{"id":"W4409710058","doi":"10.1101/2025.04.22.25326190","title":"ALPaCA: Adapting Llama for Pathology Context Analysis to enable slide-level question answering","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Context (archaeology); Question answering; Computer science; Pathology; Medicine; Information retrieval; 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"],"consensus_categories":[],"category_scores_codex":[0.001547144,0.0003166185,0.0006745248,0.0006787838,0.0001535491,0.0002065908,0.001493206,0.0003023483,0.000007796745],"category_scores_gemma":[0.0005713865,0.0003394679,0.0003233845,0.0006448029,0.00001785853,0.000136758,0.001831465,0.0003932866,0.00001067442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001555829,"about_ca_system_score_gemma":0.0001952212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003174517,"about_ca_topic_score_gemma":0.0003284552,"domain_scores_codex":[0.9971709,0.0001745313,0.0006078389,0.001279279,0.000261699,0.0005057928],"domain_scores_gemma":[0.9976324,0.0002795094,0.0002406874,0.001416211,0.0002990843,0.0001320665],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003831765,0.00009955302,0.01884484,0.0007005584,0.001300708,0.0001347037,0.005230557,0.4918141,0.002723805,0.1439195,0.0003838855,0.3348094],"study_design_scores_gemma":[0.0002800568,0.00004852129,0.00349641,0.0002967507,0.0003077358,0.000007137169,0.0001044008,0.9770411,0.002892859,0.01174916,0.003183261,0.000592651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09462239,0.0002510309,0.9010288,0.001407073,0.001269669,0.0005294138,0.0000306126,0.0002376006,0.0006234747],"genre_scores_gemma":[0.6945719,0.00001445421,0.3032751,0.000512633,0.0001741274,0.0002196889,0.00001492478,0.0000122197,0.001204946],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5999495,"threshold_uncertainty_score":0.9999057,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06290461622411195,"score_gpt":0.3110425877124073,"score_spread":0.2481379714882954,"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."}}