{"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"},"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001370421,0.0000477464,0.00008830606,0.0003870618,0.0001744758,0.00008960132,0.000444572,0.00009634953,7.117514e-8],"category_scores_gemma":[0.002993792,0.00003727445,0.00002626466,0.001406812,0.00009671003,0.002805048,0.00009420183,0.00004408501,7.969525e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001256313,"about_ca_system_score_gemma":0.00008082962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001078738,"about_ca_topic_score_gemma":0.000009883714,"domain_scores_codex":[0.9992294,0.000001257319,0.0002275229,0.00009155172,0.0003327433,0.0001175456],"domain_scores_gemma":[0.9964992,0.00004074287,0.0006039751,0.00007229724,0.002762942,0.00002086264],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005082029,0.00003113158,0.03639295,0.0001245577,0.00002582106,1.616317e-9,0.002695858,0.00004547877,0.06353903,0.5840527,0.00112228,0.3119194],"study_design_scores_gemma":[0.00118033,0.0006109732,0.008958812,0.00003395549,0.00002969442,0.000006164295,0.001323923,0.05178091,0.6785801,0.2400145,0.01730505,0.0001755904],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8047193,0.00003791061,0.1843215,0.00580182,0.001073625,0.001216126,0.00001072215,0.0002448406,0.002574155],"genre_scores_gemma":[0.9951303,0.000004353818,0.004751336,0.00003778531,0.00001446191,0.00004335972,3.689872e-7,0.000001416838,0.00001663015],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6150411,"threshold_uncertainty_score":0.3584065,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002675043,0.0000853512,0.00008835766,0.00004376358,0.0009098006,0.000790576,0.0003362272,0.00007565566,0.00000211124],"category_scores_gemma":[0.0001651823,0.0000846158,0.0000196802,0.00005031743,0.0000536523,0.0009514948,0.0003009286,0.0001437686,0.000003387249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001496366,"about_ca_system_score_gemma":0.00001740627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004756821,"about_ca_topic_score_gemma":0.00005761478,"domain_scores_codex":[0.9993248,0.00004432384,0.000109555,0.0002873258,0.00009772599,0.0001362969],"domain_scores_gemma":[0.9993016,0.00004448259,0.0001378903,0.0004201075,0.00002771842,0.00006817666],"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":[0.00002366996,0.00004008113,0.03100326,0.0001083981,0.00001926606,0.000003854664,0.01169989,0.000004394463,0.01472512,0.0203855,0.0001070774,0.9218795],"study_design_scores_gemma":[0.001279086,0.0002334497,0.3712909,0.0002285087,0.00002254969,0.0001886164,0.0004039141,0.4696524,0.007976531,0.106729,0.04122649,0.0007686623],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9474009,0.0003397476,0.04956348,0.001168871,0.0006303838,0.0001058723,8.686641e-7,0.00007676376,0.0007131502],"genre_scores_gemma":[0.9953371,0.0001667433,0.004206768,0.0000623977,0.0002128415,0.000001726475,5.678272e-7,0.000004487247,0.000007384113],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9211108,"threshold_uncertainty_score":0.7623543,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001829389,0.0000226583,0.00001828883,0.000003583332,0.0002385646,0.00006414289,0.0003291931,0.00001468779,0.00002056965],"category_scores_gemma":[0.000007234361,0.00001330471,0.00001737901,0.0001013624,0.00001289689,0.00009987138,0.00005337832,0.00003438049,0.0001086565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004411312,"about_ca_system_score_gemma":0.000008429968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000070742,"about_ca_topic_score_gemma":0.00006273555,"domain_scores_codex":[0.9997303,0.00001836434,0.00003813708,0.00006312311,0.00005264653,0.00009745096],"domain_scores_gemma":[0.9997581,0.0000347517,0.00001344092,0.0001654319,0.00001203449,0.0000162262],"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":[0.000001489718,0.000004332432,0.0005106293,2.034383e-7,0.000004208288,5.939038e-7,0.0005533605,0.000003011116,0.000009597326,0.8701804,0.02754468,0.1011875],"study_design_scores_gemma":[0.0001404323,0.0001068356,0.05221494,0.000003412823,0.000003646979,0.000008618335,0.0000430336,0.01503395,0.00192773,0.6724896,0.2578284,0.0001994359],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001257741,0.00008162925,0.7280037,0.0008229124,0.001787567,0.00003947783,1.630527e-8,0.0002317974,0.2677752],"genre_scores_gemma":[0.9793283,0.00001193536,0.01717523,0.0005512413,0.0003034925,0.000004057878,3.084164e-8,0.000002239015,0.002623471],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9780706,"threshold_uncertainty_score":0.183487,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001392678,0.0001406845,0.0001771993,0.0000929329,0.0002954591,0.0002941276,0.0004008796,0.00006081283,0.00009905649],"category_scores_gemma":[0.0001091623,0.000123644,0.00007073584,0.0002823006,0.00003375061,0.0006836046,0.00006042567,0.0009115582,0.000206244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002266982,"about_ca_system_score_gemma":0.0004363405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006481892,"about_ca_topic_score_gemma":0.0002410233,"domain_scores_codex":[0.9980308,0.0001220582,0.0003475339,0.0002731094,0.000300949,0.0009255355],"domain_scores_gemma":[0.9991241,0.00004786858,0.000208088,0.0002695452,0.0002417951,0.0001085845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001158142,0.0001186369,0.001014711,0.0002215912,0.0002022658,0.00001241781,0.001349622,0.00005352196,0.0005475483,0.4091586,0.03272712,0.5545824],"study_design_scores_gemma":[0.0009804684,0.0007346169,0.004986166,0.0009868711,0.00007349304,0.004817139,0.0005084482,0.004314067,0.0001253442,0.7492456,0.2325531,0.0006746621],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02545298,0.06180202,0.7881223,0.1153843,0.001585074,0.0007801717,0.000002344755,0.0002902746,0.006580557],"genre_scores_gemma":[0.8779886,0.1052777,0.002781282,0.009142465,0.0008080683,0.00003291375,0.000007220962,0.00003041157,0.003931313],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8525357,"threshold_uncertainty_score":0.5042055,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.049162,0.00008486337,0.0002085931,0.0003239185,0.000253951,0.0003371114,0.0004865592,0.00006116129,0.00002239542],"category_scores_gemma":[0.008465343,0.00006643793,0.00006340176,0.000427648,0.00007387887,0.0004298442,0.0001779058,0.0007289514,0.00001904665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007045324,"about_ca_system_score_gemma":0.00007394433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001245249,"about_ca_topic_score_gemma":0.000003430434,"domain_scores_codex":[0.9957678,0.002565802,0.0003938767,0.0001920205,0.0007608727,0.0003196062],"domain_scores_gemma":[0.9977555,0.001156285,0.0002838958,0.000235641,0.0004095271,0.0001591456],"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":[0.0002904386,0.00005372643,0.009105,0.0001917808,0.00001532768,0.00001144875,0.0006432978,0.00001921406,0.008530444,0.000407696,0.0145506,0.966181],"study_design_scores_gemma":[0.002847362,0.002124956,0.085605,0.003359666,0.00002891007,0.001350612,0.000285608,0.1071526,0.002483282,0.003486874,0.7906251,0.000650057],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8625475,0.004007814,0.1253376,0.003068586,0.0008710637,0.0003613117,3.20742e-7,0.00005162873,0.003754204],"genre_scores_gemma":[0.9847821,0.001479094,0.01264447,0.00008409051,0.0006423716,0.00000380456,1.761263e-7,0.00001035442,0.0003535167],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.965531,"threshold_uncertainty_score":0.9998868,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005093018,0.00007316475,0.00007389486,0.0001053947,0.0001713917,0.0001665918,0.0001183224,0.00004672012,0.000004738821],"category_scores_gemma":[0.0001277638,0.00006858497,0.0000168802,0.0001454826,0.0000138366,0.0008896849,0.0001223201,0.00006469617,0.000008373953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001863065,"about_ca_system_score_gemma":0.00001186123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007726608,"about_ca_topic_score_gemma":0.000002083803,"domain_scores_codex":[0.9994586,0.00001779028,0.0001517762,0.0001098298,0.0001216541,0.0001403407],"domain_scores_gemma":[0.9995837,0.00008314152,0.00008568187,0.0001534636,0.00004587157,0.0000481007],"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":[0.002477747,0.000299279,0.0101947,0.001910445,0.0002748879,0.00001488077,0.1529467,0.0008314913,0.009421865,0.1468808,0.00655584,0.6681914],"study_design_scores_gemma":[0.001972025,0.000484817,0.02228767,0.00006992311,0.00001691188,0.00003548809,0.0001651527,0.9368455,0.01330707,0.0006796208,0.02383004,0.000305803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4219919,0.00003651646,0.5761412,0.00004541995,0.0004704281,0.0004515708,0.00008880603,0.0001193491,0.0006547185],"genre_scores_gemma":[0.9936067,0.000003683439,0.006179343,0.0001449719,0.00002747427,0.000008883775,0.00002412435,0.000002511531,0.000002261113],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.936014,"threshold_uncertainty_score":0.2796814,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003291988,0.0001019925,0.0001040374,0.0001290535,0.00005791304,0.00006110453,0.0003603133,0.00006503311,0.0002084368],"category_scores_gemma":[0.00002280653,0.00009424385,0.00004600349,0.0003863073,0.00007519771,0.0003689465,0.00001318105,0.0001919853,0.0002579228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