{"id":"https://openalex.org/W7134069490","doi":"https://doi.org/10.48550/arxiv.2603.04852","title":"On Multi-Step Theorem Prediction via Non-Parametric Structural Priors","display_name":"On Multi-Step Theorem Prediction via Non-Parametric Structural Priors","publication_year":2026,"publication_date":"2026-03-05","ids":{"openalex":"https://openalex.org/W7134069490","doi":"https://doi.org/10.48550/arxiv.2603.04852"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.04852","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128232829","display_name":"Junbo Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhao, Junbo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128254967","display_name":"Ting Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ting","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334042","display_name":"Can Li","orcid":"https://orcid.org/0000-0002-0039-2839"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Can","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128241513","display_name":"Wei He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128244344","display_name":"Jingdong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jingdong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128220443","display_name":"Hua Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Hua","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5128232829"],"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.24490000307559967,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.24490000307559967,"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":0.08860000222921371,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.07599999755620956,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/prior-probability","display_name":"Prior probability","score":0.7569000124931335},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5942000150680542},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5684999823570251},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4823000133037567},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4754999876022339},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.45249998569488525},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4429999887943268},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.41690000891685486},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4108000099658966}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7569000124931335},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5942000150680542},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5684999823570251},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5171999931335449},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4823000133037567},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4754999876022339},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.45249998569488525},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4447999894618988},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4429999887943268},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.41690000891685486},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4009999930858612},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36550000309944153},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33090001344680786},{"id":"https://openalex.org/C2776230367","wikidata":"https://www.wikidata.org/wiki/Q7314222","display_name":"Representation theorem","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.32339999079704285},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31610000133514404},{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.3125},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C80899671","wikidata":"https://www.wikidata.org/wiki/Q1304193","display_name":"Vertex (graph theory)","level":3,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.04852","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.04852","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.04852","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":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2603.04852","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-step":[0],"theorem":[1,25,33],"prediction":[2,34],"is":[3],"a":[4,44,123,169],"central":[5],"challenge":[6],"in":[7],"automated":[8],"reasoning.":[9,176],"Existing":[10],"neural-symbolic":[11],"approaches":[12],"rely":[13],"heavily":[14],"on":[15,141],"supervised":[16,159],"parametric":[17],"models,":[18],"which":[19,93],"exhibit":[20],"limited":[21],"generalization":[22],"to":[23,64,71,75,81,131],"evolving":[24],"libraries.":[26],"In":[27],"this":[28,69,86],"work,":[29],"we":[30,88],"explore":[31],"training-free":[32],"through":[35],"the":[36,55,72,112,142],"lens":[37],"of":[38,57],"in-context":[39],"learning":[40],"(ICL).":[41],"We":[42,67],"identify":[43],"critical":[45],"scalability":[46],"bottleneck,":[47],"termed":[48],"Structural":[49],"Drift:":[50],"as":[51,101,133],"reasoning":[52],"depth":[53],"increases,":[54],"performance":[56],"vanilla":[58],"ICL":[59,154],"degrades":[60],"sharply,":[61],"often":[62],"collapsing":[63],"near":[65],"zero.":[66],"attribute":[68],"failure":[70],"LLM's":[73],"inability":[74],"recover":[76],"latent":[77],"topological":[78,107],"dependencies,":[79],"leading":[80],"unstructured":[82],"exploration.":[83],"To":[84],"address":[85],"issue,":[87],"propose":[89],"Theorem":[90],"Precedence":[91],"Graphs,":[92],"encode":[94],"temporal":[95],"dependencies":[96],"from":[97],"historical":[98],"solution":[99],"traces":[100],"directed":[102],"graphs,":[103],"and":[104,122,156],"impose":[105],"explicit":[106,165],"constraints":[108],"that":[109,146,164],"effectively":[110],"prune":[111],"search":[113],"space":[114],"during":[115],"inference.":[116],"Coupled":[117],"with":[118],"retrieval-augmented":[119],"graph":[120],"construction":[121],"stepwise":[124],"symbolic":[125,175],"executor,":[126],"our":[127,147],"approach":[128],"enables":[129],"LLMs":[130],"act":[132],"structured":[134],"planners":[135],"without":[136],"any":[137],"gradient-based":[138],"optimization.":[139],"Experiments":[140],"FormalGeo7k":[143],"benchmark":[144],"show":[145],"method":[148],"achieves":[149],"89.29%":[150],"accuracy,":[151],"substantially":[152],"outperforming":[153],"baselines":[155],"matching":[157],"state-of-the-art":[158],"models.":[160],"These":[161],"results":[162],"indicate":[163],"structural":[166],"priors":[167],"offer":[168],"promising":[170],"direction":[171],"for":[172],"scaling":[173],"LLM-based":[174]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-03-07T00:00:00"}