{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":516,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":516,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"3f3b637c43c3","filters":{"topic":"Spam and Phishing Detection"}},"results":[{"id":"W2252350410","doi":"10.1002/pra2.2015.145052010083","title":"Deception detection for news: Three types of fakes","year":2015,"lang":"en","type":"article","venue":"Proceedings of the Association for Information Science and Technology","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":544,"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; Government of Canada","keywords":"Vetting; Deception; Fake news; Computer science; Internet privacy; Disinformation; Data science; Social media; World Wide Web; Computer security; Political science; Law","authors":[{"name":"Victoria L. Rubin","is_ca":true},{"name":"Yimin Chen","is_ca":true},{"name":"Nadia Conroy","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01534788402570559,"gpt":0.2358418938291395,"spread":0.2204940098034339,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00592775,0.0007097797,0.001015947,0.00536254,0.002727857,0.004642198,0.001018435,0.00276194,0.002640979],"category_scores_gemma":[0.06971049,0.000527368,0.000834035,0.003125269,0.002750675,0.004826812,0.002350623,0.001995631,0.0009685696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001243623,"about_ca_system_score_gemma":0.0005459472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001656028,"about_ca_topic_score_gemma":0.001164706,"domain_scores_codex":[0.9885228,0.003329352,0.001412142,0.00112278,0.004922982,0.0006901036],"domain_scores_gemma":[0.8669606,0.08348106,0.01856619,0.01780226,0.01149926,0.001690592],"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":[0.005601092,0.0011432,0.4233256,0.002313185,0.0004633405,0.0101161,0.01793971,0.009817447,0.02166732,0.04351357,0.0204163,0.4436832],"study_design_scores_gemma":[0.0002655272,0.001846728,0.4529537,0.001956605,0.0009596974,0.03574385,0.01246893,0.2474372,0.1150444,0.05792407,0.07268122,0.0007179676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9270408,0.002528373,0.04330077,0.002978489,0.0004049047,0.0004957669,0.00226774,0.0007728581,0.02021029],"genre_scores_gemma":[0.9800511,0.0004548791,0.01521028,0.0002788558,0.0001632608,0.0001007505,0.001010647,0.00007025837,0.002660055],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00592775,"threshold_uncertainty_score":0.03134936,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2778443828","doi":"10.1002/spy2.9","title":"Detecting opinion spams and fake news using text classification","year":2017,"lang":"en","type":"article","venue":"Security and Privacy","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":503,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor; University of Victoria","funders":"","keywords":"Fake news; Computer science; Focus (optics); Internet privacy; Presidential system; Public opinion; World Wide Web; Data science; Political science; Politics","authors":[{"name":"Hadeer Ahmed","is_ca":true},{"name":"Issa Traoré","is_ca":true},{"name":"Sherif Saad","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0725135761541275,"gpt":0.312122856613209,"spread":0.2396092804590815,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001122844,0.001287984,0.001171143,0.005320112,0.0006235556,0.001227533,0.0006048731,0.001403557,0.0009494736],"category_scores_gemma":[0.00534784,0.0002030127,0.0008016328,0.001553698,0.0003113321,0.001788943,0.0004287844,0.000660152,0.001600139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005765505,"about_ca_system_score_gemma":0.0003956134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002004053,"about_ca_topic_score_gemma":0.002060484,"domain_scores_codex":[0.9986871,0.0002846085,0.0001318791,0.0002527067,0.0005073957,0.0001363162],"domain_scores_gemma":[0.9941262,0.002510058,0.001120007,0.0003561627,0.001689295,0.0001981546],"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":[0.001218153,0.00103254,0.07366864,0.0005976283,0.0002709939,0.001131378,0.0004427395,0.008725178,0.05180514,0.001001346,0.0181583,0.841948],"study_design_scores_gemma":[0.00006627606,0.0004751673,0.06186851,0.00008944987,0.0002094233,0.001339425,0.0004429336,0.8688172,0.05635509,0.002468189,0.007786489,0.0000818604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7852532,0.00437369,0.1906399,0.001127592,0.0006178559,0.0005650162,0.003112115,0.006415693,0.007895036],"genre_scores_gemma":[0.8987901,0.0008284942,0.09158534,0.0002081997,0.0006638986,0.0001802609,0.003859043,0.00008841047,0.00379632],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005320112,"threshold_uncertainty_score":0.005938232,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1992685726","doi":"10.1145/2076732.2076746","title":"The socialbot network","year":2011,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":442,"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; Misinformation; Malware; Internet privacy; Computer security; Botnet; World Wide Web; Infiltration (HVAC); The Internet","authors":[{"name":"Yazan Boshmaf","is_ca":true},{"name":"Ildar Muslukhov","is_ca":true},{"name":"Konstantin Beznosov","is_ca":true},{"name":"Matei Ripeanu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0322584514709548,"gpt":0.1980805148913592,"spread":0.1658220634204044,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001855258,0.001015576,0.0005919359,0.002525945,0.00231244,0.003794735,0.001602166,0.002001647,0.03776576],"category_scores_gemma":[0.007944771,0.0005806352,0.0007356363,0.001497763,0.001420935,0.005751891,0.004150288,0.001459055,0.01183687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001419565,"about_ca_system_score_gemma":0.001859974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002965822,"about_ca_topic_score_gemma":0.002941791,"domain_scores_codex":[0.9975384,0.0007871177,0.0001491408,0.0005312209,0.0007340295,0.0002600692],"domain_scores_gemma":[0.9963177,0.001058594,0.0004479841,0.0009400471,0.0005179251,0.0007176928],"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":[0.0003347789,0.0004148106,0.007216961,0.000828015,0.0001153272,0.0009206163,0.001383528,0.01046923,0.005253436,0.3998609,0.2893569,0.2838454],"study_design_scores_gemma":[0.00006979536,0.0001721888,0.002103568,0.0002145674,0.00004060619,0.0008312243,0.0004422924,0.04343722,0.001502938,0.09795503,0.8531551,0.0000754675],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.05788889,0.00449883,0.3857701,0.01381501,0.003219974,0.003482403,0.01748193,0.03800725,0.4758356],"genre_scores_gemma":[0.6294968,0.004002252,0.1440759,0.005195451,0.001340434,0.003227538,0.02557927,0.002770392,0.1843121],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03776576,"threshold_uncertainty_score":0.1263391,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1804563568","doi":"10.2139/ssrn.2293164","title":"Fake it Till You Make it: Reputation, Competition, and Yelp Review Fraud","year":2013,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":294,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Quest University Canada","funders":"","keywords":"Competition (biology); Business; Reputation; Internet privacy; Reputation management; Social media; Advertising; Computer science; World Wide Web; Political science; Law","authors":[{"name":"Michael Luca","is_ca":false},{"name":"Georgios Zervas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.008152767855161105,"gpt":0.2307077264540708,"spread":0.2225549585989097,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01174535,0.0002578938,0.0007597049,0.003495384,0.002788699,0.005653611,0.001063043,0.003508484,0.01015708],"category_scores_gemma":[0.1080205,0.0003385744,0.000476886,0.003455456,0.002678118,0.00477534,0.001665484,0.002934583,0.001657854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002396715,"about_ca_system_score_gemma":0.002025994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009082372,"about_ca_topic_score_gemma":0.01215999,"domain_scores_codex":[0.994258,0.003104457,0.000311857,0.0003794349,0.001024767,0.0009214392],"domain_scores_gemma":[0.8384525,0.08205792,0.05030433,0.005323406,0.01019618,0.01366577],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001128573,0.001341979,0.9198287,0.00007079855,0.0001589027,0.0004399912,0.002089443,0.0006028219,0.0002008477,0.008882153,0.01397977,0.05127601],"study_design_scores_gemma":[0.000126579,0.0005170561,0.9572435,0.0001214006,0.0002876585,0.0013207,0.006840666,0.01056697,0.000321944,0.01569198,0.006845091,0.0001164124],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9645362,0.001986145,0.0005824218,0.01082757,0.00008738539,0.00005199219,0.0002136992,0.00003357505,0.0216809],"genre_scores_gemma":[0.9980102,0.0002178158,0.00008476571,0.0003481501,0.0000994506,0.00001006097,0.00005938229,0.000006403179,0.001163642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01174535,"threshold_uncertainty_score":0.06211609,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2130852771","doi":"10.1509/jmr.13.0209","title":"Reviews without a Purchase: Low Ratings, Loyal Customers, and Deception","year":2014,"lang":"en","type":"article","venue":"Journal of Marketing Research","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":290,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Deception; Purchasing; Business; Product (mathematics); Marketing; Incentive; Advertising; Phenomenon; Psychology; Economics; Microeconomics; Social psychology","authors":[{"name":"Eric T. Anderson","is_ca":true},{"name":"Duncan Simester","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03781754249532004,"gpt":0.3438654773554673,"spread":0.3060479348601473,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002848988,0.0002698471,0.0004801363,0.001725106,0.001007733,0.002645335,0.0004085921,0.001385688,0.002530189],"category_scores_gemma":[0.05601606,0.0002930902,0.0002040934,0.001142629,0.0009593391,0.001848367,0.0008737926,0.001417471,0.0009140504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005590778,"about_ca_system_score_gemma":0.000276011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001825746,"about_ca_topic_score_gemma":0.002310823,"domain_scores_codex":[0.9960715,0.001348496,0.0004653778,0.0003382425,0.001533498,0.0002429585],"domain_scores_gemma":[0.8907838,0.04257916,0.05055376,0.003874186,0.009203034,0.003006127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000500229,0.0003296176,0.9142843,0.0001688193,0.0001122814,0.00169204,0.003508321,0.000173405,0.001362599,0.001098375,0.006017607,0.07075231],"study_design_scores_gemma":[0.00002576426,0.0004491346,0.968376,0.0001422721,0.0001934958,0.01151091,0.004464093,0.00459991,0.001806314,0.001984238,0.006379519,0.00006839161],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9822199,0.001318438,0.001308458,0.003056508,0.0000811772,0.00003008774,0.0002021369,0.00005294435,0.01173039],"genre_scores_gemma":[0.9983574,0.0001872073,0.0002578649,0.0003149898,0.00007743793,0.000005541292,0.00006920234,0.000007364651,0.0007230662],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002848988,"threshold_uncertainty_score":0.01506704,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1685426458","doi":"10.1007/s10791-011-9162-z","title":"Efficient and effective spam filtering and re-ranking for large web datasets","year":2011,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":277,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"National Institute of Standards and Technology","keywords":"Computer science; Information retrieval; Ranking (information retrieval); Relevance feedback; Relevance (law); Search engine; Learning to rank; Set (abstract data type); Honeypot; Web page; Rank (graph theory); Data mining; World Wide Web; Artificial intelligence; Image retrieval; Mathematics","authors":[{"name":"Gordon V. Cormack","is_ca":true},{"name":"Mark D. Smucker","is_ca":true},{"name":"Charles L. A. Clarke","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01549341487547832,"gpt":0.2325380502429347,"spread":0.2170446353674564,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004885714,0.001951224,0.00350499,0.008493712,0.001982605,0.00349207,0.002250577,0.002585345,0.002198454],"category_scores_gemma":[0.01644396,0.001046922,0.001901199,0.006012437,0.0007814644,0.005201903,0.001972395,0.001663329,0.003654731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001269435,"about_ca_system_score_gemma":0.003098424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007594257,"about_ca_topic_score_gemma":0.01963901,"domain_scores_codex":[0.9945162,0.001690384,0.0005396132,0.0008355431,0.00187982,0.0005383738],"domain_scores_gemma":[0.9875721,0.004589205,0.0008445789,0.003890014,0.002685506,0.0004186419],"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":[0.0005535228,0.0008198719,0.009108506,0.0005532436,0.0004130536,0.0002274252,0.0001915014,0.03147718,0.02803778,0.002556209,0.07151861,0.854543],"study_design_scores_gemma":[0.0001467948,0.0002221295,0.007561836,0.00003258008,0.000204024,0.0005167365,0.0002399054,0.9496571,0.01826344,0.01387241,0.009207196,0.00007591258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1723719,0.007815761,0.7662311,0.003053631,0.0007659636,0.0009342374,0.007597427,0.03760267,0.003627311],"genre_scores_gemma":[0.2854189,0.001133407,0.6916398,0.0004526824,0.000863334,0.0003819783,0.01340214,0.0006226762,0.006084955],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008493712,"threshold_uncertainty_score":0.02583843,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1576800334","doi":"10.2307/23043494","title":"Product-Related Deception in E-Commerce: A Theoretical Perspective1","year":2011,"lang":"en","type":"article","venue":"MIS Quarterly","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":262,"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":"Perspective (graphical); Deception; E-commerce; Product (mathematics); Business; Knowledge management; Epistemology; Psychology; Computer science; Sociology; Marketing; Social psychology; Philosophy; World Wide Web; Mathematics","authors":[{"name":"Xiao Xiao","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01259133268574586,"gpt":0.2155843724855823,"spread":0.2029930397998365,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004138971,0.0007583986,0.0005823622,0.00429185,0.002633239,0.007015861,0.001552374,0.005139053,0.003605029],"category_scores_gemma":[0.009900428,0.0005420129,0.0006147774,0.00323722,0.01789825,0.01139251,0.002941183,0.003946561,0.0005235167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00343202,"about_ca_system_score_gemma":0.0020766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002047555,"about_ca_topic_score_gemma":0.001786437,"domain_scores_codex":[0.99576,0.002562196,0.000217299,0.000294527,0.0008466683,0.0003192085],"domain_scores_gemma":[0.9756664,0.01860882,0.002435637,0.001319466,0.001624787,0.0003448145],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000008055443,0.00006827441,0.002247521,0.0001258109,0.000007454296,0.0001984538,0.004376665,0.0009562419,0.00008811989,0.9847986,0.0005904482,0.00653435],"study_design_scores_gemma":[0.00002503179,0.0001387284,0.004103524,0.001125223,0.00002775538,0.001225213,0.01122967,0.01691077,0.0005241177,0.9364699,0.02816757,0.00005247881],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1842961,0.02469733,0.3406475,0.07718585,0.0005389977,0.0003275106,0.0002540573,0.00008049241,0.3719723],"genre_scores_gemma":[0.9682392,0.009234232,0.0157424,0.001871373,0.0002705178,0.0001891686,0.00007232698,0.00001431392,0.004366506],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007015861,"threshold_uncertainty_score":0.02490115,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2953122191","doi":"10.1002/poi3.184","title":"Unpacking the Social Media Bot: A Typology to Guide Research and Policy","year":2018,"lang":"en","type":"article","venue":"Policy & Internet","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":262,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Typology; Unpacking; Politics; Social media; Public relations; Ambiguity; Face (sociological concept); Political science; Internet privacy; Sociology; Presidential system; Computer science; Law; Social science","authors":[{"name":"Robert Gorwa","is_ca":false},{"name":"Douglas Guilbeault","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1057954589323566,"gpt":0.4326620777063475,"spread":0.3268666187739909,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02262874,0.001519213,0.001465973,0.024417,0.01308615,0.02022478,0.003150506,0.009081354,0.004352793],"category_scores_gemma":[0.03283259,0.0008777977,0.0008678586,0.02141779,0.05639445,0.0546796,0.009536181,0.007472736,0.001009924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01568303,"about_ca_system_score_gemma":0.0111369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008830896,"about_ca_topic_score_gemma":0.0096886,"domain_scores_codex":[0.9792759,0.0143807,0.001663411,0.00134467,0.00212448,0.001210702],"domain_scores_gemma":[0.9603602,0.02736796,0.004409677,0.002903206,0.003408903,0.001550102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001156578,0.00003742743,0.005369946,0.0001946284,0.000007231109,0.0001857634,0.03816006,0.0005068628,0.0001141367,0.940556,0.004552299,0.01030401],"study_design_scores_gemma":[0.00001445905,0.00004524371,0.003443716,0.001964192,0.00001207682,0.0004372156,0.1720428,0.003620166,0.000229421,0.6925302,0.1255862,0.00007429501],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1538395,0.02759098,0.2248942,0.3490433,0.00266863,0.002938285,0.001995052,0.000411518,0.2366188],"genre_scores_gemma":[0.8310713,0.02561979,0.1054405,0.01596871,0.001193844,0.007228981,0.0009366927,0.0003244776,0.01221568],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.024417,"threshold_uncertainty_score":0.1196737,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4297970707","doi":"10.1561/1500000006","title":"Email Spam Filtering: A Systematic Review","year":2008,"lang":"en","type":"review","venue":"Foundations and Trends® in Information Retrieval","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":254,"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; World Wide Web","authors":[{"name":"Gordon V. Cormack","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03921906353638043,"gpt":0.3134118227029408,"spread":0.2741927591665603,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01052091,0.001762997,0.007428447,0.01842319,0.001017262,0.002832124,0.002700576,0.002803679,0.01046142],"category_scores_gemma":[0.05624134,0.00102531,0.006607707,0.01406608,0.001057323,0.003676336,0.002021892,0.001452539,0.001380797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0033008,"about_ca_system_score_gemma":0.0126718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005600766,"about_ca_topic_score_gemma":0.01454226,"domain_scores_codex":[0.9909906,0.002999418,0.003078411,0.0007152354,0.001989533,0.0002268105],"domain_scores_gemma":[0.9510706,0.03687585,0.005269426,0.00100796,0.0052904,0.0004858436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0002124087,0.00003224169,0.0006678194,0.837651,0.00439067,0.000161145,0.0003266775,0.0001381075,0.0001520989,0.0005068164,0.01013072,0.1456304],"study_design_scores_gemma":[0.0001391634,0.0001930681,0.002986412,0.8870235,0.02405658,0.0006421646,0.0002697278,0.0001208452,0.0002034083,0.0008692618,0.08344458,0.00005131925],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0003978773,0.9973227,0.0003607493,0.0004684563,0.0001523391,0.0002834407,0.0004657927,0.0000219693,0.0005266453],"genre_scores_gemma":[0.003992092,0.9930161,0.000844512,0.0009375277,0.0001336411,0.0004898342,0.0003643893,0.00001299473,0.0002087997],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01842319,"threshold_uncertainty_score":0.05564052,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2146752727","doi":"10.1109/sp.2013.41","title":"SoK: SSL and HTTPS: Revisiting Past Challenges and Evaluating Certificate Trust Model Enhancements","year":2013,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":217,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Certificate; Root certificate; Trust anchor; Computer security; World Wide Web; Certificate authority; Computational trust; Public-key cryptography; Political science; Theoretical computer science; Encryption","authors":[{"name":"Jeremy Clark","is_ca":true},{"name":"Paul C. van Oorschot","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.167586242170936,"gpt":0.3064368082939328,"spread":0.1388505661229968,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02914839,0.0007909196,0.001111446,0.003660986,0.001757877,0.005210497,0.002315197,0.002200247,0.001886814],"category_scores_gemma":[0.142677,0.000539247,0.0006584602,0.00329276,0.0047692,0.02498641,0.003989939,0.00384833,0.000990615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005315724,"about_ca_system_score_gemma":0.003678007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008239456,"about_ca_topic_score_gemma":0.006701717,"domain_scores_codex":[0.9717272,0.01385424,0.00182782,0.001630805,0.00950207,0.001457924],"domain_scores_gemma":[0.8437705,0.1060145,0.009381616,0.02033194,0.01753386,0.002967616],"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":[0.006009363,0.003262075,0.1672845,0.004784424,0.0003868888,0.0006269566,0.005089269,0.09326214,0.008223297,0.1087244,0.02077188,0.581575],"study_design_scores_gemma":[0.0004246939,0.003771479,0.04875062,0.001865486,0.0005522457,0.001435533,0.009404419,0.7922934,0.02135867,0.06814291,0.05160618,0.000394299],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"review","genre_scores_codex":[0.8401088,0.01427013,0.08919211,0.01143434,0.0008035864,0.0009874289,0.0008145085,0.002532747,0.0398564],"genre_scores_gemma":[0.9716322,0.002615733,0.02291132,0.0004016279,0.0001987905,0.00008093428,0.0006970544,0.0002120694,0.001250314],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.02914839,"threshold_uncertainty_score":0.1541532,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2158063174","doi":"10.1109/tnn.2011.2161999","title":"Textual and Visual Content-Based Anti-Phishing: A Bayesian Approach","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":197,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"","keywords":"Phishing; Computer science; Naive Bayes classifier; Artificial intelligence; Classifier (UML); Web page; Machine learning; Bayes classifier; Pattern recognition (psychology); Data mining; The Internet; Support vector machine; World Wide Web","authors":[{"name":"Haijun Zhang","is_ca":true},{"name":"Gang Liu","is_ca":false},{"name":"Tommy W. S. Chow","is_ca":false},{"name":"Wenyin Liu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04666925283207304,"gpt":0.2297973862758755,"spread":0.1831281334438024,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003855479,0.001169644,0.001791411,0.005584873,0.0009887354,0.003090116,0.002945619,0.002558383,0.00235294],"category_scores_gemma":[0.01580127,0.001226585,0.001427817,0.002460018,0.001916504,0.004796457,0.001872974,0.002177449,0.001334714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00200529,"about_ca_system_score_gemma":0.001924285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01022481,"about_ca_topic_score_gemma":0.01038655,"domain_scores_codex":[0.9970386,0.0008698393,0.0001893404,0.0005350437,0.001151774,0.0002154946],"domain_scores_gemma":[0.9937032,0.003265476,0.0007501512,0.0004916867,0.001539639,0.0002497716],"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":[0.0004646776,0.0007790254,0.01591803,0.0006122381,0.0004584243,0.0005075514,0.001222028,0.2998356,0.01718642,0.1127141,0.006139331,0.5441627],"study_design_scores_gemma":[0.00001808386,0.00008083443,0.002410674,0.00007697182,0.00006813858,0.000205456,0.00007970851,0.9457555,0.001948621,0.04708703,0.002206068,0.00006295259],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00791001,0.0004718778,0.9887326,0.0005021408,0.00003182602,0.00008364209,0.0001037859,0.0003503232,0.001813765],"genre_scores_gemma":[0.4866054,0.001323424,0.5043105,0.0004877223,0.0005401519,0.0004566381,0.0005159996,0.0001729789,0.005587179],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01022481,"threshold_uncertainty_score":0.02038997,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2029677459","doi":"10.1007/s10844-013-0254-7","title":"Cost-sensitive three-way email spam filtering","year":2013,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":193,"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; Focus (optics); Set (abstract data type); Machine learning; Function (biology); Binary classification; Data mining; Binary number; Artificial intelligence; Support vector machine","authors":[{"name":"Bing Zhou","is_ca":false},{"name":"Yiyu Yao","is_ca":true},{"name":"Jigang Luo","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03493937407291117,"gpt":0.2448378195062222,"spread":0.209898445433311,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003353337,0.001208244,0.003134714,0.002288636,0.00127837,0.003343592,0.002799868,0.002890083,0.004601202],"category_scores_gemma":[0.01430804,0.0006590459,0.001369945,0.001799193,0.001139913,0.003195563,0.003486871,0.001271292,0.001544294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001724291,"about_ca_system_score_gemma":0.002002686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002631472,"about_ca_topic_score_gemma":0.00315563,"domain_scores_codex":[0.9948515,0.001334487,0.000286387,0.0006114369,0.002023914,0.0008921486],"domain_scores_gemma":[0.9884901,0.005298423,0.0008158379,0.002577049,0.00230161,0.0005170557],"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":[0.006673631,0.001373222,0.01405311,0.0005443795,0.0005004414,0.0005908735,0.0003821404,0.2933176,0.05914922,0.04230156,0.01579249,0.5653213],"study_design_scores_gemma":[0.00003519285,0.0001983401,0.002642649,0.00000976575,0.00007045316,0.0002702863,0.00005233088,0.9784757,0.008226288,0.009012884,0.0009595606,0.0000465421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3333803,0.001230676,0.6507083,0.001130058,0.0003745342,0.0002382303,0.0005548882,0.003708663,0.008674366],"genre_scores_gemma":[0.9190474,0.0001630386,0.07456764,0.0001886781,0.0001427314,0.00005550263,0.0003135121,0.0001232978,0.005398242],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004601202,"threshold_uncertainty_score":0.01773441,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1505796919","doi":"","title":"Email classification with co-training","year":2011,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":191,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Co-training; Naive Bayes classifier; Computer science; Labeled data; Support vector machine; Artificial intelligence; Training set; Machine learning; Classifier (UML); Training (meteorology); Statistical classification; Pattern recognition (psychology); Semi-supervised learning","authors":[{"name":"Svetlana Kiritchenko","is_ca":true},{"name":"Stan