0002000131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002423329,"about_ca_system_score_gemma":0.001449199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005684252,"about_ca_topic_score_gemma":0.003430479,"domain_scores_codex":[0.9793689,0.013111,0.001162584,0.001437447,0.004322049,0.0005979692],"domain_scores_gemma":[0.8709599,0.1057626,0.006035572,0.009410667,0.006827046,0.001004267],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0114927,0.00416146,0.02793186,0.001285227,0.0008077489,0.000301329,0.00163138,0.6929755,0.05945041,0.02742233,0.003751463,0.1687886],"study_design_scores_gemma":[0.0008485136,0.00320429,0.004531917,0.00003362784,0.0001067975,0.0001262261,0.000141631,0.9434096,0.03400049,0.01247737,0.0009934908,0.0001260877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7993662,0.001003577,0.1937018,0.0002631991,0.00009517634,0.001144636,0.0003176575,0.001376365,0.002731489],"genre_scores_gemma":[0.9471859,0.0001015942,0.0514451,0.00009612222,0.00002282376,0.0004017455,0.0002887179,0.00008969878,0.0003683234],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02257276,"threshold_uncertainty_score":0.1193776,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}