005722205,"about_ca_system_score_gemma":0.00001901804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002000082,"about_ca_topic_score_gemma":0.00004839988,"domain_scores_codex":[0.9989908,0.0001258602,0.0001735657,0.0003580663,0.000143001,0.0002087619],"domain_scores_gemma":[0.9994542,0.00002546302,0.00003975291,0.0003809085,0.00004355359,0.00005611303],"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":[0.00005921563,0.0004140705,0.003816189,0.00001079758,0.00002130303,0.00003424364,0.1768833,0.000002036347,0.005218523,0.5653564,0.0005636667,0.2476202],"study_design_scores_gemma":[0.002146647,0.003057799,0.5227184,0.00009596498,0.00002319733,0.0001979747,0.003700427,0.02510926,0.006522258,0.4346477,0.0007885938,0.0009917902],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.923919,0.0000903077,0.05462986,0.0009686651,0.0006805395,0.000221454,5.064967e-7,0.0002917013,0.01919796],"genre_scores_gemma":[0.996662,0.000001462692,0.003120956,0.00006947946,0.00004482035,0.00001422905,7.592501e-7,0.000007187145,0.00007913919],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5189022,"threshold_uncertainty_score":0.3843153,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008041516,0.00008947519,0.00009838577,0.0003872531,0.0002721162,0.000269276,0.0009141872,0.00007283099,0.0000208614],"category_scores_gemma":[0.00101998,0.00006744855,0.0000278377,0.0008607334,0.0003243155,0.0001313165,0.000779571,0.0002202324,0.0002962853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001303269,"about_ca_system_score_gemma":0.0001486116,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01353189,"about_ca_topic_score_gemma":0.002704509,"domain_scores_codex":[0.9987128,0.0001741524,0.0001457479,0.0002893487,0.0002412886,0.000436679],"domain_scores_gemma":[0.9990715,0.0003171964,0.00003457301,0.0003196069,0.0001516743,0.0001054544],"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":[0.00002151905,0.00001640757,0.000253141,0.000003555905,0.00001882984,0.0000032687,0.06237579,2.286645e-7,0.001324293,0.7760747,0.09780625,0.06210199],"study_design_scores_gemma":[0.0005447476,0.0009567951,0.04328059,0.00005488652,0.000007153045,0.0001766135,0.0009193534,0.002433435,0.01290969,0.222108,0.7161855,0.0004232161],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6570385,0.0001285399,0.02026887,0.2190854,0.001857726,0.0003984803,0.000009874612,0.0003546976,0.1008579],"genre_scores_gemma":[0.9897558,0.000006553749,0.0005786092,0.003349312,0.005081946,0.00001350747,4.352462e-7,0.000009647696,0.001204154],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6183793,"threshold_uncertainty_score":0.9930371,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004781854,0.0003259739,0.001233436,0.001129063,0.0002321598,0.0004897544,0.0005173609,0.000194648,0.00005490247],"category_scores_gemma":[0.0003115973,0.0002706239,0.0002607798,0.002394579,0.00003779288,0.002396157,0.0001564144,0.0003443213,0.0002522736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001633808,"about_ca_system_score_gemma":0.0001267709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002013141,"about_ca_topic_score_gemma":0.000005942741,"domain_scores_codex":[0.997569,0.0001642124,0.001410457,0.000252622,0.0003777921,0.0002259237],"domain_scores_gemma":[0.998179,0.0001792253,0.000803387,0.0006425363,0.000108137,0.00008773342],"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":[0.000001293651,0.00002070868,4.364541e-7,0.4653804,0.00005777563,0.000004071238,0.0003252055,0.000001752445,5.273898e-9,0.004090767,0.00149059,0.528627],"study_design_scores_gemma":[0.0001599498,0.00004588216,0.000006135213,0.1756382,0.0001894193,0.0004180299,0.000005625997,0.001099384,8.918805e-8,0.0000641753,0.8220124,0.0003606954],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[3.16363e-7,0.9834206,0.01272268,0.00008445173,0.0005280856,0.0007439305,0.00002145523,0.0001394751,0.002339046],"genre_scores_gemma":[0.000009256618,0.9980909,0.0009754623,0.000129839,0.00004209483,0.0001198289,0.0003557096,0.00001010339,0.0002668631],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8205218,"threshold_uncertainty_score":0.9999746,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004447183,0.0001024455,0.0001056856,0.00004667811,0.0001639689,0.0002140475,0.0001647129,0.00004053548,0.00001704693],"category_scores_gemma":[0.0000426371,0.00008767015,0.00001453462,0.00006234454,0.00002217193,0.0007142172,0.0001645542,0.00008311948,0.00003190864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001285089,"about_ca_system_score_gemma":0.000008367615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003387826,"about_ca_topic_score_gemma":0.000002051109,"domain_scores_codex":[0.9990584,0.00004471416,0.000166361,0.0003685253,0.000171818,0.0001901553],"domain_scores_gemma":[0.999507,0.00005882292,0.00006806789,0.0002304131,0.00006264034,0.00007303311],"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":[0.000001613589,0.000008652889,0.0001476782,0.00004086288,0.000008762237,3.125276e-7,0.001822731,0.00007065212,0.01493623,0.003254301,0.0001076429,0.9796005],"study_design_scores_gemma":[0.0001728096,0.00005877154,0.005518336,0.00005109645,0.000005251326,0.000004933498,0.0001516324,0.9849805,0.001973493,0.006866086,0.00007199594,0.0001450973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.736765,0.002705421,0.247481,0.004238182,0.0002001115,0.0003378394,4.853545e-7,0.0002403333,0.008031659],"genre_scores_gemma":[0.970972,0.0004835925,0.02777842,0.0001580462,0.00009524442,0.00002595097,3.582841e-7,0.000006389957,0.0004799798],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9849098,"threshold_uncertainty_score":0.3575085,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001656433,0.0002194931,0.0001960696,0.0001552509,0.0003374431,0.000186841,0.0003267243,0.0001524381,0.00001753727],"category_scores_gemma":[0.000002469206,0.0002043301,0.0001088756,0.0004183562,0.00008946904,0.0005368607,0.000003370998,0.0004684671,0.000004912212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002500747,"about_ca_system_score_gemma":0.00001740835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001128796,"about_ca_topic_score_gemma":0.00003163092,"domain_scores_codex":[0.9986111,0.0001138342,0.000225198,0.0004994015,0.0002026885,0.0003478047],"domain_scores_gemma":[0.999332,0.00008747922,0.00007204079,0.0002888415,0.00004288594,0.0001767389],"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":[0.0006291369,0.002091733,0.001402924,0.00007785891,0.0002282063,0.0001230332,0.001908801,0.2231759,0.003310836,0.002238291,0.0005531529,0.7642601],"study_design_scores_gemma":[0.0005271015,0.0003680465,0.001346371,0.00001424264,0.00002129596,0.00004785171,0.00004507943,0.9941092,0.003224635,0.00002376337,0.00002888913,0.0002435847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03390646,0.00004391173,0.9640924,0.0001272089,0.0007697891,0.0001966452,0.000002011478,0.0003505918,0.0005110329],"genre_scores_gemma":[0.9930568,0.000008670511,0.00609583,0.000635927,0.00009297181,0.00002911211,0.00000121733,0.00001975161,0.00005974351],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9591503,"threshold_uncertainty_score":0.8332338,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006974103,0.0001139867,0.0002006339,0.0003181426,0.00009195897,0.0008254849,0.0004137496,0.00006839603,0.00002429356],"category_scores_gemma":[0.00009583835,0.0000888362,0.0001073725,0.0002530805,0.00001417548,0.005313002,0.00006495934,0.0002057898,0.0007617053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001396303,"about_ca_system_score_gemma":0.00004497979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001712504,"about_ca_topic_score_gemma":0.00000326657,"domain_scores_codex":[0.9983279,0.00005202774,0.0009073202,0.00006199627,0.000480966,0.0001697681],"domain_scores_gemma":[0.9978061,0.0000916745,0.0008752469,0.000212632,0.0008931353,0.0001211593],"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":[0.0001096611,0.0001514425,0.002389141,0.0004831726,0.000481357,0.00003390841,0.04137376,0.07295641,0.004571765,0.0341476,0.04754043,0.7957613],"study_design_scores_gemma":[0.0008754436,0.0008759424,0.006029048,0.0009784692,0.00002842664,0.002550117,0.005557073,0.7774924,0.0439749,0.00109639,0.1598213,0.0007205007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02710083,0.00007042575,0.9663028,0.0002210862,0.003428194,0.0002893156,0.000001222736,0.00004528021,0.002540801],"genre_scores_gemma":[0.9964986,0.00002995281,0.002911562,0.0001939897,0.0002808439,0.00001026435,0.000001402496,0.000004343116,0.0000689846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9693978,"threshold_uncertainty_score":0.9790435,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001114477,0.00003902742,0.0000347998,0.00003441191,0.00005859707,0.00004661622,0.0001982253,0.00002101053,0.00006549246],"category_scores_gemma":[0.000005056509,0.00002870985,0.000009699996,0.0001329808,0.00001455407,0.0003169423,0.00001175062,0.00004241147,0.0001001814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008599032,"about_ca_system_score_gemma":0.00001944931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005478574,"about_ca_topic_score_gemma":0.00002448803,"domain_scores_codex":[0.9996259,0.00001312317,0.00005246524,0.0001371645,0.0000876557,0.00008369153],"domain_scores_gemma":[0.9996958,0.00001153606,0.00002670481,0.0002099282,0.00002407267,0.00003193158],"