Matwin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1506716980756978,"gpt":0.2509912884462742,"spread":0.1003195903705764,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01247881,0.002204717,0.003294304,0.003903004,0.00172675,0.002605957,0.003416336,0.004929604,0.002747437],"category_scores_gemma":[0.03370918,0.00100083,0.001521743,0.003772663,0.001579596,0.007605765,0.004128665,0.004414296,0.003357119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001053853,"about_ca_system_score_gemma":0.001123654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002152,"about_ca_topic_score_gemma":0.003209313,"domain_scores_codex":[0.9865276,0.007393479,0.0007094234,0.002655132,0.001908637,0.0008058735],"domain_scores_gemma":[0.956349,0.02390946,0.001858896,0.009781363,0.007337625,0.0007637995],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001573097,0.001582337,0.01884098,0.0003736735,0.0003990559,0.0003426916,0.0004606642,0.1113433,0.006969549,0.003672208,0.01113405,0.8433084],"study_design_scores_gemma":[0.00005064964,0.0002200609,0.001551519,0.00003477993,0.00007276407,0.0002942915,0.00008600252,0.9784721,0.008823982,0.007953127,0.002409074,0.00003175106],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1424187,0.002228569,0.8370087,0.001548222,0.0004171625,0.0004893455,0.0004410167,0.008181345,0.007267092],"genre_scores_gemma":[0.6500786,0.0002549798,0.3418736,0.0005449341,0.0003602772,0.0004159258,0.001345972,0.0002514649,0.004874312],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01247881,"threshold_uncertainty_score":0.06599504,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2521519773","doi":"10.1007/978-3-319-46298-1_30","title":"Detecting Malicious URLs Using Lexical Analysis","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":187,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Blacklisting; Obfuscation; Malware; Set (abstract data type); Domain name; Phishing; Honeypot; Categorization; Computer security; Blacklist; World Wide Web; The Internet; Domain (mathematical analysis); Information retrieval; Artificial intelligence","authors":[{"name":"Mohammad Saiful Islam Mamun","is_ca":true},{"name":"Muhammad Ahmad Rathore","is_ca":true},{"name":"Arash Habibi Lashkari","is_ca":true},{"name":"Natalia Stakhanova","is_ca":true},{"name":"Ali A. Ghorbani","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0252092243512414,"gpt":0.2615634480667581,"spread":0.2363542237155167,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006732325,0.0008984991,0.001025538,0.01261244,0.001207337,0.002556089,0.0005992091,0.001064282,0.002804504],"category_scores_gemma":[0.004067914,0.0004041583,0.0008217577,0.005145563,0.0005630447,0.003415811,0.001291599,0.0006833366,0.004201163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003614377,"about_ca_system_score_gemma":0.0005365029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001507159,"about_ca_topic_score_gemma":0.002697312,"domain_scores_codex":[0.9986304,0.000252431,0.0001877308,0.0002405463,0.0005480934,0.0001407781],"domain_scores_gemma":[0.9971233,0.001215752,0.0003446956,0.0001970006,0.0009826286,0.0001365287],"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":[0.0004098842,0.0007243496,0.04900947,0.0009333576,0.0002373389,0.001758733,0.0007128908,0.00240389,0.1426568,0.00542727,0.01805537,0.7776706],"study_design_scores_gemma":[0.0001388925,0.001080695,0.1387694,0.0006590653,0.001263036,0.01042819,0.003543261,0.6032651,0.1314485,0.04814289,0.06088274,0.0003782377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.62103,0.006908975,0.3264468,0.0009552847,0.0006783978,0.0007088881,0.005378767,0.01146847,0.02642431],"genre_scores_gemma":[0.841626,0.001656444,0.1419808,0.0002654613,0.0004593791,0.0002039103,0.00662372,0.0004539899,0.006730342],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01261244,"threshold_uncertainty_score":0.009382069,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2068138600","doi":"10.1145/2492517.2492637","title":"Battling the internet water army","year":2013,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":184,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"The Internet; Internet privacy; Computer science; TRACE (psycholinguistics); World Wide Web; Sentiment analysis; Semantic analysis (machine learning); China; Internet users; Political science; Information retrieval; Artificial intelligence","authors":[{"name":"Cheng Chen","is_ca":true},{"name":"Kui Wu","is_ca":true},{"name":"Venkatesh Srinivasan","is_ca":true},{"name":"Xudong Zhang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01170349861037651,"gpt":0.1946039803168215,"spread":0.182900481706445,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001785741,0.0003717611,0.0003351354,0.003775683,0.0007870316,0.001314698,0.0005461812,0.0005931716,0.001469621],"category_scores_gemma":[0.01288902,0.0002115765,0.0002177503,0.002016417,0.0006864141,0.00285416,0.0006735133,0.000436407,0.0006859344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003888999,"about_ca_system_score_gemma":0.0006946003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002893334,"about_ca_topic_score_gemma":0.006477621,"domain_scores_codex":[0.9979029,0.0007717249,0.0002066181,0.0003035806,0.0006827067,0.0001324419],"domain_scores_gemma":[0.9866795,0.00514736,0.003656967,0.001272574,0.0028399,0.0004037744],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002128743,0.0004501455,0.7295787,0.001033842,0.00008544219,0.0005284954,0.005358416,0.0008305238,0.01156173,0.002593295,0.004642223,0.2431244],"study_design_scores_gemma":[0.00003709435,0.001093664,0.8820657,0.0004851226,0.0001522909,0.002179154,0.01292677,0.03174887,0.0243816,0.004800661,0.04000823,0.0001207694],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.980441,0.0005241609,0.01113087,0.0004065648,0.00003939274,0.0003735142,0.001413482,0.0002505305,0.00542044],"genre_scores_gemma":[0.9792132,0.0003789637,0.01558576,0.0001677213,0.00004156392,0.0001270342,0.002017327,0.00003233157,0.002436119],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003775683,"threshold_uncertainty_score":0.009443998,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2278316643","doi":"10.1016/j.chb.2016.02.065","title":"Phishing threat avoidance behaviour: An empirical investigation","year":2016,"lang":"en","type":"article","venue":"Computers in Human Behavior","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":177,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Phishing; Password; Online identity; Safeguard; Avoidance behaviour; Internet privacy; Empirical research; Computer security; Perception; Test (biology); Identity theft; Computer science; Psychology; The Internet; World Wide Web; Business","authors":[{"name":"Steve Love","is_ca":false},{"name":"Konstantin Beznosov","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05392374694464559,"gpt":0.315642397298215,"spread":0.2617186503535694,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005129938,0.0004113347,0.0005284771,0.001472115,0.001885203,0.001219757,0.0008647846,0.001272357,0.005435376],"category_scores_gemma":[0.04621033,0.0007136335,0.000409241,0.0009592752,0.001334662,0.001798974,0.001204497,0.002090026,0.001662577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006732881,"about_ca_system_score_gemma":0.0009643033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003709821,"about_ca_topic_score_gemma":0.005781485,"domain_scores_codex":[0.9978016,0.001285923,0.0001989291,0.0001820216,0.0003545538,0.0001769608],"domain_scores_gemma":[0.9158302,0.06147229,0.00999033,0.004807784,0.005375745,0.002523731],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007151555,0.01020924,0.9601424,0.0001198285,0.00008917866,0.0002493813,0.0152742,0.0002021652,0.0008026012,0.000663352,0.0005412954,0.01099119],"study_design_scores_gemma":[0.00008567225,0.002216441,0.9838039,0.00004869829,0.00007947325,0.0005945276,0.00997632,0.001372536,0.0004012478,0.000370326,0.001019489,0.00003134336],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9988635,0.00002103442,0.0001041849,0.00002749518,0.000001816187,0.00005570975,0.00005666379,0.000002307225,0.0008673745],"genre_scores_gemma":[0.9982308,0.00007497664,0.0003916116,0.00006032707,0.000008360872,0.000178874,0.000201209,0.000005603569,0.0008483738],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005435376,"threshold_uncertainty_score":0.02713001,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3195446130","doi":"10.3390/make3030034","title":"A Survey of Machine Learning-Based Solutions for Phishing Website Detection","year":2021,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":172,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Phishing; Computer science; The Internet; Computer security; Internet security; World Wide Web; Information security; Security service","authors":[{"name":"Lizhen Tang","is_ca":true},{"name":"Qusay H. Mahmoud","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03124810316152414,"gpt":0.2902130198347076,"spread":0.2589649166731834,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002424734,0.00184339,0.002017652,0.00787024,0.0007447099,0.001955776,0.0020327,0.001915021,0.00174714],"category_scores_gemma":[0.007460431,0.0007765897,0.001606601,0.006488721,0.0005209175,0.003285732,0.0009572647,0.00199393,0.002889473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007811632,"about_ca_system_score_gemma":0.0009512822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002696057,"about_ca_topic_score_gemma":0.002390349,"domain_scores_codex":[0.9971272,0.000498621,0.0002726447,0.0006032208,0.001355664,0.0001425749],"domain_scores_gemma":[0.9948,0.002444525,0.0004316073,0.0006045792,0.001606549,0.0001126872],"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":[0.0001023404,0.0002966662,0.00591325,0.001526861,0.0001486124,0.00008049489,0.0001073144,0.004752824,0.002269144,0.002240659,0.01623594,0.9663258],"study_design_scores_gemma":[0.00008395478,0.001100536,0.03396172,0.003444532,0.0007919745,0.003524994,0.0009513946,0.5417031,0.04341999,0.0287279,0.3418741,0.0004159761],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.03571674,0.3207044,0.6076649,0.004119409,0.001300379,0.0005154055,0.002040351,0.007203656,0.02073484],"genre_scores_gemma":[0.279066,0.2494723,0.439339,0.002998276,0.002662248,0.0006150919,0.007589152,0.0005630068,0.017695],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.00787024,"threshold_uncertainty_score":0.01282334,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2065915312","doi":"10.3138/jsp.41.2.176","title":"Academic Search Engine Optimization (<scp>ASEO</scp>)","year":2009,"lang":"en","type":"article","venue":"Journal of Scholarly Publishing","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":166,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Search engine optimization; Computer science; Search engine; Information retrieval","authors":[{"name":"Béla Gipp","is_ca":false},{"name":"Erik Wilde","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02772254798134443,"gpt":0.2599938540029307,"spread":0.2322713060215863,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003728942,0.001091304,0.001142151,0.002628902,0.0006777772,0.002792625,0.00103251,0.001112933,0.007738376],"category_scores_gemma":[0.01537127,0.0003764523,0.000929822,0.004158692,0.0008314882,0.002522444,0.001872729,0.001236726,0.002292259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009072268,"about_ca_system_score_gemma":0.002634653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001251403,"about_ca_topic_score_gemma":0.00158221,"domain_scores_codex":[0.9966215,0.001385783,0.000248902,0.0003268035,0.001146817,0.0002701667],"domain_scores_gemma":[0.9929579,0.0035894,0.0007384072,0.001192036,0.001292705,0.0002295422],"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":[0.0004225019,0.0005015272,0.005081893,0.0008661883,0.0002165965,0.0001731078,0.0001394629,0.1572573,0.004147465,0.1307856,0.04951646,0.6508919],"study_design_scores_gemma":[0.0001062597,0.0004730351,0.002392764,0.0001674815,0.0001534375,0.0005165094,0.0001668897,0.7922155,0.01255021,0.1186994,0.07250264,0.00005591191],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04458052,0.004578209,0.8304687,0.003545553,0.0006266132,0.001107965,0.001496847,0.005345179,0.1082504],"genre_scores_gemma":[0.4532521,0.002569568,0.5232604,0.0008641634,0.0005703318,0.0006290353,0.001664297,0.001018336,0.01617182],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9972074,"threshold_uncertainty_score":0.02588749,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2040717637","doi":"10.1145/1216016.1216017","title":"Spam and the ongoing battle for the inbox","year":2007,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":164,"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":"Battle; Computer science; Computer security; Internet privacy; Data science; History","authors":[{"name":"Joshua Goodman","is_ca":false},{"name":"Gordon V. Cormack","is_ca":true},{"name":"David Heckerman","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04140004503516648,"gpt":0.2955549490639394,"spread":0.2541549040287729,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006024315,0.0006494645,0.0008315524,0.002384044,0.007573642,0.01437855,0.001061307,0.007385735,0.02027646],"category_scores_gemma":[0.01755431,0.0004417812,0.0003739127,0.001508391,0.01127553,0.0281197,0.003879155,0.006946246,0.008891145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002998193,"about_ca_system_score_gemma":0.002400041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002788653,"about_ca_topic_score_gemma":0.003616286,"domain_scores_codex":[0.9970848,0.0009935938,0.00007417538,0.0003015113,0.001120281,0.0004256932],"domain_scores_gemma":[0.9908203,0.003548621,0.0007329948,0.0009863264,0.001964937,0.001946736],"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":[0.0001741366,0.0001014706,0.004594515,0.0002196796,0.00003668443,0.0002340129,0.005897738,0.0004163216,0.001182124,0.4645686,0.3249402,0.1976345],"study_design_scores_gemma":[0.00001738313,0.00005247604,0.003005943,0.0004195203,0.00001848321,0.0006168935,0.005379097,0.0008265704,0.0006618007,0.2464852,0.7424684,0.00004842524],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.03681953,0.05241433,0.01526056,0.7201851,0.008015345,0.00003306196,0.000259795,0.0006971155,0.1663152],"genre_scores_gemma":[0.6353369,0.04602165,0.01131548,0.09912462,0.02741492,0.00009100622,0.0003121576,0.0007187198,0.1796646],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02027646,"threshold_uncertainty_score":0.06783152,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2139204976","doi":"10.1287/isre.2014.0522","title":"<b>Research