{"id":"https://openalex.org/W7220974622","doi":"https://doi.org/10.48550/arxiv.2610.07620","title":"Explore, Then Commit: Measurement-Efficient Scientific Law Discovery with Language Models","display_name":"Explore, Then Commit: Measurement-Efficient Scientific Law Discovery with Language Models","publication_year":2026,"publication_date":"2026-10-06","ids":{"openalex":"https://openalex.org/W7220974622","doi":"https://doi.org/10.48550/arxiv.2610.07620"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.07620","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.07620","pdf_url":"https://arxiv.org/pdf/2610.07620","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.07620","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157739618","display_name":"Kautik Mandve","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mandve, Kautik","raw_affiliation_strings":["Vernon Hills High School , Vernon Hills , Illinois , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vernon Hills High School , Vernon Hills , Illinois , USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085167601","display_name":"Dileepa Fernando","orcid":"https://orcid.org/0009-0007-5126-3205","observed_orcids":["https://orcid.org/0009-0007-5126-3205"]},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Fernando, Dileepa","raw_affiliation_strings":["Information Systems Technology and Design Singapore University of Technology and Design , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Systems Technology and Design Singapore University of Technology and Design , Singapore","institution_ids":["https://openalex.org/I152815399"]}]}],"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":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/T13904","display_name":"Artificial Intelligence Applications","score":0.17180000245571136,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.17180000245571136,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.14970000088214874,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.10559999942779541,"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/measurement-efficiency","display_name":"measurement efficiency","score":0.640999972820282},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8679999709129333},{"id":"https://openalex.org/keywords/physics-problem-solving","display_name":"physics problem solving","score":0.5350000262260437},{"id":"https://openalex.org/keywords/hypothesis-generation","display_name":"hypothesis generation","score":0.49900001287460327},{"id":"https://openalex.org/keywords/measurement-selection","display_name":"measurement selection","score":0.41600000858306885}],"concepts":[{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.7138000130653381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6194000244140625},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5562999844551086},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.5302000045776367},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.48240000009536743},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.47279998660087585},{"id":"https://openalex.org/C122783720","wikidata":"https://www.wikidata.org/wiki/Q183065","display_name":"Interpreter","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3734999895095825},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35019999742507935},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32760000228881836},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3116999864578247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2849000096321106},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.27059999108314514},{"id":"https://openalex.org/C101454708","wikidata":"https://www.wikidata.org/wiki/Q17106019","display_name":"Standard Model (mathematical formulation)","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C163985040","wikidata":"https://www.wikidata.org/wiki/Q1172399","display_name":"Data acquisition","level":2,"score":0.25999999046325684}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.07620","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.07620","pdf_url":"https://arxiv.org/pdf/2610.07620","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.2610.07620","doi":"https://doi.org/10.48550/arxiv.2610.07620","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.07620","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.07620","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.07620","pdf_url":"https://arxiv.org/pdf/2610.07620","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220974622.pdf","grobid_xml":"https://content.openalex.org/works/W7220974622.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7206173079","https://openalex.org/W4415318097","https://openalex.org/W7140236766","https://openalex.org/W7162751963","https://openalex.org/W7151997388","https://openalex.org/W7162409218","https://openalex.org/W7214806857","https://openalex.org/W7203676309","https://openalex.org/W2090624226","https://openalex.org/W7160891660"],"abstract_inverted_index":{"Scientific":[0],"law":[1,38],"discovery":[2],"requires":[3],"selecting":[4],"measurements":[5,85],"and":[6,31,53,71,90,107,118,133,174],"converting":[7],"evidence":[8],"into":[9],"a":[10,20,26,32,72,122,165],"governing":[11],"equation.":[12],"We":[13],"evaluate":[14],"an":[15],"explore-then-commit":[16],"protocol":[17,43,163],"in":[18,121,144],"which":[19],"large":[21],"language":[22],"model":[23],"proposes":[24],"hypotheses,":[25],"programmatic":[27],"planner":[28],"gathers":[29],"measurements,":[30],"fresh":[33],"prompt":[34],"synthesizes":[35],"the":[36,161],"final":[37],"from":[39,103,108],"fixed":[40],"observations.":[41],"The":[42],"combines":[44],"structured":[45],"probes,":[46],"automatic":[47],"numerical":[48],"diagnostics,":[49],"restricted":[50],"measurement":[51],"batches,":[52],"optional":[54],"interpreter":[55],"access.":[56],"Across":[57],"576":[58],"NewtonBench":[59],"trials,":[60],"we":[61],"compare":[62],"eight":[63],"configurations":[64],"on":[65],"12":[66],"physics":[67],"modules":[68],"using":[69],"GPT-4.1-mini":[70,89],"medium-difficulty":[73],"GPT-4.1":[74],"replication.":[75],"On":[76],"medium":[77],"tasks,":[78],"interpreter-enabled":[79],"planners":[80],"use":[81],"8.6":[82],"versus":[83,92],"22.5":[84],"per":[86],"trial":[87],"for":[88,94],"8.9":[91],"43.0":[93],"GPT-4.1.":[95],"Their":[96],"mean":[97],"magnitude-based":[98],"root-mean-squared":[99],"logarithmic":[100],"error":[101],"falls":[102],"2.514":[104],"to":[105,110,155],"0.202":[106],"0.626":[109],"0.149,":[111],"respectively.":[112],"An":[113],"additional":[114],"audit":[115],"retains":[116],"incomplete":[117],"invalid":[119],"submissions":[120],"coverage-sensitive":[123],"analysis.":[124],"Observed":[125],"symbolic-accuracy":[126],"gains":[127],"are":[128],"less":[129],"consistent":[130],"across":[131],"modules,":[132],"random":[134],"acquisition":[135,156],"is":[136],"competitive":[137],"with":[138],"disagreement":[139],"scoring.":[140],"Measurement":[141],"savings":[142],"occur":[143],"every":[145],"module,":[146],"but":[147],"unequal":[148],"batch":[149],"constraints":[150],"prevent":[151],"attributing":[152],"them":[153],"solely":[154],"quality.":[157],"These":[158],"results":[159],"support":[160],"complete":[162],"as":[164],"promising":[166],"measurement-efficient":[167],"configuration,":[168],"while":[169],"leaving":[170],"its":[171],"causal":[172],"components":[173],"generalization":[175],"beyond":[176],"noiseless":[177],"direct-equation":[178],"tasks":[179],"unresolved.":[180]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-10-09T00:00:00"}