{"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"},"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001118959,0.0001303073,0.0001598855,0.0006024269,0.0001795816,0.0001764034,0.0005853813,0.0001123254,0.0001473661],"category_scores_gemma":[0.0000715113,0.0001170287,0.00009157811,0.0008259898,0.00003252311,0.002672687,0.000006631673,0.0001507202,0.0003455845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001491652,"about_ca_system_score_gemma":0.00007812011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004254759,"about_ca_topic_score_gemma":7.411491e-7,"domain_scores_codex":[0.9975893,0.000138947,0.0007376975,0.0001010517,0.001251262,0.0001817085],"domain_scores_gemma":[0.9976981,0.00009719337,0.0002911539,0.0007318106,0.001107644,0.00007410062],"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":[0.0000286894,0.0002578782,0.00005056374,0.0002096169,0.00004598196,5.160217e-7,0.004313079,0.1522976,0.0003685901,0.00521249,0.0009082671,0.8363067],"study_design_scores_gemma":[0.0006689828,0.0001536723,0.0001607775,0.00006822494,0.00001941634,0.000006798384,0.0001677577,0.9722133,0.02039341,0.00004926325,0.00593581,0.0001626318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005777515,0.00001729951,0.9864181,0.0002772621,0.000366441,0.0008638169,0.00002742869,0.0003407558,0.005911374],"genre_scores_gemma":[0.9948713,0.000007083131,0.004692726,0.000157989,0.00001019048,0.0001602443,0.00001790574,0.000004247733,0.00007828038],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9890938,"threshold_uncertainty_score":0.477229,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005864014,0.0000441987,0.00005087314,0.0001483768,0.0001905837,0.0000449162,0.0001677648,0.00003428003,0.00003569388],"category_scores_gemma":[0.00007728459,0.00003846972,0.00001217311,0.000353456,0.00002648174,0.00323071,0.0003195558,0.00006932268,0.00006173304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005780931,"about_ca_system_score_gemma":0.00006497626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007839203,"about_ca_topic_score_gemma":0.000006013852,"domain_scores_codex":[0.9991736,0.00002641366,0.0001477673,0.00006517081,0.0004797172,0.0001073607],"domain_scores_gemma":[0.9996206,0.00002016933,0.00003514847,0.0001120437,0.0001670652,0.00004497731],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001932684,0.0002231339,0.4530937,0.00006083758,0.00001499189,0.00002113469,0.0595904,0.0004501252,0.0004150883,0.1370026,0.003508249,0.3454265],"study_design_scores_gemma":[0.0008574483,0.00004674354,0.8110272,0.000002848722,0.000001465147,0.00002308183,0.00007373995,0.1860925,0.0006746049,0.0004544698,0.0006477935,0.00009810493],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9325886,0.000005677442,0.05964412,0.000297883,0.00007644672,0.0002006339,0.000001042284,0.00004894998,0.007136602],"genre_scores_gemma":[0.9968899,0.00001305939,0.002760035,0.0002566149,0.000004564793,0.000001271762,0.000005108865,4.67865e-7,0.00006897611],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3579335,"threshold_uncertainty_score":0.2342186,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001338302,0.00006305794,0.0001472114,0.0005829128,0.00002782924,0.0001230846,0.0002370494,0.00004343061,0.00001507887],"category_scores_gemma":[0.0006423653,0.00005515656,0.00005093512,0.0004613573,0.00001455489,0.02795029,0.00002502883,0.000124344,0.00000688922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008943478,"about_ca_system_score_gemma":0.0003591601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002560295,"about_ca_topic_score_gemma":0.000001950379,"domain_scores_codex":[0.9979936,0.00006745203,0.001115634,0.0000289476,0.0006956586,0.00009871848],"domain_scores_gemma":[0.9960431,0.00006373741,0.003060939,0.00009855426,0.0006892173,0.00004445205],"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":[0.001010327,0.0007785796,0.08139502,0.001500298,0.0001901207,0.000004386155,0.1815298,0.3483989,0.03530341,0.197025,0.001520627,0.1513435],"study_design_scores_gemma":[0.008436141,0.001068885,0.06063046,0.0004627916,0.00007623398,0.00009758306,0.01225587,0.8232027,0.08123661,0.009946882,0.002080159,0.0005056714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6292742,0.00001187646,0.3692098,0.0001369893,0.0001261617,0.0001390554,0.000002722348,0.000004375278,0.001094883],"genre_scores_gemma":[0.9776791,0.00004218436,0.02212265,0.0001384553,0.000005170315,0.000001844871,0.000003644278,0.000001164634,0.000005783456],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4748038,"threshold_uncertainty_score":0.9856453,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00199057,0.00008392227,0.0001160483,0.0001653482,0.0001457898,0.000206068,0.0003235911,0.00002546214,0.0000133807],"category_scores_gemma":[0.00004456936,0.00006034298,0.0000235819,0.0006434642,0.00006261068,0.002566693,0.00008957271,0.0000846864,0.00002511167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008561881,"about_ca_system_score_gemma":0.00003984557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001280902,"about_ca_topic_score_gemma":8.647815e-7,"domain_scores_codex":[0.9985726,0.00006599332,0.0004479587,0.00008881446,0.0006757324,0.0001488787],"domain_scores_gemma":[0.9993935,0.00004314186,0.0001507864,0.000197595,0.0001879249,0.00002701394],"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":[0.0002497541,0.00004325721,0.0001271454,0.0004117633,0.00001400212,6.594875e-7,0.003933338,0.001294436,0.000008894204,0.05458475,0.00002766542,0.9393044],"study_design_scores_gemma":[0.01657975,0.0001760072,0.3156985,0.001269776,0.00007263148,0.00001279841,0.0007474276,0.60887,0.002999929,0.02566536,0.02719804,0.00070978],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1599037,0.0002850297,0.7581871,0.002069337,0.0003038634,0.003407024,0.0000061407,0.0002297762,0.07560806],"genre_scores_gemma":[0.9965052,0.00007435706,0.00309956,0.000213182,0.00000375737,0.00004319032,0.000002786375,0.000001877711,0.00005607223],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9385946,"threshold_uncertainty_score":0.2460715,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007923901,0.0000564783,0.00009397964,0.0007182699,0.0001392258,0.0004752772,0.0001883478,0.00002614482,0.00001680916],"category_scores_gemma":[0.0001300818,0.00004931168,0.00001817943,0.0008906982,0.000148249,0.0157504,0.00004318304,0.0001337808,0.00000916534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001946448,"about_ca_system_score_gemma":0.0003423325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006936398,"about_ca_topic_score_gemma":0.000001565055,"domain_scores_codex":[0.9988365,0.00002241748,0.000450579,0.00005553818,0.0005079809,0.000127009],"domain_scores_gemma":[0.9990383,0.00005130236,0.000325524,0.00006426912,0.0004483769,0.00007220977],"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":[0.00005321247,0.00009381944,0.02505947,0.00002416853,0.00001153075,0.000006162034,0.0145499,0.0005554641,0.00783376,0.1095412,0.0003435946,0.8419277],"study_design_scores_gemma":[0.01692141,0.001853971,0.6814593,0.0002244779,0.00004169301,0.005319831,0.007763641,0.1076222,0.1411438,0.02229296,0.01441405,0.0009426352],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9309981,0.00001890221,0.06553727,0.001234849,0.0002723705,0.0001438556,9.16921e-7,0.00001306162,0.001780624],"genre_scores_gemma":[0.9739239,0.00003763883,0.02583338,0.0001524021,0.00002922002,0.000001622833,4.271095e-7,0.000001048183,0.00002031684],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8409851,"threshold_uncertainty_score":0.9980158,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007744128,0.00002030356,0.00002230041,0.0000132695,0.0002403967,0.0003843116,0.000748977,0.000009905057,0.00007490277],"category_scores_gemma":[0.00001728207,0.00001471529,0.00001368372,0.00001449585,0.00001598957,0.0009061819,0.0001643981,0.00002447467,0.0005309467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003139902,"about_ca_system_score_gemma":0.0000134903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001714452,"about_ca_topic_score_gemma":0.000001566686,"domain_scores_codex":[0.9997438,0.000002426607,0.00004181418,0.00004452241,0.00009368216,0.00007373041],"domain_scores_gemma":[0.9994684,0.000003619778,0.00002008132,0.0004441658,0.00002931113,0.00003438031],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000001118051,0.00001185527,0.004132102,0.000002105307,0.00000132199,0.000007185173,0.0001927376,5.905775e-7,0.0002894199,0.7721344,0.002767004,0.2204602],"study_design_scores_gemma":[0.0005010795,0.00009711352,0.7295088,0.000004883124,0.000001106672,0.00001931403,0.00002193683,0.03801006,0.02629483,0.004991625,0.2002949,0.0002544375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06290205,0.000002051598,0.4935652,0.003691271,0.0003336256,0.00006145295,3.9523e-7,0.0001541446,0.4392898],"genre_scores_gemma":[0.9771448,0.000001528515,0.01494333,0.0002728076,0.00001364048,0.00000150017,1.406639e-7,6.236846e-7,0.007621589],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9142428,"threshold_uncertainty_score":0.6824423,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001799534,0.00004056701,0.00008620435,0.00009874949,0.00008705493,0.0002323006,0.0007086478,0.0000251479,0.00002811188],"category_scores_gemma":[0.0001646532,0.00002917936,0.00001643538,0.0001605151,0.00004830942,0.02517032,0.0002641701,0.00008664531,0.00005377135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