{"id":"https://openalex.org/W7223181682","doi":"https://doi.org/10.26434/chemrxiv-2025-vj4fk/v2","title":"The Illusion of Chemical Continuity Limits Machine Learning Generalization","display_name":"The Illusion of Chemical Continuity Limits Machine Learning Generalization","publication_year":2026,"publication_date":"2026-10-21","ids":{"openalex":"https://openalex.org/W7223181682","doi":"https://doi.org/10.26434/chemrxiv-2025-vj4fk/v2"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv-2025-vj4fk/v2","doi":"https://doi.org/10.26434/chemrxiv-2025-vj4fk/v2","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv-2025-vj4fk/v2","pdf_url":null,"source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.26434/chemrxiv-2025-vj4fk/v2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100422270","display_name":"Zhibo Wang","orcid":"https://orcid.org/0000-0001-7320-0028","observed_orcids":["https://orcid.org/0000-0001-7320-0028"]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhibo Wang","raw_affiliation_strings":["Alliance for AI-Accelerated Materials Discovery","University of Toronto"],"raw_orcid":"https://orcid.org/0000-0001-7320-0028","affiliations":[{"raw_affiliation_string":"Alliance for AI-Accelerated Materials Discovery","institution_ids":[]},{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159248807","display_name":"Alexander Davis","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Alexander Davis","raw_affiliation_strings":["Alliance for AI-Accelerated Materials Discovery","University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alliance for AI-Accelerated Materials Discovery","institution_ids":[]},{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085602193","display_name":"Rajarshi Dutta","orcid":"https://orcid.org/0000-0002-7515-1634","observed_orcids":["https://orcid.org/0000-0002-7515-1634","https://orcid.org/0009-0000-5825-9283"]},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajarshi Dutta","raw_affiliation_strings":["Indian Institute of Technology Kanpur"],"raw_orcid":"https://orcid.org/0009-0000-5825-9283","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kanpur","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094258973","display_name":"Alex-Cristian Tomut","orcid":"https://orcid.org/0009-0005-9110-3105","observed_orcids":["https://orcid.org/0009-0005-9110-3105"]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Alex-Cristian Tomut","raw_affiliation_strings":["University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147016034","display_name":"Kanishk Yadav","orcid":"https://orcid.org/0009-0008-8032-2814","observed_orcids":["https://orcid.org/0009-0008-8032-2814"]},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kanishk Yadav","raw_affiliation_strings":["Birla Institute of Technology and Science, Pilani"],"raw_orcid":"https://orcid.org/0009-0008-8032-2814","affiliations":[{"raw_affiliation_string":"Birla Institute of Technology and Science, Pilani","institution_ids":["https://openalex.org/I74796645"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159254469","display_name":"Ihor Neporozhnii","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ihor Neporozhnii","raw_affiliation_strings":["Alliance for AI-Accelerated Materials Discovery","University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alliance for AI-Accelerated Materials Discovery","institution_ids":[]},{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159254492","display_name":"Sjoerd Hoogland","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sjoerd Hoogland","raw_affiliation_strings":["Alliance for AI-Accelerated Materials Discovery","University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alliance for AI-Accelerated Materials Discovery","institution_ids":[]},{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5159244341","display_name":"Oleksandr Voznyy","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Oleksandr Voznyy","raw_affiliation_strings":["Alliance for AI-Accelerated Materials Discovery","University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alliance for AI-Accelerated Materials Discovery","institution_ids":[]},{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"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":1.0,"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":1.0,"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/T10002","display_name":"Advanced Chemical Physics Studies","score":0.0,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/chemical-space","display_name":"chemical space","score":0.4699999988079071},{"id":"https://openalex.org/keywords/scaling-hypothesis","display_name":"scaling hypothesis","score":0.7630000114440918},{"id":"https://openalex.org/keywords/band-gap-prediction","display_name":"band gap prediction","score":0.6499999761581421},{"id":"https://openalex.org/keywords/band-structure","display_name":"electronic band structure","score":0.625},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.7070000171661377},{"id":"https://openalex.org/keywords/binary-semiconductors","display_name":"binary semiconductors","score":0.9480000138282776},{"id":"https://openalex.org/keywords/negative-learning","display_name":"negative learning","score":0.5839999914169312},{"id":"https://openalex.org/keywords/atomic-orbitals","display_name":"atomic orbitals","score":0.8420000076293945},{"id":"https://openalex.org/keywords/band-crossing","display_name":"band crossing","score":0.5230000019073486},{"id":"https://openalex.org/keywords/materials-informatics","display_name":"materials informatics","score":0.6480000019073486},{"id":"https://openalex.org/keywords/formation-energy","display_name":"formation