{"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97251016,0.000005413593,0.017368792,0.000035731482,0.000039847302,0.00010225274,0.000039741124,0.000057188146,0.009840853],"genre_scores_gemma":[0.9980557,3.4945361e-7,0.00045122424,0.000018945744,0.00010620957,0.000010498118,0.0012415029,0.0000109359,0.00010463265],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993847,0.000020597341,0.00022256294,0.00012827029,0.00014919696,0.000094654046],"domain_scores_gemma":[0.9994457,0.000013102365,0.00016541137,0.0001643264,0.00012790671,0.00008357618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006271804,0.00009959543,0.00013395493,0.000090341484,0.000023221732,0.000072011666,0.00009327421,0.000024870229,0.000058369675],"category_scores_gemma":[0.000012363348,0.000094564275,0.000059157217,0.00028221044,0.0001455795,0.00041172927,0.000034482935,0.000048569596,0.000012826428],"study_design_candidate":"theoretical_or_conceptual","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":[0.000016005746,0.000058219142,0.5713784,0.000015286325,0.00008915612,3.561155e-7,0.00080914964,0.00014674968,0.03407928,0.36544257,0.0014416408,0.026523173],"study_design_scores_gemma":[0.00017494419,0.000047662936,0.038367298,0.00002853979,0.00002697825,4.776831e-7,0.000070605194,0.0012695197,0.07577839,0.8836417,0.0004315678,0.00016232536],"about_ca_topic_score_codex":0.00003335884,"about_ca_topic_score_gemma":4.5134053e-7,"teacher_disagreement_score":0.53301114,"about_ca_system_score_codex":0.000013576881,"about_ca_system_score_gemma":0.00003252226,"threshold_uncertainty_score":0.38562194},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23731782,0.000018776655,0.7582509,0.00047582347,0.00020159312,0.00033932328,0.000008510741,0.00042641087,0.002960875],"genre_scores_gemma":[0.9646153,1.2444559e-7,0.03474785,0.00012389605,0.00004602082,0.000059392612,0.00006712442,0.000009309117,0.00033102083],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987887,0.00002329236,0.00016923272,0.0003288747,0.0004498122,0.00024007414],"domain_scores_gemma":[0.9989844,0.000062977575,0.000037661684,0.00037553685,0.00020591027,0.0003335084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025145445,0.00010947944,0.00009904249,0.00011240988,0.000040055158,0.00055238756,0.00046391817,0.000047240348,3.9866913e-7],"category_scores_gemma":[0.0005825272,0.000107473286,0.000022829814,0.00076201337,0.000044665052,0.0013511715,0.00015672782,0.000108965345,0.00028082496],"study_design_candidate":"theoretical_or_conceptual","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":[0.000039222454,0.00054476823,0.0742832,0.00017023113,0.00005930257,0.000018753984,0.0060796603,0.049329147,0.0053854254,0.7060018,0.08861727,0.069471195],"study_design_scores_gemma":[0.001782705,0.00082186423,0.21297744,0.00017678813,0.0000065528598,0.000068269765,0.00014745785,0.65761137,0.027468342,0.07182689,0.025631335,0.0014809767],"about_ca_topic_score_codex":0.000009293118,"about_ca_topic_score_gemma":2.5617808e-7,"teacher_disagreement_score":0.7272974,"about_ca_system_score_codex":0.00013432202,"about_ca_system_score_gemma":0.00015567562,"threshold_uncertainty_score":0.5326686},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8624646,0.0000035618523,0.10017312,0.0006020105,0.00019241116,0.00014491324,0.000038969585,0.00015774886,0.03622266],"genre_scores_gemma":[0.99609005,4.462682e-7,0.0030380555,0.0005326332,0.00007843127,0.000001928683,0.00020648635,0.0000029871949,0.00004895946],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991057,0.000013107838,0.00025947345,0.00016253936,0.00032626797,0.00013291248],"domain_scores_gemma":[0.99921745,0.000060226932,0.00018694873,0.00022957052,0.00021180477,0.00009401844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000045194967,0.00012054673,0.00014262884,0.00006942363,0.000035945595,0.0003422678,0.00017318055,0.000050120554,6.873466e-7],"category_scores_gemma":[0.000096410724,0.00011224166,0.00007379198,0.00027155614,0.000110573346,0.009061589,0.000043597745,0.00008364666,0.00010736