Note</b>—Influence Techniques in Phishing Attacks: An Examination of Vulnerability and Resistance","year":2014,"lang":"en","type":"article","venue":"Information Systems Research","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":159,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"University of British Columbia; Temple University","keywords":"Phishing; Persuasion; Vulnerability (computing); Computer security; Espionage; Internet privacy; Industrial espionage; Computer science; Psychology; Social psychology; World Wide Web; The Internet; Political science; Law","authors":[{"name":"Ryan Wright","is_ca":false},{"name":"Matthew L. Jensen","is_ca":false},{"name":"Jason Bennett Thatcher","is_ca":false},{"name":"Michael Dinger","is_ca":false},{"name":"Kent Marett","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06586017334989017,"gpt":0.3913550503943983,"spread":0.3254948770445082,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006818079,0.0002045668,0.0002484868,0.00223288,0.002698969,0.0029372,0.0006023191,0.001245904,0.01222166],"category_scores_gemma":[0.03081858,0.000181001,0.0004422353,0.00178535,0.003660144,0.00533529,0.00198244,0.001490677,0.001660519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0013732,"about_ca_system_score_gemma":0.001784824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006137508,"about_ca_topic_score_gemma":0.009303427,"domain_scores_codex":[0.9966904,0.001758806,0.0002537372,0.0002879506,0.0007811734,0.0002277794],"domain_scores_gemma":[0.9478609,0.03435264,0.007499551,0.002519144,0.005973712,0.001793994],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003750207,0.0016795,0.6512678,0.001099709,0.0001237513,0.0004390013,0.1317707,0.0003593422,0.003244765,0.04186626,0.02217197,0.1456024],"study_design_scores_gemma":[0.00004323968,0.0008253257,0.8078546,0.001185403,0.00009496709,0.0009748079,0.1357419,0.0007034935,0.001719614,0.01134766,0.03945727,0.00005168089],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8927578,0.001519413,0.003191381,0.01569784,0.0001502018,0.000373732,0.0004141796,0.00004909032,0.08584633],"genre_scores_gemma":[0.9925223,0.0008056318,0.001568348,0.002018282,0.00005487614,0.0001803568,0.0001205679,0.00001573035,0.002713957],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01222166,"threshold_uncertainty_score":0.04088557,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3010115535","doi":"10.1109/tps-isa48467.2019.00021","title":"Twitter Bot Detection Using Bidirectional Long Short-Term Memory Neural Networks and Word Embeddings","year":2019,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":148,"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":"Computer science; Popularity; Word (group theory); Social media; Term (time); Artificial neural network; Artificial intelligence; Long short term memory; Friendship; Recurrent neural network; Machine learning; World Wide Web","authors":[{"name":"Wei Feng","is_ca":true},{"name":"Uyen Trang Nguyen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0206729352782784,"gpt":0.2494242698842664,"spread":0.228751334605988,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004729493,0.00141819,0.0006968931,0.001668349,0.0003536292,0.0007008948,0.0008104403,0.0008754018,0.001424883],"category_scores_gemma":[0.002064437,0.000285269,0.0005659752,0.0009250693,0.0003019854,0.001665445,0.0007689818,0.0009384986,0.001379807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006621993,"about_ca_system_score_gemma":0.000557231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006844508,"about_ca_topic_score_gemma":0.01162762,"domain_scores_codex":[0.9996523,0.0000651726,0.00002698848,0.000109194,0.00007227936,0.00007411475],"domain_scores_gemma":[0.9992892,0.0002468843,0.0001638923,0.00007843733,0.0001749203,0.00004676374],"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":[0.0008294886,0.0008287627,0.02310477,0.0002755537,0.0003309638,0.0005320638,0.0002121951,0.1381199,0.01763785,0.002790166,0.02044304,0.7948952],"study_design_scores_gemma":[0.00000882992,0.00005194178,0.001233209,0.0000129678,0.00002101289,0.00004081271,0.00003334516,0.9936268,0.002469074,0.001801807,0.0006892875,0.00001089366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5185037,0.003443697,0.4523413,0.001394388,0.0004099978,0.0002603795,0.003100792,0.01170901,0.008836773],"genre_scores_gemma":[0.9312888,0.0004815798,0.05739832,0.0002399564,0.000110323,0.0001044809,0.004054568,0.0001236817,0.006198359],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006844508,"threshold_uncertainty_score":0.01360935,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2062614982","doi":"10.1145/1321440.1321486","title":"Spam filtering for short messages","year":2007,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":138,"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; Computer security","authors":[{"name":"Gordon V. Cormack","is_ca":true},{"name":"José María Gómez Hidalgo","is_ca":false},{"name":"Enrique Puertas","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02603713313869163,"gpt":0.2815240983558139,"spread":0.2554869652171222,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001616892,0.0009885629,0.001259321,0.003146808,0.001065466,0.001185892,0.0006334205,0.001663034,0.001664062],"category_scores_gemma":[0.01217744,0.0002698767,0.0005904878,0.002030637,0.0007633734,0.002529853,0.0005280164,0.0007203704,0.001067662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006758564,"about_ca_system_score_gemma":0.0004880104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002068467,"about_ca_topic_score_gemma":0.001455954,"domain_scores_codex":[0.9986926,0.0003591061,0.00006667054,0.0001912773,0.0005843446,0.0001060488],"domain_scores_gemma":[0.9903143,0.006083454,0.0009883097,0.0007652233,0.001640928,0.0002076578],"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":[0.001680915,0.0007478116,0.02726148,0.001147967,0.0003574545,0.001169719,0.001047757,0.1081334,0.09341478,0.01594584,0.01730204,0.7317908],"study_design_scores_gemma":[0.0000879759,0.0007835631,0.01291769,0.00007770143,0.0001845082,0.001284272,0.0002820803,0.8672158,0.07857825,0.0268351,0.01168911,0.00006395264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.554997,0.004019424,0.4299611,0.001381848,0.0003030986,0.0003938192,0.0006404484,0.003229313,0.005073999],"genre_scores_gemma":[0.8570942,0.00134359,0.1341025,0.0003785385,0.0006549517,0.000183822,0.001453308,0.000176686,0.004612427],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003146808,"threshold_uncertainty_score":0.008551061,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2020915469","doi":"10.1007/s10207-007-0049-3","title":"Alambic: a privacy-preserving recommender system for electronic commerce","year":2008,"lang":"en","type":"article","venue":"International Journal of Information Security","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":123,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal; Université de Montréal; Computer Research Institute of Montréal","funders":"","keywords":"Recommender system; Computer science; Personally identifiable information; Collaborative filtering; Cryptography; Information sensitivity; Internet privacy; Computer security; Privacy protection; Private information retrieval; World Wide Web","authors":[{"name":"Esma Aı̈meur","is_ca":true},{"name":"Gilles Brassard","is_ca":true},{"name":"José M. Fernandez","is_ca":true},{"name":"Flavien Serge Mani Onana","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01681907589208641,"gpt":0.2592471856976533,"spread":0.2424281098055668,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001579254,0.0006299888,0.001420874,0.001644715,0.001269622,0.001369954,0.001870495,0.001549226,0.003983829],"category_scores_gemma":[0.005162598,0.000489219,0.0004658046,0.001504633,0.0002821529,0.001872972,0.001538429,0.001232431,0.00318976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005665038,"about_ca_system_score_gemma":0.001281987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009813541,"about_ca_topic_score_gemma":0.02254196,"domain_scores_codex":[0.9989228,0.000296415,0.00006589774,0.0001577442,0.0004810038,0.0000762026],"domain_scores_gemma":[0.997434,0.0004646474,0.00009598604,0.001046932,0.0007704907,0.0001880605],"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":[0.002225646,0.001141037,0.0117065,0.0006333811,0.0005702126,0.000653149,0.0002928218,0.02272839,0.02718442,0.01159777,0.1734147,0.7478518],"study_design_scores_gemma":[0.0004906485,0.000877054,0.006368463,0.00008100264,0.0003209429,0.001560989,0.0001862159,0.8411874,0.02754464,0.0138948,0.1072363,0.0002515386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1150993,0.004543117,0.7815264,0.001969354,0.0009185601,0.001079987,0.006791099,0.07275558,0.01531671],"genre_scores_gemma":[0.4405478,0.001251383,0.5206859,0.0009508237,0.0003240893,0.0002907577,0.008884836,0.0004843488,0.02658002],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009813541,"threshold_uncertainty_score":0.01951283,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2058737869","doi":"10.1145/1247715.1247717","title":"Online supervised spam filter evaluation","year":2007,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":117,"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; Filter (signal processing); Set (abstract data type); Software; Receiver operating characteristic; Confidence interval; Information retrieval; Data mining; Machine learning; Artificial intelligence; Statistics; Mathematics; Operating system","authors":[{"name":"Gordon V. Cormack","is_ca":true},{"name":"Thomas R. Lynam","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03922481280749248,"gpt":0.2785531126448064,"spread":0.2393282998373139,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009281714,0.001971453,0.002302395,0.002655167,0.001147934,0.001277218,0.002179696,0.003620149,0.003743003],"category_scores_gemma":[0.01641863,0.0003939033,0.0008110997,0.001041538,0.0007611739,0.002085825,0.001292199,0.001240407,0.002505061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001615393,"about_ca_system_score_gemma":0.001606448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004482449,"about_ca_topic_score_gemma":0.00614198,"domain_scores_codex":[0.9936571,0.002133443,0.0005261849,0.001220067,0.001855235,0.0006079791],"domain_scores_gemma":[0.9823269,0.007634443,0.001059925,0.002541024,0.005562949,0.0008747604],"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":[0.005432546,0.004897409,0.04432132,0.0006721513,0.001080869,0.0004819783,0.0003759146,0.210568,0.01927669,0.001574801,0.03255678,0.6787615],"study_design_scores_gemma":[0.0002224845,0.001148123,0.01166896,0.00002600667,0.0001271423,0.0003076087,0.0001263018,0.9514154,0.02989076,0.0009477662,0.004062964,0.0000564743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8385979,0.00159139,0.1340302,0.0004104247,0.0004297313,0.0008312212,0.002160532,0.01426054,0.007687961],"genre_scores_gemma":[0.9022014,0.0001824381,0.08380874,0.0002115775,0.0001432042,0.0003589398,0.005601462,0.0002696189,0.00722253],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009281714,"threshold_uncertainty_score":0.04908699,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3163881436","doi":"10.1109/access.2021.3081479","title":"A Spam Transformer Model for SMS Spam Detection","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":114,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Transformer; Spamming; Short Message Service; Spambot; Machine learning; Artificial intelligence; Data mining; Computer network; World Wide Web; The Internet; Engineering; Voltage","authors":[{"name":"Xiaoxu Liu","is_ca":true},{"name":"Haoye Lu","is_ca":true},{"name":"Amiya Nayak","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05797368719015953,"gpt":0.3102206889227196,"spread":0.2522470017325601,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001252741,0.001182413,0.001132858,0.002098043,0.0004371477,0.001060601,0.001573933,0.001263787,0.002151801],"category_scores_gemma":[0.003737957,0.0004026032,0.001040624,0.0009283902,0.0007739725,0.002707686,0.000938631,0.001122507,0.001704309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009922666,"about_ca_system_score_gemma":0.0009468826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003204029,"about_ca_topic_score_gemma":0.002988727,"domain_scores_codex":[0.9993303,0.000177573,0.00004147695,0.0001780265,0.000182162,0.00009059693],"domain_scores_gemma":[0.9988081,0.0004550313,0.0001463394,0.0001318172,0.0003947711,0.00006390548],"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":[0.001904067,0.0007119884,0.02717501,0.0004281231,0.00032373,0.0008519127,0.000393071,0.2838686,0.02904473,0.03518214,0.01600924,0.6041073],"study_design_scores_gemma":[0.00001295771,0.00007537795,0.0005484544,0.000007385875,0.00003660503,0.0001674944,0.00001729339,0.9905244,0.002418119,0.005102872,0.001077569,0.0000115906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05422013,0.0007778676,0.9359179,0.0006478577,0.0001446064,0.000212045,0.0002806081,0.003794104,0.004004837],"genre_scores_gemma":[0.893626,0.0006330743,0.09626205,0.0006392305,0.0002334454,0.0002064225,0.0006294249,0.0001838648,0.007586553],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003204029,"threshold_uncertainty_score":0.007199466,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1537207111","doi":"10.1007/978-3-642-13059-5_6","title":"A Three-Way Decision Approach to Email Spam Filtering","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":111,"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; Machine learning; Odds; Binary number; Function (biology); Artificial intelligence; Bayesian probability; Data mining; Mathematics; Logistic regression","authors":[{"name":"Bing