{"id":"https://openalex.org/W7225615188","doi":"https://doi.org/10.5281/zenodo.24070369","title":"**CatBoost Machine Learning Applied to the Texture-Averaging Framework for Magnetocrystalline Anisotropy: Predicting Effective Anisotropy Energies from Single-Crystal Constants K\u2081 and K\u2082**","display_name":"**CatBoost Machine Learning Applied to the Texture-Averaging Framework for Magnetocrystalline Anisotropy: Predicting Effective Anisotropy Energies from Single-Crystal Constants K\u2081 and K\u2082**","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225615188","doi":"https://doi.org/10.5281/zenodo.24070369"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24070369","doi":"https://doi.org/10.5281/zenodo.24070369","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24070369","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24070369","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118843517","display_name":"Sudhakar Geruganti","orcid":"https://orcid.org/0009-0000-0039-7536","observed_orcids":["https://orcid.org/0009-0000-0039-7536"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"geruganti, sudhakar","raw_affiliation_strings":["PROFESSOR IN ENGINEERING COLLEGE AND PHD RESEARCH SCHOLAR"],"raw_orcid":"https://orcid.org/0009-0000-0039-7536","affiliations":[{"raw_affiliation_string":"PROFESSOR IN ENGINEERING COLLEGE AND PHD RESEARCH SCHOLAR","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5118843517"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.6401000022888184,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.6401000022888184,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11222","display_name":"Magnetic Properties and Applications","score":0.290800005197525,"subfield":{"id":"https://openalex.org/subfields/2504","display_name":"Electronic, Optical and Magnetic Materials"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11782","display_name":"Magnetic Properties of Alloys","score":0.051899999380111694,"subfield":{"id":"https://openalex.org/subfields/2504","display_name":"Electronic, Optical and Magnetic Materials"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/magnetocrystalline-anisotropy","display_name":"magnetocrystalline anisotropy","score":0.9739999771118164},{"id":"https://openalex.org/keywords/catboost-regression","display_name":"CatBoost regression","score":0.8820000290870667},{"id":"https://openalex.org/keywords/alpha-iron","display_name":"alpha-iron","score":0.7760000228881836},{"id":"https://openalex.org/keywords/fcc-nickel","display_name":"fcc nickel","score":0.9980000257492065},{"id":"https://openalex.org/keywords/hcp-cobalt","display_name":"hcp cobalt","score":0.9990000128746033},{"id":"https://openalex.org/keywords/feature-importance","display_name":"feature importance","score":0.8830000162124634},{"id":"https://openalex.org/keywords/synthetic-training-data","display_name":"synthetic training data","score":0.6800000071525574},{"id":"https://openalex.org/keywords/machine-learning-for-materials","display_name":"machine learning for materials","score":0.3959999978542328}],"concepts":[{"id":"https://openalex.org/C56803174","wikidata":"https://www.wikidata.org/wiki/Q6731660","display_name":"Magnetocrystalline