{"id":"https://openalex.org/W7138055796","doi":"https://doi.org/10.48550/arxiv.2603.15250","title":"In-Context Symbolic Regression for Robustness-Improved Kolmogorov-Arnold Networks","display_name":"In-Context Symbolic Regression for Robustness-Improved Kolmogorov-Arnold Networks","publication_year":2026,"publication_date":"2026-03-16","ids":{"openalex":"https://openalex.org/W7138055796","doi":"https://doi.org/10.48550/arxiv.2603.15250"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.15250","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15250","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.15250","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129729886","display_name":"Francesco Sovrano","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sovrano, Francesco","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129645290","display_name":"Lidia Losavio","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Losavio, Lidia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080078268","display_name":"Giulia Vilone","orcid":"https://orcid.org/0000-0002-4401-5664"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vilone, Giulia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5069422623","display_name":"Marc Langheinrich","orcid":"https://orcid.org/0000-0002-8834-7388"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Langheinrich, Marc","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5129729886"],"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":0.5113000273704529,"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":0.5113000273704529,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.05849999934434891,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.024900000542402267,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/symbolic-regression","display_name":"Symbolic regression","score":0.6353999972343445},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.5514000058174133},{"id":"https://openalex.org/keywords/symbolic-data-analysis","display_name":"Symbolic data analysis","score":0.5273000001907349},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5210000276565552},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.4975999891757965},{"id":"https://openalex.org/keywords/univariate","display_name":"Univariate","score":0.44620001316070557},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.3993000090122223},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.39239999651908875}],"concepts":[{"id":"https://openalex.org/C2776400721","wikidata":"https://www.wikidata.org/wiki/Q18171762","display_name":"Symbolic regression","level":3,"score":0.6353999972343445},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5514000058174133},{"id":"https://openalex.org/C65620979","wikidata":"https://www.wikidata.org/wiki/Q7661176","display_name":"Symbolic data analysis","level":2,"score":0.5273000001907349},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5210000276565552},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4975999891757965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45910000801086426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.44760000705718994},{"id":"https://openalex.org/C199163554","wikidata":"https://www.wikidata.org/wiki/Q1681619","display_name":"Univariate","level":3,"score":0.44620001316070557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4140999913215637},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39959999918937683},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.34790000319480896},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3138999938964844},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3093999922275543},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.30140000581741333},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2881999909877777},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.15250","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15250","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.15250","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15250","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Symbolic":[0,114],"regression":[1,101,198],"aims":[2],"to":[3,27,69,81,126,201],"replace":[4],"black-box":[5],"predictors":[6],"with":[7],"concise":[8],"analytical":[9],"expressions":[10],"that":[11,45,148],"can":[12],"be":[13,49],"inspected":[14],"and":[15,83,87,107,181,186],"validated":[16],"in":[17,47,74,105,204],"scientific":[18],"machine":[19],"learning.":[20],"Kolmogorov-Arnold":[21],"Networks":[22],"(KANs)":[23],"are":[24,162],"well":[25],"suited":[26],"this":[28,138],"goal":[29],"because":[30],"each":[31,70,157],"connection":[32],"between":[33],"adjacent":[34],"units":[35],"(an":[36],"\"edge\")":[37],"is":[38,60],"parametrised":[39],"by":[40,51,121,141,166],"a":[41,52,61,143,167],"learnable":[42],"univariate":[43],"function":[44,73],"can,":[46],"principle,":[48],"replaced":[50],"symbolic":[53,58,100,197],"operator.":[54],"In":[55],"practice,":[56],"however,":[57],"extraction":[59,104],"bottleneck:":[62],"the":[63,77,94],"standard":[64],"KAN-to-symbol":[65],"approach":[66],"fits":[67],"operators":[68],"learned":[71],"edge":[72,123],"isolation,":[75],"making":[76],"discrete":[78],"choice":[79],"sensitive":[80],"initialisation":[82],"non-convex":[84],"parameter":[85],"fitting,":[86],"ignoring":[88],"how":[89],"local":[90],"substitutions":[91],"interact":[92],"through":[93],"full":[95],"network.":[96],"We":[97,173],"study":[98],"in-context":[99,113,119,139,169,196],"for":[102],"operator":[103,146,151],"KANs,":[106],"present":[108],"two":[109],"complementary":[110],"instantiations.":[111],"Greedy":[112],"Regression":[115],"(GSR)":[116],"performs":[117],"greedy,":[118],"selection":[120,140],"choosing":[122],"replacements":[124],"according":[125],"end-to-end":[127],"loss":[128],"improvement":[129],"after":[130,159],"brief":[131],"fine-tuning.":[132],"Gated":[133],"Matching":[134],"Pursuit":[135],"(GMP)":[136],"amortises":[137],"training":[142],"differentiable":[144],"gated":[145],"layer":[147],"places":[149],"an":[150],"library":[152],"behind":[153],"sparse":[154],"gates":[155,161],"on":[156],"edge;":[158],"convergence,":[160],"discretised":[163],"(optionally":[164],"followed":[165],"short":[168],"greedy":[170,195],"refinement":[171],"pass).":[172],"quantify":[174],"robustness":[175],"via":[176],"one-factor-at-a-time":[177],"(OFAT)":[178],"hyper-parameter":[179],"sweeps":[180],"assess":[182],"both":[183],"predictive":[184],"error":[185],"qualitative":[187],"consistency":[188],"of":[189],"recovered":[190],"formulas.":[191],"Across":[192],"several":[193],"experiments,":[194],"achieves":[199],"up":[200],"99.8%":[202],"reduction":[203],"median":[205],"OFAT":[206],"test":[207],"MSE.":[208]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}