009352794,"about_ca_system_score_gemma":0.00008027624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004730763,"about_ca_topic_score_gemma":5.43782e-7,"domain_scores_codex":[0.9989668,0.00003946371,0.000561218,0.00003411448,0.0003187978,0.00007960243],"domain_scores_gemma":[0.9987403,0.00003476776,0.0003727859,0.000323453,0.000449405,0.00007929713],"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":[0.00006991973,0.00003736054,0.00224117,0.00005612273,0.00001982484,0.000001242331,0.005707963,7.286289e-7,0.0001231654,0.1165566,0.01632141,0.8588645],"study_design_scores_gemma":[0.000881172,0.0004357025,0.09708066,0.0000214165,0.000006304466,0.0001525079,0.0005163454,0.01420645,0.000936305,0.0009835155,0.8846242,0.0001553723],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1500605,0.00002018952,0.8429226,0.001937586,0.0004073869,0.00006370513,0.00005605318,0.00002186618,0.004510132],"genre_scores_gemma":[0.9488256,0.0001039695,0.04834303,0.00246861,0.0001870983,3.315828e-7,0.00003551021,0.000001279739,0.00003455031],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8683028,"threshold_uncertainty_score":0.9884641,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003464496,0.00008624146,0.00008312507,0.0001642543,0.0001410274,0.0000743983,0.0004938373,0.00004147288,0.0007314301],"category_scores_gemma":[0.000008459514,0.00007552127,0.00005757084,0.0001781342,0.00005625793,0.001194466,0.0002079665,0.0001421345,0.0001450407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002776762,"about_ca_system_score_gemma":0.0002467139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001422787,"about_ca_topic_score_gemma":0.000005187818,"domain_scores_codex":[0.9989418,0.00003980206,0.0001688194,0.0001675295,0.0003722527,0.0003097797],"domain_scores_gemma":[0.9994676,0.00001603952,0.0000347646,0.0002485742,0.0001153752,0.0001176086],"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":[0.00007465025,0.0005284063,0.225904,0.0003238615,0.00008383646,0.0005145405,0.1332709,0.00003648853,0.09847894,0.2159648,0.002823489,0.3219962],"study_design_scores_gemma":[0.001537106,0.0003018356,0.2548716,0.0001795284,0.0000308626,0.0004683568,0.001150968,0.685712,0.04677493,0.0001771192,0.007253753,0.001541926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6517931,0.0001023604,0.3043694,0.00003824197,0.0003753097,0.0001212708,4.403889e-7,0.0002130167,0.04298687],"genre_scores_gemma":[0.9450657,0.000004076597,0.05220347,0.0003158956,0.00003696734,0.000001533195,8.228051e-7,0.00000659331,0.002364992],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6856756,"threshold_uncertainty_score":0.8008647,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004747493,0.00003506408,0.00005429322,0.00005054008,0.00002798243,0.00001902843,0.0001519672,0.0000213257,0.00004667279],"category_scores_gemma":[0.00001985476,0.00002560709,0.00002620513,0.0001691564,0.00001862306,0.0007311135,0.00002582581,0.00002506155,0.00005368457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001153136,"about_ca_system_score_gemma":0.00003528405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008419541,"about_ca_topic_score_gemma":1.477508e-7,"domain_scores_codex":[0.9994867,0.00006701383,0.00009006824,0.00003927786,0.0002129666,0.0001039688],"domain_scores_gemma":[0.999658,0.00006652468,0.0000271408,0.0001261104,0.00007564215,0.00004658508],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001669239,0.001099699,0.08855211,0.0004099206,0.00004448976,0.000001785875,0.003284631,0.001948983,0.2438714,0.41571,0.001482588,0.2434274],"study_design_scores_gemma":[0.0003311743,0.00007854793,0.04391997,0.00001263121,0.000002913921,0.00000112026,0.000006330514,0.1466636,0.8080652,0.00008508265,0.0007358653,0.00009753241],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1014823,0.00001095554,0.8959702,0.00004758797,0.00007598128,0.0001019024,7.308074e-7,0.00005838146,0.002251951],"genre_scores_gemma":[0.9954974,1.786473e-7,0.004324322,0.00006324035,0.00001029655,0.000004451576,0.000002386803,0.000001202822,0.00009653969],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8940151,"threshold_uncertainty_score":0.1044227,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001447225,0.0001100672,0.0001703361,0.0005930243,0.0008231446,0.0008468323,0.0008265168,0.00006208954,6.915448e-7],"category_scores_gemma":[0.0004222608,0.00007321317,0.0001048279,0.001909507,0.001082639,0.05055865,0.0003919895,0.0002760255,0.000003918958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001463277,"about_ca_system_score_gemma":0.0002295773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001196466,"about_ca_topic_score_gemma":0.000001075217,"domain_scores_codex":[0.9983588,0.00001108177,0.0006718109,0.00005750588,0.0006602827,0.0002404682],"domain_scores_gemma":[0.9970168,0.00004046224,0.001288755,0.0002223495,0.001348969,0.00008268725],"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":[0.000008951584,0.00001831605,0.00290112,0.00002211071,0.00001425429,4.705948e-8,0.007615376,0.00005724213,0.0003939872,0.1044797,0.001261173,0.8832277],"study_design_scores_gemma":[0.004358883,0.002086213,0.1407815,0.0001308695,0.0001669969,0.0009988722,0.08357209,0.1558997,0.009483992,0.001881076,0.5994983,0.001141476],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9300962,0.000009221851,0.0627931,0.006185685,0.000141517,0.0004701242,0.00001502773,0.00006918024,0.0002199158],"genre_scores_gemma":[0.9505653,0.00004089334,0.04734977,0.001995303,0.0000200876,0.00001754089,0.000002671631,0.000001487221,0.000006954599],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8820863,"threshold_uncertainty_score":0.9627207,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003312195,0.0001057461,0.000106599,0.0001800914,0.000584682,0.0003091421,0.0003465326,0.00006036475,0.00005723083],"category_scores_gemma":[0.00005077591,0.00008795669,0.00009057885,0.0007366078,0.00002050361,0.0007665688,0.00009917783,0.0001218169,0.00009944964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001049255,"about_ca_system_score_gemma":0.0001132203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009035701,"about_ca_topic_score_gemma":0.00001803715,"domain_scores_codex":[0.9988431,0.00001903253,0.0002343804,0.0002149502,0.0003296205,0.0003588884],"domain_scores_gemma":[0.9993223,0.00008959973,0.00005383796,0.0002935976,0.0001707299,0.00006991612],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007883183,0.002131375,0.004162575,0.0002028523,0.00004822593,0.00002524233,0.001222472,0.0002283428,0.007838956,0.8025058,0.1210715,0.05977436],"study_design_scores_gemma":[0.009250958,0.003642275,0.09056766,0.0001418825,0.00004395052,0.00006400444,0.000229524,0.1622242,0.2252202,0.01171936,0.4949381,0.001957951],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1778841,0.00004015135,0.7623307,0.001107372,0.001124414,0.001609773,0.00004948156,0.0007487216,0.05510531],"genre_scores_gemma":[0.8920786,0.00001121707,0.02643081,0.0007339991,0.0002226504,0.00009347072,0.00002771138,0.00001716831,0.08038439],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7907864,"threshold_uncertainty_score":0.449696,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001461518,0.0001067165,0.0001582147,0.000219343,0.0007750009,0.000278755,0.00243581,0.0001223316,0.00007647357],"category_scores_gemma":[0.0008457378,0.00007301686,0.0001117283,0.002638191,0.0006497198,0.003944852,0.001123688,0.0004586828,0.0000284139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003413405,"about_ca_system_score_gemma":0.001710695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003885526,"about_ca_topic_score_gemma":0.000001225666,"domain_scores_codex":[0.9978011,0.0004338328,0.0004034812,0.0002679536,0.0005743833,0.0005192171],"domain_scores_gemma":[0.9965921,0.001927348,0.00008414562,0.0009108565,0.0003263821,0.0001591374],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001301841,0.00009230732,0.03321955,0.00005519159,0.000009423184,7.233879e-7,0.0008049131,0.00002390699,0.002554226,0.8639968,0.09181976,0.007293007],"study_design_scores_gemma":[0.001341647,0.0005937298,0.2410879,0.00007398747,0.000009939107,0.00002763032,0.0004685715,0.03309686,0.05494572,0.2910068,0.3769189,0.0004282303],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4006807,0.001497325,0.3845062,0.1751912,0.0007039371,0.01085022,0.001315061,0.0008757923,0.02437958],"genre_scores_gemma":[0.9516298,0.000222534,0.03790279,0.0004520965,0.0001184388,0.0005603993,0.00001690999,0.00002068046,0.009076321],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.57299,"threshold_uncertainty_score":0.5960758,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.006251435,0.00009450274,0.0001018748,0.0004682648,0.0003812773,0.001406493,0.0005104981,0.00008074609,0.0001075767],"category_scores_gemma":[0.004833509,0.00008098911,0.00003146348,0.001207661,0.00006504072,0.3958284,0.0002335796,0.0003413485,0.0002713006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001252442,"about_ca_system_score_gemma":0.0001849045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003623566,"about_ca_topic_score_gemma":3.958961e-9,"domain_scores_codex":[0.9970657,0.001509875,0.000428831,0.0001455257,0.0006056172,0.0002444304],"domain_scores_gemma":[0.9936703,0.005298172,0.0002066375,0.0004196064,0.0002483911,0.0001568404],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006207292,0.0000114354,0.00002806639,0.00003066421,0.000001882502,3.469889e-7,0.0002222