{"id":"https://openalex.org/W7213488928","doi":"https://doi.org/10.33774/coe-2026-h71gw","title":"Detecting Spurious Periodic Generalization in Neural Networks PGVP","display_name":"Detecting Spurious Periodic Generalization in Neural Networks PGVP","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7213488928","doi":"https://doi.org/10.33774/coe-2026-h71gw"},"language":"en","primary_location":{"id":"doi:10.33774/coe-2026-h71gw","doi":"https://doi.org/10.33774/coe-2026-h71gw","is_oa":true,"landing_page_url":"https://doi.org/10.33774/coe-2026-h71gw","pdf_url":"https://www.cambridge.org/engage/api-gateway/coe/assets/orp/resource/item/6aa3a9b34770e67d9290895c/original/detecting-spurious-periodic-generalization-in-neural-networks-pgvp.pdf","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.cambridge.org/engage/api-gateway/coe/assets/orp/resource/item/6aa3a9b34770e67d9290895c/original/detecting-spurious-periodic-generalization-in-neural-networks-pgvp.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5151940361","display_name":"Mohamed Samir","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mohamed Samir","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0001-2930-3609","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5151940361"],"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5835000276565552,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5835000276565552,"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/T10320","display_name":"Neural Networks and Applications","score":0.14309999346733093,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.10700000077486038,"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/out-of-distribution-generalization","display_name":"out-of-distribution generalization","score":0.7639999985694885},{"id":"https://openalex.org/keywords/distribution-shift","display_name":"distribution shift","score":0.6980000138282776},{"id":"https://openalex.org/keywords/generalization-gap","display_name":"generalization gap","score":0.5899999737739563},{"id":"https://openalex.org/keywords/model-validation","display_name":"model validation","score":0.6669999957084656},{"id":"https://openalex.org/keywords/time-series-forecasting","display_name":"time series forecasting","score":0.8019999861717224},{"id":"https://openalex.org/keywords/physics-informed-machine-learning","display_name":"physics-informed machine learning","score":0.7889999747276306}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8385999798774719},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.7918999791145325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6157000064849854},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5917999744415283},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5827999711036682},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5421000123023987},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.4864000082015991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4715999960899353},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40540000796318054},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39649999141693115},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C98644592","wikidata":"https://www.wikidata.org/wiki/Q184743","display_name":"Periodic function","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2976999878883362},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.2797999978065491},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2754000127315521},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.271699994802475}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.33774/coe-2026-h71gw","doi":"https://doi.org/10.33774/coe-2026-h71gw","is_oa":true,"landing_page_url":"https://doi.org/10.33774/coe-2026-h71gw","pdf_url":"https://www.cambridge.org/engage/api-gateway/coe/assets/orp/resource/item/6aa3a9b34770e67d9290895c/original/detecting-spurious-periodic-generalization-in-neural-networks-pgvp.pdf","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"pmh:oai:philpapers.org/rec/SAMDSP","doi":null,"is_oa":true,"landing_page_url":"https://philpapers.org/rec/SAMDSP","pdf_url":"https://philpapers.org/archive/SAMDSP.pdf","source":{"id":"https://openalex.org/S4306402130","display_name":"PhilPapers (PhilPapers