{"meta":{"query_hash":"2c1bc47393e7","filters":{"venue":"Digital Investigation"},"cohort_total":13,"direct_labels_cover":0,"predictions_cover":13,"exported":13,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/2c1bc47393e7","api":"https://metacan.xera.ac/api/v1/cohort?venue=Digital+Investigation"},"results":[{"id":"W1419517020","doi":"10.1016/j.diin.2015.05.002","title":"Graph-theoretic characterization of cyber-threat infrastructures","year":2015,"lang":"en","type":"article","venue":"Digital Investigation","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Computer security; Malware; PageRank; Cyber threats; Centrality; Key (lock); Critical infrastructure; Data science; Malware analysis; World Wide Web","score_opus":0.016332704371522334,"score_gpt":0.23333260849992132,"score_spread":0.21699990412839898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1419517020","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5680949,0.0019688217,0.40588644,0.0021999474,0.00005554983,0.00023093837,0.0037755982,0.00051877974,0.017269043],"genre_scores_gemma":[0.9622882,0.00065759633,0.03396107,0.00009667031,0.00006314945,0.00008581226,0.0018869726,0.000038118345,0.0009224205],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992218,0.00024600019,0.000044183205,0.0001902061,0.00022164684,0.000076081895],"domain_scores_gemma":[0.99271435,0.0037589276,0.0019205004,0.00064105174,0.0005653125,0.00039974955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008279723,0.000576941,0.00046787917,0.006854056,0.00069670693,0.00201655,0.0007605723,0.00080315204,0.002091802],"category_scores_gemma":[0.007035837,0.00027868967,0.00048039726,0.0034680348,0.0014451185,0.0045409896,0.00088622235,0.00084686786,0.0002471445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012833695,0.00025912246,0.06976051,0.0005912436,0.00026238602,0.0005378397,0.001001142,0.31074968,0.007994126,0.54075056,0.006910476,0.061054535],"study_design_scores_gemma":[0.000016013379,0.00006931764,0.024593372,0.000066501474,0.00006623974,0.00062596606,0.0006978576,0.62978077,0.0016002296,0.33182406,0.010625143,0.00003456087],"about_ca_topic_score_codex":0.0023466563,"about_ca_topic_score_gemma":0.0023408106,"teacher_disagreement_score":0.006854056,"about_ca_system_score_codex":0.001489577,"about_ca_system_score_gemma":0.00061836204,"threshold_uncertainty_score":0.010807693},"labels":[],"label_agreement":null},{"id":"W1779974843","doi":"10.1016/j.diin.2015.05.015","title":"BinComp: A stratified approach to compiler provenance Attribution","year":2015,"lang":"en","type":"article","venue":"Digital Investigation","topic":"Software Engineering Research","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Compiler; Computer science; Compiler correctness; Compiler construction; Optimizing compiler; Interprocedural optimization; Programming language; Loop optimization; Semantics (computer science)","score_opus":0.07929534497281193,"score_gpt":0.2663574744014908,"score_spread":0.1870621294286789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1779974843","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009430369,0.000106275955,0.97056323,0.000099348545,0.00003264008,0.0001464798,0.0005304998,0.017847223,0.001243965],"genre_scores_gemma":[0.11099168,0.00012424539,0.88123703,0.00013328009,0.000033192748,0.00017682221,0.0026167943,0.0026028825,0.0020840194],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948827,0.0011273103,0.00041376223,0.0010203143,0.002221696,0.00033413243],"domain_scores_gemma":[0.98787993,0.0024344719,0.0010668734,0.0063420236,0.001983392,0.00029334743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004095411,0.0009880832,0.0010278784,0.0031626264,0.0015647776,0.0033549725,0.0025609268,0.001257328,0.002226873],"category_scores_gemma":[0.013795319,0.001258986,0.001657175,0.0030049542,0.0015905207,0.0055818623,0.0052186726,0.0023363081,0.0017877247],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013931453,0.0005494907,0.026607214,0.0005731304,0.00042033353,0.0009945959,0.002083255,0.077826664,0.05780361,0.13256426,0.023877366,0.675307],"study_design_scores_gemma":[0.000059685935,0.00015475803,0.0044242805,0.00010422096,0.00011744103,0.0006290384,0.00022803847,0.737279,0.0907713,0.11827691,0.047789857,0.00016545941],"about_ca_topic_score_codex":0.0068059526,"about_ca_topic_score_gemma":0.010207118,"teacher_disagreement_score":0.0068059526,"about_ca_system_score_codex":0.0013894102,"about_ca_system_score_gemma":0.004451753,"threshold_uncertainty_score":0.021658838},"labels":[],"label_agreement":null},{"id":"W1982623151","doi":"10.1016/j.diin.2009.06.003","title":"Extraction