Zhou","is_ca":true},{"name":"Yiyu Yao","is_ca":true},{"name":"Jigang Luo","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02165578754746894,"gpt":0.2355973198803561,"spread":0.2139415323328872,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007062939,0.001242417,0.003575422,0.001965743,0.002453347,0.003973989,0.005521415,0.003805082,0.008684886],"category_scores_gemma":[0.01064132,0.001343571,0.00286842,0.002045721,0.001865572,0.004180024,0.003476712,0.003221527,0.002097431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001986025,"about_ca_system_score_gemma":0.002342472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01027011,"about_ca_topic_score_gemma":0.009880793,"domain_scores_codex":[0.9940493,0.00264993,0.0004437991,0.0009554277,0.001321726,0.0005798577],"domain_scores_gemma":[0.9896083,0.007519254,0.0002224676,0.0006994419,0.001639476,0.0003110843],"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":[0.001317221,0.0008390413,0.002344877,0.0002967286,0.0004982817,0.0004361592,0.0006130665,0.3372362,0.004986292,0.07864293,0.01061971,0.5621694],"study_design_scores_gemma":[0.00002329138,0.00004860065,0.0001275326,0.000007778412,0.00004164454,0.00004614487,0.00002756519,0.9683276,0.0008243808,0.02967557,0.0008240447,0.00002576737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005520041,0.0001927966,0.9920269,0.0002939499,0.00009666853,0.00006580324,0.00006050435,0.00049712,0.001246161],"genre_scores_gemma":[0.2527475,0.0002654398,0.7350591,0.0004881184,0.0004048132,0.0002959165,0.0003721786,0.0002464583,0.01012053],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01027011,"threshold_uncertainty_score":0.03735286,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3037316620","doi":"10.1016/j.osnem.2020.100079","title":"A deep learning model for Twitter spam detection","year":2020,"lang":"en","type":"article","venue":"Online Social Networks and Media","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":110,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"European Commission; Concordia University of Edmonton","keywords":"Popularity; Computer science; Spambot; Social media; Spamming; World Wide Web; Machine learning; The Internet; Artificial intelligence; Data science","authors":[{"name":"Zulfikar Alom","is_ca":false},{"name":"Barbara Carminati","is_ca":false},{"name":"Elena Ferrari","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03256720045410764,"gpt":0.252930618687531,"spread":0.2203634182334234,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008644368,0.0007955623,0.0008288496,0.0008549461,0.0005006789,0.000772518,0.001407437,0.001603672,0.002462266],"category_scores_gemma":[0.002411451,0.0005087323,0.0006134342,0.0007723126,0.0004071587,0.001387182,0.00113942,0.00183776,0.001361447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001026654,"about_ca_system_score_gemma":0.001306395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01275363,"about_ca_topic_score_gemma":0.01600749,"domain_scores_codex":[0.9997285,0.00005530726,0.00001528276,0.00007318598,0.00006196015,0.00006581825],"domain_scores_gemma":[0.9991983,0.0003188241,0.00006194655,0.00006962474,0.0002957016,0.00005557483],"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":[0.0004119593,0.0005295416,0.005613038,0.0001438245,0.0001834861,0.0001323733,0.00008211684,0.4080052,0.007150984,0.008949465,0.02527163,0.5435264],"study_design_scores_gemma":[0.00000382906,0.00001402538,0.0001417177,0.000004585793,0.000008881182,0.000007111405,0.000002985439,0.9971086,0.0005675304,0.001774155,0.0003633543,0.000003091726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09707715,0.002005552,0.8880258,0.002578435,0.0004205413,0.0001098595,0.00139184,0.003582103,0.004808612],"genre_scores_gemma":[0.8311695,0.0009378805,0.1417572,0.001014585,0.0004252988,0.0002118885,0.002427928,0.0001725914,0.02188299],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01275363,"threshold_uncertainty_score":0.0253588,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4206428177","doi":"10.1109/access.2021.3137636","title":"A Deep Learning-Based Framework for Phishing Website Detection","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Phishing; Computer science; Blacklist; Machine learning; Artificial intelligence; Personally identifiable information; Deep learning; World Wide Web; Computer security; The Internet","authors":[{"name":"Lizhen Tang","is_ca":true},{"name":"Qusay H. Mahmoud","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02951460665004112,"gpt":0.3030171318203809,"spread":0.2735025251703397,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006276653,0.0008978213,0.0007695261,0.001033383,0.0003631678,0.0006072486,0.001179099,0.001177529,0.001413876],"category_scores_gemma":[0.001166232,0.0004375631,0.0006611377,0.000661483,0.0004278906,0.000930013,0.0008070283,0.001413918,0.0006309978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001046465,"about_ca_system_score_gemma":0.001453636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02287099,"about_ca_topic_score_gemma":0.02287441,"domain_scores_codex":[0.9996798,0.0000631872,0.00001675547,0.0000811846,0.00007882877,0.00008021903],"domain_scores_gemma":[0.9997009,0.00007174342,0.00003385898,0.0000302408,0.0001318718,0.00003139823],"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":[0.000213422,0.0003516064,0.003988471,0.0001351246,0.0001597544,0.0002066451,0.0001006007,0.5079725,0.01187823,0.007305495,0.008300195,0.459388],"study_design_scores_gemma":[0.000003368249,0.00002315572,0.0002273629,0.000005881792,0.0000084571,0.00001577107,0.000003830466,0.9968823,0.001081379,0.001264232,0.0004796255,0.000004586676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02900461,0.001196777,0.9628463,0.0004305443,0.00008054738,0.00007054242,0.0002772734,0.004166957,0.001926394],"genre_scores_gemma":[0.6537105,0.001148083,0.3333547,0.0006638548,0.000130469,0.0002078694,0.001375836,0.0001901126,0.009218548],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02287099,"threshold_uncertainty_score":0.04547572,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3215010342","doi":"10.1109/tfuzz.2021.3130311","title":"Fuz-Spam: Label Smoothing-Based Fuzzy Detection of Spammers in Internet of Things","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Fuzzy Systems","topic":"Spam and Phishing Detection","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 Windsor","funders":"Japan Society for the Promotion of Science; Chongqing Municipal Education Commission; National Natural Science Foundation of China","keywords":"Spamming; Computer science; Artificial intelligence; Machine learning; Fuzzy logic; Data mining; The Internet; World Wide Web","authors":[{"name":"Zhiwei Guo","is_ca":false},{"name":"Keping Yu","is_ca":false},{"name":"Alireza Jolfaei","is_ca":false},{"name":"Feng Ding","is_ca":false},{"name":"Ning Zhang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0203475875465673,"gpt":0.2327914706668393,"spread":0.212443883120272,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001409702,0.0006351186,0.000835585,0.001430608,0.0007947368,0.0008370632,0.0008971334,0.001242556,0.0006806286],"category_scores_gemma":[0.003700598,0.0002375098,0.000623832,0.0005976648,0.0009519327,0.001497952,0.001156805,0.001032202,0.0003384649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006552419,"about_ca_system_score_gemma":0.0006711505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002390468,"about_ca_topic_score_gemma":0.002740553,"domain_scores_codex":[0.999108,0.0001776039,0.00004722986,0.0002046013,0.0003606675,0.0001018133],"domain_scores_gemma":[0.9986065,0.0005370401,0.0001970409,0.0002080104,0.0003745098,0.00007698916],"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":[0.001029675,0.0004997565,0.01995803,0.0002889184,0.0002229748,0.000682176,0.0007472706,0.2100398,0.04785958,0.01730672,0.009031669,0.6923333],"study_design_scores_gemma":[0.00001373759,0.0001019012,0.001954111,0.00001305209,0.00002645369,0.0001891427,0.00005715834,0.9781836,0.01131361,0.007039828,0.001084547,0.00002286984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1386951,0.000467217,0.8549838,0.0004700301,0.0001250414,0.0001213736,0.0001297988,0.002374996,0.002632493],"genre_scores_gemma":[0.8437194,0.0002148665,0.1525114,0.0003443334,0.0001041244,0.00005968139,0.0002997901,0.00006490648,0.002681605],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002390468,"threshold_uncertainty_score":0.007455289,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2120960514","doi":"","title":"PharmaLeaks: understanding the business of online pharmaceutical affiliate programs","year":2012,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Exploit; Counterfeit; Business; Database transaction; Key (lock); Promotion (chess); Business model; Sales promotion; Competitive advantage; Marketing; Advertising; Computer science; Computer security; Sales management; Database","authors":[{"name":"Damon McCoy","is_ca":false},{"name":"Andreas Pitsillidis","is_ca":false},{"name":"Grant Jordan","is_ca":false},{"name":"Nicholas Weaver","is_ca":false},{"name":"Christian Kreibich","is_ca":false},{"name":"Brian Krebs","is_ca":false},{"name":"Geoffrey M. Voelker","is_ca":false},{"name":"Stefan Savage","is_ca":false},{"name":"Kirill Levchenko","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1321478470409369,"gpt":0.3274863709383824,"spread":0.1953385238974455,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009140666,0.0004861277,0.0004059844,0.002932409,0.0007153892,0.004263606,0.0009595055,0.001802837,0.00582529],"category_scores_gemma":[0.007104127,0.0004102822,0.0003564524,0.002985806,0.001147382,0.01143264,0.001177849,0.001985662,0.001200776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001661483,"about_ca_system_score_gemma":0.0007524036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01846465,"about_ca_topic_score_gemma":0.01998546,"domain_scores_codex":[0.9996303,0.000140866,0.00001864155,0.00007520324,0.00005801383,0.00007695785],"domain_scores_gemma":[0.9942596,0.003295214,0.001344122,0.0004022571,0.0003316699,0.0003671969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004612279,0.001098539,0.4355517,0.0006507962,0.0001449368,0.001203359,0.006400039,0.1172101,0.002326321,0.2574434,0.02708459,0.150425],"study_design_scores_gemma":[0.00004373026,0.0001729374,0.1409104,0.0002416987,0.00006857287,0.0004232785,0.007946358,0.6360933,0.001185599,0.1850598,0.0277612,0.00009313156],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9236257,0.00419613,0.03062763,0.01111977,0.00004092654,0.0001060476,0.004118495,0.0002087915,0.02595652],"genre_scores_gemma":[0.9901832,0.001705693,0.004497266,0.0001906454,0.00008024575,0.00002937792,0.001419689,0.00002699271,0.001866904],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01846465,"threshold_uncertainty_score":0.03671438,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2344840125","doi":"","title":"Framing dependencies introduced by underground commoditization","year":2015,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Exploit; Framing (construction); Computer security; The Internet; Business; Profit (economics); Internet privacy; Computer science; Economics; Engineering","authors":[{"name":"Kurt Thomas","is_ca":false},{"name":"Danny Yuxing Huang","is_ca":true},{"name":"David Y. Wang","is_ca":false},{"name":"Elie Bursztein","is_ca":false},{"name":"Chris Grier","is_ca":false},{"name":"Tom Holt","is_ca":false},{"name":"Christopher Kruegel","is_ca":false},{"name":"Damon McCoy","is_ca":false},{"name":"Stefan Savage","is_ca":false},{"name":"Giovanni Vigna","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02517583869626246,"gpt":0.230005073355764,"spread":0.2048292346595015,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00687642,0.0009068889,0.0006186798,0.003116017,0.004803247,0.009244815,0.001400071,0.003524249,0.01266315],"category_scores_gemma":[0.02620195,0.0008701642,0.0005194244,0.001748672,0.02591251,0.02464283,0.01096445,0.005280294,0.0006873862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005217967,"about_ca_system_score_gemma":0.002893652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003644387,"about_ca_topic_score_gemma":0.005390005,"domain_scores_codex":[0.9950152,0.002882291,0.0001762856,0.0006785319,0.0006942857,0.0005534816],"domain_scores_gemma":[0.9735912,0.01773424,0.002589456,0.003931132,0.00147421,0.0006797133],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001951611,0.00001535479,0.001111268,0.00003971851,0.00000580085,0.0001446784,0.005064635,0.0005112046,0.0001954041,0.9838138,0.0009431599,0.008135453],"study_design_scores_gemma":[0.00001725723,0.00002994277,0.001590395,0.0002879649,0.00004226185,0.0002778588,0.008301089,0.005409687,0.00072268,0.9459145,0.03737429,0.00003205049],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2789776,0.00271731,0.2692102,0.04163748,0.0004942192,0.0002125132,0.0003490906,0.0002984705,0.406103],"genre_scores_gemma":[0.9797488,0.0008695821,0.01190289,0.0009979226,0.0001732652,0.0001106594,0.00005585837,0.00009185244,0.006049261],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01266315,"threshold_uncertainty_score":0.04236245,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2025635041","doi":"10.1145/1754393.1754394","title":"Detecting visually similar Web pages","year":2010,"lang":"en","type":"article","venue":"ACM Transactions on Internet Technology","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Gestalt psychology; Web page; Similarity (geometry); World Wide Web; Realization (probability); Information retrieval; Phishing; Artificial intelligence; The Internet; Image (mathematics)","authors":[{"name":"Teh-Chung Chen","is_ca":true},{"name":"Scott Dick","is_ca":true},{"name":"James