{"id":"W7084086837","doi":"10.5281/zenodo.16367716","title":"Citation Parsing and Analysis with Language Models","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Metadata; Citation; Parsing; Open research; Citation analysis; Computational linguistics","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":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.00622957,0.001682888,0.001514441,0.008367862,0.002231154,0.008078913,0.002757474,0.002160883,0.01874305],"category_scores_gemma":[0.03002559,0.001454505,0.004212596,0.009238061,0.001671977,0.01071469,0.004371884,0.004154841,0.01199869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002374749,"about_ca_system_score_gemma":0.004032556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009534411,"about_ca_topic_score_gemma":0.008369741,"domain_scores_codex":[0.9928927,0.003545773,0.0006268258,0.001358916,0.001142549,0.0004332566],"domain_scores_gemma":[0.9826276,0.01180704,0.000684515,0.002385474,0.002271371,0.0002240723],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003677061,0.0003305616,0.0032365,0.0008029146,0.0002792717,0.0004324141,0.001403298,0.06579311,0.003417376,0.4108803,0.06457636,0.4484802],"study_design_scores_gemma":[0.00004044237,0.00002594775,0.0006561305,0.0001167404,0.0001051014,0.0001357507,0.0002644302,0.4400921,0.004646169,0.5124756,0.04135679,0.0000847485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008308783,0.001182481,0.9494216,0.001888446,0.0004224182,0.0001782323,0.005467882,0.02137685,0.01175338],"genre_scores_gemma":[0.2736951,0.001637652,0.6714119,0.0006908895,0.0008032226,0.0007488057,0.02396021,0.009616815,0.01743547],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9937704,"threshold_uncertainty_score":0.06270182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01861051643420738,"score_gpt":0.2512276717484416,"score_spread":0.2326171553142342,"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."}}