of forensically sensitive information from windows physical memory","year":2009,"lang":"en","type":"article","venue":"Digital Investigation","topic":"Digital and Cyber Forensics","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; String searching algorithm; Focus (optics); String (physics); Matching (statistics); Protocol (science); Data mining; Pattern matching; Information retrieval; Artificial intelligence","score_opus":0.008646516644480599,"score_gpt":0.2095923998710739,"score_spread":0.2009458832265933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982623151","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5640455,0.0019967312,0.41898224,0.000499895,0.00025339922,0.0002450771,0.0013947708,0.003486212,0.009096136],"genre_scores_gemma":[0.8265469,0.000989037,0.16777335,0.00010047103,0.00006093916,0.00007811018,0.0008791428,0.00021382878,0.0033582982],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99961734,0.000040656767,0.000039510425,0.000055975448,0.00019954599,0.000046782443],"domain_scores_gemma":[0.99822897,0.00042305092,0.00034178744,0.0005927085,0.00036390315,0.00004958595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003901022,0.0003751513,0.0003514329,0.0033625017,0.00038505613,0.0009229743,0.0004906646,0.00068015297,0.0013202948],"category_scores_gemma":[0.0032551326,0.0002544437,0.00020331219,0.0018233072,0.00037824808,0.001528769,0.0008973894,0.0005500498,0.0007264138],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052737934,0.00010434769,0.009990716,0.00048164668,0.000049367554,0.0032779973,0.001381581,0.0029921872,0.38138255,0.00859358,0.0030031335,0.5882156],"study_design_scores_gemma":[0.000031555814,0.00036284808,0.030048657,0.0002855528,0.00016202457,0.00827236,0.0015875236,0.055595323,0.8488223,0.016708093,0.038000815,0.00012283816],"about_ca_topic_score_codex":0.00018566001,"about_ca_topic_score_gemma":0.00024527663,"teacher_disagreement_score":0.0033625017,"about_ca_system_score_codex":0.0001410043,"about_ca_system_score_gemma":0.0003818199,"threshold_uncertainty_score":0.0044168234},"labels":[],"label_agreement":null},{"id":"W2085509246","doi":"10.1016/j.diin.2009.01.004","title":"Towards an integrated e-mail forensic analysis framework","year":2009,"lang":"en","type":"article","venue":"Digital Investigation","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":86,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Phishing; Spamming; Law enforcement; Harassment; Computer security; Context (archaeology); Child pornography; Cybercrime; Digital forensics; The Internet; Internet privacy; World Wide Web; Data science","score_opus":0.03798295588258519,"score_gpt":0.28808738460247124,"score_spread":0.25010442871988603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085509246","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021275699,0.00006980805,0.99400336,0.00017347994,0.000015415144,0.00010658545,0.00008485108,0.0027167138,0.0007022418],"genre_scores_gemma":[0.07274595,0.00016873161,0.924455,0.00013497255,0.000049956947,0.00014214942,0.0005141214,0.00024750337,0.001541615],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99477947,0.0012015555,0.0005785894,0.0007977075,0.0023180598,0.0003247407],"domain_scores_gemma":[0.9933124,0.0014948937,0.0006290728,0.0018734938,0.0022449382,0.0004451262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007012168,0.001231271,0.0015315564,0.005885012,0.0017470839,0.009114946,0.0036173812,0.0025512923,0.0021638072],"category_scores_gemma":[0.009473628,0.00094385253,0.0021952237,0.0025968282,0.0014994072,0.008689633,0.0064698006,0.0027905179,0.0016797284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003024941,0.0012099233,0.008035474,0.00054528855,0.0005741271,0.00091858575,0.0014087029,0.06595964,0.023923747,0.3295059,0.014250984,0.5533652],"study_design_scores_gemma":[0.00003292141,0.00009135954,0.0013244606,0.00020202152,0.00028772748,0.00058416737,0.0005655433,0.76305676,0.023690304,0.18177192,0.02830014,0.00009264102],"about_ca_topic_score_codex":0.0028398524,"about_ca_topic_score_gemma":0.004614846,"teacher_disagreement_score":0.009114946,"about_ca_system_score_codex":0.0012489394,"about_ca_system_score_gemma":0.004266826,"threshold_uncertainty_score":0.03708434},"labels":[],"label_agreement":null},{"id":"W2118558829","doi":"10.1016/j.diin.2007.06.010","title":"Forensic memory analysis: From stack and code to execution history","year":2007,"lang":"en","type":"article","venue":"Digital Investigation","topic":"Security and Verification in Computing","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Thread (computing); Call stack; Stack (abstract data type); Process (computing); Virtual memory; Operating system; Programming language; Parallel computing; Memory management; Overlay","score_opus":0.03766217992191722,"score_gpt":0.2444065722086764,"score_spread":0.20674439228675917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118558829","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.083527185,0.0010823921,0.90902245,0.00049826346,0.000035918445,0.00010108674,0.00029616614,0.0021537838,0.0032828234],"genre_scores_gemma":[0.7855122,0.001089043,0.20937793,0.0001822391,0.000083138,0.00013352073,0.00044255162,0.00047370902,0.002705664],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99855226,0.00032751847,0.000096550946,0.00026667595,0.0005615996,0.00019540859],"domain_scores_gemma":[0.99537164,0.0018398418,0.0007768631,0.0013081272,0.00060850335,0.00009504913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017957473,0.000796774,0.0005651176,0.003828235,0.0007532024,0.0031136316,0.0014109133,0.0011476558,0.001979275],"category_scores_gemma":[0.009806622,0.00061107374,0.0009880272,0.0014576974,0.0036640235,0.0068866797,0.0022450106,0.0012144592,0.00043137855],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004710339,0.00019353091,0.01853928,0.0005892846,0.00018162176,0.0018985168,0.0024521335,0.13676503,0.043936096,0.49560007,0.0028677166,0.29650575],"study_design_scores_gemma":[0.000032064672,0.00016356156,0.0038294625,0.00028432594,0.00014631936,0.0011743639,0.0007484286,0.5457341,0.06158458,0.37357938,0.012610555,0.000112873684],"about_ca_topic_score_codex":0.0030246237,"about_ca_topic_score_gemma":0.0014350715,"teacher_disagreement_score":0.003828235,"about_ca_system_score_codex":0.0011180817,"about_ca_system_score_gemma":0.0016796795,"threshold_uncertainty_score":0.009496987},"labels":[],"label_agreement":null},{"id":"W2123407642","doi":"10.1016/j.diin.2008.05.001","title":"A novel approach of mining write-prints for authorship attribution in e-mail forensics","year":2008,"lang":"en","type":"article","venue":"Digital Investigation","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":131,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Authorship attribution; Suspect; Computer science; Attribution; Decision tree; Support vector machine; Quality (philosophy); Information retrieval; Data mining; Data science; Computer security; Artificial