{"id":"https://openalex.org/W7125577491","doi":"https://doi.org/10.1088/2632-2153/ae3c57","title":"The good, the bad, and the ugly of atomistic learning for \u2018clusters-to-bulk\u2019 generalization","display_name":"The good, the bad, and the ugly of atomistic learning for \u2018clusters-to-bulk\u2019 generalization","publication_year":2026,"publication_date":"2026-01-22","ids":{"openalex":"https://openalex.org/W7125577491","doi":"https://doi.org/10.1088/2632-2153/ae3c57"},"language":"en","primary_location":{"id":"doi:10.1088/2632-2153/ae3c57","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ae3c57","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1088/2632-2153/ae3c57","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123730641","display_name":"Miko\u0142aj Jan Gawkowski","orcid":null},"institutions":[{"id":"https://openalex.org/I2801237587","display_name":"London Centre for Nanotechnology","ror":"https://ror.org/04ptp8872","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2801237587"]},{"id":"https://openalex.org/I330495657","display_name":"Thomas Young Centre","ror":"https://ror.org/03hdrgy42","country_code":"GB","type":"other","lineage":["https://openalex.org/I330495657"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Miko\u0142aj J Gawkowski","raw_affiliation_strings":["Department of Physics and Astronomy, University College London, 7-19 Gordon St, London WC1H 0AH, United Kingdom","Thomas Young Centre and London Centre for Nanotechnology, 9 Gordon St, London WC1H 0AH, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0001-8717-3793","affiliations":[{"raw_affiliation_string":"Department of Physics and Astronomy, University College London, 7-19 Gordon St, London WC1H 0AH, United Kingdom","institution_ids":["https://openalex.org/I2801237587","https://openalex.org/I45129253"]},{"raw_affiliation_string":"Thomas Young Centre and London Centre for Nanotechnology, 9 Gordon St, London WC1H 0AH, United Kingdom","institution_ids":["https://openalex.org/I2801237587","https://openalex.org/I330495657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123750237","display_name":"Mingjia Li","orcid":null},"institutions":[{"id":"https://openalex.org/I2801237587","display_name":"London Centre for Nanotechnology","ror":"https://ror.org/04ptp8872","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2801237587"]},{"id":"https://openalex.org/I330495657","display_name":"Thomas Young Centre","ror":"https://ror.org/03hdrgy42","country_code":"GB","type":"other","lineage":["https://openalex.org/I330495657"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mingjia Li","raw_affiliation_strings":["Department of Physics and Astronomy, University College London, 7-19 Gordon St, London WC1H 0AH, United Kingdom","Thomas Young Centre and London Centre for Nanotechnology, 9 Gordon St, London WC1H 0AH, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0000-3289-6268","affiliations":[{"raw_affiliation_string":"Department of Physics and Astronomy, University College London, 7-19 Gordon St, London WC1H 0AH, United Kingdom","institution_ids":["https://openalex.org/I2801237587","https://openalex.org/I45129253"]},{"raw_affiliation_string":"Thomas Young Centre and London Centre for Nanotechnology, 9 Gordon St, London WC1H 0AH, United Kingdom","institution_ids":["https://openalex.org/I2801237587","https://openalex.org/I330495657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061668089","display_name":"Benjamin Xu Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153546","display_name":"Flatiron Health (United States)","ror":"https://ror.org/0508h6p74","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153546"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin X Shi","raw_affiliation_strings":["Initiative for Computational Catalysis, Flatiron Institute, 160 5th Avenue, New York, NY 10010, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-3272-0996","affiliations":[{"raw_affiliation_string":"Initiative for Computational Catalysis, Flatiron Institute, 160 5th Avenue, New York, NY 10010, United States of America","institution_ids":["https://openalex.org/I4210153546"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009821984","display_name":"Venkat Kapil","orcid":"https://orcid.org/0000-0003-0324-2198"},"institutions":[{"id":"https://openalex.org/I2801237587","display_name":"London Centre for Nanotechnology","ror":"https://ror.org/04ptp8872","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2801237587"]},{"id":"https://openalex.org/I330495657","display_name":"Thomas