{"id":"https://openalex.org/W7156742115","doi":"https://doi.org/10.48550/arxiv.2604.23054","title":"DeepImagine: Learning Biomedical Reasoning via Successive Counterfactual Imagining","display_name":"DeepImagine: Learning Biomedical Reasoning via Successive Counterfactual Imagining","publication_year":2026,"publication_date":"2026-04-24","ids":{"openalex":"https://openalex.org/W7156742115","doi":"https://doi.org/10.48550/arxiv.2604.23054"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.23054","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23054","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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.23054","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113777869","display_name":"Youze Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Youze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108766872","display_name":"Jianyou Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jianyou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134774209","display_name":"Yuhan Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yuhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039245824","display_name":"Matthew I. Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Matthew","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113322806","display_name":"Longtian Bao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bao, Longtian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015356599","display_name":"Hanyuan Zhang","orcid":"https://orcid.org/0000-0002-1527-9468"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hanyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074883525","display_name":"Maxim KHAN","orcid":"https://orcid.org/0000-0002-9251-1419"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khan, Maxim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134162837","display_name":"Aditya K. Sehgal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sehgal, Aditya K.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134206565","display_name":"Christopher D. Rosin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rosin, Christopher D.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042889556","display_name":"Umber Dube","orcid":"https://orcid.org/0000-0001-9324-1927"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dube, Umber","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111512545","display_name":"Ramamohan Paturi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paturi, Ramamohan","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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.36230000853538513,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.36230000853538513,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.2054000049829483,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.1136000007390976,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.9822999835014343},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.7107999920845032},{"id":"https://openalex.org/keywords/counterfactual-conditional","display_name":"Counterfactual conditional","score":0.6220999956130981},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49900001287460327},{"id":"https://openalex.org/keywords/clinical-trial","display_name":"Clinical trial","score":0.4027000069618225},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.38580000400543213},{"id":"https://openalex.org/keywords/causal-reasoning","display_name":"Causal reasoning","score":0.3720000088214874},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.33340001106262207}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.9822999835014343},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.7107999920845032},{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.6220999956130981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5394999980926514},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49900001287460327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4867999851703644},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4767000079154968},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.46299999952316284},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.43479999899864197},{"id":"https://openalex.org/C535046627","wikidata":"https://www.wikidata.org/wiki/Q30612","display_name":"Clinical trial","level":2,"score":0.4027000069618225},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.3720000088214874},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C72563966","wikidata":"https://www.wikidata.org/wiki/Q1303415","display_name":"Cohort","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C79897977","wikidata":"https://www.wikidata.org/wiki/Q5054568","display_name":"Causal chain","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.2630000114440918},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2596000134944916}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.23054","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23054","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.23054","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23054","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":"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Predicting":[0],"the":[1,136,229],"outcomes":[2],"of":[3,67,84],"prospective":[4],"clinical":[5,68,113,203],"trials":[6,69,114],"remains":[7],"a":[8,47,243],"major":[9],"challenge":[10],"for":[11,49,183],"large":[12],"language":[13,192,217,253],"models.":[14,254],"Prior":[15],"work":[16],"has":[17],"shown":[18],"that":[19,178,211,228],"both":[20,105],"traditional":[21,220],"correlational":[22,221],"predictors,":[23],"such":[24,87,126],"as":[25,88,127],"random":[26],"forests":[27],"and":[28,31,95,107,199,219,249],"logistic":[29],"regression,":[30],"strong":[32],"commercial":[33],"LLMs":[34,51],"achieve":[35],"limited":[36],"performance":[37],"on":[38,166,202],"this":[39,42,101,188],"task.":[40],"In":[41],"paper,":[43],"we":[44,103,139,156,190,224],"propose":[45],"DeepImagine,":[46],"framework":[48],"teaching":[50],"biomedical":[52,252],"reasoning":[53,176,231],"through":[54],"successive":[55],"counterfactual":[56,109,122,151,185],"imagining.":[57],"The":[58],"central":[59],"idea":[60],"is":[61,124],"to":[62,73,209,226],"approximate":[63,108,150],"hidden":[64],"causal":[65],"mechanisms":[66],"by":[70],"training":[71,173],"models":[72,141,158,193,218,238],"infer":[74],"how":[75,237],"observed":[76],"trial":[77,97,204],"results":[78],"would":[79],"change":[80],"under":[81,194],"controlled":[82],"perturbations":[83],"experimental":[85],"conditions,":[86],"dosage,":[89],"outcome":[90,129,205],"measures,":[91],"study":[92,133],"arms,":[93],"geography,":[94],"other":[96],"attributes.":[98],"To":[99],"support":[100],"objective,":[102],"construct":[104],"natural":[106],"pairs":[110,152],"from":[111],"real":[112],"with":[115,142,159,174],"reported":[116],"outcomes.":[117],"For":[118,145],"settings":[119,147],"where":[120,148],"strict":[121],"supervision":[123],"available,":[125],"paired":[128],"measures":[130],"or":[131],"dose-ranging":[132],"arms":[134],"within":[135],"same":[137],"trial,":[138],"train":[140,191],"supervised":[143],"fine-tuning.":[144],"broader":[146],"only":[149],"can":[153],"be":[154],"retrieved,":[155],"optimize":[157],"reinforcement":[160],"learning":[161],"using":[162],"verifiable":[163],"rewards":[164],"based":[165],"downstream":[167],"benchmark":[168],"correctness.":[169],"We":[170,207],"further":[171],"augment":[172],"synthetic":[175],"traces":[177],"provide":[179,233],"causally":[180],"plausible":[181],"explanations":[182],"local":[184],"transitions.":[186],"Using":[187],"pipeline,":[189],"10B":[195],"parameters,":[196],"including":[197],"Qwen3.5-9B,":[198],"evaluate":[200],"them":[201],"prediction.":[206],"aim":[208,225],"show":[210,227],"DeepImagine":[212],"consistently":[213],"improves":[214],"over":[215],"untuned":[216],"baselines.":[222],"Finally,":[223],"learned":[230],"trajectories":[232],"interpretable":[234],"signals":[235],"about":[236],"represent":[239],"trial-level":[240],"mechanisms,":[241],"suggesting":[242],"practical":[244],"path":[245],"toward":[246],"more":[247],"mechanistic":[248],"scientifically":[250],"useful":[251]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-29T00:00:00"}