{"id":"https://openalex.org/W6891896282","doi":"https://doi.org/10.48550/arxiv.2503.17604","title":"OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discovery","display_name":"OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discovery","publication_year":2025,"publication_date":"2025-03-22","ids":{"openalex":"https://openalex.org/W6891896282","doi":"https://doi.org/10.48550/arxiv.2503.17604"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2503.17604","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.17604","pdf_url":"https://arxiv.org/pdf/2503.17604","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.17604","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085202845","display_name":"Vignesh Prabhakar","orcid":"https://orcid.org/0000-0002-5459-8015","observed_orcids":["https://orcid.org/0000-0002-5459-8015"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prabhakar, Vignesh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Islam, Md Amirul","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Islam, Md Amirul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026198238","display_name":"Adam A. Atanas","orcid":"https://orcid.org/0000-0002-3357-5228","observed_orcids":["https://orcid.org/0000-0002-3357-5228"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atanas, Adam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Yao-Ting","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yao-Ting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031800830","display_name":"Joah Han","orcid":"https://orcid.org/0000-0002-8982-3788","observed_orcids":["https://orcid.org/0000-0002-8982-3788"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Joah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036143185","display_name":"Aastha Jhunjhunwala","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jhunjhunwala, Aastha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038921563","display_name":"Rucha Apte","orcid":"https://orcid.org/0009-0006-6745-9977","observed_orcids":["https://orcid.org/0009-0006-6745-9977"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Apte, Rucha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133817742","display_name":"Robert Clark","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Clark, Robert","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xu, Kang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134002055","display_name":"Zihan Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zihan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Liu, Kai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.836899995803833,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.836899995803833,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07599999755620956,"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"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.026499999687075615,"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/scientific-reasoning","display_name":"scientific reasoning","score":0.9789999723434448},{"id":"https://openalex.org/keywords/scientific-discovery","display_name":"scientific discovery","score":0.7300000190734863},{"id":"https://openalex.org/keywords/domain-adaptive-pretraining","display_name":"domain-adaptive pretraining","score":0.9259999990463257},{"id":"https://openalex.org/keywords/instruction-tuning","display_name":"instruction tuning","score":0.9819999933242798},{"id":"https://openalex.org/keywords/battery-additives","display_name":"battery additives","score":0.6620000004768372}],"concepts":[{"id":"https://openalex.org/C2776127325","wikidata":"https://www.wikidata.org/wiki/Q1424662","display_name":"Omniscience","level":2,"score":0.6657000184059143},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6381000280380249},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4977000057697296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4918000102043152},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.46950000524520874},{"id":"https://openalex.org/C2992562121","wikidata":"https://www.wikidata.org/wiki/Q3817808","display_name":"Scientific reasoning","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3172000050544739},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.266400009393692},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2503.17604","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.17604","pdf_url":"https://arxiv.org/pdf/2503.17604","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.17604","doi":"https://doi.org/10.48550/arxiv.2503.17604","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.17604","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"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":"pmh:oai:arXiv.org:2503.17604","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.17604","pdf_url":"https://arxiv.org/pdf/2503.17604","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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/W4417063443","https://openalex.org/W4403809298","https://openalex.org/W7123371188","https://openalex.org/W4415145303","https://openalex.org/W4392011693","https://openalex.org/W7159970066","https://openalex.org/W4400942383","https://openalex.org/W7077852527","https://openalex.org/W7161785974","https://openalex.org/W7108340679"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"potential":[7,98],"in":[8,58],"advancing":[9],"scientific":[10,45],"knowledge":[11,65,147],"and":[12,62,78,119,128,145],"addressing":[13],"complex":[14],"challenges.":[15],"In":[16],"this":[17],"work,":[18],"we":[19],"introduce":[20],"OmniScience,":[21],"a":[22,40,51,90],"specialized":[23,52],"large":[24,112],"reasoning":[25,113,127],"model":[26,57],"for":[27],"general":[28],"science,":[29],"developed":[30],"through":[31,67],"three":[32],"key":[33],"components:":[34],"(1)":[35],"domain":[36,142],"adaptive":[37,143],"pretraining":[38,144],"on":[39,50,115],"carefully":[41],"curated":[42],"corpus":[43],"of":[44,86],"literature,":[46],"(2)":[47],"instruction":[48],"tuning":[49],"dataset":[53],"to":[54,69,74,151],"guide":[55],"the":[56,84,116],"following":[59],"domain-specific":[60,120],"tasks,":[61],"(3)":[63],"reasoning-based":[64,146],"distillation":[66,148],"fine-tuning":[68],"significantly":[70],"enhance":[71],"its":[72],"ability":[73],"generate":[75],"contextually":[76],"relevant":[77],"logically":[79],"sound":[80],"responses.":[81],"We":[82,135],"demonstrate":[83,137],"versatility":[85],"OmniScience":[87,107],"by":[88],"developing":[89],"battery":[91,121],"agent":[92],"that":[93,106,141],"efficiently":[94],"ranks":[95],"molecules":[96],"as":[97],"electrolyte":[99],"solvents":[100],"or":[101],"additives.":[102],"Comprehensive":[103],"evaluations":[104],"reveal":[105],"is":[108],"competitive":[109],"with":[110,131],"state-of-the-art":[111],"models":[114,130],"GPQA":[117],"Diamond":[118],"benchmarks,":[122],"while":[123],"outperforming":[124],"all":[125],"public":[126],"non-reasoning":[129],"similar":[132],"parameter":[133],"counts.":[134],"further":[136],"via":[138],"ablation":[139],"experiments":[140],"are":[149],"critical":[150],"attain":[152],"our":[153],"performance":[154],"levels,":[155],"across":[156],"benchmarks.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2025-10-10T00:00:00"}