{"id":"W6979363199","doi":"","title":"Efficient Forward-Only Data Valuation for Pretrained LLMs and VLMs","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Sesquiterpenes and Asteraceae Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Valuation (finance); Scalability; Transparency (behavior); Hessian matrix; Accountability; Training set","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001785576,0.001689975,0.001319573,0.0008258231,0.0006604896,0.00218354,0.003274126,0.001878386,0.009175252],"category_scores_gemma":[0.009544242,0.0009162443,0.00122296,0.0007683457,0.001103474,0.00523715,0.00267421,0.003506638,0.003689339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001680677,"about_ca_system_score_gemma":0.002328444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006814435,"about_ca_topic_score_gemma":0.01226326,"domain_scores_codex":[0.999346,0.0001331797,0.00004588162,0.000212639,0.000160315,0.0001020264],"domain_scores_gemma":[0.9981446,0.000824834,0.0001272218,0.0004506695,0.0003649602,0.00008775858],"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":[0.0004769552,0.0002698365,0.003871095,0.0003349597,0.0001736791,0.0003129128,0.0002219432,0.3392878,0.01388338,0.04071143,0.01985335,0.5806026],"study_design_scores_gemma":[0.00002151966,0.00003467896,0.0001998231,0.00001726805,0.00001173478,0.00003787759,0.00003561842,0.9690443,0.003822197,0.02517774,0.00158392,0.00001338744],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02860539,0.0004874545,0.9562479,0.000942261,0.0002156381,0.0001332318,0.0007575309,0.009600284,0.003010315],"genre_scores_gemma":[0.5014307,0.0004586466,0.4818519,0.001001312,0.0002299353,0.0003987178,0.003846872,0.001468522,0.009313284],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009175252,"threshold_uncertainty_score":0.03069425,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04399882787259915,"score_gpt":0.3251977059625908,"score_spread":0.2811988780899917,"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."}}