anisotropy","level":5,"score":0.7163000106811523},{"id":"https://openalex.org/C85725439","wikidata":"https://www.wikidata.org/wiki/Q466686","display_name":"Anisotropy","level":2,"score":0.6887999773025513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6029000282287598},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5472000241279602},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4812999963760376},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.4440999925136566},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.414900004863739},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36480000615119934},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34299999475479126},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C13355873","wikidata":"https://www.wikidata.org/wiki/Q2920850","display_name":"Connection (principal bundle)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.2874999940395355},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2800000011920929},{"id":"https://openalex.org/C26873012","wikidata":"https://www.wikidata.org/wiki/Q214781","display_name":"Condensed matter physics","level":1,"score":0.27300000190734863},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.26809999346733093},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.26019999384880066},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24070369","doi":"https://doi.org/10.5281/zenodo.24070369","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24070369","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.24070370","doi":"https://doi.org/10.5281/zenodo.24070370","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24070370","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24070369","doi":"https://doi.org/10.5281/zenodo.24070369","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24070369","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7225638820","https://openalex.org/W7225659558","https://openalex.org/W7214435720","https://openalex.org/W7225616507","https://openalex.org/W7222514436","https://openalex.org/W7225629056","https://openalex.org/W7222632792","https://openalex.org/W7225391793","https://openalex.org/W3098287374","https://openalex.org/W7225428017"],"abstract_inverted_index":{"##":[0,292,384,513,535,567],"Alternative":[1],"Titles":[2,5,46],"###":[3,44,123,189,249,570,676,1063,1234,1349],"Concise":[4],"1.":[6,1082,1256],"**CatBoost":[7,27,128,213,257,520],"for":[8,29,72,83,96,150,219,331,376,402,422,438,475,503,521,581,671,706,724,960,976,1120,1168,1193,1283,1319],"Texture":[9,85,161,283,465,522],"Averaging:":[10,162,466],"Predicting":[11,62,260,405],"Anisotropy":[12,31,64,115,142,217,247,262,365,382,407,480,505,531],"Energies":[13,65,218,263,408,481,532],"from":[14,66,139,409,690,731,738,1163],"K\u2081":[15,69,201,412,447,548,600,655,715,730,863,883],"and":[16,70,75,94,99,116,148,153,168,178,205,207,222,241,264,285,305,329,334,353,380,413,420,425,448,452,472,485,506,549,601,609,616,656,658,674,700,709,718,736,765,784,801,854,877,893,914,946,963,992,998,1011,1025,1033,1053,1133,1172,1226,1346,1351],"K\u2082**":[17],"2.":[18,1105,1280],"**Machine":[19,525],"Learning":[20,81,111,374,396,443,501,526],"Magnetocrystalline":[21,88,114,187,403,439,504,527],"Anisotropy:":[22,89,404],"A":[23,108,441,498,681,1044],"CatBoost":[24,50,109,157,183,276,298,394,433,461,499,660,792,832,966,1045,1066