intelligence; Psychology","score_opus":0.13829818981895015,"score_gpt":0.27741527439109653,"score_spread":0.1391170845721464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123407642","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20626478,0.0007668533,0.78821474,0.00060956704,0.00014997779,0.00025287175,0.00075967005,0.0013864667,0.0015950437],"genre_scores_gemma":[0.60399765,0.00031513697,0.39253917,0.00008255549,0.00017302418,0.00017521874,0.0008403155,0.00004245376,0.0018345708],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974917,0.0005328101,0.00031925208,0.0007190591,0.00075665355,0.00018054315],"domain_scores_gemma":[0.9945996,0.0019843995,0.0011529047,0.0008477832,0.0012002441,0.00021505894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016349576,0.00069685397,0.0010292879,0.0064855036,0.0009063369,0.0016764739,0.0014126544,0.0014776567,0.00073301553],"category_scores_gemma":[0.0092917485,0.00039823548,0.00080218597,0.0040884833,0.00069745927,0.00242967,0.0010447631,0.0009566247,0.0005856178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038246726,0.0011325609,0.06326223,0.00043085896,0.00021971007,0.0006944423,0.0009081998,0.021912621,0.021841696,0.0062782466,0.0032726077,0.8796643],"study_design_scores_gemma":[0.00006647349,0.0003894044,0.027341055,0.00009325144,0.00013845587,0.0022198164,0.00068724353,0.91833746,0.027105851,0.01631269,0.0072046067,0.00010365407],"about_ca_topic_score_codex":0.0007252286,"about_ca_topic_score_gemma":0.0011351602,"teacher_disagreement_score":0.0064855036,"about_ca_system_score_codex":0.000350546,"about_ca_system_score_gemma":0.000889021,"threshold_uncertainty_score":0.008646548},"labels":[],"label_agreement":null},{"id":"W2125962012","doi":"10.1016/j.diin.2010.03.003","title":"Mining writeprints from anonymous e-mails for forensic investigation","year":2010,"lang":"en","type":"article","venue":"Digital Investigation","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Exploit; Cluster analysis; Stylometry; Anonymity; Identification (biology); Classifier (UML); Cybercrime; Focus (optics); Writing style; Information retrieval; World Wide Web; Data science; Data mining; Artificial intelligence; Computer security; The Internet","score_opus":0.04413737110212299,"score_gpt":0.2634196282676218,"score_spread":0.2192822571654988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125962012","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9057133,0.0016238178,0.060448762,0.0010007338,0.00046635454,0.0004299869,0.016474094,0.0022946459,0.011548333],"genre_scores_gemma":[0.92615265,0.0008444351,0.0465415,0.00014817626,0.00045444403,0.00021533608,0.015058315,0.00021814238,0.0103669865],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.994091,0.0012285531,0.0009818757,0.0007595256,0.0023700015,0.00056904746],"domain_scores_gemma":[0.9504859,0.019215893,0.01176661,0.008107142,0.008720583,0.0017040506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027368537,0.0007698136,0.00069779396,0.013489772,0.0013732362,0.0024397192,0.00089226733,0.0014091831,0.0031442584],"category_scores_gemma":[0.029553223,0.00035597407,0.00048213362,0.008154401,0.0005021053,0.0023763708,0.0016474702,0.0008320834,0.0054492205],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012614876,0.0006632371,0.35340017,0.001039289,0.00017818053,0.004060037,0.0035967533,0.0031001442,0.03670503,0.006260365,0.025939422,0.563796],"study_design_scores_gemma":[0.00010581076,0.0010975461,0.40966672,0.0010014748,0.0007170813,0.018174239,0.016438114,0.13005678,0.20334597,0.030487765,0.18861069,0.00029772337],"about_ca_topic_score_codex":0.000434737,"about_ca_topic_score_gemma":0.00093842665,"teacher_disagreement_score":0.013489772,"about_ca_system_score_codex":0.00038334297,"about_ca_system_score_gemma":0.0012211214,"threshold_uncertainty_score":0.014474034},"labels":[],"label_agreement":null},{"id":"W2129364433","doi":"10.1016/j.diin.2014.03.012","title":"OBA2: An Onion approach to Binary code Authorship Attribution","year":2014,"lang":"en","type":"article","venue":"Digital Investigation","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Authorship attribution; Code (set theory); Binary number; Attribution; Information retrieval; World Wide Web; Programming language; Natural language