318],"study_design_candidate":"theoretical_or_conceptual","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":[0.000020768455,0.000110249355,0.00014852366,0.0000068856257,0.000020688458,0.0000045746883,0.0027851718,0.00026131936,0.008315785,0.18473709,0.0013706575,0.8022183],"study_design_scores_gemma":[0.0004820503,0.0003545578,0.04047807,0.00006196179,0.00001321314,0.000014414149,0.00017384056,0.06384913,0.17919807,0.7142823,0.0007466025,0.00034580642],"about_ca_topic_score_codex":0.000015803853,"about_ca_topic_score_gemma":7.365643e-7,"teacher_disagreement_score":0.8018725,"about_ca_system_score_codex":0.00002960957,"about_ca_system_score_gemma":0.000050424173,"threshold_uncertainty_score":0.6569433},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13419649,0.000020113272,0.8617458,0.0017728995,0.00013055067,0.00006923142,0.000008893135,0.00033409594,0.0017219681],"genre_scores_gemma":[0.9376775,9.21371e-7,0.060591813,0.0012910373,0.00004440931,0.0000026516589,0.00025957765,0.0000035013295,0.00012857515],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989496,0.000053603035,0.000229686,0.00031871995,0.00025041983,0.00019798758],"domain_scores_gemma":[0.99913526,0.000031967815,0.00009501688,0.00038593734,0.00015051286,0.00020132872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023116627,0.00012558875,0.00014947621,0.00020612897,0.00010185491,0.000688683,0.00037614306,0.00011113141,0.0000142256295],"category_scores_gemma":[0.00028728563,0.000114501374,0.000090154615,0.0021395332,0.000055121116,0.0020424211,0.00003375033,0.00016861803,0.00008157668],"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":[0.000005758928,0.000044697692,0.0065860436,0.0000029721994,0.00006274341,0.0000060222933,0.0012862498,0.0007015635,0.0002011506,0.72462755,0.000350485,0.26612476],"study_design_scores_gemma":[0.000111959096,0.0001966119,0.04583871,0.000026575168,0.00004863188,0.0000040681903,0.00009120795,0.24625371,0.008506199,0.69716066,0.0014129832,0.00034868674],"about_ca_topic_score_codex":0.0000113533615,"about_ca_topic_score_gemma":0.0000026330536,"teacher_disagreement_score":0.80348104,"about_ca_system_score_codex":0.00005004487,"about_ca_system_score_gemma":0.00007761065,"threshold_uncertainty_score":0.6640986},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51312476,0.000109186694,0.48493513,0.0002524005,0.00020968216,0.0000647865,0.0000062304575,0.000107039945,0.001190804],"genre_scores_gemma":[0.98119247,0.0000010470162,0.017557884,0.00096684205,0.000074262454,0.0000028510472,0.000065061125,0.0000042042275,0.00013539052],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99907404,0.000017796963,0.00023139057,0.00032823303,0.00019955725,0.00014896445],"domain_scores_gemma":[0.99926984,0.00009997315,0.00009716879,0.0002858457,0.000086351334,0.00016080168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027477808,0.00008633764,0.000103017235,0.00021599086,0.000066635075,0.00018615149,0.00020584595,0.00004838851,0.0000044615317],"category_scores_gemma":[0.00010007329,0.000096632175,0.00003680096,0.0005285994,0.000067863235,0.0008779756,0.00008522354,0.000064061634,0.00004149069],"study_design_candidate":"observational","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":[0.00006513961,0.00020204196,0.07852052,0.00006435303,0.00063093106,0.00003477987,0.055747077,0.0036891976,0.016007101,0.38895252,0.0352506,0.42083573],"study_design_scores_gemma":[0.0007353522,0.0001927247,0.42982933,0.000094888324,0.0001663305,0.000012901102,0.0010174771,0.40470642,0.03363398,0.0867823,0.04167089,0.001157415],"about_ca_topic_score_codex":0.00006171383,"about_ca_topic_score_gemma":0.000045530644,"teacher_disagreement_score":0.4680677,"about_ca_system_score_codex":0.00015496126,"about_ca_system_score_gemma":0.000041213098,"threshold_uncertainty_score":0.39405456},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36993146,0.000014941459,0.6291485,0.00015873321,0.000096752,0.00020559804,0.000022080312,0.000055463166,0.00036651245],"genre_scores_gemma":[0.8657624,9.3306693e-7,0.13