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":[0.00002685258,0.00007812074,0.01713317,0.000008474512,0.00002610453,0.0000112604,0.02474273,0.000005674648,0.005572554,0.6806764,0.002709889,0.2690088],"study_design_scores_gemma":[0.001269237,0.001302876,0.7517868,0.00005666256,0.00002061255,0.0002193006,0.00208002,0.1086413,0.08077843,0.02667429,0.02613837,0.001032092],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03112452,0.00000319092,0.7893667,0.0001093099,0.0001085108,0.00003417773,6.621563e-8,0.0002363337,0.1790172],"genre_scores_gemma":[0.9431367,7.233902e-7,0.05626161,0.000140872,0.00002463132,0.000004531983,3.828188e-7,0.000002617371,0.0004279164],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9120122,"threshold_uncertainty_score":0.1287663,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001380749,0.0004995354,0.0006288149,0.001848655,0.0004382369,0.0007376428,0.002191255,0.000414428,0.00002624906],"category_scores_gemma":[0.0001478986,0.0004134994,0.0003202598,0.001699754,0.0004243566,0.0006950823,0.001054096,0.000713723,0.00004227492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004894648,"about_ca_system_score_gemma":0.0003207183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008194846,"about_ca_topic_score_gemma":0.0002077841,"domain_scores_codex":[0.9959559,0.00006863179,0.0005390402,0.001691521,0.001012597,0.0007323063],"domain_scores_gemma":[0.9971786,0.0006065078,0.0003558802,0.001445235,0.0002124978,0.0002013037],"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":[0.000007661019,0.00001793716,0.0004069814,0.00002093401,0.0001145739,0.000149561,0.0005593413,0.0726551,0.001787851,0.009425852,0.000002967511,0.9148512],"study_design_scores_gemma":[0.0001770963,0.0001094196,0.0002057946,0.0002202394,0.00008991525,0.0001370607,7.21731e-8,0.918476,0.003327478,0.076106,0.0003827665,0.0007681088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008122789,0.0002019963,0.9947646,0.0002897946,0.002011209,0.0001831515,0.000003162536,0.0002442042,0.001489571],"genre_scores_gemma":[0.7105703,0.00001280841,0.2873584,0.0007694427,0.0009913393,0.000003625223,0.000001071637,0.00003702457,0.0002558955],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9140831,"threshold_uncertainty_score":0.9998317,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001130066,0.00003542576,0.00002587214,0.00001547243,0.00004469591,0.0002804625,0.0003946344,0.00001536067,0.0003739726],"category_scores_gemma":[0.00000522328,0.00001532561,0.00001884973,0.00004256046,0.000009830688,0.0003077166,0.0001168191,0.00005673342,0.001974057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005982845,"about_ca_system_score_gemma":0.000002049544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004105683,"about_ca_topic_score_gemma":0.000008971552,"domain_scores_codex":[0.99966,0.00001776003,0.00005330562,0.00009787468,0.00006794505,0.0001030716],"domain_scores_gemma":[0.99972,0.00002664659,0.000007235536,0.0002071102,0.00001948709,0.00001953965],"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":[0.000004430007,0.00008493815,0.003921816,0.00001528792,0.00006757118,0.000006204999,0.01855783,0.0003099708,0.05458755,0.1501222,0.2421931,0.5301291],"study_design_scores_gemma":[0.0002326302,0.0001014732,0.00822462,0.00001185232,0.000004186641,0.00004132059,0.0001020511,0.443527,0.3799718,0.03945829,0.1280217,0.0003031528],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2357226,0.00001298182,0.7352465,0.00727835,0.0009845826,0.00008819631,1.930642e-8,0.0002199108,0.02044687],"genre_scores_gemma":[0.9925123,6.106268e-7,0.002359825,0.001020378,0.00007306878,0.00000836605,1.410387e-7,0.000001977091,0.004023326],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7567897,"threshold_uncertainty_score":0.998803,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004269169,0.0002090486,0.0001989347,0.0002601728,0.0002357144,0.0002779768,0.00108618,0.0001384399,0.00001596529],"category_scores_gemma":[0.00001922108,0.0001748616,0.00006801821,0.0003542192,0.0001169751,0.0017301,0.0002329844,0.000227175,0.00002618571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002246614,"about_ca_system_score_gemma":0.0000383367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009288152,"about_ca_topic_score_gemma":0.0001040957,"domain_scores_codex":[0.9981048,0.0001809468,0.0003575718,0.0006810269,0.0003208111,0.0003548297],"domain_scores_gemma":[0.9987735,0.00009125718,0.000118946,0.0007755192,0.00006078151,0.0001799841],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000004895247,0.0002141844,0.8824324,0.000006250084,0.000003101597,0.00007930119,0.00216304,0.00002123627,0.02631143,0.003350274,0.000683794,0.08473007],"study_design_scores_gemma":[0.0007757128,0.0002766227,0.9827936,0.0001389134,0.00001299941,0.00004255461,0.00001263373,0.001603048,0.0080822,0.005712611,0.0001201486,0.0004290073],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8449246,0.0000216863,0.153063,0.0004100862,0.0009803347,0.0001937313,0.000001547725,0.0003526949,0.00005226456],"genre_scores_gemma":[0.9796445,0.000002598032,0.01973012,0.0002769708,0.0002034391,0.00006074944,0.00000500412,0.00001945318,0.0000571204],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1347199,"threshold_uncertainty_score":0.713065,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001815693,0.0001876149,0.000249827,0.0002341058,0.0008777143,0.0001931818,0.0001374392,0.0001474938,0.00001975535],"category_scores_gemma":[0.001584924,0.0002022042,0.0001109947,0.0007094202,0.00003603886,0.0004427361,0.00009616778,0.0006536962,0.00001155615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007132317,"about_ca_system_score_gemma":0.0001129375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001110561,"about_ca_topic_score_gemma":0.004669997,"domain_scores_codex":[0.9980321,0.00069072,0.0003215033,0.000482862,0.000164788,0.0003080172],"domain_scores_gemma":[0.9981569,0.0008478569,0.0002612423,0.0002009471,0.000443802,0.00008923014],"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":[0.0003142455,0.0006769979,0.07859819,0.0004352889,0.0001392551,0.000009640134,0.001696517,0.02659841,0.1073209,0.0006196121,0.0001483694,0.7834426],"study_design_scores_gemma":[0.0007619748,0.0002785145,0.03993197,0.00004972693,0.00003068625,0.00003782632,0.00002153417,0.929416,0.009667629,0.0001164332,0.01946637,0.0002213262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04674602,0.004101609,0.9469688,0.0002245745,0.0009738376,0.0001545435,0.00001048637,0.0003388232,0.000481299],"genre_scores_gemma":[0.9964114,0.00009277288,0.002094066,0.00001583812,0.0001252356,0.00002414897,0.00009645087,0.00002418271,0.001115852],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9496654,"threshold_uncertainty_score":0.8245647,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","research_integrity"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.004977862,0.0001453625,0.0002155506,0.0007926989,0.0002407728,0.02413336,0.002053534,0.0002984691,0.000005964231],"category_scores_gemma":[0.005143691,0.0001327358,0.0001239295,0.001373303,0.00001588205,0.1296887,0.0001348576,0.003229367,0.000008858064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001785986,"about_ca_system_score_gemma":0.000220167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001059282,"about_ca_topic_score_gemma":3.863123e-7,"domain_scores_codex":[0.9973294,0.0001870071,0.0006002864,0.0002401006,0.001281492,0.0003616886],"domain_scores_gemma":[0.9972608,0.0002703188,0.000464608,0.0003055198,0.001382735,0.0003159822],"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":[0.00003981671,0.0003074761,0.007328746,0.00004002269,0.0001480121,0.0002721596,0.00803294,0.3780722,0.03525906,0.02037654,0.07606384,0.4740591],"study_design_scores_gemma":[0.006418151,0.003531426,0.1017054,0.001082602,0.0001453744,0.004033832,0.001221305,0.7081884,0.05089637,0.03475896,0.08713579,0.0008823975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1283825,0.00123991,0.8560486,0.01073287,0.001337601,0.00007904736,7.912908e-7,0.0001215562,0.002057022],"genre_scores_gemma":[0.881401,0.0002072611,0.1148715,0.00181563,0.001452976,6.543517e-7,0.000002272142,0.0000145356,0.0002341082],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7530185,"threshold_uncertainty_score":0.9990702,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001349855,0.00003610466,0.00004809474,0.00001722981,0.0006214986,0.00005863634,0.01638552,0.00001882043,6.017788e-7],"category_scores_gemma":[0.005533509,0.00001697507,0.00004708148,0.0001892738,0.0002714983,0.00008795688,0.0073735,0.0001075272,0.000001629563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008992871,"about_ca_system_score_gemma":0.00001368456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009621843,"about_ca_topic_score_gemma":0.0001439096,"domain_scores_codex":[0.9996156,0.00007362691,0.000108629,0.00006103525,0.00007058159,0.00007054119],"domain_scores_gemma":[0.9798878,0.005714837,0.00008963213,0.01424075,0.00005607584,0.00001091997],"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":[0.00005091726,0.00008388356,0.00242965,0.00001876193,0.00009345823,3.382485e-8,0.01012,0.0001546125,0.001731832,0.8024089,0.02213487,0.1607731],"study_design_scores_gemma":[0.00168622,0.0000634749,0.08500902,0.00007998534,0.00008895563,0.00002374787,0.0007956828,0.0731777,0.01022887,0.6155992,0.2130321,0.0002150071],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