407,0.00007269436,0.0000489466,0.7377943,0.001023504,0.2607038],"study_design_scores_gemma":[0.0002924569,0.0001917141,0.003860698,0.00006526661,0.00000410327,0.00001186157,0.0001884136,0.2047369,0.00489631,0.00118203,0.7844471,0.0001231824],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004448477,0.000104858,0.9192349,0.06496047,0.0001669219,0.0002784975,0.000001103097,0.000205035,0.01460332],"genre_scores_gemma":[0.1084581,0.0004656259,0.821514,0.06874394,0.0001518604,0.00007302668,0.00003757578,0.000008867506,0.0005471007],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7834235,"threshold_uncertainty_score":0.9996302,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001488084,0.0003715191,0.0003859019,0.00107643,0.0006123137,0.002573567,0.005841761,0.0003527534,0.00001967254],"category_scores_gemma":[0.0003878664,0.0003246144,0.0001221771,0.0007266991,0.0006111693,0.005907066,0.001704371,0.0009387552,0.0004255331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005954842,"about_ca_system_score_gemma":0.002717953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001280709,"about_ca_topic_score_gemma":0.000006386752,"domain_scores_codex":[0.9964649,0.00003393917,0.0005980833,0.0004848934,0.001716702,0.0007014466],"domain_scores_gemma":[0.9966791,0.0001902342,0.0004974272,0.00185771,0.0005687007,0.0002068323],"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":[0.00001044012,0.00001622561,0.00003221551,0.00005932732,0.000004251159,0.00002475498,0.001747606,0.002015253,0.00001821113,0.005359139,0.0006068712,0.9901057],"study_design_scores_gemma":[0.001080172,0.0004827204,0.001651088,0.0006189601,0.00001270589,0.000177119,5.247463e-7,0.8073009,0.004029308,0.09173711,0.0911239,0.001785461],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00006978378,0.00005026151,0.9844791,0.000634889,0.002421294,0.0004088851,0.000009087293,0.0001694014,0.01175731],"genre_scores_gemma":[0.1141292,0.0002046796,0.8528973,0.01224263,0.003125103,0.00004652675,0.0002512691,0.00009069162,0.01701264],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9883202,"threshold_uncertainty_score":0.9999206,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001147391,0.00006006132,0.0001264603,0.0001841391,0.0004432393,0.00009416559,0.0009961165,0.0000263736,2.240585e-7],"category_scores_gemma":[0.0001486951,0.00003662896,0.00006628405,0.002258149,0.004254815,0.002131909,0.0006681887,0.0001280012,5.183969e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000645062,"about_ca_system_score_gemma":0.0002034337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002418604,"about_ca_topic_score_gemma":5.957125e-7,"domain_scores_codex":[0.9991103,0.000002313695,0.0001860667,0.00009147712,0.0004263021,0.0001835522],"domain_scores_gemma":[0.9985722,0.00003871973,0.0003266472,0.0001124517,0.0009127847,0.00003720212],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00003153425,0.00003269024,0.005577705,0.00007384456,0.00002267253,1.582847e-8,0.03748119,0.00002071845,0.01029253,0.8937554,0.0001574476,0.05255419],"study_design_scores_gemma":[0.01209331,0.002133181,0.1606201,0.0002409697,0.0001744005,0.0001689247,0.6396951,0.07436588,0.04042519,0.02929157,0.0397618,0.001029584],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9889996,0.000006075264,0.004182336,0.006115085,0.00002347236,0.0003406131,0.000007381528,0.00003993443,0.000285473],"genre_scores_gemma":[0.9900245,0.0001364337,0.009544943,0.0002724203,0.00000249107,0.00000520184,1.803764e-7,9.76132e-7,0.00001283109],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8644639,"threshold_uncertainty_score":0.998455,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003287888,0.00005401717,0.0001670541,0.0007380756,0.0002773969,0.0002114147,0.001266098,0.00008637449,0.000001434785],"category_scores_gemma":[0.00187281,0.00003683279,0.00002184862,0.00151354,0.0001936966,0.004665062,0.0005214806,0.0001538927,9.740691e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007895001,"about_ca_system_score_gemma":0.0002404637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006911917,"about_ca_topic_score_gemma":0.000006815102,"domain_scores_codex":[0.9984492,0.00002668763,0.0005333171,0.00007256748,0.0007649813,0.0001532659],"domain_scores_gemma":[0.9973116,0.0001940592,0.0009456517,0.0002843816,0.001220508,0.00004378643],"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":[0.00002943331,0.00004344297,0.2409309,0.000025492,0.00003288166,5.689255e-8,0.006323429,0.00005986003,0.002095384,0.05298919,0.002419913,0.69505],"study_design_scores_gemma":[0.002199437,0.000498088,0.1521697,0.00006953307,0.00003474819,0.00002193364,0.004214692,0.7275831,0.01115512,0.002776722,0.09906049,0.0002163577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9375046,0.00003751723,0.04907492,0.01156973,0.0004186126,0.000154218,0.00007137441,0.00003224001,0.001136751],"genre_scores_gemma":[0.9946346,0.00001239827,0.005213458,0.00009045703,0.00001429099,0.000001260134,0.000003031629,9.811912e-7,0.00002949486],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7275233,"threshold_uncertainty_score":0.3382058,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001370903,0.0001081311,0.0002033107,0.0003132658,0.0004771361,0.0002881657,0.001323358,0.00004742028,2.790589e-7],"category_scores_gemma":[0.0001676359,0.00006646008,0.00009450783,0.003820678,0.001675496,0.007745511,0.0004619726,0.0001686537,5.266142e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006985846,"about_ca_system_score_gemma":0.0002072101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001573335,"about_ca_topic_score_gemma":0.000003294358,"domain_scores_codex":[0.9980325,0.000004691662,0.0006624724,0.0001069257,0.0009257159,0.000267703],"domain_scores_gemma":[0.9960697,0.00004685014,0.001315926,0.0002124635,0.00232319,0.00003184917],"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":[0.00009385827,0.0007190329,0.1704912,0.0007487989,0.00008189646,6.241067e-8,0.1079573,0.0002221718,0.1246272,0.1670465,0.001318693,0.4266933],"study_design_scores_gemma":[0.002632421,0.002290997,0.5182621,0.000215976,0.0001225476,0.00004818221,0.2229047,0.06396695,0.1836784,0.001469742,0.003849542,0.0005584738],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9973443,0.000007199146,0.0006493592,0.000760732,0.00006700919,0.001007904,0.00001699061,0.00004693226,0.00009960702],"genre_scores_gemma":[0.9976633,0.00002763399,0.002081271,0.0001213238,0.000005435368,0.00009050377,0.000003321482,0.000001885226,0.000005341292],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4261348,"threshold_uncertainty_score":0.6173436,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003732585,0.00008912452,0.0001709019,0.0006433043,0.0006077191,0.000361557,0.001280598,0.00004306752,8.955001e-7],"category_scores_gemma":[0.0006406009,0.00005874731,0.0001273418,0.003431178,0.0004835882,0.007621846,0.0002664788,0.0002707279,0.000003205719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001107974,"about_ca_system_score_gemma":0.0005066749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005196629,"about_ca_topic_score_gemma":6.786913e-7,"domain_scores_codex":[0.9981782,0.000008892087,0.000654252,0.00006056576,0.0008025056,0.0002955657],"domain_scores_gemma":[0.9967725,0.0001264367,0.001198377,0.0002664833,0.001561353,0.00007480508],"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":[0.0001029468,0.0001016797,0.01676506,0.00004161004,0.00004675296,9.262289e-7,0.01143688,0.000022548,0.007132152,0.01284185,0.002410391,0.9490972],"study_design_scores_gemma":[0.008361598,0.009822414,0.137052,0.000180644,0.0001275189,0.0006499867,0.09975491,0.1820745,0.06768715,0.001597423,0.4914143,0.001277457],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7166293,0.00000418679,0.274711,0.007797579,0.0002748952,0.0003518254,0.000002815878,0.00005214252,0.0001761971],"genre_scores_gemma":[0.9792667,0.000007071494,0.01512185,0.005573742,0.00001925837,0.000006120968,3.526976e-7,0.000001333717,0.000003550398],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9478198,"threshold_uncertainty_score":0.5525655,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001276606,0.0003827289,0.0004237149,0.0005387684,0.0003687619,0.0007297957,0.001501009,0.0002262605,0.000003767561],"category_scores_gemma":[0.0000699957,0.0003318909,0.00008624626,0.0003316478,0.000538291,0.001164137,0.000280287,0.0004326359,0.000005895626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002097499,"about_ca_system_score_gemma":0.0004127871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002249802,"about_ca_topic_score_gemma":0.00004663318,"domain_scores_codex":[0.9974071,0.00004683896,0.000331664,0.0009279129,0.0007758419,0.0005106284],"domain_scores_gemma":[0.9981275,0.0002885431,0.0001488217,0.0007969892,0.0004388744,0.0001992931],"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":[0.00002876748,0.000021739,0.00001829227,0.00004900671,0.000004315248,0.00001395483,0.0006533549,0.00114532,0.0002719231,0.06544508,0.00000245421,0.9323458],"study_design_scores_gemma":[0.002152862,0.002998575,0.00950426,0.0009369137,0.0000322188,0.0002173721,0.000002329946,0.4105766,0.01329366,0.5542266,0.003548359,0.002510219],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005461706,0.0001881726,0.996685,0.0003361772,0.0005671143,0.0007505756,0.000007243295,0.0001438146,0.0007757735],"genre_scores_gemma":[0.6163189,0.00004679638,0.3815663,0.001365292,0.0003617061,0.00003667791,0.00001684906