378575,0.000070937895,0.000031140735,0.00003234204,0.00018415917,0.0000073445026,0.00012496674],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874914,0.000034884328,0.00041411896,0.00031433103,0.00023799342,0.00024954148],"domain_scores_gemma":[0.9991412,0.0001406906,0.00019648201,0.00023106029,0.00018349638,0.00010707691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058804586,0.0001257471,0.00018030537,0.00015825655,0.00009686949,0.00007408536,0.00028308932,0.00012954566,7.2246087e-7],"category_scores_gemma":[0.0005785129,0.00013386017,0.000070166694,0.0006446182,0.00013277233,0.0010960466,0.00008485364,0.00011503937,0.0000066231896],"study_design_candidate":"theoretical_or_conceptual","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":[0.000058505146,0.00022873313,0.12570363,0.00022799382,0.000026548356,0.000004039815,0.010607311,0.0016926891,0.0091405865,0.8330095,0.00055342715,0.018747037],"study_design_scores_gemma":[0.0023300238,0.00026834063,0.12865885,0.00022322735,0.000012142316,0.00009550866,0.0003589574,0.6942624,0.083408296,0.08865802,0.00093665515,0.0007875805],"about_ca_topic_score_codex":0.000009026015,"about_ca_topic_score_gemma":0.0000018297951,"teacher_disagreement_score":0.74435145,"about_ca_system_score_codex":0.000077774195,"about_ca_system_score_gemma":0.00014363955,"threshold_uncertainty_score":0.54586595},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7538234,0.000010392643,0.24285537,0.0012262166,0.00083006534,0.00026526864,0.00003638771,0.00026061808,0.00069227815],"genre_scores_gemma":[0.9068083,3.7034368e-7,0.09158251,0.0006663078,0.00020572815,0.00004538142,0.00043433,0.000013462057,0.0002436071],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99869746,0.000029206944,0.00032754274,0.00044596917,0.00023851285,0.0002612886],"domain_scores_gemma":[0.9987534,0.00024917457,0.00018395594,0.00039606803,0.00019088949,0.00022646623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003341767,0.00016145356,0.0001402622,0.000102657184,0.00018766831,0.0006696037,0.0004055627,0.00015315178,0.000011890889],"category_scores_gemma":[0.00075227773,0.00016891301,0.0000697007,0.00032392456,0.00014022988,0.0020378819,0.000105719584,0.00018460625,0.00013036821],"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":[0.000028530203,0.00005564861,0.11329164,0.0000602072,0.000057979196,0.000006662077,0.0056820256,0.000096957745,0.1805705,0.5242626,0.006318494,0.16956873],"study_design_scores_gemma":[0.0008776979,0.00008836336,0.025920302,0.0000635148,0.000014040727,0.000009856008,0.000117442,0.11598227,0.31972474,0.5314464,0.0051856665,0.0005697375],"about_ca_topic_score_codex":0.00001931326,"about_ca_topic_score_gemma":0.000017784934,"teacher_disagreement_score":0.168999,"about_ca_system_score_codex":0.000029846795,"about_ca_system_score_gemma":0.000121740704,"threshold_uncertainty_score":0.68880725},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22907981,0.000009047469,0.7648439,0.001625399,0.00029537946,0.00021179374,0.000015450369,0.00044654266,0.0034726795],"genre_scores_gemma":[0.97151357,4.0124556e-7,0.026251037,0.0011510629,0.00014090011,0.000028179307,0.0005148539,0.000012884479,0.00038713665],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824184,0.00022181874,0.00029692316,0.00054359884,0.00036209266,0.00033374823],"domain_scores_gemma":[0.99855745,0.000053826792,0.00011317707,0.00051825674,0.00014958747,0.0006077177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009937354,0.00017793519,0.00014895765,0.00016026762,0.00023041555,0.00067721197,0.00054736115,0.00014915515,0.0000027430322],"category_scores_gemma":[0.00051089446,0.00017986723,0.00005104386,0.00076704024,0.00006560437,0.0025136934,0.00015420315,0.00018620025,0.00038470703],"study_design_candidate":"theoretical_or_conceptual","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":[0.000012043515,0.00009800873,0.004844332,0.000024404739,0.000006133404,8.050258e-7,0.0013139527,0.001360012,0.0034826964,0.9604365,0.0014131359,0.027007973],"study_design_scores_gemma":[