{"id":"https://openalex.org/W7164018551","doi":"https://doi.org/10.48550/arxiv.2606.08532","title":"DN-Hypo-Pipeline: An AI-Driven Workflow for Generating Hypotheses using Large Language Models and Scientific Explanations","display_name":"DN-Hypo-Pipeline: An AI-Driven Workflow for Generating Hypotheses using Large Language Models and Scientific Explanations","publication_year":2026,"publication_date":"2026-06-07","ids":{"openalex":"https://openalex.org/W7164018551","doi":"https://doi.org/10.48550/arxiv.2606.08532"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.08532","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08532","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.08532","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138266650","display_name":"Lei Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138237666","display_name":"Ronghao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Ronghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138242731","display_name":"Chunbao Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Chunbao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138221576","display_name":"Jue Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138221726","display_name":"Yangang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yangang","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":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/T13910","display_name":"Computational and Text Analysis Methods","score":0.2556000053882599,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.2556000053882599,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.22789999842643738,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.11599999666213989,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7070000171661377},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5286999940872192},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5092999935150146},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4790000021457672},{"id":"https://openalex.org/keywords/scientific-modelling","display_name":"Scientific modelling","score":0.45350000262260437},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4275999963283539},{"id":"https://openalex.org/keywords/experimental-science","display_name":"Experimental science","score":0.39410001039505005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7179999947547913},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7070000171661377},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.54339998960495},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5286999940872192},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5092999935150146},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4790000021457672},{"id":"https://openalex.org/C138379479","wikidata":"https://www.wikidata.org/wiki/Q1116876","display_name":"Scientific modelling","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43970000743865967},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4275999963283539},{"id":"https://openalex.org/C2994469624","wikidata":"https://www.wikidata.org/wiki/Q101965","display_name":"Experimental science","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2822999954223633},{"id":"https://openalex.org/C2992562121","wikidata":"https://www.wikidata.org/wiki/Q3817808","display_name":"Scientific reasoning","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.08532","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08532","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.08532","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08532","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":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.43915149569511414}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"artificial":[1],"intelligence":[2],"excels":[3],"at":[4,48],"prediction":[5],"but":[6],"cannot":[7,31],"explain.":[8],"From":[9],"large":[10],"language":[11],"models":[12],"to":[13,66,108,131],"AI-for-science":[14],"systems,":[15],"today's":[16],"machines":[17],"answer":[18],"what":[19,146,156],"by":[20,193],"recombining":[21],"patterns":[22],"already":[23],"present":[24],"in":[25,169,188],"the":[26,49,58,90,111,124,132,143,150,153,166,170,175,214,224],"human":[27,197],"literature,":[28],"yet":[29],"they":[30],"reason":[32],"out":[33],"why":[34],"a":[35,69,76,81,97,127,159,183],"phenomenon":[36],"must":[37],"arise":[38],"from":[39,126,208],"underlying":[40],"principles":[41,157],"even":[42],"though":[43],"explanation,":[44],"not":[45],"prediction,":[46],"lies":[47],"heart":[50],"of":[51,60,96,117,145,155],"scientific":[52,61],"discovery.":[53],"Here":[54],"we":[55,212],"ask":[56],"whether":[57],"structure":[59],"explanation":[62],"can":[63],"be":[64,136],"operationalized":[65],"guide":[67],"how":[68],"machine":[70],"generates":[71],"hypotheses.":[72],"We":[73],"introduce":[74],"DN-Hypo-Pipeline,":[75],"hypothesis-generation":[77],"framework":[78,151],"that":[79,134,222,235],"adopts":[80],"layered,":[82],"explanation-theoretic":[83],"scaffold:":[84],"Hempel's":[85],"deductive-nomological":[86],"(DN)":[87],"model":[88],"supplies":[89,102,123],"output":[91],"form":[92],"and":[93,114,180,191,196,233],"deductive":[94],"validity":[95],"hypothesis,":[98],"Salmon's":[99],"causal-process":[100],"account":[101],"an":[103,162],"organizing":[104],"constraint":[105],"on":[106],"where":[107],"search":[109],"for":[110],"governing":[112],"laws,":[113],"Armstrong's":[115],"view":[116],"laws":[118,133,176],"as":[119],"relations":[120],"between":[121],"universals":[122,167],"bridge":[125],"phenomenon's":[128,171],"constituent":[129],"processes":[130],"may":[135],"associated":[137],"with":[138,228,239],"it.":[139],"Rather":[140],"than":[141],"searching":[142],"space":[144,154],"has":[147],"been":[148],"written,":[149],"searches":[152],"govern":[158],"phenomenon:":[160],"given":[161],"explanandum,":[163],"it":[164],"abstracts":[165],"instantiated":[168],"formation":[172],"process,":[173],"retrieves":[174],"relating":[177],"those":[178,207],"universals,":[179],"deductively":[181],"reconstructs":[182],"new,":[184],"testable":[185],"explanation.":[186],"Evaluated":[187],"data-science":[189],"modeling":[190],"judged":[192],"both":[194],"LLMs":[195],"experts,":[198],"hypotheses":[199,217],"generated":[200],"through":[201],"this":[202],"principled":[203],"reasoning":[204],"significantly":[205],"outperform":[206],"direct":[209],"prompting.":[210],"Crucially,":[211],"translated":[213],"two":[215],"highest-scoring":[216],"into":[218],"novel":[219],"algorithms":[220],"one":[221],"reduces":[223],"Transformer's":[225],"theoretical":[226],"complexity":[227],"only":[229],"minimal":[230],"performance":[231],"loss,":[232],"another":[234],"achieves":[236],"competitive":[237],"accuracy":[238],"substantially":[240],"fewer":[241],"parameters.":[242]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-10T00:00:00"}