.05023545,0.00851602,0.269881,0.6623533,0.0016955,0.00118939,0.000005059434,0.0001303173,0.005993866],"genre_scores_gemma":[0.9556516,0.0001473782,0.04384181,0.0002477264,0.00002868864,0.00001816033,2.687493e-7,0.000002950413,0.00006142573],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9054161,"threshold_uncertainty_score":0.9889363,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03004212,0.00008878196,0.0001740021,0.001181237,0.0002928386,0.0006917514,0.0007408531,0.0001489036,0.000001451929],"category_scores_gemma":[0.001991267,0.00008641341,0.00001549038,0.001457591,0.0001874793,0.00646182,0.000228855,0.0006129086,0.000016366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002376754,"about_ca_system_score_gemma":0.00009310976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009855408,"about_ca_topic_score_gemma":0.000160538,"domain_scores_codex":[0.9948201,0.002360791,0.0006079596,0.0002679092,0.001571148,0.0003720677],"domain_scores_gemma":[0.9965746,0.001024448,0.0001735833,0.0006883732,0.001439901,0.0000990433],"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":[0.00009060126,0.0001436053,0.006291314,0.001783777,0.000007280991,0.000002224864,0.03331469,0.001135816,0.01315842,0.1612222,0.0004112726,0.7824388],"study_design_scores_gemma":[0.001307651,0.001285023,0.4738165,0.001715612,0.000001960348,0.00003301969,0.004927537,0.3970747,0.05608569,0.01339059,0.04959125,0.0007705308],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8231364,0.0000838066,0.1608068,0.0002047018,0.0001309951,0.0008444582,0.000003292063,0.0001516856,0.01463784],"genre_scores_gemma":[0.9972082,0.00002131058,0.002548626,0.000009571298,0.00004838865,0.0001162647,0.000003648258,0.0000046856,0.00003930236],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7816683,"threshold_uncertainty_score":0.9987757,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002124285,0.0001368394,0.0001205125,0.0001281668,0.0001667846,0.0003175014,0.0001776578,0.00009582821,0.00005033031],"category_scores_gemma":[0.000006484704,0.0001278136,0.00005257649,0.0003016698,0.00002404364,0.0008259666,0.0001335726,0.0002031772,0.00001285783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005499937,"about_ca_system_score_gemma":0.000009982539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001076578,"about_ca_topic_score_gemma":0.00004758894,"domain_scores_codex":[0.9989656,0.00004449971,0.0001581725,0.0004041796,0.0001901126,0.0002374972],"domain_scores_gemma":[0.9995385,0.00005456422,0.00004574947,0.0002398034,0.00004435372,0.00007707349],"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":[0.0001177347,0.00009137699,0.3007095,0.00006197142,0.0001082029,0.00003509454,0.001134203,0.05332462,0.06968389,0.0002488541,0.0004044578,0.57408],"study_design_scores_gemma":[0.0001365477,0.00005203919,0.07986248,0.00001277873,0.000007445698,0.0001798649,0.00001325183,0.9161395,0.003292787,0.00005750659,0.00006238865,0.0001834085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6897948,0.00004805525,0.307684,0.00004670964,0.001761257,0.0000703896,6.67907e-8,0.0001697429,0.0004249525],"genre_scores_gemma":[0.9970648,0.00000442345,0.001621026,0.0002546837,0.0003272244,0.000003855693,6.547735e-7,0.00001173917,0.0007115608],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8628149,"threshold_uncertainty_score":0.5212089,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000337747,0.00004088923,0.00004070808,0.00004048653,0.00006263883,0.00007345979,0.0002172169,0.00002469428,0.00001073199],"category_scores_gemma":[0.00001650063,0.00003575004,0.00002879429,0.00009319591,0.000005074277,0.0002138713,0.00004467769,0.00002829486,0.000009432559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001148214,"about_ca_system_score_gemma":0.000004854706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001422007,"about_ca_topic_score_gemma":0.00002407291,"domain_scores_codex":[0.9995854,0.000003036596,0.00007100149,0.0001326598,0.00007158897,0.0001362761],"domain_scores_gemma":[0.9997066,0.00006544415,0.000008758357,0.0001640778,0.00002103079,0.0000340335],"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":[0.00002143393,0.00004795129,0.002874447,0.00002871354,0.00002355315,0.000008957534,0.0006879129,0.00009588107,0.05389038,0.1141902,0.01132061,0.81681],"study_design_scores_gemma":[0.0003455913,0.0002733839,0.02572983,0.00001948694,0.000007088966,0.00002974518,0.000054705,0.07170282,0.7339962,0.01126313,0.1561412,0.0004368738],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01528987,0.00001496927,0.9704311,0.0001887326,0.0005120425,0.00006518346,1.636373e-7,0.0001922802,0.0133056],"genre_scores_gemma":[0.8958147,0.000001239425,0.1029483,0.0001839866,0.000119887,0.000004025753,3.528405e-7,0.000003137114,0.0009243704],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8805248,"threshold_uncertainty_score":0.1457844,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007197536,0.00008735635,0.0001310397,0.0002742635,0.000129711,0.0001896283,0.001322129,0.00005601885,0.00000976132],"category_scores_gemma":[0.000217056,0.00008056576,0.0001326332,0.0001412071,0.00001375335,0.004148132,0.0001537486,0.0002226018,0.00001439259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003118986,"about_ca_system_score_gemma":0.0001505762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002076585,"about_ca_topic_score_gemma":0.000001925217,"domain_scores_codex":[0.998623,0.00004735454,0.0005918821,0.00006538333,0.0005132182,0.0001592244],"domain_scores_gemma":[0.9979109,0.0001319234,0.0006432526,0.0001756174,0.001076057,0.00006227565],"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":[0.001247184,0.0005086897,0.007493738,0.0003459378,0.00140166,0.00006379541,0.07087353,0.003068331,0.0007970712,0.6522142,0.1734715,0.08851442],"study_design_scores_gemma":[0.006112775,0.0008168786,0.01494926,0.0003483313,0.00003359881,0.007217307,0.001071204,0.3158173,0.008254106,0.02478252,0.6199415,0.0006552331],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06586192,0.00005823976,0.9254875,0.003848563,0.002495833,0.0001450306,0.000007504047,0.00007254577,0.002022859],"genre_scores_gemma":[0.9936792,0.00004747047,0.005366042,0.0006235322,0.0002554643,0.000005921471,0.000007358521,0.000003561124,0.00001145696],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9278173,"threshold_uncertainty_score":0.3285376,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001423345,0.0001340457,0.0001201748,0.0004395843,0.000252541,0.0003242281,0.0005265882,0.0001168729,0.00005034481],"category_scores_gemma":[0.00006093248,0.0001271665,0.00007486576,0.0006147232,0.00001423222,0.003187826,0.000007364036,0.0001852314,0.000430677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001704604,"about_ca_system_score_gemma":0.00005869551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001238842,"about_ca_topic_score_gemma":0.00003121264,"domain_scores_codex":[0.9983114,0.00007381439,0.0005317117,0.0001540612,0.0007096652,0.0002193273],"domain_scores_gemma":[0.9985028,0.0001449955,0.0001468947,0.0007632796,0.0003499627,0.00009205045],"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":[0.00007374081,0.0002600287,0.0001587091,0.00009997499,0.00007899866,0.000001634502,0.006762241,0.05287727,0.0004258721,0.003438558,0.001183537,0.9346395],"study_design_scores_gemma":[0.002432073,0.0004169035,0.007154703,0.0001448591,0.00005299967,0.0001120734,0.002008959,0.8989283,0.006475163,0.0006632661,0.08093654,0.0006741566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01745955,0.00002102756,0.9763684,0.0003436571,0.00262818,0.0004538041,0.00001595286,0.000324894,0.0023846],"genre_scores_gemma":[0.9929525,0.00000677236,0.006419579,0.0003193716,0.0001075736,0.00004527009,0.00004488679,0.000006098046,0.00009795129],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.975493,"threshold_uncertainty_score":0.5535626,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001559633,0.0001072618,0.0001153254,0.0000710802,0.0001755831,0.0004279359,0.0005196912,0.00008530693,0.000008154347],"category_scores_gemma":[0.00002449011,0.0001074064,0.0001036492,0.0003785318,0.00001257587,0.001263673,0.0000270714,0.0001045373,0.00001378742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004100306,"about_ca_system_score_gemma":0.00007568418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005299817,"about_ca_topic_score_gemma":0.0002693634,"domain_scores_codex":[0.9990623,0.00002134019,0.0001533484,0.0003586651,0.0001758693,0.000228498],"domain_scores_gemma":[0.9993656,0.00005029124,0.00004547192,0.0003388977,0.0001348073,0.00006488495],"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":[0.0001263831,0.0003025355,0.0004308078,0.0002142147,0.0001087895,0.00002862042,0.002924627,0.06015046,0.2664713,0.005439469,0.003567515,0.6602353],"study_design_scores_gemma":[0.0002602002,0.00002990274,0.00012918,0.000008305592,0.000008537574,0.00001483882,0.000003687472,0.6479036,0.3408521,0.00911978,0.001550085,0.0001198813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06296917,0.00005048383,0.9338928,0.000440954,0.001647898,0.000159726,0.000003631739,0.0001740659,0.0006612982],"genre_scores_gemma":[0.9920931,0.00001669212,0.006649125,0.0004383813,0.0002263827,0.00007251829,0.000001989685,0.00001249321,0.0004893084],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9291239,"threshold_uncertainty_score":0.4379904,