processing; Arithmetic; Mathematics","score_opus":0.07222085393703048,"score_gpt":0.27987939711741455,"score_spread":0.20765854318038407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129364433","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022304859,0.0007239009,0.92548674,0.0011628624,0.0005043003,0.0006452354,0.00226637,0.030051226,0.016854636],"genre_scores_gemma":[0.28171116,0.00061742397,0.67643225,0.00099894,0.00059685874,0.00077540014,0.0071775396,0.003853606,0.02783695],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99195284,0.0016287753,0.0006049283,0.0017558534,0.0031972092,0.0008602796],"domain_scores_gemma":[0.9883562,0.0031829095,0.001566611,0.0045192013,0.0018005928,0.0005744665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056384453,0.0023448372,0.0019313,0.01347886,0.0021679911,0.0055954433,0.0034326268,0.002495188,0.010614856],"category_scores_gemma":[0.020306861,0.0010374734,0.0025157377,0.005578621,0.0019002444,0.009082415,0.009773344,0.0029940798,0.005661183],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009929063,0.0005501937,0.022412159,0.00038829667,0.00038877057,0.0010814111,0.0016365997,0.019403506,0.009106222,0.06278166,0.040519558,0.84073865],"study_design_scores_gemma":[0.000090990834,0.00022288879,0.0057592914,0.00024290246,0.00016445387,0.0011974839,0.00081052165,0.7247509,0.020766016,0.15581581,0.090025835,0.00015288054],"about_ca_topic_score_codex":0.003724997,"about_ca_topic_score_gemma":0.006826123,"teacher_disagreement_score":0.01347886,"about_ca_system_score_codex":0.0015599144,"about_ca_system_score_gemma":0.0023830987,"threshold_uncertainty_score":0.035510182},"labels":[],"label_agreement":null},{"id":"W2297444916","doi":"10.1016/j.diin.2016.01.010","title":"Tiered forensic methodology model for Digital Field Triage by non-digital evidence specialists","year":2016,"lang":"en","type":"article","venue":"Digital Investigation","topic":"Digital and Cyber Forensics","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Canadian Mounted Police","funders":"","keywords":"Triage; Digital forensics; Process (computing); Premise; Field (mathematics); Computer forensics","score_opus":0.10573361782046914,"score_gpt":0.2896694294360085,"score_spread":0.18393581161553935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2297444916","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002769389,0.0000855484,0.9924784,0.00032042997,0.00002758492,0.00048993184,0.000051937088,0.0003026124,0.00347421],"genre_scores_gemma":[0.06597104,0.00017959367,0.93001544,0.00020567946,0.000025683968,0.00072798313,0.00016022917,0.000040880474,0.0026735314],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9892532,0.005663854,0.0007968511,0.0010547516,0.002787675,0.0004436193],"domain_scores_gemma":[0.9902805,0.003829951,0.000980729,0.0016747533,0.0028169851,0.00041690547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010939722,0.00081347703,0.000401922,0.0024407222,0.001186171,0.0036575433,0.002335367,0.001664944,0.006028717],"category_scores_gemma":[0.011918952,0.0004315657,0.0011681318,0.0013135956,0.0015620288,0.0031271025,0.0022864747,0.0014073739,0.0022678378],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033361596,0.0007266364,0.0083683375,0.0008288589,0.00016140346,0.0006342252,0.0038365377,0.1380933,0.012471859,0.44306138,0.0061721546,0.38531163],"study_design_scores_gemma":[0.00011772382,0.0007218005,0.0020880084,0.000365917,0.00010403238,0.0008597029,0.0011005466,0.7442629,0.00646091,0.18733262,0.056466784,0.00011905609],"about_ca_topic_score_codex":0.004009505,"about_ca_topic_score_gemma":0.0056761294,"teacher_disagreement_score":0.010939722,"about_ca_system_score_codex":0.003067751,"about_ca_system_score_gemma":0.008855098,"threshold_uncertainty_score":0.057855427},"labels":[],"label_agreement":null},{"id":"W2465152470","doi":"10.1016/j.diin.2016.07.001","title":"Detecting predatory conversations in social media by deep Convolutional Neural Networks","year":2016,"lang":"en","type":"article","venue":"Digital Investigation","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Support vector machine; Classifier (UML); Deep learning; Identification (biology); Machine learning; Domain (mathematical