Miller","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0128471117380512,"gpt":0.2488890762803148,"spread":0.2360419645422636,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005992999,0.0004888182,0.0008055288,0.009164144,0.0007460538,0.002415271,0.0009287476,0.00146083,0.00196959],"category_scores_gemma":[0.00633232,0.0003846395,0.0006626892,0.002426852,0.0008136267,0.003225347,0.002116546,0.0007646814,0.0008349479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005783563,"about_ca_system_score_gemma":0.0005241713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00131258,"about_ca_topic_score_gemma":0.001652736,"domain_scores_codex":[0.9987522,0.0002010476,0.00007218702,0.0002504573,0.0006057977,0.0001183126],"domain_scores_gemma":[0.9969558,0.0008929883,0.0006645949,0.0004707778,0.0008219709,0.0001939281],"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":[0.0006607313,0.0006925837,0.04632932,0.0006917213,0.000393151,0.001465356,0.001651998,0.02184879,0.1114804,0.04844881,0.007202583,0.7591345],"study_design_scores_gemma":[0.00009035959,0.000621057,0.06597039,0.000107342,0.000298376,0.006951423,0.001430303,0.7313923,0.0726891,0.100178,0.02005497,0.0002162759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3022366,0.001018787,0.6848692,0.0004253708,0.00009900704,0.000352475,0.0004129427,0.002450381,0.008135105],"genre_scores_gemma":[0.742507,0.0002844222,0.2543097,0.0001274315,0.000113351,0.0001281765,0.0005013846,0.0001161749,0.001912124],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009164144,"threshold_uncertainty_score":0.006588876,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2003798735","doi":"10.1145/2184489.2184491","title":"SMSAssassin","year":2011,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"International Development Research Centre","keywords":"Computer science; Short Message Service; Support vector machine; Machine learning; Artificial intelligence; Naive Bayes classifier; Filter (signal processing); Bag-of-words model; Communication source; Blacklist; Blacklisting; Forum spam; Spamming; World Wide Web; The Internet; Spambot; Computer security; Computer network","authors":[{"name":"Kuldeep Singh Yadav","is_ca":false},{"name":"Ponnurangam Kumaraguru","is_ca":false},{"name":"Atul Goyal","is_ca":false},{"name":"Ashish Gupta","is_ca":false},{"name":"Vinayak Naik","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05160695508429729,"gpt":0.1959812090071653,"spread":0.144374253922868,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008875487,0.00117485,0.00113733,0.002256239,0.0008827468,0.001057492,0.0009715007,0.0008680318,0.01137808],"category_scores_gemma":[0.003305214,0.0003739116,0.0004610201,0.001854772,0.000310242,0.001752611,0.001210143,0.0007408815,0.01220607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006816309,"about_ca_system_score_gemma":0.000580786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004641762,"about_ca_topic_score_gemma":0.006440571,"domain_scores_codex":[0.9986488,0.0001741815,0.0001204194,0.0002954198,0.0006239662,0.00013724],"domain_scores_gemma":[0.9977482,0.0003853219,0.0003174322,0.0005528049,0.000674225,0.0003218747],"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":[0.003803767,0.0009328288,0.07966259,0.002650731,0.0003027807,0.00144887,0.002131517,0.003242933,0.02171468,0.004673343,0.5007778,0.3786582],"study_design_scores_gemma":[0.0003061877,0.001114312,0.156547,0.0002770674,0.0001552221,0.00276728,0.001072485,0.05298373,0.04816522,0.002734198,0.7336105,0.0002667893],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"software","genre_scores_codex":[0.5336639,0.002257953,0.0156498,0.001511123,0.001198509,0.002459599,0.2132295,0.1364094,0.09362024],"genre_scores_gemma":[0.6133652,0.0009400807,0.03472812,0.001027115,0.0003342534,0.0009355452,0.281966,0.002863515,0.06384018],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01137808,"threshold_uncertainty_score":0.03806347,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1995554356","doi":"10.1145/1978942.1979244","title":"Does domain highlighting help people identify phishing sites?","year":2011,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Phishing; Legitimacy; Domain (mathematical analysis); Exploit; Computer science; World Wide Web; Internet privacy; Domain name; Web page; Computer security; The Internet; Political science; Law","authors":[{"name":"Eric Lin","is_ca":true},{"name":"Saul Greenberg","is_ca":true},{"name":"Eileah C. Trotter","is_ca":true},{"name":"David W.L.","is_ca":true},{"name":"John Aycock","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02471575098055676,"gpt":0.2357652450595044,"spread":0.2110494940789476,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004626465,0.0005725823,0.0005954176,0.001351986,0.0009681345,0.001755529,0.0003308182,0.00180402,0.006510728],"category_scores_gemma":[0.0293729,0.0002801303,0.0003690012,0.0006384772,0.0007291707,0.004101004,0.0009695977,0.0007215576,0.002717844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002432957,"about_ca_system_score_gemma":0.000558514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009188937,"about_ca_topic_score_gemma":0.001400208,"domain_scores_codex":[0.9983611,0.0009895345,0.00007190773,0.0001681411,0.0002216101,0.0001877179],"domain_scores_gemma":[0.9832231,0.01147177,0.001851158,0.000987003,0.001463515,0.001003402],"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":[0.0009425872,0.001668808,0.3946095,0.001260138,0.0001419903,0.0004922024,0.03429061,0.0004114598,0.01579276,0.001511988,0.01895131,0.5299266],"study_design_scores_gemma":[0.0005798353,0.006210316,0.6825276,0.001449673,0.00108843,0.00536669,0.1534926,0.01533565,0.0275527,0.01499607,0.09085695,0.0005434766],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9716271,0.00126154,0.004114083,0.006454598,0.0001241571,0.0002044295,0.0001611506,0.0005138764,0.01553897],"genre_scores_gemma":[0.9920265,0.0006073813,0.005028666,0.000959487,0.00004953105,0.00004841459,0.00006594859,0.00002748669,0.001186649],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006510728,"threshold_uncertainty_score":0.02446741,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2251262990","doi":"","title":"Detecting Deceptive Opinions with Profile Compatibility","year":2013,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","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":"University of Toronto","funders":"","keywords":"Compatibility (geochemistry); Computer science; Information retrieval; Data mining; Artificial intelligence; Engineering","authors":[{"name":"Vanessa Wei Feng","is_ca":true},{"name":"Graeme Hirst","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01453577432006802,"gpt":0.2260262368757863,"spread":0.2114904625557183,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003312657,0.001310582,0.00115982,0.004711844,0.0009024514,0.002664291,0.001082279,0.002010085,0.001274505],"category_scores_gemma":[0.0259508,0.0005172337,0.0007081291,0.002470854,0.0005222646,0.005426022,0.001573306,0.001946502,0.002353135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006590727,"about_ca_system_score_gemma":0.0006546009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001648019,"about_ca_topic_score_gemma":0.001973667,"domain_scores_codex":[0.9957546,0.001260773,0.0003225211,0.0007051437,0.001616351,0.0003406552],"domain_scores_gemma":[0.981927,0.006168188,0.004347696,0.002719606,0.004097678,0.0007399507],"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":[0.002171402,0.001119909,0.3134316,0.0005800481,0.0004960889,0.00149184,0.002077405,0.01425426,0.04431754,0.009566766,0.01867467,0.5918185],"study_design_scores_gemma":[0.0000860864,0.0009337193,0.1378317,0.0001397084,0.0003008025,0.005207962,0.001366991,0.779161,0.03537316,0.02174073,0.01765994,0.0001981537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.658069,0.002136747,0.3159142,0.001423626,0.0002769677,0.0005262874,0.002722439,0.002779287,0.01615139],"genre_scores_gemma":[0.9494575,0.0002654037,0.04604978,0.0002423967,0.0002643422,0.000101145,0.00169162,0.00006755204,0.001860182],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.004711844,"threshold_uncertainty_score":0.01751924,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1721870969","doi":"10.2139/ssrn.885568","title":"The Dimensions of Reputation in Electronic Markets","year":2009,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"University of California, Irvine; Carnegie Mellon University; Microsoft Research; York University; Microsoft; National Science Foundation","keywords":"Business; Electronic markets; Reputation; Marketing; Industrial organization; Computer science; World Wide Web; The Internet; Political science; Law","authors":[{"name":"Anindya Ghose","is_ca":false},{"name":"Panagiotis G. Ipeirotis","is_ca":false},{"name":"Arun Sundararajan","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.004434693325151219,"gpt":0.2233368307387511,"spread":0.2189021374135998,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004486401,0.0002583436,0.0006687256,0.003213028,0.002127459,0.01013236,0.0006760689,0.003168528,0.006357317],"category_scores_gemma":[0.03703942,0.0005375384,0.0004074896,0.003345254,0.008299625,0.01820937,0.002942564,0.002428949,0.000426071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002051676,"about_ca_system_score_gemma":0.001139465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001514895,"about_ca_topic_score_gemma":0.001778999,"domain_scores_codex":[0.9962681,0.00219549,0.000172571,0.0003125041,0.0007175462,0.0003338564],"domain_scores_gemma":[0.9458878,0.03499442,0.009649797,0.002589509,0.003305656,0.003572803],"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":[0.0002311572,0.0002137756,0.06578828,0.0000979204,0.00009695927,0.0002322866,0.003031001,0.003180569,0.0004903614,0.8982461,0.002446265,0.02594535],"study_design_scores_gemma":[0.0000484651,0.00008041709,0.05701354,0.00005712267,0.00004329662,0.0002170659,0.003030762,0.009252474,0.0001239165,0.9262063,0.00386344,0.00006324012],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7834752,0.005424723,0.02097537,0.02234828,0.0001439914,0.00005483194,0.0002922345,0.00007494403,0.1672103],"genre_scores_gemma":[0.998457,0.0003089657,0.0005028455,0.00007697543,0.00007795145,0.000008169035,0.00001645035,0.000004109992,0.0005475759],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01013236,"threshold_uncertainty_score":0.02372664,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2104001538","doi":"10.1109/innovations.2012.6207742","title":"Phishing in a university community: Two large scale phishing experiments","year":2012,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Phishing; Password; Internet privacy; Computer science; Demographics; Computer security; Scale (ratio); Confidentiality; World Wide Web; The Internet","authors":[{"name":"Jamshaid G. Mohebzada","is_ca":true},{"name":"Ahmed El Zarka","is_ca":true},{"name":"Arsalan H. Bhojani","is_ca":true},{"name":"Ali Darwish","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03453917666610522,"gpt":0.2690974735576027,"spread":0.2345582968914975,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003351537,0.0006502377,0.0007221668,0.001080221,0.001521554,0.0006564022,0.000670872,0.001620193,0.001436436],"category_scores_gemma":[0.01070643,0.0003218358,0.0004675658,0.00078175,0.000850905,0.001232842,0.001513242,0.001437593,0.0005458153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005219354,"about_ca_system_score_gemma":0.000528727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002669883,"about_ca_topic_score_gemma":0.004556514,"domain_scores_codex":[0.9977809,0.001159632,0.0001264782,0.0002214484,0.000444749,0.0002668522],"domain_scores_gemma":[0.9808087,0.009277921,0.002252446,0.0023721,0.002148734,0.003139918],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01666367,0.1203786,0.5898842,0.0008604656,0.0008876706,0.003928244,0.02670286,0.01587762,0.0630088,0.002264346,0.01262897,0.1469147],"study_design_scores_gemma":[0.002322802,0.05459317,0.8094013,0.000127856,0.0003698232,0.002267628,0.01456341,0.08122162,0.02203447,0.002781043,0.009981063,0.0003358101],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9989076,0.00002827906,0.000336653,0.00006574589,0.000008858083,0.0001552349,0.00008915122,0.00003163108,0.0003768317],"genre_scores_gemma":[0.9952121,0.0000734202,0.002803225,0.0001159804,0.00002822449,0.0002963988,0.0004963325,0.000009696573,0.0009644858],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003351537,"threshold_uncertainty_score":0.01772487,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2788314565","doi":"10.1007/s10664-018-9601-1","title":"App store mining is not enough for app improvement","year":2018,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University of Calgary","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Alberta Innovates - Technology Futures","keywords":"App store; Computer science; Mobile apps; Smartphone app; World Wide Web","authors":[{"name":"Maleknaz Nayebi","is_ca":true},{"name":"Henry Cho","is_ca":true},{"name":"Guenther Ruhe","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02549139422760458,"gpt":0.2673284083448976,"spread":0.241837014117293,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01076294,0.002037523,0.002373668,0.006136754,0.001694082,0.005938727,0.00320959,0.002605909,0.007900404],"category_scores_gemma":[0.1002599,0.001148416,0.001552414,0.004262989,0.001610925,0.01972388,0.002048558,0.004213605,0.008334548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001230145,"about_ca_system_score_gemma":0.004016206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005084589,"about_ca_topic_score_gemma":0.008800792,"domain_scores_codex":[0.9870325,0.003134628,0.001085506,0.001793518,0.006229762,0.0007238835],"domain_scores_gemma":[0.8506922,0.0712537,0.010459,0.02631956,0.0388659,0.002409575],"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":[0.0003610436,0.001262975,0.1814674,0.00121822,0.0005818627,0.0002331555,0.000633903,0.003864944,0.004481129,0.007210069,0.08108281,0.7176025],"study_design_scores_gemma":[0.0002414391,0.001883648,0.2184519,0.003634074,0.001854045,0.002660835,0.006684524,0.3296129,0.03052205,0.1805318,0.223533,0.0003898426],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5167426,0.01612417,0.2313608,0.1272828,0.002833852,0.001305341,0.0114547,0.02215057,0.07074511],"genre_scores_gemma":[0.8316839,0.003511346,0.1341305,0.007935736,0.001497342,0.0003503844,0.006574576,0.00111683,0.01319938],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01076294,"threshold_uncertainty_score":0.05692059,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4220686914","doi":"10.1007/s13278-022-00869-w","title":"DeeProBot: a hybrid deep neural network model for social bot detection based on user profile data","year":2022,"lang":"en","type":"article","venue":"Social Network Analysis and Mining","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":83,"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":"Zayed University","keywords":"Computer science; Artificial neural network; Artificial intelligence; Social network (sociolinguistics); Data mining; Machine learning; Social media; World Wide Web","authors":[{"name":"Kadhim Hayawi","is_ca":false},{"name":"Sujith Samuel Mathew","is_ca":false},{"name":"Neethu Venugopal","is_ca":false},{"name":"Mohammad Mehedy Masud","is_ca":false},{"name":"Pin‐Han Ho","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03954773012374535,"gpt":0.2695036051973896,"spread":0.2299558750736443,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006124454,0.001243233,0.0007130865,0.0007178314,0.0003435983,0.0007294706,0.001969553,0.00122874,0.002056372],"category_scores_gemma":[0.001472961,0.0004825387,0.0005668697,0.0006114851,0.0003974119,0.001731592,0.001045682,0.001804066,0.001172486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001084148,"about_ca_system_score_gemma":0.001011295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01287022,"about_ca_topic_score_gemma":0.01920343,"domain_scores_codex":[0.9997465,0.0000500036,0.00001194776,0.00008847181,0.00005570384,0.00004749847],"domain_scores_gemma":[0.9996463,0.0001138911,0.00005534508,0.00004848155,0.0001019407,0.00003413225],"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":[0.0006352451,0.0006508418,0.00818108,0.0002291746,0.0002697411,0.000336944,0.0002126237,0.5647097,0.008812232,0.005300705,0.02208845,0.3885733],"study_design_scores_gemma":[0.000005839614,0.00003187791,0.0002449659,0.000007899597,0.000006671626,0.00001491942,0.000008376118,0.9971264,0.0008418747,0.001058274,0.0006467676,0.000006131606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1697419,0.002159423,0.8020208,0.00172961,0.0004287374,0.0002649463,0.003510321,0.0123378,0.00780634],"genre_scores_gemma":[0.8136823,0.0008245414,0.1576683,0.000846271,0.0001459952,0.0003529432,0.005847739,0.0002780643,0.020354],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01287022,"threshold_uncertainty_score":0.0255906,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2800638151","doi":"10.1093/geronb/gby036","title":"Uncovering Susceptibility Risk to Online Deception in Aging","year":2018,"lang":"en","type":"article","venue":"The Journals of Gerontology Series B","topic":"Spam and Phishing Detection","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":"McGill University; Montreal Neurological Institute and Hospital; York University","funders":"National Institute on Aging; National Institutes of Health; National Science Foundation","keywords":"Deception; Psychology; Cognitive psychology; Social psychology; Computer science","authors":[{"name":"Natalie C. Ebner","is_ca":false},{"name":"Donovan M. Ellis","is_ca":false},{"name":"Tian Lin","is_ca":false},{"name":"Harold A. Rocha","is_ca":false},{"name":"Huizi Yang","is_ca":false},{"name":"Sandeep Dommaraju","is_ca":false},{"name":"Adam Soliman","is_ca":false},{"name":"Damon L. Woodard","is_ca":false},{"name":"Gary R. Turner","is_ca":true},{"name":"R. Nathan Spreng","is_ca":true},{"name":"Daniela S Oliveira","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03963682329527232,"gpt":0.3194239522863014,"spread":0.2797871289910291,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001841522,0.0003549953,0.0002930251,0.001301512,0.000572378,0.001298705,0.000277939,0.0004616497,0.001732749],"category_scores_gemma":[0.0134663,0.0001868007,0.0003389117,0.0005533567,0.0004258269,0.001213212,0.001246098,0.0006380912,0.000309187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003279424,"about_ca_system_score_gemma":0.000428443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002236387,"about_ca_topic_score_gemma":0.003115651,"domain_scores_codex":[0.9995527,0.0001324422,0.00005010813,0.00008374743,0.0001062577,0.00007470462],"domain_scores_gemma":[0.993937,0.001174901,0.00286805,0.0005647615,0.0009084932,0.0005469249],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001184442,0.0002467473,0.9841793,0.00003077796,0.00004339895,0.00008461174,0.002268442,0.0000677158,0.0003797529,0.0001861145,0.0001641539,0.01223053],"study_design_scores_gemma":[0.000003444223,0.0002633002,0.9971036,0.0000243087,0.00004155725,0.0001707861,0.0009480051,0.0003087338,0.0002436966,0.0005217916,0.0003618371,0.000008793663],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9985412,0.0002203148,0.0002626268,0.0000834769,0.000006556612,0.00001438609,0.00008989823,0.000004013136,0.0007774321],"genre_scores_gemma":[0.999361,0.0001142591,0.0002081657,0.00003026652,0.00001001372,0.00001050159,0.00005622005,0.000001083137,0.0002086413],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002236387,"threshold_uncertainty_score":0.009738982,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2560459036","doi":"10.14722/ndss.2016.23407","title":"What Mobile Ads Know About Mobile Users","year":2016,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Mobile telephony; Mobile computing; Internet privacy; Mobile radio; Telecommunications","authors":[{"name":"Sooel Son","is_ca":true},{"name":"Daehyeok Kim","is_ca":true},{"name":"Vitaly Shmatikov","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.009135491329581665,"gpt":0.2383592746906329,"spread":0.2292237833610513,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005062025,0.0003289488,0.000429293,0.002482914,0.0005310273,0.002559296,0.0003268397,0.001152606,0.005321641],"category_scores_gemma":[0.01175187,0.0003058886,0.000349038,0.001808682,0.0004859192,0.004316331,0.0004627531,0.0009193571,0.002418973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005317313,"about_ca_system_score_gemma":0.0003469265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01019213,"about_ca_topic_score_gemma":0.0083497,"domain_scores_codex":[0.9991477,0.0001717986,0.0000731289,0.0001722668,0.0003114442,0.0001236982],"domain_scores_gemma":[0.9870402,0.006665568,0.002900465,0.0007336587,0.001955364,0.0007047487],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002938144,0.000191697,0.8860765,0.0003942047,0.0001587094,0.0004207578,0.003243831,0.0006706045,0.002018411,0.002046528,0.007355988,0.09712894],"study_design_scores_gemma":[0.00002021034,0.000230285,0.9263224,0.0003424088,0.0003679748,0.003219406,0.007372999,0.006937443,0.004183169,0.005401938,0.04549478,0.0001070776],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9439756,0.005694206,0.001873718,0.006116191,0.00009632263,0.00003684898,0.007719529,0.0001797162,0.03430788],"genre_scores_gemma":[0.9922781,0.001796457,0.0005120239,0.0007068941,0.0002536138,0.000009275152,0.001703021,0.0000294757,0.002711119],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01019213,"threshold_uncertainty_score":0.02026558,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2996568036","doi":"10.1109/iemcon.2019.8936148","title":"Spam Review Detection Using Deep Learning","year":2019,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","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 British Columbia","funders":"","keywords":"Artificial intelligence; Computer science; Machine learning; Perceptron; Deep learning; Support vector machine; Convolutional neural network; Perplexity; Recurrent neural network; Naive Bayes classifier; Focus (optics); Artificial neural network; Language model","authors":[{"name":"G. M. Shahariar","is_ca":false},{"name":"Swapnil Biswas","is_ca":false},{"name":"Faiza Omar","is_ca":false},{"name":"Faisal Muhammad Shah","is_ca":false},{"name":"Samiha Binte Hassan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01473273037901539,"gpt":0.2406082519381134,"spread":0.225875521559098,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007725216,0.000597966,0.0005843833,0.001767618,0.0003017595,0.0007536878,0.0006402783,0.0007990356,0.000833212],"category_scores_gemma":[0.002816982,0.0002646322,0.0003940965,0.0006027714,0.0002146535,0.0008634519,0.0005240439,0.0006066748,0.0008371933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008005736,"about_ca_system_score_gemma":0.00072633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004522417,"about_ca_topic_score_gemma":0.005744947,"domain_scores_codex":[0.9993364,0.000137385,0.00004823689,0.0001226572,0.0002724281,0.00008279891],"domain_scores_gemma":[0.9980626,0.0003362075,0.0003797606,0.0001192792,0.001018157,0.0000840238],"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":[0.0005609038,0.0005037991,0.02213306,0.0004204057,0.0002113169,0.0006527783,0.0002277648,0.05665868,0.03830904,0.002403181,0.02136336,0.8565558],"study_design_scores_gemma":[0.0000123365,0.0001215198,0.004424817,0.00002248617,0.00004090471,0.0001684871,0.00003703338,0.971002,0.01911884,0.001357792,0.003674856,0.00001886503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3506318,0.006113077,0.6207013,0.001441849,0.0004472608,0.0003553592,0.0009284072,0.008256595,0.01112438],"genre_scores_gemma":[0.9130851,0.0009388186,0.07481919,0.0004350268,0.0002105804,0.00008267314,0.001043159,0.00005916153,0.009326207],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004522417,"threshold_uncertainty_score":0.008992195,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3000358430","doi":"10.1016/j.cose.2020.101716","title":"A semantic-based classification approach for an enhanced spam detection","year":2020,"lang":"en","type":"article","venue":"Computers & Security","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Computer science; Categorization; Text categorization; Domain (mathematical analysis); Information retrieval; Bag-of-words model; Set (abstract data type); Semantic analysis (machine learning); Artificial intelligence; Data mining","authors":[{"name":"Nadjate Saidani","is_ca":true},{"name":"Kamel Adi","is_ca":true},{"name":"Mohand Saïd Allili","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04376752072950654,"gpt":0.2557178883192978,"spread":0.2119503675897913,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009847854,0.0007659252,0.0008860146,0.003670984,0.001025222,0.001389916,0.001013235,0.00150437,0.002812453],"category_scores_gemma":[0.001737561,0.0002158833,0.001216509,0.001968024,0.000556311,0.001906035,0.00111055,0.0009016349,0.001932051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006584266,"about_ca_system_score_gemma":0.001167282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002609462,"about_ca_topic_score_gemma":0.003808496,"domain_scores_codex":[0.9987769,0.0001819415,0.00008870148,0.0002262746,0.0005837472,0.0001423952],"domain_scores_gemma":[0.9990309,0.0001501729,0.00005162884,0.0001075621,0.0006096083,0.00004997429],"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":[0.0005389274,0.001081729,0.005699321,0.0002606431,0.0001871293,0.0002674602,0.0002332807,0.01299719,0.1066333,0.0188004,0.01112065,0.8421799],"study_design_scores_gemma":[0.00003282679,0.0003315671,0.006335113,0.00006342083,0.0002432115,0.0006086376,0.0002166522,0.9112495,0.0415017,0.02333117,0.01601004,0.00007618217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0443475,0.0006373179,0.9442947,0.000509347,0.0003215051,0.0002268224,0.0004473467,0.00262991,0.006585546],"genre_scores_gemma":[0.4823981,0.0004565307,0.5061788,0.0004290145,0.0003567728,0.000209279,0.00145714,0.0001615831,0.008352853],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003670984,"threshold_uncertainty_score":0.009408593,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1269365933","doi":"10.5281/zenodo.3264613","title":"Key Challenges in Defending Against Malicious Socialbots","year":2012,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":75,"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":"Exploit; Computer science; Computer security; Internet privacy; USable; Key (lock); Set (abstract data type); World Wide Web; Action (physics); Identity (music); Position paper; Malware","authors":[{"name":"Yazan Boshmaf","is_ca":true},{"name":"Ildar Muslukhov","is_ca":true},{"name":"Konstantin Beznosov","is_ca":true},{"name":"Matei Ripeanu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07050190566233419,"gpt":0.2613052626677512,"spread":0.190803357005417,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01142064,0.001203709,0.00166047,0.002257221,0.004044111,0.007791164,0.002738394,0.007384753,0.003924478],"category_scores_gemma":[0.03342269,0.001146188,0.0007078575,0.0008505596,0.006294872,0.0138034,0.006077369,0.005717563,0.002875529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001010469,"about_ca_system_score_gemma":0.001353529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007264211,"about_ca_topic_score_gemma":0.0005527784,"domain_scores_codex":[0.9903343,0.004417652,0.0005481011,0.001236212,0.002637829,0.0008258205],"domain_scores_gemma":[0.9537406,0.02753607,0.003440756,0.008138161,0.005174598,0.001969837],"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":[0.0004260306,0.0007019587,0.01396453,0.001839163,0.0003163718,0.001170159,0.00540792,0.04624446,0.01686818,0.4891883,0.0330162,0.3908568],"study_design_scores_gemma":[0.00009267591,0.0004968306,0.002612979,0.0005297063,0.0001014216,0.003445488,0.004393328,0.2080212,0.008712434,0.6966911,0.07475143,0.0001513964],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.1102944,0.01449662,0.6623697,0.1267801,0.001373228,0.0007214795,0.0002426246,0.001581638,0.08214021],"genre_scores_gemma":[0.9033965,0.003215464,0.07980045,0.003161406,0.001039224,0.0002908206,0.0001222286,0.0001296083,0.00884423],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.01142064,"threshold_uncertainty_score":0.06039882,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2009423697","doi":"10.1007/s10115-013-0658-2","title":"Email