energy","score":0.40799999237060547},{"id":"https://openalex.org/keywords/rock-salt-structure","display_name":"rock salt structure","score":0.3190000057220459}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6190000176429749},{"id":"https://openalex.org/C15627037","wikidata":"https://www.wikidata.org/wiki/Q541961","display_name":"Classification of discontinuities","level":2,"score":0.6097000241279602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6049000024795532},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4945000112056732},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.44350001215934753},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43689998984336853},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4101000130176544},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40610000491142273},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.359499990940094},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C189394030","wikidata":"https://www.wikidata.org/wiki/Q53860","display_name":"Atomic orbital","level":3,"score":0.3361000120639801},{"id":"https://openalex.org/C2779687425","wikidata":"https://www.wikidata.org/wiki/Q7166998","display_name":"Percept","level":3,"score":0.32670000195503235},{"id":"https://openalex.org/C2781204021","wikidata":"https://www.wikidata.org/wiki/Q6497091","display_name":"Lattice (music)","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C184047640","wikidata":"https://www.wikidata.org/wiki/Q182593","display_name":"Illusion","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C151876577","wikidata":"https://www.wikidata.org/wiki/Q7049464","display_name":"Nonlinear dimensionality reduction","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.27219998836517334},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2667999863624573},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C114852677","wikidata":"https://www.wikidata.org/wiki/Q899044","display_name":"Fock space","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.25360000133514404},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C110729354","wikidata":"https://www.wikidata.org/wiki/Q185478","display_name":"Countable set","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv-2025-vj4fk/v2","doi":"https://doi.org/10.26434/chemrxiv-2025-vj4fk/v2","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv-2025-vj4fk/v2","pdf_url":null,"source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv-2025-vj4fk/v2","doi":"https://doi.org/10.26434/chemrxiv-2025-vj4fk/v2","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv-2025-vj4fk/v2","pdf_url":null,"source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4412512602","https://openalex.org/W7220670942","https://openalex.org/W7129717758","https://openalex.org/W7165851818","https://openalex.org/W7157648674","https://openalex.org/W7138990047","https://openalex.org/W4293720195","https://openalex.org/W4308090287","https://openalex.org/W7155535998","https://openalex.org/W3044033594"],"abstract_inverted_index":{"The":[0],"central":[1],"dogma":[2],"of":[3,63,87,115,141,178,186,195],"materials":[4],"informatics":[5],"is":[6,15,94,189],"the":[7,10,79,83,90,112,116,138,145,154,164,175],"\"Scaling":[8],"Hypothesis\":":[9],"assumption":[11],"that":[12],"chemical":[13],"space":[14],"a":[16,51,60,160,182],"continuous":[17],"manifold,":[18],"and":[19,66,73,144],"that,":[20],"with":[21],"sufficient":[22],"data,":[23],"deep":[24],"learning":[25],"models":[26],"can":[27,133],"approximate":[28],"any":[29],"structure-property":[30],"relationship.":[31],"While":[32],"this":[33,76],"strategy":[34],"has":[35],"achieved":[36],"near-DFT":[37],"accuracy":[38,46,128],"for":[39,47,129,163],"thermodynamic":[40],"properties":[41],"like":[42],"formation":[43],"energy,":[44,89],"prediction":[45,127],"bandgaps":[48],"suffers":[49],"from":[50],"fundamental,":[52],"non-converging":[53],"error":[54],"floor":[55],"(~0.4":[56],"eV).":[57],"By":[58],"analyzing":[59],"comprehensive":[61],"dataset":[62,99],"binary":[64],"semiconductors":[65],"state-of-the-art":[67],"Graph":[68],"Neural":[69],"Networks":[70],"(including":[71],"coGN":[72],"foundational":[74],"embeddings),":[75],"work":[77,158],"isolates":[78],"root":[80],"cause:":[81],"unlike":[82],"smooth,":[84],"transferable":[85],"landscape":[86],"total":[88],"electronic":[91],"bandgap":[92],"manifold":[93],"topologically":[95],"disjoint.":[96],"Consequently,":[97],"increasing":[98,111],"size":[100],"fails":[101],"to":[102,123,137],"improve":[103],"predictions,":[104],"instead":[105],"resulting":[106,146],"in":[107,153],"negative":[108],"learning,":[109],"where":[110],"structural":[113],"diversity":[114],"training":[117],"set":[118],"(e.g.,":[119],"adding":[120],"rocksalt":[121],"data":[122],"zincblende":[124],"models)":[125],"degrades":[126],"unseen":[130],"chemistries.":[131],"This":[132,157],"be":[134],"traced":[135],"back":[136],"discrete":[139],"quantization":[140],"atomic":[142,171],"orbitals":[143],"band":[147],"crossings,":[148],"which":[149],"create":[150],"non-differentiable":[151],"cusps":[152],"property":[155],"surface.":[156],"establishes":[159],"boundary":[161],"condition":[162],"\"Big":[165],"Data\"":[166],"paradigm:":[167],"simple":[168],"regression":[169],"on":[170],"coordinates":[172],"cannot":[173],"resolve":[174],"intrinsic":[176],"discontinuities":[177],"eigenvalue":[179],"phenomena.":[180],"Instead,":[181],"more":[183],"detailed":[184],"integration":[185],"quantum":[187],"mechanics":[188],"required,":[190],"such":[191],"as":[192,197],"direct":[193],"entrainment":[194],"Hamiltonians":[196],"descriptors.":[198]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-22T00:00:00"}