{"id":"W2951232267","doi":"10.48550/arxiv.1211.6321","title":"Citation content analysis (cca): A framework for syntactic and semantic analysis of citation content","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Joint Information Systems Committee; National Science Foundation","keywords":"Citation; Computer science; Scope (computer science); Content analysis; Semantic analysis (machine learning); Citation analysis; Content (measure theory); Context (archaeology); Information retrieval; Ranking (information retrieval); Data science; World Wide Web; Sociology; Social science; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005901202,0.0003616586,0.001133171,0.002962901,0.0001149977,0.0001067217,0.0008768199,0.0003374665,0.00001523807],"category_scores_gemma":[0.0003221193,0.0004015994,0.001020241,0.005155237,0.0001326896,0.0006549899,0.0006175009,0.0003264536,0.000002247003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000249975,"about_ca_system_score_gemma":0.0000572308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000319762,"about_ca_topic_score_gemma":0.0002009428,"domain_scores_codex":[0.9976074,0.0001998811,0.0005370041,0.001110526,0.0001972786,0.0003479561],"domain_scores_gemma":[0.9956946,0.0008602993,0.001208086,0.001287033,0.0007792875,0.0001706757],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001295406,0.0003751763,0.1150464,0.000325897,0.03002192,0.00002331857,0.002445723,0.1675131,0.0009086829,0.6805245,0.00001013003,0.00267554],"study_design_scores_gemma":[0.0002640142,0.00006628047,0.06130416,0.00008555032,0.02672931,4.631843e-7,0.0004576572,0.8299485,0.0004407797,0.08021792,0.000005720933,0.0004795687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3133503,0.0001474498,0.6858265,0.00005096934,0.00007229122,0.0003773068,0.00002642337,0.0001196575,0.00002905715],"genre_scores_gemma":[0.92344,0.0002096183,0.07606571,0.00004650256,0.00001956828,0.000009521793,0.00009838283,0.00001489283,0.00009581941],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6624354,"threshold_uncertainty_score":0.9998436,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1788789219699019,"score_gpt":0.2557730388244376,"score_spread":0.07689411685453576,"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."}}