Young Centre","ror":"https://ror.org/03hdrgy42","country_code":"GB","type":"other","lineage":["https://openalex.org/I330495657"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Venkat Kapil","raw_affiliation_strings":["Department of Physics and Astronomy, University College London, 7-19 Gordon St, London WC1H 0AH, United Kingdom","Thomas Young Centre and London Centre for Nanotechnology, 9 Gordon St, London WC1H 0AH, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-0324-2198","affiliations":[{"raw_affiliation_string":"Department of Physics and Astronomy, University College London, 7-19 Gordon St, London WC1H 0AH, United Kingdom","institution_ids":["https://openalex.org/I2801237587","https://openalex.org/I45129253"]},{"raw_affiliation_string":"Thomas Young Centre and London Centre for Nanotechnology, 9 Gordon St, London WC1H 0AH, United Kingdom","institution_ids":["https://openalex.org/I2801237587","https://openalex.org/I330495657"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3000,"currency":"USD","value_usd":3000},"apc_paid":{"value":3000,"currency":"USD","value_usd":3000},"fwci":10.5634,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.98309729,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"7","issue":"2","first_page":"025004","last_page":"025004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9700000286102295,"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":0.9700000286102295,"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/T11804","display_name":"Quantum many-body systems","score":0.004000000189989805,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11471","display_name":"Block Copolymer Self-Assembly","score":0.003000000026077032,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.7497000098228455},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.692300021648407},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.6579999923706055},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5612999796867371},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4733000099658966},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.45969998836517334},{"id":"https://openalex.org/keywords/reference-data","display_name":"Reference data","score":0.3971000015735626},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.3970000147819519}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.7497000098228455},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.692300021648407},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.6579999923706055},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5612999796867371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.521399974822998},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.5187000036239624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5103999972343445},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4733000099658966},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.45969998836517334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.398499995470047},{"id":"https://openalex.org/C60478076","wikidata":"https://www.wikidata.org/wiki/Q3036835","display_name":"Reference data","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.35920000076293945},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C106447425","wikidata":"https://www.wikidata.org/wiki/Q11379","display_name":"Energy transfer","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C2777938197","wikidata":"https://www.wikidata.org/wiki/Q7834022","display_name":"Transfer of training","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C2780695315","wikidata":"https://www.wikidata.org/wiki/Q3799040","display_name":"Unobservable","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1088/2632-2153/ae3c57","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ae3c57","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2a8ea9e46dca437f83f5f6aca36fee1d","is_oa":true,"landing_page_url":"https://doaj.org/article/2a8ea9e46dca437f83f5f6aca36fee1d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning: Science and Technology, Vol 7, Iss 2, p 025004 