{"id":"W4412386968","doi":"10.26434/chemrxiv-2025-540c6","title":"Spectral Trends in DART-MS Data Obtained from the NIST DART-MS Forensics Database: A resource for unknown compound classification","year":2025,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Advanced Chemical Sensor Technologies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trent University","funders":"","keywords":"Dart; DART ion source; NIST; Database; Computer science; Resource (disambiguation); Chemistry; Natural language processing","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002740288,0.0007021366,0.0005883622,0.01202368,0.0008285571,0.00138842,0.0009183038,0.0011285,0.005879867],"category_scores_gemma":[0.005167719,0.0002776241,0.0005500978,0.007327244,0.0004223838,0.00169461,0.0009041335,0.0009836269,0.004198299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005811576,"about_ca_system_score_gemma":0.001010103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001131169,"about_ca_topic_score_gemma":0.0024255,"domain_scores_codex":[0.998322,0.0001169962,0.0001726718,0.0002882397,0.001021518,0.00007852435],"domain_scores_gemma":[0.9961588,0.000881753,0.0009299704,0.0006612444,0.001276739,0.00009163399],"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":[0.001299032,0.000523984,0.05455638,0.002537969,0.0004084549,0.002678834,0.0009196302,0.005202116,0.3022274,0.005960843,0.05233809,0.5713473],"study_design_scores_gemma":[0.00008939507,0.0006516491,0.1523533,0.0005332953,0.000393714,0.01261883,0.001330474,0.05585307,0.4756421,0.01461445,0.2854025,0.0005172224],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.4696989,0.01278296,0.2292457,0.003134433,0.0007727245,0.0005245186,0.2025185,0.03629813,0.04502409],"genre_scores_gemma":[0.4924243,0.007311019,0.3560588,0.0007825986,0.0003228124,0.0003032626,0.1312626,0.0025134,0.009021233],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01202368,"threshold_uncertainty_score":0.01967013,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06667772736430144,"score_gpt":0.2982523225824393,"score_spread":0.2315745952181379,"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."}}