analysis)","score_opus":0.018045751487694432,"score_gpt":0.2084786305199205,"score_spread":0.19043287903222605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2465152470","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.862143,0.0018747643,0.12239532,0.0011390307,0.00031232488,0.0001238378,0.0016337862,0.001765777,0.008612147],"genre_scores_gemma":[0.98085976,0.00034299088,0.014405744,0.00013031854,0.00011405612,0.00002794863,0.0008402668,0.000029259816,0.0032497132],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995571,0.000101007085,0.00001858828,0.00009178067,0.000108462176,0.00012313698],"domain_scores_gemma":[0.9987766,0.0006452805,0.00022124953,0.00008404422,0.00019519616,0.000077732286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000554258,0.0009870441,0.0004419665,0.0020237118,0.00045817925,0.0008742249,0.0005783356,0.0010680208,0.0012820434],"category_scores_gemma":[0.0021413635,0.00035009513,0.00044032768,0.0007917016,0.00034805448,0.0014614648,0.0010671213,0.001197104,0.00086306786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013952766,0.0015602553,0.15659408,0.00038109667,0.0004551312,0.0013030113,0.0011291554,0.06040564,0.07289783,0.0049920003,0.017063005,0.6818235],"study_design_scores_gemma":[0.000008343316,0.00007636798,0.0170365,0.000030912033,0.000050120852,0.00014983729,0.00024324589,0.9678331,0.0099385725,0.0029579147,0.0016540687,0.000021057069],"about_ca_topic_score_codex":0.006875437,"about_ca_topic_score_gemma":0.012187104,"teacher_disagreement_score":0.006875437,"about_ca_system_score_codex":0.0006644533,"about_ca_system_score_gemma":0.0004775351,"threshold_uncertainty_score":0.013670802},"labels":[],"label_agreement":null},{"id":"W2516577067","doi":"10.1016/j.diin.2016.04.002","title":"BinGold: Towards robust binary analysis by extracting the semantics of binary code as semantic flow graphs (SFGs)","year":2016,"lang":"en","type":"article","venue":"Digital Investigation","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Code refactoring; Control flow graph; Data-flow analysis; Obfuscation; Theoretical computer science; Binary code; Compiler; Static program analysis; Programming language; Binary number; Malware; Semantics (computer science); Data flow diagram; Software; Database; Software development","score_opus":0.02176898801439601,"score_gpt":0.2510651739241297,"score_spread":0.2292961859097337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2516577067","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034418996,0.00044721426,0.91231024,0.00018572366,0.00006434875,0.00021654565,0.001409908,0.048335385,0.002611658],"genre_scores_gemma":[0.24324621,0.0003644238,0.7418364,0.00031631236,0.000042453175,0.00025533658,0.005411224,0.006100492,0.0024269945],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985347,0.00024936226,0.000114923816,0.00029810335,0.00068099884,0.00012198162],"domain_scores_gemma":[0.9967518,0.0013045297,0.00060491596,0.00064222625,0.0006382803,0.000058304748],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012545126,0.0014433208,0.00065791945,0.0045963195,0.00067954167,0.0012218754,0.0010556907,0.0009207574,0.0024797006],"category_scores_gemma":[0.0068695075,0.0005904377,0.0012500207,0.0016310448,0.0013084841,0.0031361699,0.0015725453,0.0012351149,0.0013429967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083199766,0.00029520813,0.011176747,0.0015518672,0.00018923703,0.0005842931,0.0011712053,0.044567596,0.10914019,0.045517914,0.020658733,0.764315],"study_design_scores_gemma":[0.00009833127,0.00030222896,0.006675863,0.00032082087,0.00015052613,0.00083703623,0.00040156228,0.6442687,0.16404226,0.1392621,0.04347272,0.00016783485],"about_ca_topic_score_codex":0.0037358035,"about_ca_topic_score_gemma":0.004407742,"teacher_disagreement_score":0.0045963195,"about_ca_system_score_codex":0.0008345732,"about_ca_system_score_gemma":0.0015800927,"threshold_uncertainty_score":0.008295417},"labels":[],"label_agreement":null},{"id":"W285492148","doi":"","title":"Steve Anson and Steve Bunting, Mastering Windows network forensics and investigations , Sybex (an imprint of Wiley Publishing Inc.), US and Canada (2007) ISBN 978-0-4700-9762-5 530 pp.","year":2009,"lang":"en","type":"article","venue":"Digital