,1071,1086,1109,1143,1180,1200,1244,1323],"Approach**":[25],"3.":[26,1137,1296],"Regression":[28,51,129,856],"Texture-Averaged":[30,42,106,216,261,496],"Energies**":[32,43,248],"4.":[33,1175],"**Predicting":[34,530],"\u27e8E_aniso\u27e9":[35,56,623],"with":[36,225,268,533,798,823,1058,1140],"CatBoost:":[37],"From":[38,492],"Single-Crystal":[39,67,103,410,446,493],"Constants":[40,68,104,411,494],"to":[41,52,105,113,119,160,186,228,253,278,361,398,464,495,509,590,617,650,667,733,740,954,973,1078,1091,1198,1204,1212,1236,1278,1335],"Descriptive":[45],"5.":[47,1196],"**Application":[48],"of":[49,87,134,215,288,340,364,445,478,584,684,747,821,827,882,896,957,1041,1070,1125,1147,1177,1207,1215,1276,1301,1315,1332],"the":[53,84,125,140,191,197,245,251,266,286,297,306,399,435,476,582,592,596,603,610,619,634,641,645,651,659,691,744,865,889,894,897,902,927,931,938,942,955,969,987,1006,1020,1029,1096,1115,1126,1152,1159,1165,1191,1205,1216,1227,1247,1253,1302,1313,1316,1336],"Texture-Averaging":[54,198,400,436],"Integral":[55],"=":[57,270,311,318,321,324,327,624,695,698,702,711,714,720,750,758,762,768,772,796,809,813,839,869,1224,1232,1239],"\u222b":[58,625],"E_aniso":[59],"f":[60],"d\u03a9:":[61],"Effective":[63,406,479],"K\u2082":[71,203,320,414,737,753,761,771,873,900],"bcc-Fe,":[73,151,220,332,423,961,986],"fcc-Ni,":[74,152,221,333,424,962,1005],"hcp-Co**":[76,154],"6.":[77],"**A":[78],"CatBoost-Based":[79],"Machine":[80,110,281,373,395,442,500],"Framework":[82,375,401,437,502],"Averaging":[86],"Model":[90,144],"Development,":[91],"Feature":[92,146,315,417],"Importance,":[93,147],"Predictions":[95,149,214,277,330,421],"Iron,":[97],"Nickel,":[98],"Cobalt**":[100],"7.":[101],"**From":[102,275],"Energies:":[107,497],"Approach":[112],"Its":[117,507],"Connection":[118,252,508,1235],"Sudhakar's":[120,254,279,510,1237,1266,1291,1333],"E\\*":[121,269,511,555,1238,1267,1292,1303,1334],"Equation**":[122],"Emphasizing":[124,190,250],"Methodology":[126],"8.":[127],"on":[130],"a":[131,372,576,663,824,950,1088,1145,1155,1328],"Synthetic":[132,358],"Dataset":[133,359],"212":[135,685],"Data":[136],"Points":[137],"Generated":[138],"Analytic":[141,226],"Formulas:":[143],"Comparison,":[145],"9.":[155],"**The":[156,232],"Workflow":[158,299,462],"Applied":[159,185,397,463],"Digitization,":[163,467],"Splitting,":[164,468],"Hyperparameter":[165,469],"Tuning,":[166,470],"Evaluation,":[167,471],"Five-Fold":[169,307,473],"Cross-Validation**":[170],"10.":[171],"**Ordered":[172,1083],"Target":[173],"Statistics,":[174],"Symmetric":[175],"Tree":[176,850],"Structures,":[177],"Ordered":[179],"Boosting:":[180],"The":[181,460,587,629,727,775,791,831,880,912,934,965,1064,1068,1218,1243,1259,1271,1285,1299,1322],"Key":[182,677,1065],"Principles":[184,1067],"Anisotropy**":[188,528],"Physics":[192],"11.":[193],"**Feature":[194,861],"Importance":[195,316,418],"in":[196,244,482,638,909,930,1072,1154,1252,1263],"Framework:":[199],"Why":[200],"Dominates,":[202],"Follows,":[204],"Direction":[206,323,454],"Structure":[208,326],"Have":[209],"Smaller":[210],"Effects**":[211],"12.":[212],"hcp-Co:":[223],"Agreement":[224],"Values":[227],"Within":[229],"1%**":[230],"13.":[231],"Three":[233],"Fundamental":[234],"Obstacles":[235],"Revisited:":[236],"Units":[237],"Mismatch,":[238,240],"Sign":[239],"Ratio":