{"id":"https://openalex.org/W7160992965","doi":"https://doi.org/10.48550/arxiv.2605.11570","title":"OUI as a Structural Observable: Towards an Activation-Centric View of Neural Network Training","display_name":"OUI as a Structural Observable: Towards an Activation-Centric View of Neural Network Training","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W7160992965","doi":"https://doi.org/10.48550/arxiv.2605.11570"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.11570","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11570","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":"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.2605.11570","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136070984","display_name":"Alberto Fern\u00e1ndez-Hern\u00e1ndez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fern\u00e1ndez-Hern\u00e1ndez, Alberto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007319120","display_name":"Jose I. Mestre","orcid":"https://orcid.org/0000-0001-5954-4131"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mestre, Jose I.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124332705","display_name":"Cristian P\u00e9rez-Corral","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P\u00e9rez-Corral, Cristian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136079064","display_name":"Manuel F. Dolz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dolz, Manuel F.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040384183","display_name":"J. Duato","orcid":"https://orcid.org/0000-0002-7785-0607"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duato, Jose","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136041099","display_name":"Enrique S. Quintana-Ort\u00ed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quintana-Ort\u00ed, Enrique S.","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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2957000136375427,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2957000136375427,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.11079999804496765,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.10779999941587448,"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/training","display_name":"Training (meteorology)","score":0.5730000138282776},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48559999465942383},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.31769999861717224},{"id":"https://openalex.org/keywords/network-model","display_name":"Network model","score":0.3109000027179718},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3093000054359436},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.30250000953674316},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.29809999465942383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6660000085830688},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5730000138282776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.499099999666214},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48559999465942383},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.38029998540878296},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28839999437332153},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2879999876022339},{"id":"https://openalex.org/C28427503","wikidata":"https://www.wikidata.org/wiki/Q13580300","display_name":"Internal model","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.2766000032424927},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C2988224531","wikidata":"https://www.wikidata.org/wiki/Q20830730","display_name":"Network structure","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C2778491795","wikidata":"https://www.wikidata.org/wiki/Q25109883","display_name":"Structural approach","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.11570","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11570","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":"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.2605.11570","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11570","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":"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":[{"score":0.4288412034511566,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Activation":[0],"functions":[1],"are":[2],"what":[3],"make":[4],"deep":[5],"networks":[6],"expressive:":[7],"without":[8],"them,":[9],"the":[10,24,34,39,50],"model":[11],"collapses":[12],"to":[13,133],"a":[14,58,82,86,141],"linear":[15],"map.":[16],"Yet":[17],"we":[18,47],"still":[19],"evaluate":[20],"training":[21,90,149],"mostly":[22],"from":[23],"outside,":[25],"through":[26],"loss,":[27],"accuracy,":[28],"return,":[29],"or":[30,88],"final":[31],"calibration,":[32],"while":[33],"internal":[35,64],"structural":[36],"evolution":[37],"of":[38,62,148],"network":[40,83],"remains":[41],"largely":[42],"unobserved.":[43],"In":[44,94],"this":[45,158],"paper,":[46],"argue":[48],"that":[49,63,79,129],"Overfitting--Underfitting":[51],"Indicator":[52],"(OUI)":[53],"should":[54],"be":[55],"understood":[56],"as":[57,73],"first":[59],"practical":[60],"observable":[61],"structure.":[65],"Across":[66],"our":[67],"recent":[68,127],"results,":[69],"OUI":[70,151],"consistently":[71],"appears":[72],"an":[74,145,154],"early,":[75],"label-free,":[76],"activation-based":[77],"signal":[78],"reveals":[80],"whether":[81],"is":[84,152],"entering":[85],"poor":[87],"promising":[89],"regime":[91],"before":[92],"convergence.":[93],"supervised":[95],"learning,":[96,104],"it":[97,105,117],"anticipates":[98],"weight":[99,121],"decay":[100,122],"regimes;":[101],"in":[102,110,114],"reinforcement":[103],"discriminates":[106],"learning-rate":[107],"regimes":[108],"early":[109],"PPO":[111],"actor--critic;":[112],"and":[113],"online":[115],"control,":[116],"can":[118],"drive":[119],"layer-wise":[120],"adaptation.":[123],"Read":[124],"together":[125],"with":[126],"evidence":[128],"activation":[130],"patterns":[131],"tend":[132],"stabilize":[134],"earlier":[135],"than":[136],"parameters,":[137],"these":[138],"results":[139],"suggest":[140],"broader":[142],"research":[143],"direction:":[144],"activation-centric":[146],"theory":[147],"dynamics.":[150],"becoming":[153],"empirical":[155],"foothold":[156],"toward":[157],"theory.":[159]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-14T00:00:00"}