,0.0000394927,0.0002480046],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9298356,"threshold_uncertainty_score":0.9999133,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":["sts","scholarly_communication"],"category_scores_codex":[0.008114836,0.0001599695,0.0001331087,0.0007179883,0.003762576,0.005570079,0.003680839,0.0001061987,0.00001911188],"category_scores_gemma":[0.001424348,0.00007656434,0.00005205593,0.006377771,0.002849899,0.05544851,0.001659885,0.001761571,0.0002281133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007405628,"about_ca_system_score_gemma":0.0004222787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004268475,"about_ca_topic_score_gemma":0.000001704083,"domain_scores_codex":[0.9947928,0.0004111069,0.0008490775,0.0001710745,0.002885382,0.0008905111],"domain_scores_gemma":[0.9970937,0.001441476,0.0002610141,0.0007307121,0.0002728232,0.0002002568],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002451095,0.00001044068,0.006394987,0.00003376634,0.000004196131,0.000001038551,0.05026491,0.0002119411,0.0000769504,0.811784,0.004351682,0.1268416],"study_design_scores_gemma":[0.001633182,0.00008591475,0.05235251,0.0001309313,0.00000412737,0.00008788989,0.01522882,0.8250691,0.00126432,0.01649359,0.0872405,0.0004091698],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5954607,0.001095166,0.007771438,0.3085632,0.00122449,0.005510685,0.0000288503,0.0006290505,0.07971641],"genre_scores_gemma":[0.9953623,0.0007401347,0.0006380032,0.002821629,0.00003774261,0.0001277082,0.000006508269,0.000004552779,0.0002614628],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8248571,"threshold_uncertainty_score":0.9998637,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006862268,0.00002400639,0.00002504146,0.00002965452,0.00003640928,0.00007091826,0.0002512056,0.00001120463,0.00007425474],"category_scores_gemma":[0.000005071455,0.00001731143,0.00001644563,0.0001403573,0.000003743026,0.0004283729,0.00001843758,0.0000293473,0.0004442063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005051906,"about_ca_system_score_gemma":0.00001272682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001430367,"about_ca_topic_score_gemma":1.00691e-7,"domain_scores_codex":[0.9996791,0.000004148259,0.00005781887,0.00004648346,0.000122654,0.00008975113],"domain_scores_gemma":[0.9997873,0.00000469887,0.00000744396,0.0001330223,0.00002917947,0.00003839867],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[6.757047e-7,0.00001442593,0.00004413369,3.274442e-7,3.203763e-7,0.000002419094,0.0001329443,0.000001739918,0.0003962794,0.7011703,0.003826562,0.2944099],"study_design_scores_gemma":[0.001535423,0.001010065,0.2897743,0.00001120808,0.000004031976,0.00009015264,0.00006896102,0.1449968,0.08315761,0.06345244,0.4150506,0.0008484102],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009796324,0.000006624486,0.7852288,0.004169064,0.0000812635,0.00005038541,1.232202e-7,0.0002330069,0.2004344],"genre_scores_gemma":[0.9665822,0.000001806234,0.02633506,0.003163403,0.00001422766,5.620066e-7,3.981199e-7,4.222214e-7,0.003901916],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9567859,"threshold_uncertainty_score":0.5709522,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002352689,0.00006085778,0.0001429821,0.0004265704,0.0001524448,0.0007441708,0.0006422836,0.00002984279,0.00006914209],"category_scores_gemma":[0.0001696587,0.00003646252,0.0001972366,0.0009137203,0.00002927044,0.006858698,0.000044266,0.0003129457,0.00001563363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009144232,"about_ca_system_score_gemma":0.00009099937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006758154,"about_ca_topic_score_gemma":0.000006855348,"domain_scores_codex":[0.9979573,0.0001482893,0.000842385,0.00005280341,0.0008785538,0.0001206488],"domain_scores_gemma":[0.9977341,0.00009652045,0.001076351,0.000158544,0.0008536074,0.00008092143],"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":[0.0004873716,0.000346859,0.01004887,0.00001685864,0.001019587,0.00004381671,0.02409542,0.03967751,0.007521332,0.00649986,0.00408786,0.9061546],"study_design_scores_gemma":[0.01566302,0.003448893,0.6698182,0.0001336394,0.00216109,0.001971401,0.005349173,0.1702973,0.08315227,0.007027066,0.04015563,0.0008222977],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4196717,0.0001769085,0.5722006,0.006744643,0.0002709864,0.00008843729,0.00000219356,0.000006793555,0.0008377826],"genre_scores_gemma":[0.9780238,0.00008019681,0.02133955,0.000246429,0.0001408731,3.869771e-7,0.000001212787,0.000001760022,0.000165746],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9053323,"threshold_uncertainty_score":0.7176056,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001128162,0.00004767728,0.00005028689,0.00004845845,0.0001381448,0.00005480187,0.0004173724,0.00002061967,0.0002848314],"category_scores_gemma":[0.000004050763,0.00003752925,0.00003052431,0.0001911238,0.00001715132,0.0005412911,0.0001772934,0.00007586095,0.0005216041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001895297,"about_ca_system_score_gemma":0.00004231204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004636126,"about_ca_topic_score_gemma":0.000001812135,"domain_scores_codex":[0.9992843,0.00001362325,0.0001084673,0.0001002541,0.0002962126,0.0001971232],"domain_scores_gemma":[0.9995894,0.00002072036,0.000009944378,0.000229303,0.00006764795,0.00008295973],"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":[0.00001855211,0.0003939218,0.2638316,0.00006582557,0.00002770718,0.0004559174,0.02265274,0.001691009,0.004622106,0.06225188,0.005166486,0.6388222],"study_design_scores_gemma":[0.001681932,0.0007576226,0.487696,0.00003132941,0.000003423426,0.0007186169,0.0007395206,0.2940382,0.1572701,0.0002212066,0.0557223,0.001119763],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.586125,0.000004123721,0.4085482,0.00004844583,0.0000590326,0.00007058951,4.891976e-7,0.0001126084,0.005031602],"genre_scores_gemma":[0.9863901,0.00001611599,0.01042601,0.0001918167,0.00001913423,0.00001216971,9.649194e-7,0.000002264896,0.002941494],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6377025,"threshold_uncertainty_score":0.6704341,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003011022,0.0001879947,0.0001847251,0.0002589248,0.00009060935,0.0003312917,0.000767597,0.0002505414,0.000758964],"category_scores_gemma":[0.00002799838,0.0001552856,0.0001142795,0.00005061335,0.00003346382,0.001248194,0.0002567185,0.0002912004,0.00912034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006082634,"about_ca_system_score_gemma":0.0001131117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002311336,"about_ca_topic_score_gemma":3.61e-7,"domain_scores_codex":[0.9986242,0.000006621139,0.0004130431,0.000102973,0.000664027,0.0001891541],"domain_scores_gemma":[0.9988193,0.00003506661,0.0001916615,0.0005358233,0.0003030896,0.0001150938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003171806,7.894306e-7,2.918283e-7,0.00001338341,0.000004062191,6.260336e-7,0.00008929905,0.000001033889,9.129444e-7,0.9370886,0.009740746,0.05305708],"study_design_scores_gemma":[0.0001358138,0.00006871068,0.00001490172,0.00001872159,0.000004542427,0.00001094182,0.000001797609,0.002507522,0.0001017761,0.009231973,0.9876646,0.0002387074],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.000001590225,0.000005303541,0.3409377,0.0002509474,0.0002743655,0.0001295598,0.000004161313,0.0001936405,0.6582027],"genre_scores_gemma":[0.0005126723,0.00002575339,0.004637189,0.001687234,0.00009598723,0.000001539909,0.0000717161,0.000008244139,0.9929597],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9779239,"threshold_uncertainty_score":0.9916512,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004543763,0.0001514952,0.0002217576,0.00008019483,0.0001259549,0.0001380988,0.001585726,0.00008695435,0.0002486268],"category_scores_gemma":[0.0001498203,0.00009915593,0.0001428233,0.00104194,0.00009826345,0.0005909562,0.000149827,0.0002629655,0.0001366591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003761409,"about_ca_system_score_gemma":0.000427779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000103657,"about_ca_topic_score_gemma":0.00000314765,"domain_scores_codex":[0.9982626,0.00009596199,0.0004066919,0.0002232816,0.0007059554,0.000305472],"domain_scores_gemma":[0.9985422,0.00006436472,0.0001878406,0.0007459125,0.0003539263,0.0001057654],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0001049974,0.0002818466,0.001012261,0.00007809139,0.00001730235,0.000009825684,0.002425437,0.00001132835,0.02657913,0.5875516,0.003571629,0.3783565],"study_design_scores_gemma":[0.003571992,0.002038413,0.5455216,0.0006108407,0.00007687527,0.000125097,0.0002037698,0.06355919,0.268313,0.0316722,0.08269104,0.001616001],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8756815,0.001441493,0.03274683,0.01211961,0.00114509,0.001409233,0.00007430393,0.0005071023,0.07487483],"genre_scores_gemma":[0.9966022,0.0001219281,0.0007620483,0.0007134377,0.00002337445,0.000001053247,0.000001526343,0.000003018302,0.00177136],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5558794,"threshold_uncertainty_score":0.4043461,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003256651,0.00006525632,0.00007230221,0.0001154548,0.00005611641,0.0001045105,0.0001909052,0.00003636014,0.0001214199],"category_scores_gemma":[0.00003567808,0.0000327148,0.00001385836,0.0001483133,0.00004237407,0.001588132,0.0001338639,0.00006753