[242],"Mismatch":[243],"CatBoost-Predicted":[246],"Equation":[255,512],"14.":[256],"Meets":[258],"Sudhakar:":[259],"Assessing":[265],"Compatibility":[267],"0.355A\\*":[271,1240],"\u2212":[272,1241],"1.89**":[273],"15.":[274],"E\\*:":[280],"Learning,":[282],"Averaging,":[284],"Limits":[287],"Direct":[289],"Numerical":[290],"Mapping**":[291],"Subtitle":[293],"Options":[294],"-":[295,313,336,356,370,519,524,529],"*With":[296],"(Digitize,":[300],"Split,":[301],"Tune,":[302],"Evaluate,":[303],"Validate)":[304],"Cross-Validation":[308,474],"Result":[309],"R\u00b2":[310,795,802,820,1223,1231],"0.9824*":[312],"*Including":[314],"(K\u2081":[317,749,757,767],"0.62,":[319],"0.21,":[322],"0.12,":[325],"0.05)":[328],"hcp-Co*":[335],"*A":[337],"Comparative":[338],"Study":[339,444],"CatBoost,":[341],"Extreme":[342,835],"Gradient":[343,345,836,841],"Boosting,":[344,346],"Random":[347,844],"Forest,":[348],"AdaBoost,":[349],"Decision":[350,849],"Tree,":[351],"Lasso,":[352],"Linear":[354,855],"Regression*":[355],"*From":[357],"Generation":[360],"Multiclass":[362],"Classification":[363],"Behavior":[366],"(POS,":[367],"NEG,":[368],"ZERO)*":[369],"*Toward":[371],"Rapid":[377],"Alloy":[378],"Screening":[379],"First-Principles-Informed":[381],"Prediction*":[383],"Suggested":[385],"Combined":[386],"Title":[387,515],"Formats":[388],"**Format":[389,427,455,487],"1":[390],"(Descriptive":[391],"+":[392,430,458,490,704,716,722],"Subtitle):**":[393],"\u2014":[415],"With":[416],"Analysis":[419],"hcp-Co":[426,766],"2":[428],"(Question":[429],"Answer):**":[431],"Can":[432],"Learn":[434],"Anisotropy?":[440],"K\u2082,":[449,602,657,717],"Crystal":[450],"Structure,":[451],"Crystallographic":[453],"3":[456],"(Method":[457],"Application):**":[459],"Prediction":[477],"Fe,":[483],"Ni,":[484],"Co":[486],"4":[488],"(Broad":[489],"Specific):**":[491],"Running":[514],"(for":[516],"journal":[517],"headers)":[518],"Averaging**":[523],"CatBoost**":[534],"Keywords":[536],"CatBoost;":[537],"gradient":[538,1102,1148,1170],"boosting;":[539],"machine":[540,578],"learning;":[541],"texture":[542,647],"averaging;":[543],"magnetocrystalline":[544,585],"anisotropy;":[545],"single-crystal":[546,597,653,1260,1317,1337],"constants":[547,599,654],"K\u2082;":[550],"bcc-Fe;":[551],"fcc-Ni;":[552],"hcp-Co;":[553],"Sudhakar":[554],"equation;":[556],"feature":[557,1117],"importance;":[558],"alloy":[559],"screening;":[560],"five-fold":[561],"cross-validation;":[562],"multiclass":[563,1046],"classification;":[564],"synthetic":[565,682],"dataset":[566,683,728,776],"Detailed":[568],"Description":[569],"Overview":[571],"This":[572,1128],"research":[573],"paper":[574,630],"presents":[575],"CatBoost-based":[577],"learning":[579,811],"framework":[580],"texture-averaging":[583,642,1254],"anisotropy.":[586],"objective":[588],"is":[589,631,688,777,864,884,901,949,1118,1201,1339],"learn":[591],"nonlinear":[593],"relationship":[594],"between":[595,944],"anisotropy":[598,621,891,1042,1056],"crystallographic":[604],"direction":[605,875,913,1035],"(\u27e8100\u27e9,":[606],"\u27e8110\u27e9,":[607,997],"\u27e8111\u27e9),":[608],"crystal":[611],"structure":[612,878,915,935,1130,1187],"(bcc,":[613],"fcc,":[614],"hcp),":[615],"predict":[618],"texture-averaged":[620,971],"energy":[622],"E_aniso(\u03b8,\u03c6,\u03c8)":[626],"f(\u03b8,\u03