{"id":"W2057960659","doi":"10.1007/s10579-004-8682-1","title":"Article: Collating Texts Using Progressive Multiple Alignment","year":2004,"lang":"en","type":"article","venue":"Computers and the Humanities","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"Universität Basel","keywords":"Collation; Witness; Computer science; Natural language processing; Phrase; Word (group theory); Base (topology); Point (geometry); Information retrieval; Linguistics; Artificial intelligence; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001794181,0.0001159359,0.0001314754,0.00004703184,0.000588276,0.0007224323,0.0004174934,0.00002650664,0.000001249474],"category_scores_gemma":[0.00002097971,0.00007564553,0.00003299369,0.00009804704,0.0003241173,0.0003246,0.0004146586,0.00009366513,0.000001287576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004782086,"about_ca_system_score_gemma":0.00003435951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000676944,"about_ca_topic_score_gemma":0.000006402882,"domain_scores_codex":[0.9992686,0.00004400912,0.0001459375,0.000194122,0.000157426,0.0001898912],"domain_scores_gemma":[0.9994949,0.0001099118,0.00009725391,0.0002211632,0.00005376917,0.00002304059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001762352,0.00003691111,0.00009818012,0.00004103832,0.00003538126,0.00005027781,0.01602816,0.0004278021,0.0005323068,0.9581048,0.00007137281,0.0245561],"study_design_scores_gemma":[0.004351631,0.0001651414,0.0001859614,0.0006414168,0.00003456889,0.0003435186,0.0008085265,0.2804194,0.02302194,0.6884276,0.0009591896,0.0006411763],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1641993,0.009016515,0.8246617,0.0006609757,0.0002895976,0.0004265558,0.000001077882,0.0004961603,0.0002481373],"genre_scores_gemma":[0.7442157,0.00000528096,0.2551077,0.0005668092,0.00006772465,0.000008624866,3.20995e-7,0.000005731743,0.0000221387],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5800164,"threshold_uncertainty_score":0.6966431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02261266426027232,"score_gpt":0.2515213186214391,"score_spread":0.2289086543611668,"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."}}