{"id":"https://openalex.org/W7225824313","doi":"https://doi.org/10.5281/zenodo.24141713","title":"The conservation of inductive bias: every learner is a code, and generalization is its length","display_name":"The conservation of inductive bias: every learner is a code, and generalization is its length","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225824313","doi":"https://doi.org/10.5281/zenodo.24141713"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24141713","doi":"https://doi.org/10.5281/zenodo.24141713","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24141713","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":"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24141713","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139088093","display_name":"Luca Eliseo Pavesi","orcid":"https://orcid.org/0009-0003-0532-2850","observed_orcids":["https://orcid.org/0009-0003-0532-2850"]},"institutions":[{"id":"https://openalex.org/I25217355","display_name":"University of Pavia","ror":"https://ror.org/00s6t1f81","country_code":"IT","type":"education","lineage":["https://openalex.org/I25217355"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Pavesi, Luca Eliseo","raw_affiliation_strings":["University of Pavia"],"raw_orcid":"https://orcid.org/0009-0003-0532-2850","affiliations":[{"raw_affiliation_string":"University of Pavia","institution_ids":["https://openalex.org/I25217355"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5139088093"],"corresponding_institution_ids":["https://openalex.org/I25217355"],"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9570000171661377,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9570000171661377,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.010900000110268593,"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":0.00860000029206276,"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":[],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6072999835014343},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5623000264167786},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.503000020980835},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.49480000138282776},{"id":"https://openalex.org/C2780990831","wikidata":"https://www.wikidata.org/wiki/Q319141","display_name":"Conjecture","level":2,"score":0.4763000011444092},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.44190001487731934},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4302999973297119},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.426800012588501},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.40059998631477356},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39750000834465027},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36309999227523804},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3327000141143799},{"id":"https://openalex.org/C92393732","wikidata":"https://www.wikidata.org/wiki/Q1790374","display_name":"Learning theory","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.29589998722076416},{"id":"https://openalex.org/C9376300","wikidata":"https://www.wikidata.org/wiki/Q168817","display_name":"Algebraic number","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2775999903678894},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C50292564","wikidata":"https://www.wikidata.org/wiki/Q2462783","display_name":"Computational learning theory","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C32254414","wikidata":"https://www.wikidata.org/wiki/Q4724364","display_name":"Algorithmic learning theory","level":3,"score":0.2538999915122986},{"id":"https://openalex.org/C162392398","wikidata":"https://www.wikidata.org/wiki/Q272404","display_name":"Finite set","level":2,"score":0.25}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24141713","doi":"https://doi.org/10.5281/zenodo.24141713","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24141713","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":"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"},{"id":"doi:10.5281/zenodo.24141714","doi":"https://doi.org/10.5281/zenodo.24141714","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24141714","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":"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"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24141713","doi":"https://doi.org/10.5281/zenodo.24141713","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24141713","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":"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Machine":[0],"learning":[1,11,157,161,199],"lacks":[2],"a":[3,33,45,62,70,96,110,116,123,138,209,226,246,257],"single":[4],"quantity":[5,34],"that":[6,31,44,99,239,260],"is":[7,95,121,163,218,267],"defined":[8],"for":[9,73,112,126,252],"every":[10,74,77,119],"algorithm,":[12],"measurable":[13],"on":[14,55,176,178,183,230],"real":[15],"training":[16,54],"pipelines,":[17],"and":[18,26,76,182,206,225,255,270],"sufficient":[19],"to":[20],"state":[21,233],"what":[22],"the":[23,36,40,81,143,149,152,156,160,164,168,184,195,201,216,240],"algorithm":[24],"can":[25,100],"cannot":[27],"learn.":[28],"We":[29,57,232],"argue":[30],"such":[32],"exists:":[35],"implicit":[37,82,129,145],"code":[38,83,146,169],"length,":[39],"cumulative":[41],"log":[42],"loss":[43],"learner":[46,75,120],"incurs":[47],"when":[48],"it":[49,172],"predicts":[50],"each":[51,263],"example":[52],"before":[53],"it.":[56,231],"develop":[58],"this":[59],"idea":[60],"into":[61,200,221],"small,":[63],"self-contained":[64],"theory":[65,241],"with":[66],"complete":[67],"proofs.":[68],"First,":[69],"conservation":[71],"law:":[72],"set":[78],"of":[79,85,151,167,186,194,197],"inputs,":[80],"lengths":[84],"all":[86],"possible":[87],"labelings":[88],"satisfy":[89],"Kraft's":[90],"equality,":[91],"so":[92,159],"inductive":[93],"bias":[94],"fixed":[97],"budget":[98],"be":[101],"moved":[102],"between":[103,204],"tasks":[104],"but":[105],"never":[106],"increased;":[107],"we":[108,173],"give":[109],"version":[111],"noisy":[113],"tasks.":[114],"Second,":[115],"representation":[117],"theorem:":[118],"exactly":[122],"Bayesian":[124],"predictor":[125],"its":[127],"own":[128],"prior":[130],"over":[131],"labelings.":[132],"Third,":[133],"an":[134,191],"identity":[135],"rather":[136],"than":[137],"bound:":[139],"under":[140],"independent":[141],"sampling,":[142],"expected":[144],"length":[147],"equals":[148],"sum":[150],"test":[153],"risks":[154],"along":[155],"curve,":[158],"curve":[162],"discrete":[165],"derivative":[166],"length.":[170],"From":[171],"derive":[174],"constraints":[175],"plateaus,":[177],"power-law":[179],"scaling":[180],"exponents,":[181],"area":[185],"any":[187],"double-descent":[188],"bump.":[189],"Fourth,":[190],"exact":[192],"decomposition":[193],"cost":[196],"in-context":[198],"mutual":[202],"information":[203],"task":[205],"data":[207],"plus":[208],"pretraining":[210],"gap.":[211],"Most":[212],"ingredients":[213],"are":[214],"classical;":[215],"contribution":[217],"their":[219],"synthesis":[220],"one":[222],"accounting":[223],"system,":[224],"research":[227],"programme":[228],"built":[229],"three":[234],"conjectures":[235],"about":[236],"deep":[237],"networks":[238],"makes":[242],"precise,":[243],"explain":[244],"why":[245],"naive":[247],"simplicity":[248],"conjecture":[249],"must":[250],"fail":[251],"computational":[253],"reasons,":[254],"specify":[256],"laptop-scale":[258],"protocol":[259],"would":[261],"refute":[262],"conjecture.":[264],"The":[265],"paper":[266],"purely":[268],"theoretical":[269],"reports":[271],"no":[272],"experiments.":[273]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}