mining: tasks, common techniques, and tools","year":2013,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Categorization; World Wide Web; Data science; Visualization; Information retrieval; Data mining; Artificial intelligence","authors":[{"name":"Guanting Tang","is_ca":true},{"name":"Jian Pei","is_ca":true},{"name":"Wo-Shun Luk","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01539316849572635,"gpt":0.2287722311190385,"spread":0.2133790626233122,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009927617,0.002324489,0.002752721,0.01454405,0.002490113,0.007769799,0.003619723,0.003849448,0.001779404],"category_scores_gemma":[0.02434436,0.001162136,0.001958015,0.0162762,0.00176431,0.01004421,0.004155178,0.002900436,0.002587523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001155683,"about_ca_system_score_gemma":0.002504646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001199823,"about_ca_topic_score_gemma":0.001602099,"domain_scores_codex":[0.9870652,0.004455486,0.001852212,0.001936981,0.004121812,0.0005684348],"domain_scores_gemma":[0.9783638,0.012121,0.001603125,0.004175346,0.002947624,0.0007892702],"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":[0.0002506389,0.0005257511,0.01262045,0.003089922,0.000250043,0.0001944724,0.001049569,0.004089974,0.005254285,0.02611569,0.02167418,0.924885],"study_design_scores_gemma":[0.0001349604,0.0005337095,0.02943647,0.002633886,0.0006597433,0.005985161,0.004791792,0.2484223,0.04568275,0.4731155,0.1881957,0.0004081519],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.03655865,0.01923406,0.9237629,0.004986897,0.0003188959,0.0007993868,0.003449337,0.005123331,0.005766587],"genre_scores_gemma":[0.1756071,0.01434323,0.7970798,0.0008235562,0.0009404365,0.0007357559,0.00601661,0.000609273,0.003844228],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.01454405,"threshold_uncertainty_score":0.05250287,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2022302485","doi":"10.1145/1655008.1655012","title":"Browser interfaces and extended validation SSL certificates","year":2009,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; The Internet; USable; Certificate; Usability; World Wide Web; Public key certificate; User interface; Interface (matter); Computer security; Human–computer interaction; Public-key cryptography; Encryption; Operating system","authors":[{"name":"Robert Biddle","is_ca":true},{"name":"Paul C. van Oorschot","is_ca":true},{"name":"Andrew S. Patrick","is_ca":true},{"name":"Jennifer Sobey","is_ca":true},{"name":"Tara Whalen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01704865918906741,"gpt":0.2391694077861859,"spread":0.2221207485971185,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01565997,0.0006292352,0.0004258444,0.0008870811,0.0004526115,0.003663404,0.0008878891,0.001722038,0.00861811],"category_scores_gemma":[0.06457396,0.0006254236,0.0003902997,0.0005455909,0.001533686,0.006145308,0.002777517,0.001339147,0.002352576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004384262,"about_ca_system_score_gemma":0.000954462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000485947,"about_ca_topic_score_gemma":0.0004047509,"domain_scores_codex":[0.9836911,0.01234367,0.001119355,0.0004793777,0.001931269,0.0004351855],"domain_scores_gemma":[0.9393761,0.04034285,0.002803138,0.009905582,0.006406354,0.001165895],"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":[0.005116607,0.0008951166,0.05695044,0.001886493,0.0001407396,0.00220231,0.03414313,0.0112939,0.08507013,0.1735273,0.02016012,0.6086137],"study_design_scores_gemma":[0.001238515,0.006480257,0.04632495,0.002466293,0.0004012152,0.0142334,0.00992559,0.1593717,0.09058566,0.1635936,0.5044684,0.0009104211],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.3942153,0.001787221,0.5470086,0.001963318,0.0002089829,0.000398781,0.0003363457,0.01728496,0.03679658],"genre_scores_gemma":[0.9331164,0.0003680013,0.05908617,0.0003601639,0.00005268845,0.0001082504,0.0003042926,0.0006902943,0.005913778],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01565997,"threshold_uncertainty_score":0.08281887,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2049023511","doi":"10.1109/icdm.2013.131","title":"Classifying Spam Emails Using Text and Readability Features","year":2013,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":72,"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":"Computer science; Support vector machine; Artificial intelligence; Naive Bayes classifier; Header; Random forest; Machine learning; Readability; Bag-of-words model; Classifier (UML); Natural language processing","authors":[{"name":"Rushdi Shams","is_ca":true},{"name":"Robert E. Mercer","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02317222889243716,"gpt":0.2407261376359102,"spread":0.217553908743473,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001174694,0.0008913161,0.0008561107,0.007950076,0.0004719858,0.001028958,0.0004039297,0.0009545389,0.001179337],"category_scores_gemma":[0.006701939,0.0001416582,0.0004900876,0.002075192,0.0002765963,0.001647873,0.0004821442,0.0003919682,0.001364066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003513816,"about_ca_system_score_gemma":0.000310203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000968828,"about_ca_topic_score_gemma":0.001255609,"domain_scores_codex":[0.9989071,0.000215325,0.0001236969,0.0001526222,0.0004802102,0.0001209737],"domain_scores_gemma":[0.9938825,0.002255931,0.001270109,0.0004364156,0.001885022,0.000270056],"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":[0.001099206,0.001310761,0.2426354,0.0005740616,0.0002604267,0.0005814412,0.0004726051,0.01482489,0.05035232,0.001052693,0.0125202,0.6743161],"study_design_scores_gemma":[0.00007862636,0.001053803,0.3383529,0.000147797,0.0002924984,0.001579919,0.0006833056,0.5664331,0.07705244,0.004394293,0.00980023,0.0001309835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9006356,0.00115467,0.08548559,0.0002599725,0.0001466145,0.0003130198,0.00196803,0.003925317,0.006111185],"genre_scores_gemma":[0.9546387,0.0002470997,0.03859828,0.00008997674,0.0001989034,0.0001034724,0.003596093,0.00006984258,0.002457534],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007950076,"threshold_uncertainty_score":0.006212413,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3008564823","doi":"10.1016/j.ijhm.2020.102468","title":"Unveiling the cloak of deviance: Linguistic cues for psychological processes in fake online reviews","year":2020,"lang":"en","type":"article","venue":"International Journal of Hospitality Management","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"National Research Foundation of Korea; Ministry of Education","keywords":"Psychology; Perception; Interpersonal communication; Tourism; Deviance (statistics); Social media; Deception; Social psychology; Hospitality; Cognitive psychology; Computer science","authors":[{"name":"Lin Li","is_ca":false},{"name":"Kyung Young Lee","is_ca":true},{"name":"Minwoo Lee","is_ca":false},{"name":"Sung‐Byung Yang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06595700486655567,"gpt":0.3618096536729598,"spread":0.2958526488064042,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002840297,0.0002781776,0.0002336385,0.001384996,0.0009522625,0.003407258,0.0003159985,0.001526053,0.00297547],"category_scores_gemma":[0.0773428,0.0003372798,0.0001464405,0.0005819052,0.001082172,0.003810416,0.001936487,0.001699284,0.0005799819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004355338,"about_ca_system_score_gemma":0.0003538481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008131225,"about_ca_topic_score_gemma":0.001339983,"domain_scores_codex":[0.997519,0.001323549,0.000151598,0.0002508044,0.000635093,0.0001198956],"domain_scores_gemma":[0.9210468,0.05277318,0.01538479,0.003572098,0.005810154,0.001412997],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.004795558,0.001022575,0.2596526,0.001761939,0.0002445826,0.002946028,0.1340613,0.001222324,0.3931049,0.04336482,0.006936632,0.1508868],"study_design_scores_gemma":[0.0001787447,0.00135849,0.845156,0.0005472449,0.0003009666,0.003965796,0.03391995,0.02428729,0.02494094,0.04407367,0.02087068,0.0004002387],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9767537,0.0002479001,0.005773526,0.001270893,0.00008250197,0.00004762628,0.0001535208,0.00009845494,0.0155719],"genre_scores_gemma":[0.9962965,0.0000619809,0.002655079,0.0002421384,0.00006323568,0.00001707573,0.0000649197,0.00005566216,0.0005434538],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003407258,"threshold_uncertainty_score":0.01502109,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2913491028","doi":"10.1108/itp-05-2018-0241","title":"Purchase intention in an electronic commerce environment","year":2018,"lang":"en","type":"article","venue":"Information Technology and People","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Originality; Context (archaeology); Marketing; Order (exchange); Business; Value (mathematics); Identity theft; Sample (material); Perception; Test (biology); Identity (music); Conjoint analysis; E-commerce; Psychology; Computer science; Internet privacy; Economics; Social psychology; Microeconomics; World Wide Web","authors":[{"name":"Mahmud Akhter Shareef","is_ca":false},{"name":"Yogesh K. Dwivedi","is_ca":false},{"name":"Vinod Kumar","is_ca":true},{"name":"Gareth Davies","is_ca":false},{"name":"Nripendra P. Rana","is_ca":false},{"name":"Abdullah M. Baabdullah","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.005585596939215584,"gpt":0.2130304758763558,"spread":0.2074448789371402,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00113688,0.0002041029,0.0002498225,0.0005150916,0.0004578446,0.002095222,0.0002037813,0.0005038576,0.005856939],"category_scores_gemma":[0.004843152,0.0001439097,0.0005551478,0.0006842235,0.0004827082,0.0008693823,0.0007639025,0.0009039634,0.0005408868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005392131,"about_ca_system_score_gemma":0.00054358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002986263,"about_ca_topic_score_gemma":0.003506202,"domain_scores_codex":[0.9989507,0.0005129112,0.00006656077,0.0001092261,0.0002473381,0.0001132357],"domain_scores_gemma":[0.9947166,0.003101462,0.0009782292,0.0002516528,0.0004535881,0.0004984423],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004898219,0.002392449,0.962845,0.0001640141,0.0001476608,0.0004055329,0.004659029,0.00102217,0.001483359,0.001976807,0.0003921151,0.02402207],"study_design_scores_gemma":[0.00002926594,0.001598583,0.9798056,0.00007549259,0.0001039292,0.0001562975,0.008877899,0.006285975,0.0006785995,0.001088276,0.001260514,0.00003952133],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9962763,0.00003732998,0.0002622746,0.00007188367,0.000005500828,0.00002927527,0.0000504931,0.000004327836,0.003262609],"genre_scores_gemma":[0.9987695,0.00004011893,0.0002689447,0.00004227853,0.000003849947,0.00002048825,0.00006630106,0.000001774713,0.000786824],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005856939,"threshold_uncertainty_score":0.01959336,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1755863839","doi":"10.1007/3-540-45105-6_28","title":"Developing an Immunity to Spam","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Artificial immune system; Computer security; Computer virus; Immune system; Artificial intelligence; Immunology; Biology","authors":[{"name":"Terri Oda","is_ca":true},{"name":"Tony White","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03200594326978187,"gpt":0.2638408140163573,"spread":0.2318348707465754,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001110016,0.0005477781,0.0007979615,0.0009801068,0.0009954438,0.001499959,0.001013552,0.002564631,0.005627327],"category_scores_gemma":[0.004440375,0.0003807937,0.0006093081,0.000273183,0.001850078,0.002981005,0.002675464,0.002379239,0.002181282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004342168,"about_ca_system_score_gemma":0.0005744064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000143195,"about_ca_topic_score_gemma":0.0001389885,"domain_scores_codex":[0.9991032,0.0001965304,0.0000325623,0.0002455508,0.0002330522,0.0001891965],"domain_scores_gemma":[0.9973558,0.001041548,0.0002417103,0.0007877451,0.000394088,0.0001790185],"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":[0.0003446967,0.0007726195,0.003498457,0.0003331287,0.000132959,0.0003628895,0.0007169641,0.03192005,0.08381743,0.5129156,0.03173465,0.3334506],"study_design_scores_gemma":[0.0001265498,0.001020857,0.001844164,0.0001289921,0.0001561558,0.001221733,0.0003124467,0.3026055,0.07153998,0.5355911,0.08539816,0.00005439185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1526498,0.001707617,0.7505453,0.0074504,0.0008325905,0.0002613061,0.000115211,0.004478061,0.08195968],"genre_scores_gemma":[0.7920873,0.0008353562,0.162356,0.002681941,0.0005901133,0.0002026716,0.0001888509,0.0002300915,0.04082771],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005627327,"threshold_uncertainty_score":0.01882529,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}