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001151889,0.000570946,0.0005081454,0.001102133,0.0004152778,0.00116545,0.004440122,0.0005147332,0.00001732237],"category_scores_gemma":[0.0001727868,0.0005155897,0.0001572476,0.0009162541,0.0002930029,0.0006791278,0.002125324,0.001384968,0.0001370753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002262061,"about_ca_system_score_gemma":0.0002429805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007687433,"about_ca_topic_score_gemma":0.0003575998,"domain_scores_codex":[0.9954895,0.00001633162,0.0004894051,0.002032836,0.001245135,0.0007267463],"domain_scores_gemma":[0.9968012,0.0003960161,0.000202509,0.00207113,0.000208991,0.0003201313],"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":[0.000009718587,0.0000293998,0.00002688896,0.00002201065,0.000005794296,0.00002262164,0.0007033122,0.01413309,0.001292153,0.006359766,0.00004025192,0.977355],"study_design_scores_gemma":[0.0003229963,0.0003233272,0.0006016277,0.0005145152,0.000009214742,0.0002077954,1.146817e-7,0.687315,0.006079202,0.2955309,0.007777695,0.001317581],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004136013,0.0001044597,0.9887847,0.0002955441,0.004726035,0.0004648118,0.000002714502,0.0002781879,0.004929963],"genre_scores_gemma":[0.07306693,0.000007134407,0.9246679,0.001120542,0.0009483292,0.00001726207,0.000002388689,0.00004307746,0.0001264304],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9760374,"threshold_uncertainty_score":0.9998714,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001021737,0.00008159294,0.0001104354,0.00001835297,0.0002324147,0.00007648337,0.0001094314,0.00009556853,0.000001294045],"category_scores_gemma":[0.00006201801,0.00008011344,0.00005308351,0.0001504385,0.00001901601,0.0001396108,0.00005396685,0.0002026327,9.179958e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001069405,"about_ca_system_score_gemma":0.00001221935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006193839,"about_ca_topic_score_gemma":0.00005896824,"domain_scores_codex":[0.9993972,0.00002417604,0.000102621,0.0002139163,0.00008903227,0.0001730636],"domain_scores_gemma":[0.9997085,0.00006406235,0.00005210106,0.00004449239,0.0000395938,0.00009123975],"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":[0.00005938964,0.00002959336,0.0002095361,0.00002101321,0.00002185994,0.00000180514,0.01161468,0.07917334,0.0003701383,0.0008519926,0.0007424575,0.9069042],"study_design_scores_gemma":[0.0002896627,0.00006626529,0.0003992924,0.000003433041,0.000009966287,0.000001000811,0.00007033839,0.9956532,0.00001736165,0.0009393386,0.002454872,0.00009532165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02105508,0.000145694,0.9761401,0.00203472,0.0003772191,0.00009094836,7.744663e-7,0.0001285058,0.00002693511],"genre_scores_gemma":[0.9865302,0.00006312209,0.009469603,0.001216364,0.002657945,0.00001088886,0.00001125398,0.00001045185,0.00003020022],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9666705,"threshold_uncertainty_score":0.3266931,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002566383,0.0001144952,0.0001246747,0.00009291187,0.0003443526,0.001016576,0.000609428,0.0001317872,0.00001820537],"category_scores_gemma":[0.0003971155,0.0001244795,0.0001026821,0.0006552144,0.00001378429,0.001031468,0.00007406581,0.0002957613,0.0000237762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005857494,"about_ca_system_score_gemma":0.00005461528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003781848,"about_ca_topic_score_gemma":0.0001276848,"domain_scores_codex":[0.9988981,0.00008446259,0.000155399,0.0004134752,0.0002026862,0.0002458606],"domain_scores_gemma":[0.9989064,0.0003764773,0.0001055142,0.0003680814,0.000174916,0.00006858041],"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":[0.000143256,0.0002558361,0.006351794,0.0002692958,0.0001070965,0.00008973066,0.001609727,0.1707467,0.03086593,0.006740903,0.000639724,0.7821801],"study_design_scores_gemma":[0.0004343996,0.000095644,0.002331089,0.00006521965,0.00001724728,0.00001674896,0.00001468263,0.6945519,0.2679216,0.0247211,0.009536423,0.000293974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03324974,0.0001280584,0.9630386,0.0004878668,0.002498154,0.0001145287,4.84886e-7,0.0003418879,0.0001406666],"genre_scores_gemma":[0.9722764,0.000006293827,0.0264426,0.0006824104,0.000448876,0.00005609035,0.000002442467,0.00001585482,0.00006906605],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9390266,"threshold_uncertainty_score":0.9802866,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000581479,0.0002001717,0.0003806017,0.0004973726,0.00007155018,0.00008415538,0.0004116939,0.0001927349,0.000006977511],"category_scores_gemma":[0.00002033722,0.000213164,0.000154537,0.001218968,0.00005358853,0.0005240529,0.000004050445,0.0003714467,0.00001657816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001590615,"about_ca_system_score_gemma":0.0001370591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003181239,"about_ca_topic_score_gemma":0.0004120123,"domain_scores_codex":[0.9979047,0.0002788425,0.0006359769,0.0004595657,0.0004658492,0.0002550186],"domain_scores_gemma":[0.9986026,0.0002185683,0.0002768326,0.0006006659,0.000220617,0.00008073126],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000494586,0.002374088,0.0006277461,0.001839834,0.0003818202,0.0001104403,0.01206383,0.1577673,0.6686377,0.00318663,0.0001836776,0.1523324],"study_design_scores_gemma":[0.001413362,0.0004293649,0.0002436761,0.0005770609,0.00003573989,0.00003656749,0.0002926126,0.2699089,0.7261865,0.0002573873,0.0003081125,0.0003106852],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09966881,0.0001915809,0.895238,0.0001298254,0.003463705,0.0002265085,0.000006133208,0.0001274574,0.0009479505],"genre_scores_gemma":[0.9980184,0.00001434485,0.001567836,0.00007370923,0.00003092715,0.00003699408,0.000001381261,0.00001983703,0.0002365156],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8983496,"threshold_uncertainty_score":0.8692576,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003900795,0.0000753985,0.00007802284,0.00003750466,0.00009118619,0.00005822833,0.000403022,0.00002910495,0.00003330568],"category_scores_gemma":[0.00002147249,0.00004639003,0.00003727193,0.0005510167,0.00006167048,0.0004961527,0.0001200823,0.0001053411,0.00001411949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003525068,"about_ca_system_score_gemma":0.00002012855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002157024,"about_ca_topic_score_gemma":0.000006144319,"domain_scores_codex":[0.9992594,0.00005174109,0.0001334936,0.0001132847,0.000200538,0.0002415245],"domain_scores_gemma":[0.9995431,0.00007075419,0.00005074555,0.0002175713,0.00004872938,0.00006907007],"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":[0.00009332326,0.002142318,0.03408002,0.0001929318,0.0001844885,0.000005602525,0.00647988,0.0003022802,0.01915634,0.4402696,0.002420211,0.494673],"study_design_scores_gemma":[0.004591452,0.0003850481,0.06971352,0.0002506402,0.0002552715,0.0003530854,0.003509373,0.7184394,0.1022278,0.01608525,0.08248207,0.001707063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06422258,0.0002231073,0.9295939,0.002225577,0.001162526,0.0001624429,8.131892e-7,0.000192057,0.002217033],"genre_scores_gemma":[0.9955724,0.0000202755,0.003884933,0.0002269771,0.000191971,0.000003849173,0.000001397642,0.000004966913,0.00009323205],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9313498,"threshold_uncertainty_score":0.1891731,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002392645,0.00005943024,0.00005609787,0.00004230577,0.00008271957,0.0002538338,0.000301794,0.00004251241,0.000009280622],"category_scores_gemma":[0.00008061386,0.00005477044,0.00001389588,0.0002198611,0.0000126325,0.000716953,0.00008059906,0.00006827294,0.00006865068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005773729,"about_ca_system_score_gemma":0.00003956001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000198735,"about_ca_topic_score_gemma":0.00009140465,"domain_scores_codex":[0.9993673,0.00004010059,0.00008881144,0.0001765994,0.0002128289,0.0001143773],"domain_scores_gemma":[0.9995359,0.00004277083,0.00003243857,0.0002435425,0.00007517845,0.00007019229],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001798527,0.0001912117,0.005209719,0.00002121456,0.00004626244,0.000008353605,0.004982763,0.001333327,0.02491343,0.4296001,0.4442925,0.0893831],"study_design_scores_gemma":[0.00196662,0.0006307876,0.00333781,0.00002746613,0.00002018643,0.000113704,0.001160534,0.5111934,0.142869,0.2034323,0.1340479,0.001200345],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02646113,0.00006998134,0.963667,0.001099836,0.000722578,0.00004303599,3.299702e-7,0.0002770213,0.007659031],"genre_scores_gemma":[0.9889342,0.000002755588,0.009794836,0.0003762427,0.0001046153,0.000002973267,0.000005088213,0.000004115751,0.0007751345],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9624731,"threshold_uncertainty_score":0.2447726,"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)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001828201,0.0001723844,0.0001493528,0.0006285537,0.0001587063,0.0001119365,0.001674999,0.0003648911,0.0001151852],"category_scores_gemma":[0.0001455516,0.0001720235,0.00008693312,0.0007139886,0.0001036822,0.0002888106,0.000045822,0.001093369,0.0002175511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003207076,"about