962,0.00009481698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004326036,"about_ca_system_score_gemma":0.0000429145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001278632,"about_ca_topic_score_gemma":0.0006690363,"domain_scores_codex":[0.9991781,0.00004624285,0.0001513272,0.0001637483,0.0002640541,0.000196592],"domain_scores_gemma":[0.9995263,0.0001030152,0.00002181948,0.0002090583,0.00006833961,0.00007147247],"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":[0.00002701059,0.0000293635,0.2162172,0.00002555715,0.000004938698,0.00001196693,0.003052045,0.000003447946,0.0109612,0.1248004,0.001033003,0.6438339],"study_design_scores_gemma":[0.002115778,0.0001476541,0.8911662,0.0001139873,0.000002694683,0.00002330163,0.0002964493,0.009375655,0.07101128,0.00587234,0.0193681,0.0005065699],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8859439,0.000005105297,0.1105505,0.002460436,0.0001141534,0.0001277283,0.000002441529,0.0000847955,0.0007109135],"genre_scores_gemma":[0.9911603,0.00003632887,0.005684252,0.0001511668,0.00001350198,0.000007955879,2.209842e-7,0.000002814911,0.002943413],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.674949,"threshold_uncertainty_score":0.1334071,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008910933,0.00007178185,0.00008970604,0.00007536613,0.0002133688,0.0003464242,0.00170212,0.00003849155,0.0000350576],"category_scores_gemma":[0.00005827629,0.00005731293,0.00003460233,0.0002817316,0.00001541533,0.002035095,0.0003248786,0.0001062454,0.00007117527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002053516,"about_ca_system_score_gemma":0.0001044455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001179211,"about_ca_topic_score_gemma":0.0000019255,"domain_scores_codex":[0.9988899,0.00002129193,0.0001967619,0.000233386,0.0003494306,0.000309207],"domain_scores_gemma":[0.9988727,0.00008462767,0.00002656985,0.0008356754,0.0001122287,0.00006822834],"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":[0.00001746098,0.00006451214,0.0001224437,0.00001722201,0.000006276432,0.000004494324,0.001125468,0.00003429547,0.002204302,0.3286289,0.01188789,0.6558867],"study_design_scores_gemma":[0.001017376,0.0002116537,0.002747339,0.00001769418,0.000004756871,0.00001390375,0.00009419022,0.8586345,0.004116146,0.002717483,0.1301491,0.0002758587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007487622,0.00001728446,0.9772093,0.004746515,0.0001489591,0.0002989991,0.00001158555,0.0002174576,0.009862315],"genre_scores_gemma":[0.7443203,0.00001076758,0.2504095,0.003680865,0.000123108,0.000005473285,0.00005676073,0.000004857499,0.001388422],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8586002,"threshold_uncertainty_score":0.3340577,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00925406,0.0005629864,0.0005872521,0.000468231,0.0006127947,0.001401116,0.01121854,0.0002877162,0.0001165246],"category_scores_gemma":[0.0009958389,0.0003301203,0.0001797069,0.0008398675,0.001018158,0.001751373,0.006752414,0.0009977368,0.0001818056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003156411,"about_ca_system_score_gemma":0.001070555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000537423,"about_ca_topic_score_gemma":0.00003058507,"domain_scores_codex":[0.9926118,0.000119481,0.0009166752,0.003910317,0.001587539,0.0008541927],"domain_scores_gemma":[0.9898199,0.0006356,0.0004540861,0.008087706,0.0007831211,0.0002195175],"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":[0.00001361792,0.00004657966,0.00004317526,0.00004271083,0.000008162523,0.00002300424,0.001760199,0.0009536639,0.00004833169,0.02367813,0.0001373715,0.9732451],"study_design_scores_gemma":[0.001910315,0.001137104,0.0009977854,0.002147285,0.00004826574,0.0003301973,0.00000401483,0.2636248,0.01319574,0.4446822,0.2679442,0.003978116],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00007408601,0.000567008,0.9634353,0.02325216,0.001987444,0.001235522,0.00001271832,0.0002290212,0.009206723],"genre_scores_gemma":[0.4285395,0.002290525,0.4772457,0.02837297,0.009203536,0.0005345094,0.00003517353,0.0003488691,0.05342925],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.969267,"threshold_uncertainty_score":0.9999151,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0016957,0.0001508608,0.0001418321,0.0004259717,0.0006014589,0.0007944013,0.001164265,0.00008551559,0.00001755547],"category_scores_gemma":[0.0002774484,0.0001200272,0.00008251475,0.0008725254,0.0001362779,0.04896191,0.0001771045,0.0001132303,0.0001391982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007082627,"about_ca_system_score_gemma":0.0003408958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003985027,"about_ca_topic_score_gemma":0.000001946137,"domain_scores_codex":[0.9978327,0.00002607002,0.0007753436,0.0001393091,0.0008205794,0.0004059996],"domain_scores_gemma":[0.9984921,0.00004706626,0.0002428702,0.0003017888,0.0007886574,0.000127561],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001084817,0.00006362472,0.0001282543,0.0001884703,0.00000982233,2.572116e-7,0.03633067,0.04268863,0.00002511681,0.8350751,0.0002377223,0.08514386],"study_design_scores_gemma":[0.0003143122,0.0001630335,0.0002028037,0.00001419656,0.000003692129,0.000007402828,0.0003464707,0.9716008,0.0004992166,0.02622872,0.0004326719,0.0001866266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03129516,0.000004043897,0.9540742,0.0001598795,0.0003358236,0.0009215252,0.00001881939,0.0002412686,0.01294927],"genre_scores_gemma":[0.9307245,0.000005172716,0.06855341,0.0005689256,0.00002045398,0.00007765043,0.00002588629,0.000002165509,0.00002184835],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9289122,"threshold_uncertainty_score":0.9643398,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005937943,0.0001184956,0.0001551279,0.0004482252,0.00007559639,0.000465679,0.0005679903,0.00005100502,0.00001542854],"category_scores_gemma":[0.00003178,0.00009693004,0.0000305133,0.001840076,0.00001422447,0.0008037492,0.0001855421,0.0001464981,0.0001791957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001682505,"about_ca_system_score_gemma":0.00009797532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006081023,"about_ca_topic_score_gemma":0.000005542781,"domain_scores_codex":[0.9982157,0.00007006828,0.0004209343,0.0002409673,0.0006259906,0.0004263072],"domain_scores_gemma":[0.9993774,0.00004630309,0.00006371542,0.0002993821,0.00009726055,0.0001159232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001310144,0.0009446028,0.03949077,0.0003467866,0.0000204919,0.00007653835,0.005873256,0.06617916,0.0005810781,0.8537304,0.01080534,0.02182061],"study_design_scores_gemma":[0.001714363,0.0001734378,0.05089711,0.00005656174,0.0000043026,0.00004152085,0.0006535726,0.9365571,0.0006577121,0.0006479091,0.008030144,0.0005663071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1624321,0.0000334176,0.7971647,0.0002527313,0.0002112937,0.0008631374,0.00000150041,0.000173594,0.03886753],"genre_scores_gemma":[0.987642,0.000001258178,0.008316522,0.0001741157,0.00002799072,0.00002080452,0.000005347029,0.000005220236,0.003806765],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8703779,"threshold_uncertainty_score":0.4490553,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001427349,0.00005133774,0.0001292316,0.0001731918,0.00006241751,0.0001306477,0.0002134361,0.00001802062,0.000002575471],"category_scores_gemma":[0.0002159055,0.00003179842,0.00003141678,0.0002483873,0.00006290906,0.003224635,0.00005223515,0.0001618335,0.000002297243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006676501,"about_ca_system_score_gemma":0.00002849392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002380793,"about_ca_topic_score_gemma":0.000006398002,"domain_scores_codex":[0.9987767,0.0001756351,0.0004771699,0.00003633308,0.0004549877,0.00007919782],"domain_scores_gemma":[0.998774,0.0002727335,0.0003721009,0.0000693539,0.0004877837,0.00002403826],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0009950418,0.0002756212,0.01584713,0.0002819882,0.0001502934,0.000009071244,0.6232991,0.000624619,0.007028828,0.1085626,0.0006075019,0.2423183],"study_design_scores_gemma":[0.01007195,0.003779277,0.5784203,0.0005824956,0.00007790125,0.0003260365,0.2610133,0.08098947,0.04879327,0.01400438,0.001470424,0.0004711682],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9722354,0.00003050514,0.02648447,0.0009313315,0.0001056816,0.0001241878,0.000001583042,0.000003020256,0.00008377367],"genre_scores_gemma":[0.9982427,0.00004668613,0.001471455,0.0002140759,0.00001903491,6.566057e-7,0.000002360562,7.95225e-7,0.00000225863],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5625732,"threshold_uncertainty_score":0.2337783,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003111621,0.0002111822,0.0001963881,0.0002807199,0.0001888048,0.0001481292,0.001426067,0.0002329551,0.00006751197],"category_scores_gemma":[0.00001746133,0.0002249446,0.0001543405,0.0004916166,0.00006898494,0.0008209433,0.001304281,0.0005138493,0.0003922268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001567726,"about_ca_system_score_gemma":0.0001814497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001087654,"about_ca_topic_score_gemma":0.000008057721,"domain_scores_codex":[0.9987226,0.00009170674,0.0002036163,0.0005466917,0.0001359596,0.0002994383],"domain_scores_gemma":[0.9985375,0.00002605496,0.0002238825,0.0008020629,0.0002800626,0.0001304118],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