{"id":"https://openalex.org/W7203761945","doi":"https://doi.org/10.48550/arxiv.2608.17270","title":"Do LLMs Know a Good Hypothesis When They See One? Logit-Based Energy Scoring Outperforms Prompted LLM-as-Judge for Scientific Hypothesis Ranking","display_name":"Do LLMs Know a Good Hypothesis When They See One? Logit-Based Energy Scoring Outperforms Prompted LLM-as-Judge for Scientific Hypothesis Ranking","publication_year":2026,"publication_date":"2026-08-18","ids":{"openalex":"https://openalex.org/W7203761945","doi":"https://doi.org/10.48550/arxiv.2608.17270"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.17270","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17270","pdf_url":"https://arxiv.org/pdf/2608.17270","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.17270","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010369927","display_name":"Swati Rajwal","orcid":"https://orcid.org/0000-0002-3826-5069","observed_orcids":["https://orcid.org/0000-0002-3826-5069"]},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajwal, Swati","raw_affiliation_strings":["Oak Ridge National Laboratory , {rajwals , dass3 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory , {rajwals , dass3 ,","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147516308","display_name":"Sanjay Das","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Das, Sanjay","raw_affiliation_strings":["Oak Ridge National Laboratory , {rajwals , dass3 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory , {rajwals , dass3 ,","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123509080","display_name":"Tirthankar Ghosal","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ghosal, Tirthankar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8314999938011169,"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":0.8314999938011169,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.07859999686479568,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.01209999993443489,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hypothesis-ranking","display_name":"hypothesis ranking","score":0.9340000152587891},{"id":"https://openalex.org/keywords/llm-as-a-judge","display_name":"LLM-as-a-judge","score":0.7689999938011169},{"id":"https://openalex.org/keywords/hypothesis-generation","display_name":"hypothesis generation","score":0.7649999856948853},{"id":"https://openalex.org/keywords/trustworthy-ai","display_name":"trustworthy AI","score":0.6169999837875366},{"id":"https://openalex.org/keywords/scientific-discovery","display_name":"scientific discovery","score":0.47999998927116394}],"concepts":[{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.6834999918937683},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6439999938011169},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.46869999170303345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43459999561309814},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3707999885082245},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3628999888896942},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C124056412","wikidata":"https://www.wikidata.org/wiki/Q3320364","display_name":"Scientific evidence","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.28690001368522644},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2694000005722046}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.17270","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17270","pdf_url":"https://arxiv.org/pdf/2608.17270","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.17270","doi":"https://doi.org/10.48550/arxiv.2608.17270","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.17270","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:2608.17270","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17270","pdf_url":"https://arxiv.org/pdf/2608.17270","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1019100964","display_name":null,"funder_award_id":"AC0500OR22725","funder_id":"https://openalex.org/F4320337480","funder_display_name":"Basic Energy Sciences"},{"id":"https://openalex.org/G1026679911","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"},{"id":"https://openalex.org/G121915436","display_name":null,"funder_award_id":"DEAC05- 00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G166562317","display_name":null,"funder_award_id":"DE-AC05- 00OR22725","funder_id":"https://openalex.org/F4320306250","funder_display_name":"Battelle"},{"id":"https://openalex.org/G203625172","display_name":null,"funder_award_id":"DE--AC05--00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2757267231","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306250","funder_display_name":"Battelle"},{"id":"https://openalex.org/G2988778103","display_name":null,"funder_award_id":"DE-AC05?","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G313676650","display_name":null,"funder_award_id":"DEAC05-00OR22725","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"},{"id":"https://openalex.org/G4370606643","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"},{"id":"https://openalex.org/G4423657506","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G5726405315","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306250","funder_display_name":"Battelle"},{"id":"https://openalex.org/G675320460","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G807938293","display_name":null,"funder_award_id":"DEAC05-00OR22725","funder_id":"https://openalex.org/F4320337480","funder_display_name":"Basic Energy Sciences"},{"id":"https://openalex.org/G8269158468","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8943143067","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320306250","display_name":"Battelle","ror":"https://ror.org/01h5tnr73"},{"id":"https://openalex.org/F4320316892","display_name":"UT-Battelle","ror":"https://ror.org/04nza6677"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337480","display_name":"Basic Energy Sciences","ror":"https://ror.org/05mg91w61"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203761945.pdf","grobid_xml":"https://content.openalex.org/works/W7203761945.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W4285429195","https://openalex.org/W4387561528","https://openalex.org/W4387724705","https://openalex.org/W4401306979","https://openalex.org/W4404341075","https://openalex.org/W4405354744","https://openalex.org/W4415062263","https://openalex.org/W4416043407","https://openalex.org/W7075994024","https://openalex.org/W7119523234","https://openalex.org/W7129024206","https://openalex.org/W7140287209","https://openalex.org/W7167604932"],"related_works":["https://openalex.org/W4414359578","https://openalex.org/W7162110049","https://openalex.org/W6979310735","https://openalex.org/W4415718479","https://openalex.org/W4416540539","https://openalex.org/W4416527493","https://openalex.org/W4388650906","https://openalex.org/W4415062263","https://openalex.org/W7162751963","https://openalex.org/W4416095466"],"abstract_inverted_index":{"Large":[0],"language":[1,55,66],"models":[2,67],"(LLMs)":[3],"are":[4],"increasingly":[5],"used":[6],"for":[7,18,97,131,144],"scientific":[8,21,132,147],"hypothesis":[9,80,133],"generation.":[10],"However,":[11],"evaluating":[12],"generated":[13],"hypotheses":[14,52],"remains":[15],"a":[16,45,54,104],"challenge":[17],"trustworthy":[19,145],"AI-enabled":[20,146],"workflows.":[22],"Existing":[23],"approaches":[24],"often":[25],"use":[26],"LLMs":[27],"as":[28],"judges":[29],"or":[30],"rely":[31],"on":[32,68,141],"semantic":[33],"similarity,":[34],"which":[35],"can":[36],"favor":[37],"familiar":[38],"ideas":[39],"over":[40],"novel":[41],"ones.":[42],"We":[43,63],"propose":[44],"logit-based":[46,108],"energy":[47,109],"scoring":[48,86],"method":[49],"that":[50],"evaluates":[51],"using":[53,107],"model's":[56],"intrinsic":[57,126],"confidence":[58,128],"rather":[59],"than":[60],"comparative":[61],"judgment.":[62],"benchmarked":[64],"seven":[65],"1,323":[69],"papers":[70],"across":[71,91,118],"12":[72],"disciplines.":[73],"Each":[74],"paper":[75],"was":[76,115],"paired":[77],"with":[78,95],"its":[79],"and":[81],"fifteen":[82],"incorrect":[83],"alternatives.":[84],"Intrinsic":[85],"reached":[87,111],"33.0%":[88],"Hit@1":[89],"pooled":[90],"both":[92],"scorers,":[93],"compared":[94],"16.6%":[96],"prompted":[98],"listwise":[99],"ranking.":[100],"The":[101],"strongest":[102],"configuration,":[103],"1-billion-parameter":[105],"model":[106,127],"scoring,":[110],"53.1%,":[112],"though":[113],"this":[114],"the":[116],"maximum":[117],"14":[119],"model-by-scorer":[120],"combinations":[121],"selected":[122],"post":[123],"hoc.":[124],"Overall,":[125],"shows":[129],"potential":[130],"evaluation.":[134],"This":[135],"study":[136],"also":[137],"motivates":[138],"future":[139],"research":[140],"confidence-based":[142],"methods":[143],"discovery.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-20T00:00:00"}