{"id":"https://openalex.org/W7166694700","doi":"https://doi.org/10.48550/arxiv.2606.29799","title":"The CRISTAL Method: Neurosymbolic analysis from AI-synthesized world models","display_name":"The CRISTAL Method: Neurosymbolic analysis from AI-synthesized world models","publication_year":2026,"publication_date":"2026-06-29","ids":{"openalex":"https://openalex.org/W7166694700","doi":"https://doi.org/10.48550/arxiv.2606.29799"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.29799","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29799","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,"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.2606.29799","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113712335","display_name":"R. Kaufmann","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaufmann, Rafael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052346863","display_name":"Felix Neub\u00fcrger","orcid":"https://orcid.org/0000-0002-8983-6466"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Neub\u00fcrger, Felix","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121374400","display_name":"Michael Walters","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Walters, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139671633","display_name":"Thomas Kopinski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kopinski, Thomas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076881344","display_name":"Dimitrije Markovi\u0107","orcid":"https://orcid.org/0000-0002-4185-696X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Markovi\u0107, Dimitrije","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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.4542999863624573,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.4542999863624573,"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":0.04149999842047691,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.03669999912381172,"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/benchmark","display_name":"Benchmark (surveying)","score":0.5989000201225281},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5925999879837036},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5407000184059143},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.46639999747276306},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4097999930381775},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4074000120162964},{"id":"https://openalex.org/keywords/investment","display_name":"Investment (military)","score":0.3662000000476837}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6197999715805054},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5989000201225281},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5925999879837036},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5407000184059143},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.46639999747276306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46239998936653137},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4097999930381775},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4074000120162964},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40450000762939453},{"id":"https://openalex.org/C27548731","wikidata":"https://www.wikidata.org/wiki/Q88272","display_name":"Investment (military)","level":3,"score":0.3662000000476837},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3513999879360199},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3052000105381012},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2921000123023987},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2858999967575073},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2854999899864197},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2718000113964081},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2572999894618988},{"id":"https://openalex.org/C512654426","wikidata":"https://www.wikidata.org/wiki/Q19652","display_name":"Public domain","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.29799","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29799","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,"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.2606.29799","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29799","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,"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":{"This":[0,31],"project":[1],"introduces":[2],"the":[3,47],"CRISTAL":[4,101,125,144,161,180],"Method":[5],"(Coherent":[6],"Reliable":[7],"Intentional":[8],"Synthesis":[9],"of":[10,88,92,109,166],"Truthful":[11],"Analysis":[12],"Logic),":[13],"a":[14,27,106,120,127,163,176,189],"neurosymbolic":[15],"framework":[16],"for":[17,49,154],"automating":[18],"complex":[19],"analysis":[20,25],"workflows,":[21],"with":[22,169,184,201],"fundamental":[23],"investment":[24],"as":[26,78],"primary":[28],"use":[29],"case.":[30],"domain":[32,59],"poses":[33],"major":[34],"challenges:":[35],"high":[36],"structural":[37],"uncertainty,":[38,89],"noisy":[39],"and":[40,46,64,90,115,140,157,172,188,206],"subjective":[41],"data,":[42],"tight":[43],"attention":[44],"budgets,":[45],"need":[48],"justified,":[50],"reproducible":[51],"decisions.":[52],"Human":[53],"analysts":[54],"often":[55],"struggle":[56],"in":[57,69,98],"this":[58,99],"due":[60],"to":[61],"cognitive":[62],"biases":[63],"limitations,":[65],"suggesting":[66],"significant":[67],"value":[68],"automation.":[70],"But":[71],"while":[72],"LLM-based":[73],"agents":[74],"have":[75],"been":[76],"proposed":[77],"analytical":[79],"aids,":[80],"their":[81,96],"limitations":[82],"--":[83,94],"poor":[84],"numerical":[85],"reasoning,":[86],"unawareness":[87],"lack":[91],"reproducibility":[93],"hinder":[95],"effectiveness":[97],"context.":[100],"addresses":[102],"these":[103],"gaps":[104],"through":[105],"principled":[107],"blend":[108],"statistical":[110],"model":[111,149],"synthesis,":[112],"continuous":[113],"learning,":[114],"active":[116],"learning.":[117,158],"Starting":[118],"from":[119],"natural-language":[121],"prior":[122],"knowledge":[123],"curriculum,":[124],"builds":[126],"dynamic,":[128],"interpretable":[129],"probabilistic":[130],"program":[131],"that":[132,195],"enables":[133],"full":[134],"Bayesian":[135],"inference,":[136],"including":[137],"uncertainty":[138],"quantification":[139],"budget-aware":[141],"data":[142,205],"acquisition.":[143],"continually":[145],"refines":[146],"its":[147],"world":[148],"during":[150],"analysis,":[151],"leveraging":[152],"LLMs":[153,194],"code":[155],"synthesis":[156],"We":[159],"validate":[160],"on":[162],"novel":[164],"benchmark":[165],"synthetic":[167],"equities":[168],"rich":[170],"financial":[171],"textual":[173],"data.":[174],"On":[175],"company":[177],"classification":[178],"task,":[179],"achieves":[181],"Bayes-optimal":[182],"accuracy":[183,199],"just":[185],"5":[186],"examples":[187],"5-second":[190],"budget,":[191],"outperforming":[192],"state-of-the-art":[193],"plateau":[196],"around":[197],"40\\%":[198],"even":[200],"order-of-magnitude":[202],"more":[203],"input":[204],"compute.":[207]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-01T00:00:00"}