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1088/2632-2153/ae3c57","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ae3c57","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.6824734210968018}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1496833370","https://openalex.org/W1554563779","https://openalex.org/W1971044734","https://openalex.org/W2011159427","https://openalex.org/W2012458244","https://openalex.org/W2047316564","https://openalex.org/W2048195126","https://openalex.org/W2055526416","https://openalex.org/W2092930273","https://openalex.org/W2234552091","https://openalex.org/W2318948631","https://openalex.org/W2520205627","https://openalex.org/W2601081289","https://openalex.org/W2795562645","https://openalex.org/W2910857709","https://openalex.org/W2942326588","https://openalex.org/W2989999252","https://openalex.org/W3041909131","https://openalex.org/W3110392041","https://openalex.org/W3128119843","https://openalex.org/W4221045050","https://openalex.org/W4225405705","https://openalex.org/W4283774473","https://openalex.org/W4309830151","https://openalex.org/W4311822110","https://openalex.org/W4318958052","https://openalex.org/W4378745805","https://openalex.org/W4384206875","https://openalex.org/W4385062438","https://openalex.org/W4389132751","https://openalex.org/W4392506021","https://openalex.org/W4393973933","https://openalex.org/W4394896752","https://openalex.org/W4399303478","https://openalex.org/W4399498474","https://openalex.org/W4400902738","https://openalex.org/W4401443596","https://openalex.org/W4401584941","https://openalex.org/W4403940006","https://openalex.org/W4404808888","https://openalex.org/W4405767531","https://openalex.org/W4408535115","https://openalex.org/W4408556840","https://openalex.org/W4410498985","https://openalex.org/W4410642015","https://openalex.org/W4410810877","https://openalex.org/W4412074968","https://openalex.org/W4412555154","https://openalex.org/W4414005844","https://openalex.org/W4414514094","https://openalex.org/W4416015471","https://openalex.org/W4416758539"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Training":[1],"machine":[2],"learning":[3,17,100,123],"interatomic":[4],"potentials":[5],"(MLIPs)":[6],"on":[7,70,126,135],"total":[8],"energies":[9,76,82,128,136,181],"of":[10,27,67,93,161,212],"molecular":[11],"clusters":[12,111],"using":[13],"differential":[14],"or":[15,198],"transfer":[16,99,122],"is":[18,117],"becoming":[19],"a":[20],"popular":[21],"route":[22],"to":[23,31,112,150,193,199],"extend":[24],"the":[25,51,65,89,191,208],"accuracy":[26,90,109],"correlated":[28],"wave-function":[29],"theory":[30],"condensed":[32,216],"phases.":[33],"A":[34],"key":[35],"challenge,":[36],"however,":[37],"lies":[38],"in":[39,44],"validation,":[40],"as":[41,180],"reference":[42,52,58],"observables":[43],"finite-temperature":[45],"ensembles":[46],"are":[47,83],"not":[48],"available":[49,84],"at":[50],"level.":[53],"Here,":[54],"we":[55,156],"construct":[56],"synthetic":[57],"data":[59],"from":[60,110],"pretrained":[61],"MLIPs":[62,214],"and":[63,77,79,91,97,129,141,182,210,218,225],"evaluate":[64],"generalizability":[66],"cluster-trained":[68,213],"models":[69],"ice-Ih,":[71],"considering":[72],"scenarios":[73],"where":[74,80],"both":[75,127],"forces":[78,195],"only":[81,134,171],"for":[85,215,221],"training.":[86],"We":[87,105],"study":[88],"data-efficiency":[92],"differential,":[94],"single-fidelity":[95],"transfer,":[96],"multi-fidelity":[98,121],"against":[101],"ground-truth":[102],"thermodynamic":[103],"observables.":[104,153],"find":[106],"that":[107,158],"transferring":[108],"bulk":[113],"requires":[114],"regularization,":[115],"which":[116],"best":[118],"achieved":[119],"through":[120],"when":[124],"training":[125,133,197],"forces.":[130],"By":[131],"contrast,":[132],"introduces":[137],"artefacts:":[138],"stable":[139],"trajectories":[140],"low":[142,167,186],"energy":[143,174,187],"errors":[144,169],"conceal":[145],"large":[146],"force":[147,168],"errors,":[148,175],"leading":[149],"inaccurate":[151],"microscopic":[152,162],"More":[154],"broadly,":[155],"show":[157],"accurate":[159],"reproduction":[160],"structure":[163],"correlates":[164],"strongly":[165],"with":[166,173,185],"but":[170],"weakly":[172],"whereas":[176],"global":[177],"properties":[178],"such":[179],"densities":[183],"correlate":[184],"errors.":[188],"This":[189],"highlights":[190],"need":[192],"incorporate":[194],"during":[196],"apply":[200],"careful":[201],"validation":[202],"before":[203],"production.":[204],"Our":[205],"results":[206],"highlight":[207],"promise":[209],"pitfalls":[211],"phases":[217],"provide":[219],"guidelines":[220],"developing\u2014and":[222],"critically,":[223],"validating\u2014robust":[224],"data-efficient":[226],"MLIPs.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-01-25T00:00:00"}