0.00051582494,0.0006384119,0.048009247,0.00008075844,0.0000111883255,0.0000296922,0.00009013802,0.7429405,0.028235411,0.14639874,0.032094214,0.00095589017],"about_ca_topic_score_codex":0.000008290155,"about_ca_topic_score_gemma":9.614563e-7,"teacher_disagreement_score":0.81403774,"about_ca_system_score_codex":0.00010410059,"about_ca_system_score_gemma":0.00008344285,"threshold_uncertainty_score":0.7334773},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053070944,0.00005230211,0.93319505,0.0028212422,0.0005477654,0.00048408948,0.0004457763,0.00024058751,0.009142212],"genre_scores_gemma":[0.97521716,0.000005947151,0.011446333,0.00087210647,0.00020534334,0.000067425644,0.00016051756,0.00003336814,0.011991805],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977841,0.000019936655,0.0005441037,0.0007323112,0.00039674182,0.00052284973],"domain_scores_gemma":[0.9974805,0.0011368514,0.00024034618,0.0006035803,0.00023824083,0.00030044507],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00021970183,0.00032716533,0.00034865632,0.00010682882,0.00010400412,0.0020190303,0.00083650043,0.00016937828,0.000004129411],"category_scores_gemma":[0.0021622116,0.00024867692,0.00021695043,0.00029836988,0.00029888656,0.0098797,0.00030983504,0.00008913806,0.0001628215],"study_design_candidate":"theoretical_or_conceptual","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":[0.000121710524,0.000098648095,0.0011902493,0.000047599773,0.00006220147,0.00000869654,0.00054637087,0.000036986774,0.002442284,0.092851855,0.1518792,0.7507142],"study_design_scores_gemma":[0.0014200693,0.0007139283,0.00016519586,0.00028906486,0.000018378423,0.000034509103,0.000032411353,0.056715548,0.03194677,0.8990506,0.008659861,0.00095366366],"about_ca_topic_score_codex":0.0000038387498,"about_ca_topic_score_gemma":0.000002786665,"teacher_disagreement_score":0.9221462,"about_ca_system_score_codex":0.00008996832,"about_ca_system_score_gemma":0.00017059704,"threshold_uncertainty_score":0.99999654},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5697053,0.00010931729,0.42652205,0.00152996,0.001041237,0.00017823698,0.00001944878,0.0002767671,0.0006176833],"genre_scores_gemma":[0.9991639,0.0000043680416,0.0002344427,0.00023761726,0.00025587354,0.000018803657,0.000031583568,0.0000072133826,0.000046162153],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989011,0.000069365364,0.00027224227,0.00028713854,0.00023421226,0.00023589219],"domain_scores_gemma":[0.99932754,0.00025635792,0.000120851575,0.0001277485,0.00007585301,0.00009165375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017851019,0.00011169513,0.000097669625,0.00010215253,0.00018573068,0.00019751315,0.00023919677,0.00011501153,0.000021668184],"category_scores_gemma":[0.0002309594,0.0000993684,0.000041678155,0.0004127873,0.00015931365,0.0024705303,0.000095591866,0.00013679343,0.000036703626],"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":[0.000068073,0.00019387556,0.03750525,0.000031630607,0.000053856358,0.000014490145,0.0066715037,0.0029776192,0.010384038,0.16889754,0.024777284,0.7484248],"study_design_scores_gemma":[0.0009259149,0.000058954483,0.01645142,0.00004127896,0.000003829816,0.000012954161,0.000078594596,0.9314091,0.002353148,0.045905445,0.0023722104,0.0003871169],"about_ca_topic_score_codex":0.0000068363433,"about_ca_topic_score_gemma":0.00003251887,"teacher_disagreement_score":0.9284315,"about_ca_system_score_codex":0.00012597367,"about_ca_system_score_gemma":0.000036657464,"threshold_uncertainty_score":0.40521258},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34279835,0.000053401498,0.6541989,0.0017472444,0.000120807425,0.00019689616,0.00003216093,0.00044527033,0.00040696686],"genre_scores_gemma":[0.97816503,0.000028088938,0.02098342,0.00018016969,0.00001870324,0.000024862167,0.000021966345,0.00001918498,0.0005585528],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983455,0.00007173862,0.0004472063,0.00044489026,0.00043930925,0.00025138567],"domain_scores_gemma":[0.9983989,0.00022038509,0.0004041751,0.00069097424,0.00018055215,0.00010503785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030880625,0.0002060027,0.00024054405,0.0003420919,0.00015395848,0.00019206193,0.0006399225,0.00009650526,0.000010990809],"category_scores_gemma":[0.00041266772,0.00013923412,0.0001671754,0.0021019634,0.00027184177,0.0023024715,0.00027994238,0.00012696761,0.000029211262],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051225048,0.0003982731,0.025813099,0.00017806192,0.0008598615,0.00006830918,0.0025933343,0.017106595,0.6231569,0.019371742,0.015520475,0.29488212],"study_design_scores_gemma":[0.00049294176,0.0005968419,0.008608936,0.0002866241,0.00025373223,0.000063001666,0.00017212796,0.2620619,0.6457543,0.07741416,0.0033416327,0.00095384195],"about_ca_topic_score_codex":0.00004409445,"about_ca_topic_score_gemma":0.000005631949,"teacher_disagreement_score":0.6353667,"about_ca_system_score_codex":0.00008069247,"about_ca_system_score_gemma":0.000078043435,"threshold_uncertainty_score":0.56778026},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99177855,0.00038897275,0.0039965115,0.00091383845,0.00027645644,0.0002966738,0.000059402457,0.000102546284,0.0021870208],"genre_scores_gemma":[0.98938495,0.000030491516,0.009109742,0.0011213949,0.00012890638,0.0000065000886,0.00012603393,0.000018277951,0.00007371179],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99798715,0.000038915587,0.0005340468,0.0005706909,0.0004325878,0.00043662576],"domain_scores_gemma":[0.9984724,0.00009235993,0.0003325288,0.00038134324,0.00022652459,0.0004948741],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002615469,0.00030070846,0.00030819478,0.00008224663,0.00020205823,0.002474833,0.00031775245,0.00011826562,9.006217e-7],"category_scores_gemma":[0.00020710359,0.00030485258,0.000026595584,0.0003683861,0.00035467232,0.0077481247,0.0003505433,0.00022084739,7.609525e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029426183,0.0000918132,0.28219682,0.00026084363,0.000111459274,0.000046416902,0.0041944995,0.0021992945,0.0013256089,0.20344758,0.01050529,0.49559096],"study_design_scores_gemma":[0.0018968924,0.001155813,0.4355908,0.0011481445,0.0000826846,0.00029590836,0.0010279117,0.13398217,0.004684796,0.40676373,0.01125776,0.0021133765],"about_ca_topic_score_codex":0.01887102,"about_ca_topic_score_gemma":0.01819744,"teacher_disagreement_score":0.49347758,"about_ca_system_score_codex":0.00007083351,"about_ca_system_score_gemma":0.000336645,"threshold_uncertainty_score":0.99994034},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18964086,0.000011068121,0.80586255,0.00004480061,0.000043046442,0.0002959839,0.000020414243,0.0014807723,0.002600472],"genre_scores_gemma":[0.9776198,8.66479e-7,0.02199327,0.00014654828,0.00002025407,0.00011596672,0.000046760946,0.0000053374833,0.000051182196],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99925804,0.000012285962,0.00022130323,0.00024541147,0.00016736965,0.000095610776],"domain_scores_gemma":[0.9990953,0.00005027941,0.00017841731,0.00040041428,0.00022172426,0.000053841035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000063299594,0.00008219101,0.00012982922,0.00036296638,0.00006534978,0.00009565779,0.00025469877,0.000040500167,0.0000032122157],"category_scores_gemma":[0.00003754996,0.00008022281,0.000054256034,0.0019642278,0.00015923892,0.0008415218,0.000055726396,0.000036190624,0.000037039277],"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":[0.000033507942,0.00046001244,0.02150445,0.000118011834,0.0010357413,0.0000037806617,0.0024611894,0.0073906444,0.055038065,0.2856085,0.0060663964,0.6202797],"study_design_scores_gemma":[0.00012046237,0.0005497327,0.012503728,0.00002579719,0.00007201906,0.0000027413403,0.00003592321,0.3479387,0.5974036,0.03636255,0.004714708,0.00027004702],"about_ca_topic_score_codex":0.0000062485146,"about_ca_topic_score_gemma":0.0000080152695,"teacher_disagreement_score":0.78797895,"about_ca_system_score_codex":0.00003248351,"about_ca_system_score_gemma":0.000023193348,"threshold_uncertainty_score":0.3271391},"labels":[],"label_agreement":null}]}