_ca_system_score_gemma":0.00003336269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002801259,"about_ca_topic_score_gemma":0.0005310873,"domain_scores_codex":[0.9988413,0.00002692244,0.0002167882,0.0004666184,0.0001502215,0.0002980873],"domain_scores_gemma":[0.9985304,0.0001399169,0.00007207292,0.001131769,0.00006879863,0.00005702451],"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":[0.00001685509,0.0001521282,0.0002277789,0.000008906815,0.0000590629,0.00002476191,0.0002903735,0.00006297451,0.155866,0.00853595,0.0003423157,0.8344129],"study_design_scores_gemma":[0.0006113944,0.0009021828,0.0003165044,0.0000405821,0.00002489617,0.0004092245,0.00009981285,0.02805362,0.899895,0.02836155,0.04077437,0.00051083],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2533928,0.00001491772,0.7378473,0.004542626,0.001864341,0.0001049053,0.000001543656,0.001689888,0.0005416301],"genre_scores_gemma":[0.9649818,0.0000161858,0.0343467,0.0002426297,0.00004719804,0.00003483353,3.771435e-7,0.00001744531,0.0003128645],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8339021,"threshold_uncertainty_score":0.7014916,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006110691,0.00002158515,0.00001882881,0.00002109709,0.00002691073,0.00002671537,0.0002144658,0.00001412935,0.0001694116],"category_scores_gemma":[0.000004942687,0.00001767866,0.00001222519,0.0000903941,0.000004977393,0.0002126146,0.00003563998,0.00002277682,0.0002467766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003749627,"about_ca_system_score_gemma":0.000005767211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009241748,"about_ca_topic_score_gemma":0.000009262669,"domain_scores_codex":[0.9997805,0.000007673759,0.00003187357,0.00007758236,0.00004530255,0.00005709028],"domain_scores_gemma":[0.9997911,0.000005382372,0.000008193329,0.000162879,0.000009787522,0.0000226549],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000003150318,0.00005968674,0.003524218,0.000002252532,0.000007446549,0.00001052688,0.002352921,7.103829e-7,0.002001098,0.7096899,0.01654657,0.2658015],"study_design_scores_gemma":[0.0005634505,0.0004035654,0.2294575,0.00001134622,0.000006286259,0.00008397148,0.00006745658,0.02431673,0.3889694,0.2644358,0.09103126,0.0006532844],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004518081,0.000005917129,0.6984869,0.00009604006,0.0003093675,0.00001113549,1.677376e-8,0.0001900384,0.2963825],"genre_scores_gemma":[0.9299197,5.302966e-7,0.06869514,0.0002235687,0.0000198184,0.000001167407,3.108893e-8,0.000001130013,0.001138878],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9254016,"threshold_uncertainty_score":0.3171896,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004616316,0.0001183399,0.000117985,0.0001050745,0.0002392441,0.0003492439,0.0007077975,0.00006582643,0.0002249783],"category_scores_gemma":[0.0000442232,0.00007542394,0.00006663367,0.0003912092,0.00001476597,0.001302746,0.00024488,0.0001262121,0.0002462573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003105258,"about_ca_system_score_gemma":0.00001535309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005077508,"about_ca_topic_score_gemma":0.000719368,"domain_scores_codex":[0.9988698,0.00005718986,0.0001919818,0.0003738987,0.0002339623,0.0002731965],"domain_scores_gemma":[0.9992675,0.00005802223,0.00008344598,0.0004542528,0.00005030468,0.00008645776],"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":[0.00004327825,0.0004231381,0.188034,0.0001367999,0.0001387005,0.0001438193,0.08528548,0.00001766234,0.1248016,0.5208678,0.01241411,0.06769368],"study_design_scores_gemma":[0.001268864,0.0003334404,0.3767746,0.0001230271,0.00003671977,0.0001175034,0.001316865,0.0211281,0.3352051,0.24884,0.01304863,0.001807056],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4606587,0.00002417137,0.5169584,0.0006811615,0.001711824,0.00008526786,3.960653e-7,0.0006398554,0.01924022],"genre_scores_gemma":[0.9428809,0.000004556456,0.05582936,0.0002560355,0.0001926776,0.000007176241,8.445597e-7,0.000008966579,0.000819521],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4822221,"threshold_uncertainty_score":0.3367767,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000111736,0.00007121228,0.0000701824,0.00003568631,0.0001537052,0.0001614893,0.0002648273,0.00002652959,0.0002506264],"category_scores_gemma":[0.00002818329,0.00005019943,0.00002002083,0.0002633,0.00002557672,0.0006122974,0.00007691688,0.00009412652,0.0004562557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002672867,"about_ca_system_score_gemma":0.00002579645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007690769,"about_ca_topic_score_gemma":0.0001391884,"domain_scores_codex":[0.9993476,0.00003868788,0.00009242756,0.000243075,0.0001259553,0.0001522101],"domain_scores_gemma":[0.9993919,0.00008243586,0.00003850724,0.0003257303,0.00009840381,0.00006305057],"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":[0.00003977918,0.0005546772,0.1926813,0.00008327101,0.0001369861,0.000006758258,0.01011099,0.0006747371,0.01323275,0.05564516,0.0209304,0.7059032],"study_design_scores_gemma":[0.001019239,0.001181203,0.5755179,0.00006324451,0.000009060444,0.0000666292,0.0006067458,0.314317,0.09085083,0.01321811,0.002312531,0.0008375546],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2763421,0.000004153431,0.7094615,0.0003906879,0.0001819245,0.0002701242,4.591007e-7,0.0003656693,0.01298345],"genre_scores_gemma":[0.9119312,1.560078e-7,0.08767033,0.0001035033,0.00003117587,0.00003822491,0.000001000324,0.000003449415,0.0002210168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7050657,"threshold_uncertainty_score":0.5864396,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002612968,0.00008114721,0.00009444371,0.0001202661,0.000224622,0.0000773299,0.0004775499,0.00004441002,0.000001044002],"category_scores_gemma":[0.0001051403,0.00005284529,0.00006569197,0.0004681409,0.00001804985,0.0003388345,0.00002244642,0.001081544,0.000003887308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000522732,"about_ca_system_score_gemma":0.001012948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002429391,"about_ca_topic_score_gemma":0.000466339,"domain_scores_codex":[0.9979647,0.000148888,0.0002680675,0.0001477163,0.0002358835,0.001234703],"domain_scores_gemma":[0.9994006,0.0001085934,0.0001649443,0.0002301725,0.00006408855,0.00003161758],"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":[0.00006076022,0.0000591247,0.0004006901,8.878885e-7,0.00002545404,0.00000244031,0.0002643448,0.0002516439,0.002246208,0.6462635,0.00008537804,0.3503395],"study_design_scores_gemma":[0.000385107,0.0005621082,0.01178922,0.00001520015,0.000005848066,0.0003255276,0.000113395,0.005911006,0.0007967678,0.9789276,0.001070351,0.00009794348],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7708027,0.007640707,0.2132302,0.00675278,0.000501485,0.0001992872,1.422629e-7,0.00007434226,0.0007983831],"genre_scores_gemma":[0.9949902,0.00454803,0.000146179,0.00007150941,0.00005490275,0.000001454603,2.460711e-7,0.000003985735,0.0001834796],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3502416,"threshold_uncertainty_score":0.4698829,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001017767,0.00009525308,0.0001076974,0.000151096,0.0003584739,0.0001300204,0.0007235113,0.00005123945,0.00003632575],"category_scores_gemma":[0.00002536284,0.0001035949,0.0000390945,0.0004746063,0.00001668518,0.002675271,0.0004852609,0.00036185,0.00005249715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001562773,"about_ca_system_score_gemma":0.00001624588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002103921,"about_ca_topic_score_gemma":0.0006023893,"domain_scores_codex":[0.9989013,0.0002994052,0.0001068875,0.0001427886,0.0001722354,0.000377387],"domain_scores_gemma":[0.9992994,0.00008988327,0.00004360708,0.0004348131,0.00002087107,0.000111389],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008536932,0.003482413,0.5294379,0.0000642984,0.00007805767,0.00004931537,0.2751337,0.0002509282,0.0351656,0.09401022,0.004968441,0.05727376],"study_design_scores_gemma":[0.01862369,0.0006077226,0.3290209,0.00057158,0.00006496695,0.0002052966,0.04422971,0.2235816,0.1886377,0.009967357,0.1799668,0.004522726],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8410222,0.00007702974,0.1318738,0.0002151044,0.0006035698,0.00008522072,8.588922e-7,0.0002487892,0.02587347],"genre_scores_gemma":[0.9906209,0.000003494416,0.008700172,0.0003060235,0.00006857031,0.000001035507,0.000001522872,0.000005796905,0.0002925401],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.230904,"threshold_uncertainty_score":0.4224479,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002025678,0.0001680099,0.0001539665,0.00008028747,0.0001561207,0.0001281513,0.0004332547,0.00009730754,0.00001727217],"category_scores_gemma":[0.0002695507,0.0001654103,0.00009136083,0.0002884888,0.00001697276,0.0002639825,0.0001482353,0.000119087,0.00003672165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009785647,"about_ca_system_score_gemma":0.00002820875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001223596,"about_ca_topic_score_gemma":0.000001588617,"domain_scores_codex":[0.9987914,0.000006578483,0.00019612,0.0004053984,0.0002277199,0.0003728042],"domain_scores_gemma":[0.9991916,0.0002089946,0.00004565119,0.0003507295,0.00008125326,0.0001217793],"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":[0.0001310518,0.0003