001200419,0.0002982292,0.003574438,0.0003136004,0.0001309976,0.0005263006,0.003729965,0.02766639,0.000488341,0.928011,0.0004699066,0.03467077],"study_design_scores_gemma":[0.0006589247,0.0001040308,0.004088652,0.0001047196,0.00006458268,0.00001359407,0.00004875093,0.9174299,0.003322742,0.07247823,0.0008895947,0.000796331],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1289704,0.000009490028,0.8636357,0.00003745,0.0005316574,0.0003228885,0.000003914083,0.0002753346,0.006213206],"genre_scores_gemma":[0.9967715,0.00002596632,0.001701199,0.00007433034,0.00004566749,0.000001053799,0.00002107403,0.000008637173,0.001350581],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8897635,"threshold_uncertainty_score":0.9172974,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003326976,0.00007770459,0.00007570891,0.00005563377,0.0001198048,0.00007471038,0.0003997546,0.00003954223,0.00001492368],"category_scores_gemma":[0.00004909343,0.00005987996,0.00005918014,0.0001587296,0.00001603762,0.00155604,0.00006013006,0.00006657745,0.0000880759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002742766,"about_ca_system_score_gemma":0.00008364383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000202152,"about_ca_topic_score_gemma":8.739795e-7,"domain_scores_codex":[0.9991425,0.00001071086,0.0001541063,0.0001090465,0.0002312807,0.0003523191],"domain_scores_gemma":[0.9993637,0.00006074139,0.00003770348,0.0002831504,0.0001244141,0.0001303342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000431224,0.0003078774,0.001678563,0.00009052997,0.000006640803,4.12519e-7,0.001490176,0.004115114,0.001428215,0.9226785,0.008136636,0.06002427],"study_design_scores_gemma":[0.0002681243,0.00003140011,0.0003082892,0.000002917898,0.000001766133,0.00000114084,0.00000468953,0.9864953,0.007098031,0.0009757636,0.004705801,0.0001068142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008253768,0.00000928788,0.9877173,0.0007668509,0.0001313152,0.0003203025,0.000004036366,0.0001743875,0.002622806],"genre_scores_gemma":[0.5892619,9.529289e-7,0.4067216,0.001237937,0.00003612628,0.00006370916,0.000003652671,0.000004158265,0.002669902],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9823802,"threshold_uncertainty_score":0.2441834,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001080183,0.00008070714,0.0001103985,0.0003477609,0.0003052652,0.0001939361,0.0004489345,0.00006410682,0.000004722667],"category_scores_gemma":[0.000250654,0.00007062966,0.00004330418,0.0008729079,0.00001132392,0.001840704,0.0002565903,0.0001686019,0.00001846327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008020515,"about_ca_system_score_gemma":0.00005032499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001273669,"about_ca_topic_score_gemma":4.586656e-7,"domain_scores_codex":[0.9988046,0.00003199366,0.0002830684,0.0001322914,0.0004402437,0.0003078498],"domain_scores_gemma":[0.9995488,0.00003582087,0.00005880712,0.0001170749,0.000109927,0.0001295701],"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":[0.0002724684,0.0004181645,0.004505234,0.0001435524,0.00001022244,0.000004664786,0.08598507,0.001754397,0.0007748854,0.1094901,0.0006626667,0.7959785],"study_design_scores_gemma":[0.00115955,0.0004667993,0.01034168,0.00002572567,0.000002471922,0.000008142272,0.0003511666,0.9831022,0.0007148873,0.0008114285,0.002791773,0.000224147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04096011,8.835385e-7,0.9527091,0.000982244,0.00005310341,0.0005207351,7.406696e-7,0.0001339114,0.004639123],"genre_scores_gemma":[0.9187841,3.699304e-7,0.08053049,0.0005856578,0.0000194472,0.000004475717,0.00001454742,0.000001251346,0.00005965021],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9813479,"threshold_uncertainty_score":0.2880194,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005714427,0.0000952207,0.00008164852,0.00007275992,0.0001854558,0.000066835,0.0008775347,0.00005439701,0.0001335377],"category_scores_gemma":[0.000697594,0.00004885896,0.00007907953,0.000282668,0.00004792056,0.0004752442,0.0002151672,0.00023687,0.0001903771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000289759,"about_ca_system_score_gemma":0.0000286004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002286465,"about_ca_topic_score_gemma":0.00000392726,"domain_scores_codex":[0.9989135,0.00005869164,0.0002940682,0.0001462643,0.0003950512,0.0001923826],"domain_scores_gemma":[0.9978141,0.0007336983,0.0002211081,0.001054947,0.0001418811,0.00003429969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006301181,0.0009088526,0.008691542,0.0000307416,0.0001214164,0.00007844019,0.01703345,0.009924971,0.002177711,0.5349891,0.05351597,0.3718976],"study_design_scores_gemma":[0.001290452,0.002289847,0.1529462,0.0004324206,0.00005947477,0.0001076907,0.004207219,0.4521331,0.2254675,0.0589851,0.1008309,0.00125014],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8781482,0.000009040293,0.07114058,0.01933846,0.001905116,0.0008807002,0.000004454383,0.0001699477,0.02840353],"genre_scores_gemma":[0.9975439,0.000002916856,0.0003261895,0.001063239,0.00002762729,0.00001556126,0.000002997514,0.000004721941,0.001012806],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.476004,"threshold_uncertainty_score":0.2446975,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001930998,0.00005820594,0.00007553308,0.00007266951,0.000118969,0.0002063808,0.0002092739,0.00005728098,0.0000206019],"category_scores_gemma":[0.0002726969,0.0000503968,0.00003714559,0.0001913098,0.00009592762,0.002761699,0.00004847725,0.0000870203,0.00002098593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009563576,"about_ca_system_score_gemma":0.00009871759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004704238,"about_ca_topic_score_gemma":0.00005265773,"domain_scores_codex":[0.9989694,0.00002496466,0.0003185104,0.00008493639,0.000477212,0.0001249339],"domain_scores_gemma":[0.998844,0.00008057685,0.00009695977,0.0001778993,0.0007588587,0.00004165886],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001488396,0.00001406113,0.000006139953,0.000007031804,0.000002502917,2.75796e-8,0.000528876,0.000038605,0.003750851,0.7896446,0.000012155,0.2059803],"study_design_scores_gemma":[0.00007369622,0.0001781936,0.0002084514,0.000007760588,0.00002386083,0.000003334905,0.0002404679,0.2896822,0.5024339,0.2039177,0.003100448,0.000129982],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2678267,0.00001164658,0.7283528,0.0003851154,0.0005357733,0.0004692393,0.0000116559,0.00003210266,0.002374971],"genre_scores_gemma":[0.9952688,0.000003520725,0.004515744,0.0001431238,0.00003592514,0.0000110162,0.000008169855,0.000001501804,0.00001219499],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7274421,"threshold_uncertainty_score":0.2055122,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["bibliometrics","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["scholarly_communication","insufficient_payload"],"category_scores_codex":[0.01709403,0.000194161,0.0001799286,0.004187442,0.004079244,0.008652079,0.005600144,0.0001139554,0.001720333],"category_scores_gemma":[0.003480508,0.0001401996,0.00007614146,0.02229653,0.0009188993,0.1056146,0.00269081,0.001347117,0.02400227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002762504,"about_ca_system_score_gemma":0.002343809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005398616,"about_ca_topic_score_gemma":0.000002112072,"domain_scores_codex":[0.9889911,0.0004909071,0.0009910592,0.0003652731,0.007480478,0.001681185],"domain_scores_gemma":[0.9943852,0.0004590668,0.0001565314,0.001492507,0.002716643,0.00079002],"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":[0.00007669896,0.00003234584,0.0004233944,0.00002351274,0.000004295488,0.000002040174,0.01730069,0.0005356512,0.00007762725,0.1203206,0.6375679,0.2236352],"study_design_scores_gemma":[0.0002049027,0.0001647896,0.006205012,0.00001596143,6.702318e-7,0.00002693828,0.00296051,0.01828965,0.001031448,0.0005885085,0.9703268,0.0001847642],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.04238926,0.00003769139,0.08729023,0.4236799,0.005276751,0.004445142,0.00003595075,0.0008722893,0.4359728],"genre_scores_gemma":[0.8467503,0.001221349,0.03272791,0.03088647,0.05480909,0.001468162,0.0004041089,0.00007251073,0.03166015],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.804361,"threshold_uncertainty_score":0.9997801,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00005521019,0.00001955137,0.00001821082,0.0000245545,0.00002294705,0.00002470208,0.0002430557,0.000009586455,0.000603832],"category_scores_gemma":[0.000002357484,0.00001339065,0.00001294405,0.00007842109,0.000006802627,0.0004118577,0.00005557772,0.00002191992,0.001148746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002797331,"about_ca_system_score_gemma":0.00000882453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001056785,"about_ca_topic_score_gemma":4.094882e-7,"domain_scores_codex":[0.9997586,0.000003923236,0.00004809897,0.0000393337,0.00007764965,0.00007236365],"domain_scores_gemma":[0.9998044,0.000002680315,0.000006664357,0.0001266208,0.00002777881,0.00003182429],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000001317461,0.0000250513,0.0012269,0.000001284577,0.000001341241,0.000004633089,0.002117644,4.545258e-8,0.0001051408,0.915329,0.002924462,0.07826313],"study_design_scores_gemma":[0.001197601,0.0005898807,0.5311429,0.000009571638,0.000005668934,0.00008901938,0.0002740601,0.0469219,0.2128911,0.03954592,0.1664