{"id":"https://openalex.org/W7208735911","doi":"https://doi.org/10.26434/chemrxiv.15008299/v1","title":"PolyGLOT: Graph-Token Language Modeling for Unified Polymer Property Prediction and Programmable Generation","display_name":"PolyGLOT: Graph-Token Language Modeling for Unified Polymer Property Prediction and Programmable Generation","publication_year":2026,"publication_date":"2026-09-04","ids":{"openalex":"https://openalex.org/W7208735911","doi":"https://doi.org/10.26434/chemrxiv.15008299/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15008299/v1","doi":"https://doi.org/10.26434/chemrxiv.15008299/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008299/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008299/v1","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008299/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102863432","display_name":"Tianle Yue","orcid":"https://orcid.org/0009-0005-3390-1344","observed_orcids":["https://orcid.org/0009-0005-3390-1344"]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianle Yue","raw_affiliation_strings":["Department of Mechanical Engineering","University of Wisconsin\u2013Madison Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering","institution_ids":[]},{"raw_affiliation_string":"University of Wisconsin\u2013Madison Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100414156","display_name":"Ying Li","orcid":"https://orcid.org/0000-0002-1487-3350","observed_orcids":["https://orcid.org/0000-0002-1487-3350","https://orcid.org/0000-0002-9711-0059","https://orcid.org/0009-0005-1388-6685","https://orcid.org/0009-0005-0308-1883"]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Li","raw_affiliation_strings":["Department of Mechanical Engineering","University of Wisconsin\u2013Madison Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering","institution_ids":[]},{"raw_affiliation_string":"University of Wisconsin\u2013Madison Madison","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.9574999809265137,"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":0.9574999809265137,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.0203000009059906,"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"}},{"id":"https://openalex.org/T11476","display_name":"Graph theory and applications","score":0.004600000102072954,"subfield":{"id":"https://openalex.org/subfields/2607","display_name":"Discrete Mathematics and Combinatorics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/polymer-design","display_name":"polymer design","score":0.6370000243186951},{"id":"https://openalex.org/keywords/molecular-graph-representation","display_name":"molecular graph representation","score":0.6970000267028809},{"id":"https://openalex.org/keywords/polymer-property-prediction","display_name":"polymer property prediction","score":0.8399999737739563},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.3479999899864197},{"id":"https://openalex.org/keywords/masked-token-prediction","display_name":"masked token prediction","score":0.6499999761581421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791100025177002},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.63919997215271},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5874000191688538},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C2780022179","wikidata":"https://www.wikidata.org/wiki/Q1986794","display_name":"Molecular graph","level":3,"score":0.44279998540878296},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41749998927116394},{"id":"https://openalex.org/C2780239667","wikidata":"https://www.wikidata.org/wiki/Q2102850","display_name":"Polyglot","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C96333769","wikidata":"https://www.wikidata.org/wiki/Q907955","display_name":"Graph traversal","level":3,"score":0.35850000381469727},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C56654003","wikidata":"https://www.wikidata.org/wiki/Q7858715","display_name":"Two-graph","level":5,"score":0.3160000145435333},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.31529998779296875},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2903999984264374},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27399998903274536},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C54540088","wikidata":"https://www.wikidata.org/wiki/Q3498041","display_name":"Intersection graph","level":4,"score":0.2648000121116638},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C64339825","wikidata":"https://www.wikidata.org/wiki/Q722659","display_name":"Graph