Foundation)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"info:eu-repo/semantics/article"},{"id":"pmh:oai:philarchive.org/rec/SAMDSP","doi":null,"is_oa":false,"landing_page_url":"https://philarchive.org/rec/SAMDSP","pdf_url":null,"source":{"id":"https://openalex.org/S4306402130","display_name":"PhilPapers (PhilPapers Foundation)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"info:eu-repo/semantics/article"},{"id":"doi:10.5281/zenodo.18576470","doi":"https://doi.org/10.5281/zenodo.18576470","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18576470","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.18576471","doi":"https://doi.org/10.5281/zenodo.18576471","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18576471","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"doi:10.33774/coe-2026-h71gw","doi":"https://doi.org/10.33774/coe-2026-h71gw","is_oa":true,"landing_page_url":"https://doi.org/10.33774/coe-2026-h71gw","pdf_url":"https://www.cambridge.org/engage/api-gateway/coe/assets/orp/resource/item/6aa3a9b34770e67d9290895c/original/detecting-spurious-periodic-generalization-in-neural-networks-pgvp.pdf","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213488928.pdf","grobid_xml":"https://content.openalex.org/works/W7213488928.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4318605493","https://openalex.org/W3211352252","https://openalex.org/W4403884198","https://openalex.org/W4408520247","https://openalex.org/W7160829828","https://openalex.org/W3204351398","https://openalex.org/W3157096341","https://openalex.org/W4379540121","https://openalex.org/W3205792141","https://openalex.org/W3183790451"],"abstract_inverted_index":{"Modern":[0],"neural":[1],"networks":[2],"often":[3],"achieve":[4],"near-perfect":[5,102],"performance":[6],"within":[7],"the":[8,37,44,77,162,179],"training":[9],"distribution":[10],"while":[11,105],"failing":[12],"catastrophically":[13],"under":[14,69],"structured":[15],"distributional":[16],"shifts.":[17],"This":[18,41],"failure":[19,100],"mode":[20],"is":[21,127],"especially":[22],"prevalent":[23],"in":[24,133,149],"periodic":[25,58,71,98,109],"and":[26,75,143,154,184],"cyclic":[27,140],"learning":[28,36],"tasks,":[29],"where":[30],"models":[31,68,106],"may":[32],"interpolate":[33],"locally":[34],"without":[35],"underlying":[38],"generative":[39],"structure.":[40],"work":[42,151,177],"introduces":[43],"Periodic":[45,79],"Generalization":[46,80],"Verification":[47],"Protocol":[48],"(PGVP),":[49],"a":[50,117],"model-agnostic":[51],"diagnostic":[52],"framework":[53,173],"designed":[54],"to":[55,156,190],"distinguish":[56],"true":[57],"generalization":[59],"from":[60],"spurious":[61],"in-domain":[62,103],"curve":[63],"fitting.":[64],"PGVP":[65,126,163,172],"evaluates":[66],"trained":[67],"controlled":[70,87],"out-of-distribution":[72],"(OOD)":[73],"shifts":[74],"quantifies":[76],"resulting":[78],"Gap":[81],"using":[82],"standard":[83,92,123],"regression":[84],"metrics.":[85],"Through":[86],"evaluations,":[88],"we":[89],"show":[90],"that":[91,121],"multilayer":[93],"perceptrons":[94],"frequently":[95],"exhibit":[96],"catastrophic":[97],"OOD":[99],"despite":[101],"accuracy,":[104],"with":[107],"explicit":[108],"inductive":[110],"bias":[111],"generalize":[112],"reliably.":[113],"The":[114,171],"protocol":[115,164],"provides":[116],"structural":[118],"validation":[119,132],"layer":[120],"complements":[122],"train/validation":[124],"pipelines.":[125],"intended":[128,155],"for":[129],"pre-deployment":[130],"model":[131],"applications":[134],"involving":[135],"time-series":[136],"forecasting,":[137],"signal":[138],"processing,":[139],"feature":[141],"modeling,":[142],"physics-informed":[144],"learning.":[145],"Note:":[146],"Figures":[147],"included":[148],"this":[150],"are":[152,187],"illustrative":[153],"visualize":[157],"typical":[158],"behaviors":[159],"targeted":[160],"by":[161,178],"rather":[165],"than":[166],"report":[167],"specific":[168],"experimental":[169],"runs.":[170],"constitutes":[174],"original":[175],"intellectual":[176],"author.":[180],"Specific":[181],"decision":[182],"thresholds":[183],"implementation":[185],"details":[186],"intentionally":[188],"omitted":[189],"preserve":[191],"proprietary":[192],"methodology.":[193]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-09-17T00:00:00"}