176,0.0009148171],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008993495,0.000001073544,0.6093306,0.00009296815,0.00008757684,0.00002671947,7.81564e-8,0.0001036948,0.3813638],"genre_scores_gemma":[0.9224865,6.107753e-7,0.0710454,0.0008289649,0.000007644439,0.000002363343,1.727556e-7,8.465066e-7,0.005627519],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.913493,"threshold_uncertainty_score":0.999629,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0005132779,0.0001564315,0.0002309509,0.0001929212,0.0001630872,0.004325103,0.001016641,0.0001080255,0.00001637531],"category_scores_gemma":[0.003395339,0.0001174804,0.0000698603,0.0004275448,0.0002586285,0.04270484,0.0004734685,0.0001909408,0.000007584359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004097367,"about_ca_system_score_gemma":0.0001226183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008234042,"about_ca_topic_score_gemma":0.000005299723,"domain_scores_codex":[0.9986141,0.00001792378,0.0004732722,0.0001362881,0.0004696123,0.000288836],"domain_scores_gemma":[0.9710596,0.00006801851,0.0005716812,0.000118525,0.02807211,0.0001100431],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00007777546,0.00009945336,0.5388659,0.0008924939,0.00009413805,1.379581e-7,0.2041283,0.00002793714,0.0109212,0.1291563,0.009457024,0.1062794],"study_design_scores_gemma":[0.0007841026,0.0004823429,0.8748888,0.0002919163,0.00004009218,0.00005304739,0.009491333,0.02505286,0.05037129,0.00828454,0.02975684,0.000502827],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9916632,0.00001249552,0.001942648,0.001193267,0.00005941403,0.0003707143,0.00001503916,0.00006886382,0.004674317],"genre_scores_gemma":[0.99813,0.00003318594,0.001097891,0.0002002751,0.00002356401,0.0000321505,0.000002421395,0.000004921412,0.0004756017],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3360229,"threshold_uncertainty_score":0.9967085,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002562703,0.00006186879,0.00006962365,0.00008061174,0.00008178514,0.0001493822,0.0004244422,0.0000365298,0.001623583],"category_scores_gemma":[0.00001476519,0.00004905097,0.00003601531,0.0002135711,0.00001576792,0.001107974,0.0001501696,0.00008263139,0.01886663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003686298,"about_ca_system_score_gemma":0.00005406741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006331765,"about_ca_topic_score_gemma":6.948941e-7,"domain_scores_codex":[0.9992408,0.00001608728,0.000149354,0.0001058314,0.0002613064,0.0002266809],"domain_scores_gemma":[0.9995751,0.00002672525,0.00002640521,0.0002220067,0.00005982259,0.00008987483],"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":[0.00002245958,0.0001982745,0.0006586493,0.00001440331,0.00002015868,0.00002001378,0.002592053,0.0003521114,0.008989175,0.1358515,0.1355406,0.7157406],"study_design_scores_gemma":[0.0004335929,0.00009936959,0.002386385,0.00001075431,0.000002656682,0.00003114869,0.000007828607,0.6567092,0.02501553,0.0004753373,0.3144835,0.0003446852],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.07172827,0.00002730964,0.2929491,0.01204876,0.0002207602,0.0003797587,0.000003369146,0.001388828,0.6212539],"genre_scores_gemma":[0.467304,0.00000723573,0.1666131,0.01153158,0.0004435446,0.00001692669,0.00001740921,0.00001795239,0.3540483],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7153959,"threshold_uncertainty_score":0.9992891,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002726625,0.0000651695,0.0001474147,0.0004129865,0.0001617023,0.0001024553,0.001132893,0.00002104309,0.000002223519],"category_scores_gemma":[0.0002761797,0.00003318952,0.0000723329,0.001255234,0.0001441926,0.006324191,0.0001482422,0.000144376,0.000003965046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005697185,"about_ca_system_score_gemma":0.0002280916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000140655,"about_ca_topic_score_gemma":7.209104e-7,"domain_scores_codex":[0.9973434,0.00007182809,0.0007716775,0.00004418324,0.001648515,0.000120372],"domain_scores_gemma":[0.9978105,0.00008901306,0.001072411,0.0002792479,0.0007074693,0.00004128879],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00104603,0.002207256,0.4318886,0.0005411202,0.00004313604,0.00001441536,0.06586263,0.02771747,0.08485121,0.0372624,0.001566764,0.346999],"study_design_scores_gemma":[0.001321127,0.003168749,0.767946,0.000101976,0.000007716056,0.00004861103,0.000425708,0.004326132,0.2224205,0.00008229868,0.00006932757,0.00008177988],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9915966,0.000001600804,0.006796835,0.00007257122,0.0002686228,0.0002679055,7.976279e-7,0.000005409905,0.0009896737],"genre_scores_gemma":[0.9994965,7.197254e-7,0.0004465972,0.00003351617,0.00001135054,0.000001533731,8.740068e-8,6.444731e-7,0.00000906662],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3469172,"threshold_uncertainty_score":0.4584886,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005125868,0.0001681493,0.0001563692,0.0007177205,0.0003129271,0.000429317,0.0005232611,0.0001132209,0.00003617468],"category_scores_gemma":[0.0002542534,0.0001590991,0.00002580514,0.001838709,0.0001467141,0.003771929,0.00006972671,0.0002830768,0.0002268301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002215176,"about_ca_system_score_gemma":0.0003726577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004624862,"about_ca_topic_score_gemma":0.000006946223,"domain_scores_codex":[0.9983349,0.00008222531,0.0005606762,0.0002067562,0.0005361529,0.0002792206],"domain_scores_gemma":[0.9985917,0.0001246762,0.0002140217,0.0003361478,0.0006046116,0.0001288788],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000004344172,0.0002108258,0.9038705,0.000005663811,0.000001265097,3.417504e-7,0.0104578,1.787873e-7,0.00002513814,0.009918164,0.0002434646,0.07526228],"study_design_scores_gemma":[0.000374215,0.00006757932,0.9971925,0.00005068448,0.00000971803,0.000008029219,0.0008423819,0.0001035287,0.0001219169,0.0006880482,0.0003569211,0.0001844767],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9863663,0.00001340489,0.008852172,0.0007566981,0.0009008576,0.0006671855,0.000007266549,0.00008932638,0.002346791],"genre_scores_gemma":[0.994686,9.101723e-7,0.004388761,0.0002153071,0.0001603171,0.0001883482,0.00006596183,0.000007089878,0.0002873091],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09332196,"threshold_uncertainty_score":0.6487871,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001076175,0.00005311563,0.00004956354,0.00008747909,0.0001544484,0.00005163485,0.0002017447,0.0000167141,0.0001770034],"category_scores_gemma":[0.00003128631,0.00003598621,0.00001878094,0.0003741072,0.00001338935,0.0005030555,0.0000791043,0.00009520283,0.0008364824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001750419,"about_ca_system_score_gemma":0.00003621958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001323861,"about_ca_topic_score_gemma":0.0000338141,"domain_scores_codex":[0.9994763,0.00001841408,0.00007688125,0.0001133065,0.0001621606,0.0001529635],"domain_scores_gemma":[0.9995801,0.00002544815,0.00001755729,0.000145542,0.0001373329,0.00009405617],"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":[0.000596776,0.0005870826,0.2336237,0.00002721189,0.0001101521,0.00006344467,0.1940706,0.001884981,0.002786305,0.09554356,0.005172526,0.4655337],"study_design_scores_gemma":[0.002820812,0.004848082,0.8094293,0.00003511319,0.0000202185,0.00008375565,0.009675405,0.08431771,0.04459678,0.0003045846,0.04278858,0.001079699],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1062339,7.14305e-7,0.8351648,0.00008854316,0.00007239264,0.0001467302,4.15776e-7,0.0002026582,0.05808976],"genre_scores_gemma":[0.951319,2.434075e-7,0.04104467,0.00021051,0.000008979457,0.00001839363,7.850804e-7,0.000002492728,0.007394905],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8450851,"threshold_uncertainty_score":0.9999415,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1503824486","doi":"10.1023/a:1023936321956","title":"Query Expansion with Long-Span Collocates","year":2003,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Microsoft Research","keywords":"Collocation (remote sensing); Computer science; Window (computing); Information