c6,\u03c8)":[627],"d\u03a9.":[628],"motivated":[632],"by":[633,872,926,1274],"conceptual":[635],"bridge":[636],"established":[637],"previous":[639],"work:":[640],"integral":[643,670],"connects":[644],"abstract":[646],"factor":[648],"A\\*":[649],"concrete":[652],"model":[661,967],"provides":[662],"fast,":[664],"data-driven":[665],"way":[666],"evaluate":[668],"this":[669,1073],"arbitrary":[672],"compositions":[673],"structures.":[675],"Findings":[678],"**Dataset":[679],"generation:**":[680],"data":[686,1153,1167],"points":[687],"generated":[689],"analytic":[692,932,970],"formulas:":[693],"E\u27e8100\u27e9":[694],"0,":[696,712,990,1001,1009,1015,1023,1037],"E\u27e8110\u27e9":[697],"(1/4)K\u2081,":[699],"E\u27e8111\u27e9":[701],"(1/3)K\u2081":[703],"(1/27)K\u2082":[705],"cubic":[707,945],"materials,":[708],"E(c-axis)":[710],"E(basal)":[713],"E(\u27e8111\u27e9)":[719],"(2/3)K\u2081":[721],"(4/9)K\u2082":[723],"hexagonal":[725,947],"materials.":[726],"spans":[729],"\u22121\u00d710\u2076":[732],"+1\u00d710\u2076":[734],"J/m\u00b3":[735,994,1013,1027],"\u22125\u00d710\u2075":[739],"+5\u00d710\u2075":[741],"J/m\u00b3,":[742,752,760,770,1264],"including":[743],"experimental":[745],"values":[746,1293,1304],"bcc-Fe":[748],"+4.8\u00d710\u2074":[751],"\u2248":[754,803],"0),":[755],"fcc-Ni":[756,1286],"\u22124.5\u00d710\u00b3":[759],"\u22122.3\u00d710\u00b3":[763],"J/m\u00b3),":[764],"+4.1\u00d710\u2075":[769],"+1.5\u00d710\u2075":[773],"J/m\u00b3).":[774],"split":[778],"into":[779],"80%":[780],"training":[781],"(170":[782],"points)":[783],"20%":[785],"testing":[786],"(42":[787],"points).":[788],"**Model":[789],"performance:**":[790],"regressor":[793,833],"achieves":[794],"0.78":[797],"default":[799,859,1219],"settings":[800,1220,1229],"0.99":[804],"after":[805],"hyperparameter":[806],"optimization":[807],"(depth":[808],"8,":[810],"rate":[812],"0.03).":[814],"Five-fold":[815],"cross-validation":[816],"gives":[817],"an":[818],"average":[819],"0.9824,":[822],"standard":[825],"deviation":[826],"0.008":[828],"across":[829],"folds.":[830],"outperforms":[834],"Boosting":[837,842],"(R\u00b2":[838],"0.68),":[840],"(0.65),":[843],"Forest":[845],"(0.64),":[846],"AdaBoost":[847],"(0.53),":[848],"(0.47),":[851],"Lasso":[852],"(0.33),":[853],"(0.33)":[857],"under":[858],"settings.":[860],"importance:**":[862],"dominant":[866],"predictor":[867],"(importance":[868],"0.62),":[870],"followed":[871],"(0.21),":[874],"(0.12),":[876],"(0.05).":[879],"dominance":[881],"physically":[885,1341],"sensible:":[886],"it":[887,1210],"determines":[888],"primary":[890],"scale":[892],"sign":[895],"easy":[898,1211],"axis.":[899],"second":[903],"most":[904],"important,":[905],"reflecting":[906],"its":[907,1079],"role":[908],"second-order":[910,951],"corrections.":[911],"indices":[916],"have":[917],"smaller":[918],"importance":[919,940],"because":[920,941],"their":[921],"effects":[922],"are":[923,989,1008,1022,1262,1288,1294],"already":[924,1221],"captured":[925],"geometric":[928],"factors":[929,1275],"formulas.":[933],"index":[936],"has":[937,1268],"smallest":[939],"difference":[943],"formulas":[948],"effect":[952],"compared":[953],"magnitude":[956],"K\u2081.":[958],"**Predictions":[959],"hcp-Co:**":[964],"reproduces":[968],"energies":[972,1261,1287,1318,1338],"within":[974],"1%":[975],"all":[977],"nine":[978],"cases":[979],"(three":[980],"materials":[981],"\u00d7":[982],"three":[983,1248],"directions).":[984],"For":[985,1004,1018],"predictions":[988,1007,1021,1245,1324],"1.19\u00d710\u2074,":[991],"1.59\u00d710\u2074":[993],"along":[995,1028],"\u27e8100\u27e9,":[996],"\u27e8111\u27e9":[999,1034],"(analytic:":[1000,1014,1036],"1.2\u00d710\u2074,":[1002],"1.6\u00d710\u2074).":[1003],"\u22121.13\u00d710\u00b3,":[1010],"\u22121.60\u00d710\u00b3":[1012],"\u22121.125\u00d710\u00b3,":[1016],"\u22121.585\u00d710\u00b3).":[1017],"hcp-Co,":[1019],"5.58\u00d710\u2075,":[1024],"3.39\u00d710\u2075":[1026],"c-axis,":[1030],"basal":[1031],"plane,":[1032],"5.6\u00d710\u2075,":[1038],"3.4\u00d710\u2075).":[1039],"**Classification":[1040],"behavior:**":[1043],"classifier":[1047],"distinguishes":[1048],"positive":[1049],"(POS),":[1050],"negative":[1051],"(NEG),":[1052],"zero":[1054],"(ZERO)":[1055],"classes":[1057],"class":[1059],"probabilities":[1060],"above":[1061],"91%.":[1062],"success":[1069],"application":[1074],"can":[1075,1181],"be":[1076],"attributed":[1077],"key":[1080],"principles:":[1081],"target":[1084,1093,1097],"statistics:**":[1085],"uses":[1087,1110,1144],"permutation-based":[1089],"approach":[1090],"compute":[1092],"statistics,":[1094],"avoiding":[1095],"leakage":[1098],"that":[1099,1150,1161,1327],"plagues":[1100],"other":[1101],"boosting":[1103,1139,1149],"implementations.":[1104],"**Symmetric":[1106],"tree":[1107,1173],"structures:**":[1108],"oblivious":[1111],"decision":[1112],"trees,":[1113],"where":[1114],"same":[1116,1166],"used":[1119],"splitting":[1121],"at":[1122],"each":[1123],"level":[1124],"tree.":[1127],"symmetric":[1129],"reduces":[1131],"overfitting":[1132],"speeds":[1134],"up":[1135],"prediction.":[1136],"**Gradient":[1138],"ordered":[1141],"boosting:**":[1142],"variant":[1146],"processes":[1151],"random":[1156],"order,":[1157],"reducing":[1158],"bias":[1160],"arises":[1162],"using":[1164],"both":[1169],"estimation":[1171],"construction.":[1174],"**Handling":[1176],"categorical":[1178,1183],"features:**":[1179],"handle":[1182],"features":[1184],"(direction":[1185],"index,":[1186],"index)":[1188],"natively,":[1189],"without":[1190,1343],"need":[1192],"one-hot":[1194],"encoding.":[1195],"**Robustness":[1197],"hyperparameters:**":[1199],"relatively":[1202],"insensitive":[1203],"choice":[1206],"hyperparameters,":[1208],"making":[1209],"use":[1213],"out":[1214],"box.":[1217],"give":[1222,1230],"0.78,":[1225],"optimized":[1228],"0.99.":[1233],"1.89":[1242],"confirm":[1246,1326],"fundamental":[1249],"obstacles":[1250],"identified":[1251],"analysis:":[1255],"**Units":[1257],"mismatch:**":[1258,1298],"while":[1265,1290],"unspecified":[1269],"units.":[1270],"magnitudes":[1272],"differ":[1273],"10\u00b3":[1277],"10\u2075.":[1279],"**Sign":[1281],"mismatch":[1282],"Ni:**":[1284],"negative,":[1289],"positive.":[1295],"**Ratio":[1297],"ratios":[1300,1314],"(1":[1305],":":[1306,1308],"1.763":[1307],"1.942)":[1309],"do":[1310],"not":[1311,1340],"match":[1312],"any":[1320],"material.":[1321],"therefore":[1325],"direct":[1329],"numerical":[1330],"mapping":[1331],"meaningful":[1342],"units":[1344],"specification":[1345],"realistic":[1347],"ODFs.":[1348],"Significance":[1350],"Limitation":[1352]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}