352782,0.01267989,0.0006119062,0.000342052,0.00002800393,0.02752668,0.005494665,0.02379232,0.001998923,0.1224897,0.8045695],"study_design_scores_gemma":[0.00103528,0.001316466,0.01022745,0.0001036304,0.00002589156,0.00001796729,0.00003143495,0.2745195,0.08418881,0.000349186,0.6272004,0.0009840395],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08635495,0.00004617598,0.910548,0.0005946341,0.001387161,0.0001704359,0.00000454143,0.0008697935,0.00002431784],"genre_scores_gemma":[0.7604935,0.000001456055,0.2367647,0.001262234,0.001113167,0.00007261984,0.000003024299,0.00003094546,0.0002584015],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8035855,"threshold_uncertainty_score":0.6745236,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001153156,0.0001800878,0.0003330652,0.000132939,0.003314662,0.0002602656,0.0005977403,0.00006148577,0.00001456001],"category_scores_gemma":[0.00002503079,0.000198508,0.0002296239,0.001483939,0.00003258643,0.0002687861,0.0004347431,0.000245622,5.665423e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007284704,"about_ca_system_score_gemma":0.00004365522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003419378,"about_ca_topic_score_gemma":0.0003293702,"domain_scores_codex":[0.9979731,0.000221349,0.0002771247,0.0007059688,0.0003468454,0.0004756071],"domain_scores_gemma":[0.9991347,0.0001568686,0.0002310874,0.0003616155,0.00005323361,0.00006253407],"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":[0.0000867972,0.00003117256,0.0007094766,0.000005499473,0.0001967623,0.000001931093,0.0007125624,0.9033332,0.00001003999,0.0003717589,0.00280731,0.09173353],"study_design_scores_gemma":[0.0003366045,0.0001049824,0.0009938536,0.000002042621,0.0003792373,0.000001065944,0.00006604535,0.9961125,0.000005113096,0.001032864,0.0007425888,0.000223141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02065276,0.00009896008,0.977894,0.0003984915,0.0004728364,0.000233502,0.00002574868,0.0001253485,0.00009831921],"genre_scores_gemma":[0.9770885,0.000002027097,0.02016204,0.0007111428,0.001634936,0.0001365259,0.0001701957,0.00001994944,0.00007475408],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.957732,"threshold_uncertainty_score":0.9979829,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001312409,0.00008392493,0.000170892,0.000112204,0.0001561737,0.00004120113,0.0005696415,0.00005619103,0.00003264585],"category_scores_gemma":[0.0002607982,0.00006277546,0.00004110507,0.0003159074,0.0001231647,0.0005062018,0.0001671525,0.0002094711,0.00001162872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005994276,"about_ca_system_score_gemma":0.00002413036,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009247382,"about_ca_topic_score_gemma":0.0251254,"domain_scores_codex":[0.9989186,0.0002501379,0.0003049861,0.0001767234,0.000137679,0.000211878],"domain_scores_gemma":[0.9991145,0.0001101278,0.0001949606,0.0004176753,0.0001153677,0.00004737232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007446519,0.0003236626,0.5101698,0.00004258919,0.0001128949,0.00001621824,0.04387042,0.00524371,0.08557575,0.00149614,0.001822963,0.3505812],"study_design_scores_gemma":[0.0003482909,0.0008121143,0.9571387,0.00007711834,0.00001193009,0.0001268756,0.0007180032,0.001740961,0.01738493,0.01982022,0.001645589,0.0001752623],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9348211,0.0001752345,0.05973782,0.004423554,0.0006343862,0.00007444089,0.000001596508,0.00003290856,0.00009897149],"genre_scores_gemma":[0.9908812,0.0001067469,0.008488921,0.0002920972,0.0001975427,0.000001704101,2.211014e-7,0.00000407907,0.00002747218],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4469689,"threshold_uncertainty_score":0.9926635,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001625118,0.00009091688,0.0000825004,0.00005987479,0.00007813163,0.0002935455,0.0004975303,0.00005800151,0.0002406166],"category_scores_gemma":[0.00001130221,0.00005695342,0.00005439084,0.0001680706,0.00003792273,0.001999352,0.0001178596,0.00004726108,0.0008092942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003962674,"about_ca_system_score_gemma":0.00002516732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005530588,"about_ca_topic_score_gemma":0.00003045366,"domain_scores_codex":[0.9991801,0.00003055777,0.000114305,0.0002965028,0.0001693515,0.0002091227],"domain_scores_gemma":[0.9992394,0.00008613291,0.00003525989,0.0005048898,0.00004863762,0.00008562942],"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":[0.000005616053,0.00005113828,0.0008643612,0.000005600164,0.00001230944,0.000004544816,0.0008995152,0.0000499765,0.009581718,0.009733574,0.008174638,0.970617],"study_design_scores_gemma":[0.0007855626,0.0006649196,0.003347839,0.0001749241,0.00000722607,0.00002031269,0.0001889883,0.004999592,0.08567262,0.004952548,0.8986414,0.0005440686],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3852855,0.002310566,0.5948685,0.001104981,0.007541539,0.0005019888,0.000001540673,0.001320146,0.007065229],"genre_scores_gemma":[0.9858277,0.0005068575,0.003280426,0.0003983873,0.0001557615,0.0001009799,2.238813e-7,0.000009096895,0.009720545],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9700729,"threshold_uncertainty_score":0.9999687,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002713827,0.00006051232,0.00008566798,0.0000455612,0.00007943776,0.00007312779,0.0001873787,0.00003163409,0.0001123837],"category_scores_gemma":[0.00003450933,0.00005410034,0.00004227908,0.000306335,0.000003870276,0.0004229659,0.00006229468,0.0001239818,0.000428748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003495567,"about_ca_system_score_gemma":0.000008743396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007288987,"about_ca_topic_score_gemma":0.000009683867,"domain_scores_codex":[0.9993975,0.0000536941,0.0001013633,0.0001970899,0.0001313624,0.0001189862],"domain_scores_gemma":[0.9996315,0.00002607748,0.00005074034,0.0002243228,0.00003621423,0.00003118976],"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":[0.000004714632,0.00002583084,0.005199705,0.0004866469,0.00002041182,0.000004161066,0.0002551453,0.003035323,0.04562715,0.003456335,0.0000949961,0.9417896],"study_design_scores_gemma":[0.0001557985,0.0001302166,0.001732394,0.0003299761,0.00001103621,0.00007730384,0.00001158683,0.9537795,0.01249937,0.000481285,0.03054954,0.0002420123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0684861,0.0017986,0.9213421,0.0001291444,0.0008899957,0.0001456645,1.308437e-8,0.0003154049,0.006892934],"genre_scores_gemma":[0.9890862,0.0003291402,0.009318814,0.0005114811,0.00006378733,0.000002082415,2.165754e-7,0.00000589038,0.0006823961],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9507442,"threshold_uncertainty_score":0.5510831,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002520181,0.0001658257,0.0001767504,0.00007270459,0.0002213869,0.0002654917,0.0006404109,0.0001055683,0.000001200564],"category_scores_gemma":[0.0000429916,0.0001773394,0.0001049763,0.0004970687,0.00003127378,0.0005710846,0.00006813784,0.0001689096,0.000008870608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005372889,"about_ca_system_score_gemma":0.00004591546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001948137,"about_ca_topic_score_gemma":0.000006425259,"domain_scores_codex":[0.9985601,0.0001124829,0.0002166733,0.0006610975,0.0002088792,0.0002408155],"domain_scores_gemma":[0.9990469,0.00007701892,0.0001293514,0.0004418585,0.0001198682,0.0001849684],"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":[0.0006858197,0.001551117,0.0004012048,0.00101637,0.0001380871,0.000006188731,0.02197628,0.02048871,0.3197951,0.02465392,0.00517503,0.6041122],"study_design_scores_gemma":[0.0005296177,0.0004614147,0.001102174,0.000007016807,0.000009762298,0.000002166361,0.00002508926,0.9620135,0.03335742,0.001117362,0.00116508,0.0002093292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03212957,0.00002109934,0.9652181,0.0007409312,0.0006071453,0.0004768367,0.000002877275,0.0006128065,0.0001906364],"genre_scores_gemma":[0.9157631,0.000001314143,0.08274621,0.001034827,0.0003603242,0.00005528903,0.00002462444,0.00001285914,0.000001386514],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9415249,"threshold_uncertainty_score":0.7231693,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003550348,0.0000618589,0.00006894136,0.00008546204,0.0000561109,0.00004546473,0.0002328753,0.0000526924,0.000008512367],"category_scores_gemma":[0.00002249757,0.0000577144,0.00002638925,0.0001553602,0.000007696841,0.0005195513,0.00007857152,0.00008044452,0.0001028119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000467152,"about_ca_system_score_gemma":0.000008842335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000471181,"about_ca_topic_score_gemma":0.0001156917,"domain_scores_codex":[0.9993698,0.00004379298,0.00008864059,0.0001338396,0.0001116511,0.0002522891],"domain_scores_gemma":[0.9996974,0.00004420962,0.00002523251,0.0001676735,0.000009838112,0.00005561214],"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":[0.000003623681,0.0001452466,0.02018016,0.00002087741,0.00001210771,0.000007813028,0.01973623,0.00004841371,0.001939259,0.4264511,0.0009019553,0.5305532],"study_design_scores_gemma":[0.002524814,0.000307382,0.7354403,0.0001835249,0.00001742601,0.0001117854,0.00314212,0.034597,0.02962453,0.03758315,0.1539908,0.002477179],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6344297,0.004397481