{"id":"W4385571887","doi":"10.18653/v1/2023.acl-long.180","title":"HistRED: A Historical Document-Level Relation Extraction Dataset","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Supercomputing Center, Korea Institute of Science and Technology Information; Defense Acquisition Program Administration; Korea Advanced Institute of Science and Technology; Agency for Defense Development; Korea University","keywords":"Computer science; Natural language processing; Relationship extraction; Robustness (evolution); Relation (database); Sentence; Artificial intelligence; Context (archaeology); Information retrieval; License; Information extraction; Data mining; History; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002333017,0.00007529849,0.0000672881,0.0001503557,0.00008374323,0.00009615062,0.0004404455,0.00006217352,0.00003607601],"category_scores_gemma":[0.00008032811,0.00006521787,0.00002173625,0.0005514966,0.000007058025,0.001031298,0.0001789757,0.0001272392,0.0002344788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003629967,"about_ca_system_score_gemma":0.00002720765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001609952,"about_ca_topic_score_gemma":0.00001141264,"domain_scores_codex":[0.9991671,0.0000266593,0.0001453732,0.000267746,0.0002396998,0.0001533947],"domain_scores_gemma":[0.9994297,0.00005390057,0.0000615453,0.0003784987,0.00003122638,0.00004514814],"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":[0.000004035216,0.00002193133,0.00007593493,0.00001248183,0.000004642246,0.00005103397,0.0001231651,0.000004299705,0.005701637,0.07873772,0.8014017,0.1138615],"study_design_scores_gemma":[0.0004255245,0.0001223227,0.002320021,0.00004363832,0.00001505725,0.0001081248,0.00002004844,0.03733522,0.02366242,0.2183863,0.7168792,0.0006820977],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002774892,0.0002404075,0.9916096,0.004246314,0.0004274144,0.00009052378,0.00001799769,0.002392663,0.000697631],"genre_scores_gemma":[0.09015269,0.00002234504,0.8992048,0.0003472773,0.00009338332,0.00002447795,0.0005336513,0.00001073771,0.009610664],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1396486,"threshold_uncertainty_score":0.3013829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04333989060999734,"score_gpt":0.3219132920197142,"score_spread":0.2785734014097169,"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."}}