{"id":"W4385776918","doi":"10.1016/j.fsidi.2023.301616","title":"CAMID: An assuasive approach to reveal source camera through inconspicuous evidence","year":2023,"lang":"en","type":"article","venue":"Forensic Science International Digital Investigation","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Hong Kong Government; Hong Kong Polytechnic University; Glaucoma Research Foundation","keywords":"Artificial intelligence; Computer vision; Computer science; Robustness (evolution); Carving; Digital camera; Confusion; Identification (biology); Camera auto-calibration; Camera resectioning; Pattern recognition (psychology); Geography; Archaeology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0007359725,0.0002796567,0.000205967,0.0007666628,0.0003097915,0.002500471,0.002425861,0.00008043862,0.000003608911],"category_scores_gemma":[0.002779141,0.0002742994,0.00007923404,0.004169033,0.001054341,0.0176997,0.0008644452,0.000195014,0.001022502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004527419,"about_ca_system_score_gemma":0.0003610848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001710531,"about_ca_topic_score_gemma":0.00001340431,"domain_scores_codex":[0.9956241,0.00002932745,0.0004952154,0.001194502,0.002039911,0.000616915],"domain_scores_gemma":[0.9975113,0.000188252,0.0002264701,0.0007591239,0.0008305091,0.0004843997],"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":[0.00005972337,0.000267896,0.009107955,0.00004948469,0.00007130834,0.00006354912,0.01867123,0.01871553,0.02147463,0.3320483,0.01888491,0.5805855],"study_design_scores_gemma":[0.0007326145,0.001279713,0.06622229,0.0005721217,0.00001964034,0.0005041382,0.001990986,0.5069963,0.06820109,0.3443746,0.007225359,0.001881157],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7991603,0.00000842429,0.1684151,0.002716669,0.003895339,0.000571486,0.00002701137,0.001099346,0.02410628],"genre_scores_gemma":[0.9696632,0.000002149651,0.02664373,0.001362612,0.0002935964,0.00009366109,0.00008286406,0.00002238846,0.001835775],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5787044,"threshold_uncertainty_score":0.9999709,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05439263144801229,"score_gpt":0.2949232492614984,"score_spread":0.2405306178134861,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}