,0.07383828,0.004580386,0.003602737,0.0001960103,3.570228e-7,0.0007267532,0.2782283],"genre_scores_gemma":[0.9959313,0.0001793086,0.003330656,0.0002418451,0.000202022,0.00000532214,2.069964e-7,0.000004420172,0.0001049473],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7152601,"threshold_uncertainty_score":0.2353525,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000269684,0.00008651211,0.0001182465,0.0001241055,0.0001370568,0.001125468,0.0001475569,0.00007648922,0.000003222534],"category_scores_gemma":[0.00001774483,0.00007361711,0.00001386274,0.00016643,0.00002031368,0.007821758,0.00009426787,0.0000626214,0.0001517724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001846667,"about_ca_system_score_gemma":0.00001565341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001233378,"about_ca_topic_score_gemma":0.0000041162,"domain_scores_codex":[0.9993973,0.00003775317,0.0002678625,0.00009093162,0.00009219969,0.0001139831],"domain_scores_gemma":[0.9994678,0.00005265635,0.0001025156,0.0001927405,0.0001129001,0.00007141756],"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":[0.000002228769,0.00001244349,0.001167536,0.0002013258,0.00001055204,4.747519e-7,0.007039928,0.000001448544,0.0001184494,0.03513667,0.02678557,0.9295233],"study_design_scores_gemma":[0.0003308432,0.0001528561,0.004331955,0.0001355436,0.000004368319,0.0001818838,0.000699776,0.04502887,0.001005423,0.0001732885,0.9476953,0.0002599056],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4495901,0.005807269,0.1189352,0.0008664399,0.003206076,0.002332732,0.00001075316,0.001700756,0.4175507],"genre_scores_gemma":[0.9985225,0.00006858673,0.0008617189,0.00007741179,0.0001014685,0.00007686704,0.000006866403,0.000002917044,0.0002816151],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9292635,"threshold_uncertainty_score":0.9999115,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009615922,0.00004753577,0.00004218415,0.00004089102,0.00005557013,0.0002093652,0.0001500275,0.00002503536,0.00001885551],"category_scores_gemma":[0.00001443389,0.00003866431,0.000009984742,0.0001080889,0.000009189138,0.0004613601,0.00002477546,0.00003711697,0.00002905134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006657503,"about_ca_system_score_gemma":0.000003701946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001928944,"about_ca_topic_score_gemma":0.000002067836,"domain_scores_codex":[0.9995968,0.00001732579,0.00007247637,0.0001663258,0.00007081353,0.00007629376],"domain_scores_gemma":[0.9997573,0.00001953815,0.00002142143,0.000151459,0.00002123715,0.00002896695],"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":[0.0000121452,0.00007918401,0.0005319265,0.000005615784,0.000008525395,0.00000203657,0.001270311,0.00003389135,0.1275385,0.04121162,0.004697002,0.8246093],"study_design_scores_gemma":[0.0002206825,0.0003022513,0.06820229,0.00001235818,0.000004943596,0.00002492628,0.00004198542,0.03106896,0.8359324,0.06023329,0.003733683,0.0002222714],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5039491,0.0001490568,0.4780508,0.00830255,0.0003817376,0.00009496621,1.82813e-7,0.0004567576,0.008614913],"genre_scores_gemma":[0.9924403,0.000009365887,0.006794868,0.0002445124,0.00002581492,0.000001057143,3.781167e-7,0.000001357305,0.0004823145],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.824387,"threshold_uncertainty_score":0.2018913,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001601926,0.0000707861,0.00007451203,0.00004136456,0.0001360114,0.0003753848,0.0001732859,0.00005236179,0.00004765221],"category_scores_gemma":[0.00004295239,0.00005546677,0.00002076703,0.0001452682,0.00003020414,0.0007340124,0.0001154461,0.00009202537,0.00002759333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002474726,"about_ca_system_score_gemma":0.0000147519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001200879,"about_ca_topic_score_gemma":0.00004300315,"domain_scores_codex":[0.9993774,0.00003640916,0.00008802808,0.0002445747,0.0001099335,0.0001437058],"domain_scores_gemma":[0.9995199,0.00006483561,0.00002933586,0.0002805703,0.00004128822,0.00006403116],"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":[0.00000952796,0.0001135582,0.06665201,0.0001033646,0.00004223083,0.000007613863,0.002803319,0.000147217,0.1146292,0.04037078,0.01354022,0.761581],"study_design_scores_gemma":[0.0003388007,0.0001572963,0.5305276,0.00005850475,0.00001387527,0.0001983907,0.0002445181,0.3705335,0.04077718,0.05260353,0.003854539,0.0006922617],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7782711,0.0001084346,0.2132415,0.001048992,0.0003477157,0.0001455255,1.446462e-7,0.0002205353,0.00661603],"genre_scores_gemma":[0.9491464,0.000003081079,0.05017306,0.0002398417,0.00005774199,0.000003222959,1.191604e-7,0.000003213756,0.0003732961],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7608888,"threshold_uncertainty_score":0.3619845,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006829078,0.00007461537,0.0001671304,0.00006438177,0.00002246652,0.00007106541,0.001108846,0.00002067394,0.000004761712],"category_scores_gemma":[0.0008307919,0.00004975213,0.00009776255,0.0002192164,0.00002615664,0.0001687864,0.0001144394,0.0001171006,0.000001815493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003644458,"about_ca_system_score_gemma":0.00001620969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003914235,"about_ca_topic_score_gemma":0.00000708793,"domain_scores_codex":[0.9988148,0.0000487744,0.0005786082,0.0001446277,0.0003300249,0.00008316234],"domain_scores_gemma":[0.9989498,0.00009754164,0.0004362037,0.0001145382,0.0003699866,0.00003197724],"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":[0.0007537571,0.002749681,0.02159659,0.001912788,0.00081777,0.000273044,0.01255549,0.006266646,0.0003617776,0.08801596,0.01114562,0.8535509],"study_design_scores_gemma":[0.0071571,0.005143368,0.2338077,0.003590711,0.0002501761,0.0001166225,0.001815915,0.04164222,0.003078276,0.1160023,0.5862766,0.001119082],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.269501,0.003906902,0.6959779,0.02617949,0.00279227,0.0006932763,0.00001274349,0.00003009989,0.0009063468],"genre_scores_gemma":[0.9766136,0.0009059788,0.02105089,0.001021983,0.0003788434,0.000007813612,0.000001703563,0.000003199205,0.00001592634],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8524318,"threshold_uncertainty_score":0.2060531,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001732494,0.00004973641,0.00005233156,0.0003758489,0.00009817912,0.00004794843,0.000190104,0.0001012548,0.0000159932],"category_scores_gemma":[0.00001418703,0.00005023781,0.000007349801,0.0003459917,0.00005050853,0.001490164,0.00007431151,0.0001301054,0.00009594913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003395593,"about_ca_system_score_gemma":0.00001095147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003090563,"about_ca_topic_score_gemma":0.0001708835,"domain_scores_codex":[0.9995856,0.00001406502,0.0001292566,0.00008200971,0.00005403374,0.0001349819],"domain_scores_gemma":[0.9997105,0.000006805338,0.0000496027,0.0001951982,0.00001920182,0.00001870545],"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":[0.00002540968,0.00006027821,0.03089206,0.00001148475,0.000005613807,4.183046e-7,0.005832097,0.00001961865,0.0007070314,0.3216955,0.0001222859,0.6406282],"study_design_scores_gemma":[0.002660677,0.003836091,0.2880954,0.00004261874,0.00001162429,0.0001772045,0.002076138,0.2969501,0.02060722,0.240071,0.1446771,0.0007949139],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6562585,0.00002161459,0.3415856,0.001601427,0.00007824173,0.00007453095,4.605559e-7,0.0001427682,0.0002369034],"genre_scores_gemma":[0.9985042,0.00002347689,0.001208529,0.0002215222,0.000009398967,0.0000154851,0.000005950772,0.000001198364,0.00001030531],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6398333,"threshold_uncertainty_score":0.2048639,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00121182,0.0004487156,0.000386507,0.0008832066,0.0004268957,0.0008290166,0.003559427,0.0002931057,0.00001234129],"category_scores_gemma":[0.0001244546,0.0004416756,0.00007994896,0.0009477536,0.0002147306,0.0008806768,0.000963682,0.000795158,0.00008225143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004884753,"about_ca_system_score_gemma":0.0005163089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007170431,"about_ca_topic_score_gemma":0.0001628016,"domain_scores_codex":[0.9967735,0.00006366312,0.0003907855,0.001361585,0.0007925716,0.0006179037],"domain_scores_gemma":[0.9974723,0.0002017261,0.0001595195,0.001667443,0.0002453342,0.000253712],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000005505865,0.00002422794,0.00006396481,0.00002366808,0.000008383769,0.00005175159,0.001670129,0.01582664,0.0002884863,0.04693478,0.00003878569,0.9350637],"study_design_scores_gemma":[0.000472851,0.0009635109,0.001070435,0.0008799594,0.00001360344,0.0003457798,6.4176e-7,0.2443256,0.01551068,0.7016294,0.0316883,0.00309922],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005041658,0.0001077783,0.9921503,0.001043658,0.003327116,0.0002915909,0.000001344523,0.0002239675,0.002350065],"genre_scores_gemma":[0.07061162,0.0000176562,0.9208078,0.007795108,0.0004604659,0.000009246579,0.000003256479,0.00003996744,0.0002548823],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9319645,"threshold_uncertainty_score":0.9998035,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}