{"id":"W4416034984","doi":"10.18653/v1/2025.findings-emnlp.223","title":"Sequence Structure Aware Retriever for Procedural Document Retrieval: A New Dataset and Baseline","year":2025,"lang":"","type":"article","venue":"","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; South China University of Technology; Natural Science Foundation of Guangxi Province; Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Baseline (sea); Sequence (biology); Labrador Retriever; Pattern recognition (psychology); Component (thermodynamics)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.001819324,0.002135975,0.001381267,0.006298163,0.001684069,0.002071139,0.003632603,0.003260839,0.005370718],"category_scores_gemma":[0.0069772,0.0003441679,0.002301055,0.004814036,0.001096453,0.003326539,0.00201249,0.00233161,0.008273577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002100724,"about_ca_system_score_gemma":0.002441428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02523114,"about_ca_topic_score_gemma":0.03792111,"domain_scores_codex":[0.9979234,0.0002727839,0.0002773889,0.00075271,0.0005981911,0.0001755275],"domain_scores_gemma":[0.9964988,0.0009170397,0.00025927,0.001174466,0.0008783182,0.0002720074],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002272155,0.003741455,0.01461988,0.00614515,0.0005222264,0.001468271,0.0004310845,0.01858342,0.03758715,0.004408333,0.5373257,0.3728952],"study_design_scores_gemma":[0.001645715,0.00218317,0.05020919,0.0007373039,0.000692997,0.005039136,0.001899512,0.141548,0.06142732,0.01133979,0.7227809,0.0004968735],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1646359,0.01161187,0.05920341,0.003301829,0.0009458445,0.003368319,0.7031753,0.03800926,0.01574825],"genre_scores_gemma":[0.05051097,0.001114297,0.09341963,0.0006792185,0.0001461641,0.001179402,0.8476637,0.0004837067,0.004802971],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02523114,"threshold_uncertainty_score":0.05016851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02106856039612271,"score_gpt":0.3304530265921004,"score_spread":0.3093844661959776,"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."}}