retrieval; Mathematics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.009880289279499396,"gpt":0.2239308871336277,"spread":0.2140505978541283,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005693992,0.0001714368,0.0001539137,0.0002843468,0.0002626609,0.0004917196,0.0004483455,0.00009944453,0.0001007315],"category_scores_gemma":[0.0001565168,0.000131152,0.00005450564,0.001132674,0.00006208379,0.006169804,0.00006504168,0.0001985593,0.0007388521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000921547,"about_ca_system_score_gemma":0.0003377448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009464384,"about_ca_topic_score_gemma":0.000001859468,"domain_scores_codex":[0.9981608,0.00006013302,0.0004603011,0.0001324086,0.0008290841,0.0003572848],"domain_scores_gemma":[0.9986442,0.00006251842,0.0001920389,0.0004332163,0.0004934813,0.0001745135],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001185887,0.0005615865,0.02854419,0.0005410814,0.0001848769,0.0001046682,0.03103234,0.007450412,0.001013661,0.6845196,0.01275044,0.2321112],"study_design_scores_gemma":[0.01129591,0.003960942,0.07571846,0.0003009606,0.00007388744,0.001205494,0.003431266,0.1154809,0.2728475,0.002278146,0.5098674,0.003539114],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1789887,0.00002441738,0.80165,0.0003841164,0.000410167,0.0005313431,0.000007018786,0.0003995154,0.01760468],"genre_scores_gemma":[0.9913939,0.00001206317,0.00714157,0.0008805265,0.00001788861,0.00001198678,0.00003398614,0.000006365418,0.0005017775],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8124051,"threshold_uncertainty_score":0.9496695,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004492154,0.0001398455,0.000230866,0.0003901579,0.0001564606,0.0002850004,0.001288528,0.00002605032,0.0001414546],"category_scores_gemma":[0.00001922158,0.0001107773,0.0001658632,0.0002372157,0.0000754819,0.001519085,0.0001944486,0.000235275,0.0001270156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001331347,"about_ca_system_score_gemma":0.00006338211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003231725,"about_ca_topic_score_gemma":0.000005897507,"domain_scores_codex":[0.9979816,0.00005535722,0.0006880147,0.0001379232,0.0009539394,0.0001831541],"domain_scores_gemma":[0.9982111,0.000121725,0.0003052897,0.0001575586,0.001128992,0.00007526913],"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":[0.0001722392,0.0005845166,0.007548861,0.00005150806,0.001642731,0.001188718,0.01729749,0.002561827,0.0008343873,0.05511813,0.0881401,0.8248595],"study_design_scores_gemma":[0.01382888,0.003255233,0.08614942,0.002404553,0.0001693813,0.003006997,0.0008752862,0.06319448,0.01359471,0.04193487,0.7691901,0.002396038],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9230189,0.0008135634,0.05715291,0.007344116,0.005746778,0.0001864434,0.000006930522,0.0001327981,0.005597591],"genre_scores_gemma":[0.9742267,0.0002120455,0.02040848,0.001395478,0.001227439,0.000003881753,0.000004520433,0.000008600917,0.002512873],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8224635,"threshold_uncertainty_score":0.4517366,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002549531,0.00006200956,0.00006963671,0.00004624907,0.00008148774,0.0002298624,0.0003427567,0.00002677561,0.0001213537],"category_scores_gemma":[0.00005596432,0.00004323698,0.00005448198,0.00009557336,0.00001633189,0.0008919853,0.0001166672,0.00005442177,0.0002951525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003704543,"about_ca_system_score_gemma":0.00001978247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006927198,"about_ca_topic_score_gemma":0.000004317937,"domain_scores_codex":[0.9993942,0.00002440557,0.0001189357,0.0001126532,0.0001767702,0.0001730467],"domain_scores_gemma":[0.9993944,0.00008905102,0.00002396386,0.0001834988,0.0002383143,0.0000708408],"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":[0.000009611641,0.00006718978,0.0006413017,0.00002596769,0.00001886852,5.81083e-7,0.001033752,0.00001261156,0.001014611,0.1040989,0.02052226,0.8725543],"study_design_scores_gemma":[0.003929612,0.002380384,0.1042845,0.0000538416,0.00002466211,0.00002018169,0.0004278643,0.3093754,0.2934055,0.08861033,0.1961556,0.001332182],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0160094,0.000004528418,0.9765486,0.001534173,0.0001749458,0.0009691737,9.570191e-7,0.0001141691,0.004644125],"genre_scores_gemma":[0.9677365,0.000001094218,0.02921752,0.0009842913,0.00002562782,0.0003627199,0.000001737381,0.000002589975,0.001667948],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9517271,"threshold_uncertainty_score":0.3793687,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001219324,0.0001995351,0.0002320358,0.0005481443,0.0006910927,0.001033953,0.0008097646,0.000172139,0.000008193233],"category_scores_gemma":[0.0005072763,0.0001861337,0.000150792,0.0006404936,0.00002262715,0.01058997,0.00001730006,0.000226946,0.0004595486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002600379,"about_ca_system_score_gemma":0.0001402956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003348617,"about_ca_topic_score_gemma":0.000001903244,"domain_scores_codex":[0.9975811,0.00007875726,0.001101554,0.0001327279,0.0007431466,0.000362731],"domain_scores_gemma":[0.9975281,0.0002702194,0.000313877,0.0007488562,0.0009936354,0.0001453374],"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":[0.0001217862,0.0001196922,0.00003975174,0.0004687152,0.00007453164,9.868288e-8,0.008178724,0.7106193,0.00003578198,0.1523962,0.0005112718,0.1274341],"study_design_scores_gemma":[0.0009147583,0.0001905312,0.0001576936,0.00003878732,0.0000172248,0.000007081514,0.0002538302,0.9852974,0.0001616613,0.0007059237,0.01199703,0.0002580488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003204045,0.000002462561,0.9919385,0.0004732589,0.0011338,0.001287036,0.0001477747,0.0004174098,0.001395737],"genre_scores_gemma":[0.9880298,0.000005046729,0.01077511,0.0004752988,0.00006085423,0.0002938729,0.0002447093,0.00000764164,0.0001076571],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9848258,"threshold_uncertainty_score":0.9970433,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["bibliometrics","sts","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.01615966,0.0001325364,0.000157619,0.002819717,0.001430266,0.002495141,0.005277521,0.0001092951,0.00008371569],"category_scores_gemma":[0.007287004,0.0001201696,0.00001887114,0.02157056,0.001023569,0.06620374,0.002369811,0.0006916339,0.0005627469],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002113592,"about_ca_system_score_gemma":0.006071931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008087862,"about_ca_topic_score_gemma":0.000002250811,"domain_scores_codex":[0.9947984,0.0003839592,0.0006785523,0.0004611614,0.002438814,0.001239157],"domain_scores_gemma":[0.9943826,0.0006796586,0.0000926326,0.001425092,0.00307664,0.0003433742],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000110484,0.00007733337,0.0009277197,0.00004479725,0.000001612373,9.334842e-7,0.02185646,0.0004485267,0.0006962748,0.9580711,0.007329999,0.01053422],"study_design_scores_gemma":[0.000651359,0.0000956728,0.0008095389,0.00003657518,6.019753e-7,0.000008571275,0.003631161,0.9412885,0.0109803,0.004542595,0.03773674,0.0002183389],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09560639,0.0001162473,0.8288856,0.00377232,0.0005222504,0.003592222,0.0001150092,0.0005193027,0.06687064],"genre_scores_gemma":[0.9586664,0.00006805937,0.03982745,0.0002249215,0.00003731458,0.00006577219,0.0001694909,0.00001422805,0.0009263604],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9535285,"threshold_uncertainty_score":0.9998698,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003330251,0.0002335824,0.0003507728,0.001021365,0.0002349686,0.001060002,0.001025725,0.0001400995,0.00001165247],"category_scores_gemma":[0.000324921,0.0001759787,0.0001639579,0.000845939,0.00002021695,0.01362536,0.00004545123,0.000442225,0.0005271869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005164701,"about_ca_system_score_gemma":0.0004112405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003750504,"about_ca_topic_score_gemma":3.027093e-8,"domain_scores_codex":[0.9947683,0.0001504261,0.002383783,0.00008453657,0.002273022,0.0003399839],"domain_scores_gemma":[0.994579,0.0001293947,0.002074435,0.0004470187,0.002557389,0.0002128037],"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":[0.001431538,0.0002014275,0.0006872615,0.001172991,0.00006410896,0.000008470997,0.009247165,0.5522454,0.0002440872,0.08408574,0.003191887,0.3474199],"study_design_scores_gemma":[0.0008642125,0.002209312,0.002117003,0.0007444338,0.00001372832,0.0001683873,0.0008880615,0.972643,0.004445682,0.000009154788,0.01563407,0.0002629306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1092518,0.00002926483,0.87791,0.0002909479,0.002256649,0.0007900308,0.00001070108,0.0001650333,0.009295506],"genre_scores_gemma":[0.9951518,0.00001758853,0.004027694,0.000623383,0.0001039476,0.000005011333,0.00001647634,0.000003383907,0.00005070103],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8859,"threshold_uncertainty_score":0.999977,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006232847,0.0001149469,0.000173333,0.0001446847,0.0001818132,0.0003375967,0.0003203077,0.00004947987,0.00006239542],"category_scores_gemma":[0.00005779899,0.00009016228,0.00006661979,0.0004650504,0.00001581663,0.0008456431,0.00009515354,0.00007845271,0.0003076569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008525179,"about_ca_system_score_gemma":0.0001124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001532879,"about_ca_topic_score_gemma":0.00002467858,"domain_scores_codex":[0.9985248,0.00006553107,0.0003741098,0.0002219814,0.0005374302,0.000276113],"domain_scores_gemma":[0.99914,0.00004590485,0.00007693517,0.0002901282,0.0003575245,0.00008948087],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006752491,0.0005808244,0.0007956347,0.00003851559,0.0000678905,0.00005487754,0.001452008,0.1571144,0.3371141,0.1947639,0.02499033,0.2823523],"study_design_scores_gemma":[0.00259636,0.0000586599,0.0006028269,0.000005081906,0.000005850667,0.000008045408,0.000007518536,0.9775915,0.01686506,0.0002923041,0.00180488,0.0001619058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1924775,0.0000220195,0.8026686,0.0006521158,0.0003317473,0.0004838047,0.000001427808,0.0001026181,0.003260122],"genre_scores_gemma":[0.518294,0.000005497152,0.4705709,0.001527647,0.0004803836,0.00004928166,0.00001393882,0.00001156836,0.009046777],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8204771,"threshold_uncertainty_score":0.3954409,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}