Investigation","topic":"Digital and Cyber Forensics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bunting; Computer science; Network forensics; Operating system; Geology; Digital forensics; Paleontology","score_opus":0.01252887328574015,"score_gpt":0.18843665974312493,"score_spread":0.17590778645738478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W285492148","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021012586,0.65369743,0.0807788,0.16949439,0.020755155,0.00021359672,0.0006128287,0.0020077655,0.07033883],"genre_scores_gemma":[0.020405509,0.69032234,0.0621484,0.028766356,0.011121448,0.00020897818,0.00079180975,0.00076936535,0.18546581],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979175,0.00034360558,0.00011722621,0.00023605488,0.0013119064,0.00007375604],"domain_scores_gemma":[0.9957557,0.002173319,0.00026299895,0.0001991413,0.0012366386,0.00037217414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031336108,0.0011625323,0.000672037,0.0032357418,0.0015576213,0.003778803,0.0016449554,0.0050402656,0.019422326],"category_scores_gemma":[0.009406154,0.0008345422,0.00032318465,0.0017593204,0.0026222328,0.0074885576,0.0022947416,0.0037143538,0.023436058],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039329727,0.000026894335,0.00032663456,0.00050231797,0.000010943178,0.00015498466,0.00041845703,0.00029406798,0.00060008373,0.008221391,0.7906202,0.19878463],"study_design_scores_gemma":[0.000009308702,0.000021038066,0.00051614473,0.00048197465,0.000007398626,0.0010710644,0.0005321537,0.00043882467,0.0011479928,0.013393682,0.9823417,0.000038661838],"about_ca_topic_score_codex":0.0048093214,"about_ca_topic_score_gemma":0.0083697215,"teacher_disagreement_score":0.019422326,"about_ca_system_score_codex":0.0008714782,"about_ca_system_score_gemma":0.0011540563,"threshold_uncertainty_score":0.06497413},"labels":[],"label_agreement":null},{"id":"W2884079571","doi":"10.1016/j.diin.2018.04.012","title":"Automated forensic analysis of mobile applications on Android devices","year":2018,"lang":"en","type":"article","venue":"Digital Investigation","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Android (operating system); Taint checking; Digital forensics; Static analysis; Scalability; Mobile device; Bytecode; Parsing; SQL injection; Database; Java; Operating system; World Wide Web; Programming language; Search engine","score_opus":0.014514305423983595,"score_gpt":0.2762935327133167,"score_spread":0.2617792272893331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884079571","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8814383,0.0014401259,0.096362576,0.00038866402,0.000103434155,0.00033575512,0.0015495686,0.01314984,0.005231825],"genre_scores_gemma":[0.94061595,0.00038750278,0.055916827,0.00011168342,0.000021773854,0.000091687274,0.0012134566,0.0003144186,0.0013265699],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989022,0.00021167537,0.000094487776,0.00020811858,0.00044671295,0.00013688914],"domain_scores_gemma":[0.99619293,0.0014570697,0.00052300154,0.0008327468,0.00091286545,0.00008135148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006932948,0.00079527625,0.00041806174,0.0031370313,0.0005360032,0.0006633764,0.0006411127,0.00047221527,0.0008805773],"category_scores_gemma":[0.0054205745,0.00031939903,0.0005547492,0.0009417277,0.00037397633,0.0011819437,0.0011355052,0.00039640645,0.0005905117],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010014898,0.00030453346,0.06320271,0.0009000418,0.00017773463,0.0042591523,0.0021575545,0.023657704,0.121336065,0.0060201706,0.015126028,0.7618568],"study_design_scores_gemma":[0.00014289287,0.00091835373,0.14366712,0.00049563084,0.0003608096,0.0075125173,0.002255998,0.53402406,0.25329614,0.015449843,0.04158631,0.000290468],"about_ca_topic_score_codex":0.0018909404,"about_ca_topic_score_gemma":0.0024460114,"teacher_disagreement_score":0.0031370313,"about_ca_system_score_codex":0.00035640752,"about_ca_system_score_gemma":0.0008658676,"threshold_uncertainty_score":0.0037599206},"labels":[],"label_agreement":null}]}