property","level":5,"score":0.2621000111103058},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C114408938","wikidata":"https://www.wikidata.org/wiki/Q333373","display_name":"Abstract syntax","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15008299/v1","doi":"https://doi.org/10.26434/chemrxiv.15008299/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008299/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008299/v1","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15008299/v1","doi":"https://doi.org/10.26434/chemrxiv.15008299/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008299/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008299/v1","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7208735911.pdf","grobid_xml":"https://content.openalex.org/works/W7208735911.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W1988037271","https://openalex.org/W2291908932","https://openalex.org/W2754122850","https://openalex.org/W2883528235","https://openalex.org/W2903425689","https://openalex.org/W2973074478","https://openalex.org/W2996604169","https://openalex.org/W3009321976","https://openalex.org/W3090892334","https://openalex.org/W3094686696","https://openalex.org/W3095656008","https://openalex.org/W3107551345","https://openalex.org/W3197690017","https://openalex.org/W4307468223","https://openalex.org/W4361284807","https://openalex.org/W4386020939","https://openalex.org/W4398764792","https://openalex.org/W4403249895","https://openalex.org/W4403577922","https://openalex.org/W4404840891","https://openalex.org/W4405613539","https://openalex.org/W4406903299","https://openalex.org/W4412121399","https://openalex.org/W4416034930","https://openalex.org/W7172424594"],"related_works":["https://openalex.org/W7160899084","https://openalex.org/W7167040985","https://openalex.org/W4366769286","https://openalex.org/W4415967446","https://openalex.org/W3162823304","https://openalex.org/W7119033435","https://openalex.org/W7110850922","https://openalex.org/W7148178779","https://openalex.org/W7203630830","https://openalex.org/W7163646426"],"abstract_inverted_index":{"Polymer":[0],"design":[1],"benefits":[2],"from":[3,101],"representations":[4,18],"that":[5,158],"combine":[6],"efficient":[7],"sequence":[8,60],"modeling":[9],"with":[10],"explicit":[11],"access":[12],"to":[13,26,105],"molecular":[14,39,64],"graph":[15,33,67,71,103,130],"structure.":[16],"String":[17],"provide":[19],"compact":[20],"sequences":[21],"but":[22],"most":[23],"remain":[24],"sensitive":[25],"syntax":[27],"and":[28,73,83,109,122,151,163,171],"connectivity":[29],"errors,":[30],"whereas":[31],"sequential":[32],"generation":[34],"becomes":[35],"more":[36],"costly":[37],"as":[38,57],"graphs":[40,119],"grow.":[41],"We":[42],"introduce":[43],"PolyGLOT":[44,92,159],"(Polymer":[45],"Graph":[46],"Language":[47],"of":[48,61],"Tokens),":[49],"which":[50],"represents":[51],"a":[52,58,74,99,161],"linear":[53],"homopolymer":[54],"repeat":[55],"unit":[56],"reconstructable":[59],"mostly":[62],"small":[63,125],"subgraphs.":[65],"A":[66],"encoder":[68],"embeds":[69],"each":[70],"token,":[72],"common":[75],"Transformer":[76],"backbone":[77],"is":[78],"pretrained":[79],"by":[80,120],"masked-token":[81],"prediction":[82,88],"subsequently":[84],"fine-tuned":[85],"for":[86,166],"property":[87,168],"or":[89],"causal":[90],"generation.":[91],"achieves":[93],"competitive":[94],"property-prediction":[95],"performance":[96],"while":[97],"learning":[98],"hierarchy":[100],"local":[102,129,147],"chemistry":[104],"context-dependent":[106],"token":[107,126],"states":[108],"property-organized":[110],"polymer":[111,167],"representations.":[112],"Its":[113],"attachment-constrained":[114],"decoder":[115],"produces":[116],"valid":[117],"repeat-unit":[118],"construction,":[121],"the":[123,136,143],"typically":[124],"size":[127],"makes":[128],"operations":[131],"tractable.":[132],"Beyond":[133],"direct":[134],"generation,":[135,170],"same":[137],"graph-token":[138],"interface":[139],"supports":[140],"expansion":[141],"beyond":[142],"fixed":[144],"vocabulary,":[145],"property-guided":[146],"editing,":[148],"required-substructure":[149],"control,":[150],"small-molecule":[152],"structural-precedent":[153],"analysis.":[154],"These":[155],"results":[156],"show":[157],"provides":[160],"unified":[162],"extensible":[164],"representation":[165],"prediction,":[169],"downstream":[172],"design.":[173]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-05T00:00:00"}