{"id":"https://openalex.org/W7159675822","doi":"https://doi.org/10.48550/arxiv.2604.27551","title":"Beyond the Training Distribution: Mapping Generalization Boundaries in Neural Program Synthesis","display_name":"Beyond the Training Distribution: Mapping Generalization Boundaries in Neural Program Synthesis","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W7159675822","doi":"https://doi.org/10.48550/arxiv.2604.27551"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.27551","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27551","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.27551","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083133119","display_name":"Henrik Voigt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Voigt, Henrik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134975628","display_name":"Michael Habeck","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Habeck, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027313464","display_name":"Joachim Giesen","orcid":"https://orcid.org/0000-0001-6598-6833"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giesen, Joachim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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/T10260","display_name":"Software Engineering Research","score":0.3301999866962433,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.3301999866962433,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.13650000095367432,"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/T10028","display_name":"Topic Modeling","score":0.08760000020265579,"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/generalization","display_name":"Generalization","score":0.7878999710083008},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5314000248908997},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43860000371932983},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4203000068664551},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.3682999908924103},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.3564000129699707},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.33739998936653137}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7878999710083008},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6694999933242798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5655999779701233},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5314000248908997},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43860000371932983},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42989999055862427},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C2776937632","wikidata":"https://www.wikidata.org/wiki/Q4117718","display_name":"Program synthesis","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2842999994754791},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2694999873638153},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2590000033378601},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.27551","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27551","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":"doi:10.48550/arxiv.2604.27551","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27551","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":false,"raw_source_name":null,"raw_type":"article"},"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":{"Large-scale":[0],"transformers":[1,114],"achieve":[2],"impressive":[3],"results":[4],"on":[5,45],"program":[6,41],"synthesis":[7,42],"benchmarks,":[8],"yet":[9],"their":[10],"true":[11],"generalization":[12,92,111,151],"capabilities":[13],"remain":[14],"obscured":[15],"by":[16],"data":[17,73],"contamination":[18],"and":[19,53,63,75,78,100,159],"opaque":[20],"training":[21,154],"corpora.":[22],"To":[23],"rigorously":[24],"assess":[25],"whether":[26],"models":[27],"are":[28],"truly":[29],"generalizing":[30],"or":[31],"merely":[32],"retrieving":[33],"memorized":[34],"templates,":[35],"we":[36,59],"introduce":[37],"a":[38,46,120,143],"strictly":[39,144],"controlled":[40],"environment":[43],"based":[44],"domain-specific":[47],"arithmetic":[48],"grammar.":[49],"By":[50],"systematically":[51],"enumerating":[52],"evaluating":[54,109],"millions":[55],"of":[56,123],"unique":[57],"programs,":[58],"construct":[60],"interpretable":[61],"syntactic":[62,101],"semantic":[64,99],"metric":[65],"spaces.":[66],"This":[67],"allows":[68],"us":[69],"to":[70,128,169],"precisely":[71],"map":[72],"distributions":[74],"sample":[76],"train":[77],"test":[79],"splits":[80],"that":[81,89,113,149],"isolate":[82],"specific":[83],"distributional":[84],"shifts.":[85],"Our":[86],"experiments":[87],"demonstrate":[88],"optimizing":[90],"density":[91],"--":[93,103],"through":[94,171],"diverse":[95],"sampling":[96],"over":[97,124],"both":[98],"spaces":[102],"induces":[104],"robust":[105,150],"out-of-distribution":[106],"generalization.":[107],"Conversely,":[108],"support":[110],"reveals":[112],"severely":[115],"struggle":[116],"with":[117],"extrapolation,":[118],"experiencing":[119],"performance":[121],"drop":[122],"30%":[125],"when":[126],"forced":[127],"generate":[129],"syntactically":[130],"novel":[131,166],"programs.":[132],"While":[133],"steadily":[134],"scaling":[135,174],"up":[136],"compute":[137],"improves":[138],"generalization,":[139],"the":[140,163],"gains":[141],"follow":[142],"log-linear":[145,173],"relationship.":[146],"We":[147],"conclude":[148],"requires":[152],"maximizing":[153],"diversity":[155],"across":[156],"multiple":[157],"manifolds,":[158],"our":[160],"findings":[161],"indicate":[162],"necessity":[164],"for":[165],"search-based":[167],"approaches":[168],"break":[170],"current":[172],"bottlenecks.":[175]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-02T00:00:00"}